title_s
stringlengths 2
79
| title_dl
stringlengths 0
200
| source_url
stringlengths 13
64
| authors
listlengths 0
10
| snippet_s
stringlengths 0
291
| text
stringlengths 21
100k
| date
timestamp[ns]date 1926-02-14 00:00:00
2030-07-14 00:00:00
| publish_date_dl
stringlengths 0
10
| url
stringlengths 15
590
| matches
listlengths 1
278
|
|---|---|---|---|---|---|---|---|---|---|
HR AI Agents | Conversational AI Human Resources
|
HR AI Agents
|
https://crafter.ai
|
[
"Luca Di Benedetto",
"Roberto Renai"
] |
Adopting AI solutions, like HR AI Agents, means making information access faster and personalizing interactions with employees.
|
The AI agent for Automated HR Onboarding of Humanitas Research Hospital guides the onboarding process of new hires, contributing to the efficiency of the HR process.
The HR AI Agent, integrated on the Whatsapp channel, responds to frequent requests from candidates and new hires (e.g. credentials, badges, canteen, parking, etc.), collects data, forms and pre-filled documents, provides information on company policies and operating procedures, sends daily reminders to encourage completion of the process.
The HR AI Agent accelerates the onboarding process, improves the employee experience and reduces the volume of data entry activities for the HR team.
| 2023-02-23T00:00:00 |
https://crafter.ai/en/our-ai-solutions/soluzioni-hr-en/
|
[
{
"date": "2023/02/23",
"position": 50,
"query": "AI workers"
}
] |
|
JPMorgan Chase bars employees from using ChatGPT
|
JPMorgan Chase bars employees from using ChatGPT
|
https://www.cbsnews.com
|
[
"Megan",
"Reporter",
"Megan Cerullo Is A New York-Based Reporter For Cbs Moneywatch Covering Small Business",
"Workplace",
"Health Care",
"Consumer Spending",
"Personal Finance Topics. She Regularly Appears On Cbs News To Discuss Her Reporting.",
"Read Full Bio",
"Alain",
"Anne Marie D. Lee"
] |
JPMorgan Chase is banning workers from using artificial intelligence tool ChatGPT, a source familiar with the matter confirmed to CBS MoneyWatch Thursday.
|
Artificial intelligence could create more jobs than it displaces
JPMorgan Chase is banning workers from using artificial intelligence tool ChatGPT, a source familiar with the matter confirmed to CBS MoneyWatch Thursday.
Access to ChatGPT, which was developed by Microsoft-backed OpenAI and which is free to use, is currently restricted at JPMorgan, consistent with its policies around using third-party software, Bloomberg reported. The nation's largest bank declined to comment on the company's policy on employees using ChatGPT for work-related tasks.
Employees in a range of jobs are increasingly turning to ChatGPT and other so-called generative artificial intelligence tools, using the technology to write everything from marketing materials and emails to speeches and real estate listings. In fields such as medicine, meanwhile, physicians are using it for research purposes.
The tool has revealed its limitations, however, on occasion spitting out false information or otherwise botching communications. Vanderbilt University recently apologized for using the tool to write a memo to its community addressing a mass shooting at Michigan State University. Students blasted the move as "sick and twisted."
New York City Public Schools, the largest school district in the country, banned students' use of ChatGPT over cheating concerns.
OpenAI did not immediately respond to a request for comment.
| 2023-02-23T00:00:00 |
https://www.cbsnews.com/news/chatgpt-jpmorgan-chase-bars-workers-from-using-ai-tool/
|
[
{
"date": "2023/02/23",
"position": 55,
"query": "AI workers"
}
] |
|
Pay Equity vs. Pay Transparency: Defining the Difference
|
Pay Equity vs. Pay Transparency: Defining the Difference
|
https://www.adp.com
|
[] |
Pay transparency is the employer practice of disclosing information about employee compensation standards to others — internally, externally or both ...
|
Risk Pay Equity vs. Pay Transparency: Defining the Difference and Unscrambling the Jargon Part of a series | Pay Transparency Series Hannah Beppel
Pay transparency laws are popping up all over the country on state and local levels. What does that mean for employers? Pay transparency laws take the Equal Pay Act of 1963 a step further, requiring businesses to show pay ranges or report company wages.
Pay transparency is a hot phrase right now. Everyone's using it, writing it, saying it — so what does it mean? Pay equity is another popular one. Are these two phrases the same? Are they interchangeable? Do they refer to the same thing? With all the legal jargon, business owners and HR teams are scrambling to determine how these new laws might affect their businesses.
This article will break down the jargon to help you understand what pay transparency and pay equity are, how they are related and to help you feel more confident moving forward. To go more in-depth, launch this on-demand webcast anytime: Pay Transparency Compliance: Strategic & Practical Consideration.
What is pay transparency?
Pay transparency is the employer practice of disclosing information about employee compensation standards to others — internally, externally or both. Pay transparency is not defined by a single level or degree. Instead, it's described as a spectrum on which employers can choose varying degrees of transparency based on state and local mandates or their own pay strategy.
While laws differ from state to state, some require publishing pay ranges for all open positions. Others require employers to provide the pay range by the time of the final interview or upon request by the applicant, including internal applicants. Still, other states have opted to require businesses to file annual reports showing company wages broken out by race, gender, ethnicity, age and other categories. This rule enforces transparency between companies, applicants, employees and their state's division of labor authority.
What is pay equity?
Pay equity is the concept that equal work deserves equal pay no matter the person, their race, gender identity or age. Equal pay for equal work has been legislated since 1963 with the Equal Pay Act, again in 1964 with the Civil Rights Act and other landmark laws. This concept goes back to one of the most basic ideas of equality: If two people perform the same work, they should receive the same pay. Even though this legislation has been in place on a federal level for decades, it has not stopped companies from paying people different wages for the same work. It doesn't matter whether this is due to intentional decisions or subconscious bias because it's unethical in both cases. It's important to note that while this definition of pay equity is widely accepted in the United States, there may be alternative approaches considered in other countries when defining pay equity.
Regardless of the motive, educating leaders on how pay decisions should be made using a "pay for performance" compensation approach is essential. Discover more in-depth resources about pay equity in this article: Pay Equity.
In this Workforce News Minute video, above, Helena Almeida, Managing Counsel ADP, shares the trends we're seeing in the workforce to work to close the pay gap.
Is pay transparency the same thing as pay equity?
No, pay transparency is not the same thing as pay equity. But they are connected. Pay equity refers to the principle of equal pay for equal work. This standard was initially legislated in the Equal Pay Act of 1963. Moreover, pay equity refers to compensation practices that are fair, unbiased, ethical, and free from discrimination. Pay transparency is likely to be an excellent motivator for companies to practice equitable pay. Interestingly, the fact that pay equity has been federally legislated for over 60 years has not meant that companies have always been committed to equitable pay practices (or following the law). Most labor economists still calculate a pay gap between genders and other protected groups. This gap is most likely why states are stepping in to legislate pay transparency — and, in effect — enforce pay equity.
Why do employees want pay transparency?
Employees want pay transparency because it can help provide reassurance that they aren't being discriminated against by being paid lower wages. Employees and job applicants want to know they are being treated fairly. It was a common workplace rule in the past that employees weren't supposed to discuss what they were paid. Some employers have banned employees from discussing pay with each other, considering it an offense worthy of termination. This practice keeps employees in the dark about whether they are discriminated against or underpaid for whatever reason. But prohibiting employees from talking about their income has been illegal since 1935 (National Labor Relations Act). Yet many employers still discourage employees from talking openly about pay. Now, states are also enacting legislation prohibiting pay secrecy. Managers making pay a taboo topic may be illegal, depending on the state.
Employees want to feel like they can trust their employer. They want to be compensated fairly for their work and feel valued for what they contribute. Many employees are excited about newly enacted pay transparency laws for these reasons.
What are the pros and cons of pay transparency?
The pros of pay transparency are multifaceted and include increased awareness of and commitment to social responsibility, lower likelihood of lawsuits, improved productivity and morale, lower turnover rates, and being attractive to new talent. While committing to the social responsibility of pay transparency is important, pay transparency affects the business's overall brand reputation, which can ultimately impact the bottom line.
The cons of pay transparency can include adverse employee reactions and potential turnover if unethical pay practices are exposed. Shining light on unethical pay practices could also negatively affect the brand image and, in turn, the business's ability to bring in new employees and potential customers.
Is there a federal pay transparency law?
No, currently, there is no federal pay transparency law. Federal law requires equal work for equal pay. But no other federal laws require companies to be transparent about pay practices. Because of the lack of federal law, states are stepping in to enact their own laws requiring pay transparency. Since laws have been passed on a state level, this creates additional complexity for multi-state employers. Even if a single remote employee is working in a state with a specified pay transparency law, the company — even if it's located in another state where there is no pay transparency law — is required to follow the law concerning that employee and, depending on the law, for all other employees as well. If and when more states enact similar laws, employers should stay alert and continue their commitments to pay equity.
The wrap-up
Pay transparency laws aim to move the needle on pay equity and create a workplace where employees are paid fairly for their work. Employers should seek the advice of their employment counsel if they are unsure of how laws may affect them. Ultimately, it is up to business leaders to adhere to pay practices that attract strong talent and comply with the laws in their states and localities.
Did you know?
ADP offers an on-demand webinar that covers pay transparency laws and how they affect organizations. Subject-matter experts broke down the complex language of the law and spelled out how these new rules affect employers. Launch it here, anytime: Pay Transparency Compliance: Strategic & Practical Considerations.
Dive Deeper
Get up-to-date pay transparency resources and best practices at ADP.com/PayTransparency.
| 2023-02-23T00:00:00 |
2023/02/23
|
https://www.adp.com/spark/articles/2023/02/pay-equity-vs-pay-transparency-defining-the-difference-and-unscrambling-the-jargon.aspx
|
[
{
"date": "2023/02/23",
"position": 38,
"query": "AI wages"
}
] |
Navigating wage drift
|
Navigating wage drift
|
https://www.peoplehum.com
|
[] |
AI & Analytics. Make people decisions based on accurate data - not guesswork ... If there is a shortage of workers with specific skills, for example, employers ...
|
What is Wage Drift?
The definition of "wage drift" can be termed as a phenomenon in which wages increase at a rate faster than the rate of inflation. This occurs when employees receive raises that exceed the market rate for their position and can lead to significant increases in wages over time. Wage drift can also lead to salary inequities, as employees who are not receiving the same amount of raises may feel like they are being shortchanged.
Understanding what is wage drift can be important for both employers and employees. For employers, it is important to know that wage drift pay can lead to higher labor costs, which can have negative effects on the bottom line. Some of the examples of wage drift are overtime, company bonuses, and performance rewards.
What factors contribute to wage drift?
As we have learned the definition of "wage drift," let’s also take a look at the various factors that contribute to wage drift:
Market forces: Supply and demand imbalances can cause wages to fluctuate. If there is a shortage of workers with specific skills, for example, employers may be willing to pay higher wages to attract and retain workers. On the other hand, if there is an oversupply of workers, wages may decrease.
Changes in economy: Economic changes, such as inflation, recession, or changes in government policies, can also impact wage drift pay. Inflation can reduce the purchasing power of wages, while a recession can lead to wage cuts or job losses. Government policies such as minimum wage increases or changes to tax codes can also affect wages.
Company factors: Some employers may choose to offer higher wages than their competitors to attract top talent, retain experienced workers, or maintain employee morale. Other employers may offer lower wages to stay competitive, cut costs, or improve profitability.
Employee productivity: Employers may offer wage increases to reward employees who demonstrate exceptional performance or increased productivity. Conversely, employees who consistently underperform may see their wages stagnate or decline
Collective bargaining: In some cases, collective bargaining between unions and employers can lead to higher wages for workers. This can occur through negotiations for wage increases or through collective bargaining agreements that set specific wage rates for workers.
Also read: What are supplementary wages?
What are the advantages and disadvantages of wage drift?
Wage drift pay can be a useful tool for companies when it comes to managing pay within a company. This method assists firms in maintaining and promoting fair compensation for all employees while also recognising good performance. Wage drift can also help firms manage their resources more effectively, saving money and enhancing efficiency.
It contributes to increasing job satisfaction and devotion to one's work and organization. Companies can use wage drift to improve working conditions and retain employees. It aids employees in remaining focused and motivated at work. Wage drift can help ensure organizational fairness. It enables businesses to recognise employee efforts and reward them for accomplishing positive results.
It goes without saying that wage drift can be a useful tool for both companies and employees. Sadly, the most obvious downside of pay drift is that it can cost employers money because employees can continue to earn raises without having to argue for them. As a result, those employees who are the most knowledgeable and experienced may be the ones who suffer from pay inequity.
Conclusion:
In conclusion, while we address the issue of what is wage drift, we can also conclude that wage drifts have implications for labor markets and economic policy since it affects wages, employment, and inequality. To mitigate the risks of wage drift, employers may need to implement measures such as clear and consistent pay policies, performance-based pay systems, and regular reviews of compensation packages. Overall, understanding the causes and effects of wage drift is important for employers and employees alike in ensuring fair and sustainable compensation practices.
| 2023-02-23T00:00:00 |
https://www.peoplehum.com/glossary/wage-drift
|
[
{
"date": "2023/02/23",
"position": 42,
"query": "AI wages"
}
] |
|
UVU Jobs | People & Culture | Utah Valley ...
|
Utah Valley University
|
https://www.uvu.edu
|
[] |
Like other student jobs, FWS wages are earned through employment at an ... ai/virtualadvisor/362,344,1,345,369,346,2,374,337,3,343,25,4,468,470,373,479 ...
|
UVU Federal Work Study: Federal Work Study (FWS) is a financial aid program available for qualified students. The FWS program is designed to help students to pay for college while getting on-the-job training and experience, preferably related to their field of study. Like other student jobs, FWS wages are earned through employment at an hourly rate, with competitive pay based on job duties and the employee's job-related knowledge, skills, and experience. We recommend that students interested in FWS employment contact the Financial Aid and Scholarships office to determine eligibility and learn more about the program before applying for FWS jobs.
Welcome to Utah Valley University! As you explore UVU, you’ll gain a powerful sense of the incredible energy and momentum that drives this thriving institution. If you are determined, passionate and enthusiastic, you will thrive at UVU. UVU inspires great people, with great passion, working for a great purpose!
ABOUT UVU
Utah Valley University (UVU) is a student-centered teaching institution dedicated to building communities of engaged learners by developing its students and employees to be people of integrity who are good stewards of their community and professionally competent in their chosen profession.
ABOUT THE AREA
UVU's service region includes Utah, Wasatch, and Summit counties. Located near the Wasatch Mountains, many students choose UVU for its ideal location. Others come for access to a dynamic economy, employment and career opportunities. Our campus is recognized as one of the safest colleges in the country. Within 20 miles, you can enjoy winter sports, hiking, mountain biking, water recreation and more.
NOTICES
Background Checks
Utah Valley University is committed to providing a safe working and learning environment for its employees, students, and visitors. It also seeks to protect its assets, comply with laws and regulations, and preserve its reputation. All background checks are conducted in conformity with the Federal Fair Credit Reporting Act, the American with Disabilities Act, and state and federal privacy and anti-discrimination laws. Volunteers that work with minors and/or in security-sensitive areas will also undergo a background check.
A background check can consist of one or more verification processes, including a criminal background check, employment, credit check, and/or motor vehicle check. The background check may also include the search of public records outside the United States of America.
REASONABLE ACCOMMODATIONS
Any applicant who requires an accommodation in order to apply for a position or proceed with the job search process should contact Employee Accommodations, Cameron Evans, at 801-863-8389 or [email protected]
| 2023-02-23T00:00:00 |
https://www.uvu.edu/peopleandculture/jobs/index.html
|
[
{
"date": "2023/02/23",
"position": 45,
"query": "AI wages"
}
] |
|
PAI's Responsible Practices for Synthetic Media
|
PAI’s Responsible Practices for Synthetic Media
|
https://syntheticmedia.partnershiponai.org
|
[] |
A framework on how to responsibly develop, create, and share synthetic media: the audiovisual content often generated or modified by AI.
|
For more information on the creation, goals, and continued development of PAI’s Responsible Practices for Synthetic Media, see the FAQ.
Further, while the ethical implications of synthetic media are vast, implicating elements like copyright, the future of work, and even the meaning of art, the goal of this document is to target an initial set of stakeholder groups identified by the PAI AI and Media Integrity community that can play a meaningful role in: (a) reducing the potential harms associated with abuses of synthetic media and promoting responsible uses, (b) increasing transparency, and (c) enabling audiences to better identify and respond to synthetic media.
Synthetic media presents significant opportunities for responsible use, including for creative purposes. However, it can also cause harm. As synthetic media technology becomes more accessible and sophisticated, its potential impact also increases. This applies to both positive and negative possibilities — examples of which we only begin to explore in this Framework. The Framework focuses on how to best address the risks synthetic media can pose while ensuring its benefits are able to be realized in a responsible way.
PAI’s Responsible Practices for Synthetic Media is a living document. While it is grounded in existing norms and practices, it will evolve to reflect new technology developments, use cases, and stakeholders. Responsible synthetic media, infrastructure development, creation, and distribution are emerging areas with fast-moving changes, requiring flexibility and calibration over time. PAI plans to conduct a yearly review of the Framework and also to enable a review trigger at any time as called for by the AI and Media Integrity Steering Committee.
PAI will not be auditing or certifying organizations. This Framework includes suggested practices developed as guidance.
Several of these stakeholders will launch PAI’s Responsible Practices for Synthetic Media, formally joining this effort. These organizations will:
The intended stakeholder audiences are those building synthetic media technology and tools, or those creating, sharing, and publishing synthetic media.
With this Framework, we seek to:
These practices are the result of feedback from more than 100 global stakeholders. It builds on PAI’s work over the past four years with representatives from industry, civil society, media/journalism, and academia.
The Partnership on AI’s (PAI) Responsible Practices for Synthetic Media is a set of recommendations to support the responsible development and deployment of synthetic media.
PAI’s Responsible Practices for Synthetic Media
Those building technology and infrastructure for synthetic media, creating synthetic media, and distributing or publishing synthetic media will seek to advance ethical and responsible behavior.
Here, synthetic media, also referred to as generative media, is defined as visual, auditory, or multimodal content that has been generated or modified (commonly via artificial intelligence). Such outputs are often highly realistic, would not be identifiable as synthetic to the average person, and may simulate artifacts, persons, or events. See Appendix A for more information on the Framework’s scope.
PAI offers recommendations for different categories of stakeholders with regard to their roles in developing, creating, and distributing synthetic media. These categories are not mutually exclusive. A given stakeholder could fit within several categories, as in the case of social media platforms. These categories include:
Those building technology and infrastructure for synthetic media Those creating synthetic media Those distributing and publishing synthetic media
Section 1:
Practices for Enabling Ethical and Responsible Use of Synthetic Media
Collaborate to advance research, technical solutions, media literacy initiatives, and policy proposals to help counter the harmful uses of synthetic media. We note that synthetic media can be deployed responsibly or can be harnessed to cause harm.
Responsible categories of use may include, but are not limited to:
Entertainment
Art
Satire
Education
Research
Conduct research and share best practices to further develop categories of responsible and harmful uses of synthetic media.
These uses often involve gray areas, and techniques for navigating these gray areas are described in the sections below.
When the techniques below are deployed to create and/or distribute synthetic media in order to cause harm (see examples of harm in Appendix B), pursue reasonable mitigation strategies, consistent with the methods described in Sections 2, 3, and 4.
The following techniques can be deployed responsibly or to cause harm:
Representing any person or company, media organization, government body, or entity
Creating realistic fake personas
Representing a specific individual having acted, behaved, or made statements in a manner in which the real individual did not
Representing events or interactions that did not occur
Inserting synthetically generated artifacts or removing authentic ones from authentic media
Generating wholly synthetic scenes or soundscapes
For examples of how these techniques can be deployed to cause harm and an explicit, nonexhaustive list of harmful impacts, see Appendix B.
Section 2:
Practices for Builders of Technology and Infrastructure
Those building and providing technology and infrastructure for synthetic media can include: B2B and B2C toolmakers; open-source developers; academic researchers; synthetic media startups, including those providing the infrastructure for hobbyists to create synthetic media; social media platforms; and app stores.
Be transparent to users about tools and technologies’ capabilities, functionality, limitations, and the potential risks of synthetic media.
Take steps to provide disclosure mechanisms for those creating and distributing synthetic media.
Disclosure can be direct and/or indirect, depending on the use case and context:
Direct disclosure is viewer or listener-facing and includes, but is not limited to, content labels, context notes, watermarking, and disclaimers.
Indirect disclosure is embedded and includes, but is not limited to, applying cryptographic provenance to synthetic outputs (such as the C2PA standard), applying traceable elements to training data and outputs, synthetic media file metadata, synthetic media pixel composition, and single-frame disclosure statements in videos.
When developing code and datasets, training models, and applying software for the production of synthetic media, make best efforts to apply indirect disclosure elements (steganographic, media provenance, or otherwise) within respective assets and stages of synthetic media production.
Aim to disclose in a manner that mitigates speculation about content, strives toward resilience to manipulation or forgery, is accurately applied, and also, when necessary, communicates uncertainty without furthering speculation. (Note: The ability to add durable disclosure to synthetic media is an open challenge where research is ongoing).
Support additional research to shape future data-sharing initiatives and determine what types of data would be most appropriate and beneficial to collect and report, while balancing considerations such as transparency and privacy preservation.
Take steps to research, develop, and deploy technologies that:
Are as forensically detectable as possible for manipulation, without stifling innovation in photorealism.
Retain durable disclosure of synthesis, such as watermarks or cryptographically bound provenance that are discoverable, preserve privacy, and are made readily available to the broader community and provided open source.
Provide a published, accessible policy outlining the ethical use of your technologies and use restrictions that users will be expected to adhere to and providers seek to enforce.
Section 3:
Practices for Creators
Those creating synthetic media can range from large-scale producers (such as B2B content producers) to smaller-scale producers (such as hobbyists, artists, influencers and those in civil society, including activists and satirists). Those commissioning and creative-directing synthetic media also can fall within this category. Given the increasingly democratized nature of content creation tools, anyone can be a creator and have a chance for their content to reach a wide audience. Accordingly, these stakeholder examples are illustrative but not exhaustive.
Be transparent to content consumers about:
How you received informed consent from the subject(s) of a piece of manipulated content, appropriate to product and context, except for when used toward reasonable artistic, satirical, or expressive ends.
from the subject(s) of a piece of manipulated content, appropriate to product and context, except for when used toward reasonable artistic, satirical, or expressive ends. How you think about the ethical use of technology and use restrictions (e.g., through a published , accessible policy, on your website, or in posts about your work) and consult these guidelines before creating synthetic media.
, accessible policy, on your website, or in posts about your work) and consult these guidelines before creating synthetic media. The capabilities, limitations, and potential risks of synthetic content.
Disclose when the media you have created or introduced includes synthetic elements especially when failure to know about synthesis changes the way the content is perceived. Take advantage of any disclosure tools provided by those building technology and infrastructure for synthetic media.
Disclosure can be direct and/or indirect, depending on the use case and context:
Direct disclosure is viewer or listener-facing and includes, but is not limited to, content labels, context notes, watermarking, and disclaimers.
Indirect disclosure is embedded and includes, but is not limited to, applying cryptographic provenance to synthetic outputs (such as the C2PA open standard), applying traceable elements to training data and outputs, synthetic media file metadata, synthetic media pixel composition, and single-frame disclosure statements in videos.
Aim to disclose in a manner that mitigates speculation about content, strives toward resilience to manipulation or forgery, is accurately applied, and also, when necessary, communicates uncertainty without furthering speculation.
Section 4:
Practices for Distributors and Publishers
Those distributing synthetic media include both institutions with active, editorial decision-making around content that mostly host first-party content and may distribute editorially created synthetic media and/or report on synthetic media created by others (i.e., media institutions, including broadcasters) and online platforms that have more passive displays of synthetic media and host user-generated or third-party content (i.e., social media platforms).
For both active and passive distribution channels
Disclose when you confidently detect third-party/user-generated synthetic content.
Disclosure can be direct and/or indirect, depending on the use case and context:
Direct disclosure is viewer or listener-facing, and includes, but is not limited to, content labels, context notes, watermarking, and disclaimers.
Indirect disclosure is embedded and includes, but is not limited to, applying cryptographic provenance (such as the C2PA open standard) to synthetic outputs, applying traceable elements to training data and outputs, synthetic media file metadata, synthetic media pixel composition, and single-frame disclosure statements in videos.
Aim to disclose in a manner that mitigates speculation about content, strives toward resilience to manipulation or forgery, is accurately applied, and also, when necessary, communicates uncertainty without furthering speculation.
Provide a published, accessible policy outlining the organization’s approach to synthetic media that you will adhere to and seek to enforce.
For active distribution channels
Channels (such as media institutions) that mostly host first-party content and may distribute editorially created synthetic media and/or report on synthetic media created by others.
Make prompt adjustments when you realize you have unknowingly distributed and/or represented harmful synthetic content.
Avoid distributing unattributed synthetic media content or reporting on harmful synthetic media created by others without clear labeling and context to ensure that no reasonable viewer or reader could take it to not be synthetic.
Work towards organizational content provenance infrastructure for both non-synthetic and synthetic media, while respecting privacy (for example, through the C2PA open standard).
Ensure that transparent and informed consent has been provided by the creator and the subject(s) depicted in the synthetic content that will be shared and distributed, even if you have already received consent for content creation.
For passive distribution channels
Channels (such as platforms) that mostly host third-party content.
Identify harmful synthetic media being distributed on platforms by implementing reasonable technical methods, user reporting, and staff measures for doing so.
Make prompt adjustments via labels, downranking, removal, or other interventions like those described here, when harmful synthetic media is known to be distributed on the platform.
20. Clearly communicate and educate platform users about synthetic media and what kinds of synthetic content are permissible to create and/or share on the platform.
Appendices
| 2023-02-23T00:00:00 |
https://syntheticmedia.partnershiponai.org/
|
[
{
"date": "2023/02/23",
"position": 34,
"query": "AI journalism"
}
] |
|
1000+ Stability Ai Jobs in Worldwide (25 new)
|
1,000+ Stability Ai Jobs in Worldwide
|
https://www.linkedin.com
|
[] |
AI/ML Engineer (Graduate). Cyncly. Kochi, Kerala, India. Actively Hiring. 4 weeks ago.
|
This button displays the currently selected search type. When expanded it provides a list of search options that will switch the search inputs to match the current selection.
Jobs
People
Learning
| 2023-02-23T00:00:00 |
https://www.linkedin.com/jobs/stability-ai-jobs-worldwide
|
[
{
"date": "2023/02/23",
"position": 42,
"query": "artificial intelligence hiring"
}
] |
|
AI is helping your company decide who to lay off
|
AI is helping your company decide who to lay off
|
https://www.businessinsider.com
|
[
"Jacob Zinkula"
] |
98% of respondents plan to use software and algorithms to help them make any layoff decisions in 2023.
|
This story is available exclusively to Business Insider subscribers. Become an Insider and start reading now.
AI might not take your job any time soon, but companies are already using it to help them decide who to lay off.
That's according to a November Capterra survey of 300 US human resources leaders, which found that 98% of respondents plan to use software and algorithms to help them make any layoff decisions in 2023.
While many companies have access to a wide range of employee data — including information on employee attendance, pay, and experience — the HR leaders said "skills" and "performance" data would be most likely to be used in a layoff decision, with 70% of the leaders saying each of these would be considered.
While not specified in the survey, skills and performance data could range from more traditional measures — like an employee's sales figures — to more complicated "productivity scores" that can measure details as small as how much time workers use their emails or who has their camera on during meetings.
While this survey is just a small sampling of HR professionals, it does feed into a broader discussion of how companies embrace new AI tools, and how much of a role they'll play in hiring decisions going forward. In certain cases HR departments have, in fact, started to use AI for both hiring and firing.
Since the Great Recession, HR departments have become "incredibly data-driven," Brian Westfall, senior HR analyst at Capterra, a software review site, told The Washington Post. But now, he says these departments are "more data-driven than ever before."
Since launching in November, ChatGPT and related tools have taken the world by storm, and it's led to speculation about whether AI will replace jobs and threaten Americans' job security. It's unclear how many companies use AI tools when conducting performance reviews and promotions, but some employees say they're concerned about it. And with many companies doing layoffs in recent months, these tools now may be being called upon to help with job cuts.
Related stories Business Insider tells the innovative stories you want to know Business Insider tells the innovative stories you want to know
While companies aren't asking ChatGPT who to lay off, AI is already well established in many HR departments, many of whom have workers who are feeling burned out and might welcome the extra help. Incorporating algorithms when making difficult layoff decisions can also be "particularly comforting" for some HR managers, Westfall said.
AI is being used for hiring and firing, but some experts have concerns
For many years, companies have used AI to process resumes, conduct interviews, and evaluate candidates. Over the past year — when the labor shortage has at times made talent difficult to find — many HR departments have looked for any edge they can get.
Amazon and Goldman Sachs, for instance, have used the hiring platform HireVue to conduct more video interviews. The platform's AI has also been used to assess and score candidates based on problem-solving and communication skills.
"The result is that we can improve candidate quality and double the number of interviews and hires a company can make, while cutting the time in half," Patrick Morrissey, the chief growth officer at HireVue, previously told Insider.
Companies have also used AI to assess performance and monitor employees. JP Morgan, for example, has used an internal company system that provides data on employees' workplace activities, including how much time they spend on Zoom calls and what they do on their company-provided cell phones, Insider previously reported.
While US companies are generally allowed to monitor employees, the legality of some practices has been called into question. In early February, three Democratic lawmakers introduced the Stop Spying Bosses Act, which would prohibit businesses from collecting "sensitive data" on workers and require them to make "timely and public disclosures" about what data they're collecting.
While some experts have argued AI tools could help reduce bias during the hiring process, others have raised concerns. In 2017, Amazon reportedly stopped using an AI hiring tool that it found showed a bias against women candidates.
AI has even been used for "predictive attrition," helping companies predict which employees are most likely to quit. But there are some ways the use of this data could go awry, Capterra's Westfall told the Post. If a company doesn't treat minority employees well, for instance, and many of them quit, the AI might predict that other minorities are likely to quit as well. And this could potentially put these employees at higher risk during the next round of layoffs.
"You can kind of see where the snowball gets rolling," Westfall said, "and all of a sudden, these data points where you don't know how that data was created or how that data was influenced suddenly lead to poor decisions."
Due in part to these concerns, only 47% of the HR leaders surveyed by Capterra said they were "entirely comfortable" using AI to make layoff decisions. A majority said they weren't "completely confident" in the quality of their employers' data.
As companies embrace new AI tools, those in positions of power will continue to be faced with the question of how much of a role AI should play when making key decisions. Some, however, have expressed optimism that the right balance can be struck.
"What AI is able to do is use pattern recognition to help with insights so we can make better decisions," Amy Wright, managing partner of talent and transformation at IBM Global Business Services, said in 2021. "It does not make decisions for us."
Correction — February 22, 2023: This article corrected a misspelling of Capterra's company name.
| 2023-02-23T00:00:00 |
https://www.businessinsider.com/layoffs-today-trends-ai-data-companies-jobs-algorithms-chatgpt-2023-2
|
[
{
"date": "2023/02/23",
"position": 11,
"query": "artificial intelligence layoffs"
}
] |
|
Microsoft Wants To Cut 120 Jobs In Germany
|
Microsoft Wants To Cut 120 Jobs In Germany
|
https://globalradiancereview.com
|
[] |
... artificial intelligence (AI), and digital health. The company recently ... However, the company will not be able to avoid layoffs elsewhere around the world due ...
|
Microsoft is one of the largest brand across the globe. The company has been working on a number of products and services that have helped it gain an edge over its competitors.
Microsoft is also known for its cutting-edge technologies, especially as it relates to cloud computing. In fact, cloud computing has become such an integral part of the company's business that it was named one of Time magazine's 100 Best Companies in 2016.
The tech giant has been hiring more people in Germany than any other country in Europe and now wants to cut 120 jobs from its workforce in Germany by early 2023. The company has a huge customer base and therefore, it is not easy to cut down on its workforce. However, Microsoft wants to cut down 120 jobs in Germany due to the economic slowdown in Europe. This was announced by Microsoft Germany on Monday, according to Reuters.
Microsoft Germany said that they had decided to reduce their workforce because they wanted to be competitive in this tough time for the technology industry. The company wants to make sure that they will have enough resources to focus on their customers' needs and demands. This decision was made after many negotiations with employees and unions, who believed that such reductions would not be beneficial for the company's business.
The news about Microsoft cutting down on their workforce has been received well by investors who believe that Microsoft can still get back on track if they keep their focus on what matters most – their customers' needs and demands. Microsoft is one of the largest brand across the globe, and it has been trying to diversify its business by investing in new areas like cloud computing, artificial intelligence (AI), and digital health.
The company recently announced that it will cut 120 jobs in Germany as part of a restructuring plan to reduce the work force by 3%. According to a report by German daily Handelsblatt, the job cuts are aimed at reducing costs and increasing profitability.
Microsoft's CFO Amy Hood said that with this strategy, no jobs would be lost in Germany itself. However, the company will not be able to avoid layoffs elsewhere around the world due to financial constraints.
This comes after Microsoft's CEO Satya Nadella said last month that he wants to cut about 12% of the company's workforce over two years as part of a broader goal to innovate faster and invest more in advanced technology research projects. Microsoft is looking to cut 120 jobs in Germany. The company has notified the country's economy ministry of its intention to restructure the German operation with a total workforce of 1,200 employees.
The cuts are part of Microsoft's plan to reduce its global workforce by 25 per cent, which includes layoffs and other measures like attrition, according to Reuters.
Microsoft said it will focus on areas where it can improve productivity through technology developments and reorganisation of its teams. It also plans to invest more in research and development for Windows, Azure and Office 365 products as well as gaming consoles and HoloLens.
"We're taking these actions now so we can better adapt our business model for today's fast-changing technology landscape," Microsoft CEO Satya Nadella said in a statement released on Thursday. "To drive future growth in our cloud services, we need to be agile and nimble." When it comes to the tech or clouding part, in fact in windows there is not even a single competitor who can even think of competing with a brand like Microsoft. Microsoft has come a long way and hopefully they will be doing the best in future.
| 2023-02-23T00:00:00 |
https://globalradiancereview.com/it-services/microsoft-wants-to-cut-120-jobs-in-germany
|
[
{
"date": "2023/02/23",
"position": 55,
"query": "artificial intelligence layoffs"
}
] |
|
The risks of using AI to create designs - CSD
|
The risks of using AI to create designs
|
https://www.csd.org.uk
|
[] |
One of the major concerns of using AI in design is the potential for errors or malfunctions that could result in financial losses or other damages.
|
The rise of artificial intelligence (AI) has led to an increased interest in its application to various industries, including the world of graphic and product design.
Whilst AI has many benefits, including automating repetitive tasks, improving design accuracy and speed, as well as generating new ideas and styles, this article strikes a cautionary note.
As with any new technology of this kind, there are potential insurance, intellectual property, and risk management issues that need to be considered. Particularly when the application of that technology is so new, that we are in unchartered territory with little to no legal framework that has been provided by the courts, to decide on issues that arise from its use.
Contractual Issues
One of the first issues that may need to be considered is the contractual position in respect of the use of AI and there are two aspects to this.
The first relates to the appointment by the Client. They have appointed the designer to provide the services, but if those services are provided by an AI, has the designer ‘really’ fulfilled their contractual obligations?
The second aspect relates to the terms agreed upon between the designer and the providers of the AI service. There are a number of areas that need to be considered; for example, with the benefit of legal advice, you can seek advice on the positions in respect of both liability and copyright.
Insurance Issues
One of the major concerns of using AI in design is the potential for errors or malfunctions that could result in financial losses or other damages.
Zurich Insurance, who have created a whitepaper called ‘Artificial Intelligence And Algorithmic Liability’, noted that the “AI risk” is defined as arising from the use of data analytics and cognitive technology-based software algorithms in automated and semi-automated decision-making. Where the algorithms fail to perform as expected, the result can be losses from property damage, business interruption, personal injury, professional liability and cyber exposures.
To give a simple yet reasonable example, if an AI system generates a design that is not suitable or infringes on someone else’s intellectual property, the designer could face legal action from their claims in addition to potentially hefty fines.
There are two issues in this scenario:
The first is that there is no certainty about where the error or omission exists. Is it the creators of the AI and the algorithms that are at fault or is it the designer for not having adequate mechanisms for checking the work and rectifying any errors?
From a claims perspective, it is difficult to determine how this issue would be approached by both Insurers and the Courts. As outlined by Zurich in their whitepaper, the insurance implications will take some time to determine “… because of a lack of loss experience data and models that can estimate the frequency and severity of potential losses …”.
The first issue leads into the second, which relates to the cover position.
It is likely that insurance coverage held by the designer relates to the provision of their professional services. Whilst there are unlikely to be any terms within those policies that would prohibit the use of an AI system, has the designer provided a professional service if they have used AI to complete the project?
As it is likely that the designer will ultimately retain a duty to inspect and approve any design work before it is released, if the designs are in error there would be an expectation that a further related claim could be brought against the providers of AI. But, if the terms of any contract with the AI provider does not provide any route for a claim (because they accept no liability as mentioned in their agreement), the position of Insurers has arguably been prejudiced.
Whilst it is difficult to predict how Insurers would react in these circumstances, it is possible that they would look to restrict or remove any cover offered in respect of any designs produced by AI Systems. As such, there is a great deal of uncertainty regarding the future landscape of the insurance sector as these new technologies continue to emerge.
Intellectual Property Issues
Another important consideration when using AI in design is intellectual property (IP) rights. AI-generated designs may incorporate elements or features that are protected by copyright, trademark, or patent laws. As such, designers and companies need to understand the potential IP issues associated with the use of AI in design.
Again, for simplicity… an AI system may generate a design that incorporates a copyrighted image or trademarked logo without permission. This could result in legal action against the designer and their client for copyright or trademark infringement, which could incur defence costs.
Whilst the AI creator is likely at fault, this is not certain. Therefore, it would be prudent to avoid these risks, but if you are using AI, we suggest being vigilant in checking the legality of any elements used in AI-generated designs.
In addition, designers and companies may also need to consider issues related to the ownership and licensing of AI-generated designs. In some cases, the copyright and other IP rights in an AI-generated design may be owned by the developer of the AI system, rather than the designer or their client.
As such, designers and companies need to clarify ownership and licensing rights upfront to avoid any disputes or legal action down the line.
Conclusion
Whilst AI has the potential to revolutionise the world of design, it also presents a range of unanswered questions about insurance, intellectual property, and risk management, which all need to be carefully considered.
The good thing is it is generating a lot of debate amongst regulators and technology companies. But until these questions are answered, it is important that you develop clear policies and procedures for using AI. These policies should include guidelines for testing and validating AI systems, as well as protocols for reviewing designs and responding to any errors or malfunctions that may occur.
| 2023-02-23T00:00:00 |
https://www.csd.org.uk/design-insight/risks-of-using-ai-to-create-designs/
|
[
{
"date": "2023/02/23",
"position": 22,
"query": "artificial intelligence graphic design"
}
] |
|
Exploring the Possibilities of AI-Assisted Graphic Design
|
Exploring the Possibilities of AI-Assisted Graphic Design – MAIDArt
|
https://maidart.com
|
[
"Author"
] |
As technology advances, AI-assisted graphic design is becoming increasingly popular among designers. AI-tools are being used to develop unique compositions, ...
|
As technology advances, AI-assisted graphic design is becoming increasingly popular among designers. AI-tools are being used to develop unique compositions, augment the creative process, and enhance the overall design quality. In this blog post, we’ll explore the different tools and techniques available to designers and how they can be used to develop interesting compositions.
One of the most exciting recent developments in AI-assisted graphic design is the introduction of OpenAI’s DALL-E. DALL-E is an AI model that can generate high-quality images from textual descriptions. It has been trained on a vast dataset of images and is capable of creating a wide range of compositions, from simple objects to complex scenes. Designers can input a textual description of the image they want to create, and DALL-E will generate a high-quality image based on that description. This tool is still in its early stages, but it has already been used to create some stunning artwork.
Another popular AI tool that has been around for a while is Adobe’s Sensei. Sensei is an AI-powered platform that uses machine learning to help designers automate tasks and improve the design process. It can be used to generate color palettes, suggest font combinations, and even create mockups. The platform is designed to work alongside designers, not replace them, and it can save designers a lot of time and effort by automating repetitive tasks.
MidJourney is another AI-powered platform that has been gaining popularity in the graphic design world. It uses machine learning to create custom illustrations and animations that are unique to the brand. The platform analyzes the brand’s visual identity, target audience, and messaging to create illustrations and animations that are both on-brand and visually appealing.
While AI-assisted graphic design has many benefits, it’s important to note that it’s not a one-size-fits-all solution. AI tools can automate many tasks, but they cannot replace the creativity and skill of human designers. It’s important to strike a balance between using AI to streamline the design process and relying on human creativity to create unique and compelling designs.
AI-assisted graphic design is a rapidly evolving field that has the potential to revolutionize the design industry. Tools like DALL-E, Sensei, and MidJourney are just a few examples of the many AI-powered platforms available to designers. By incorporating these tools into their design process, designers can create more compelling and unique designs while streamlining their workflow. However, it’s important to remember that AI tools should be used to augment human creativity, not replace it entirely. As the field continues to evolve, we can expect to see even more exciting developments in AI-assisted graphic design.
| 2023-02-23T00:00:00 |
https://maidart.com/exploring-the-possibilities-of-ai-assisted-graphic-design/
|
[
{
"date": "2023/02/23",
"position": 50,
"query": "artificial intelligence graphic design"
}
] |
|
What Is Midjourney? How is Midjourney, An AI Image ...
|
What Is Midjourney? How is Midjourney, An AI Image Generating Tool, Helping Designers?
|
https://maxxpace.com
|
[
"Anwar Ul Haq",
"Posted May"
] |
AI has advanced in design with various tools and software that assist designers in producing beautiful images and graphics. In this article, we'll look at the ...
|
In conclusion, midjourney AI transforms design by enabling designers to produce high-quality images and visuals more quickly and easily. This technology has various advantages, such as time and effort savings, increased creative potential, and overcoming obstacles. In the future, we may anticipate seeing even more fascinating applications for AI image generating tools thanks to continued advancements in AI technology.
| 2023-02-23T00:00:00 |
2023/02/23
|
https://maxxpace.com/what-is-midjourney-how-midjourney-helping-designers/
|
[
{
"date": "2023/02/23",
"position": 69,
"query": "artificial intelligence graphic design"
}
] |
The Pros and Cons of Using AI to Automate Tasks and Boost ...
|
The Pros and Cons of Using AI to Automate Tasks and Boost Productivity
|
https://cubo.to
|
[
"Obbaatt Angadia",
"Feb"
] |
The biggest con to using AI to automate tasks is that it can lead to a loss of job security for human workers. Additionally, AI can also lead to a loss of ...
|
Our daily lives are impacted by automation on a significant level. This is especially true in the workplace, where it can help boost productivity and reduce the amount of time that we need to spend on tasks that are not essential.
Yet, adopting automation at work has both benefits and drawbacks.
We'll go over these benefits and drawbacks in this article to help you decide if utilizing AI to automate chores is the best option for you.
The Pros of Automating Tasks with AI
There are a number of pros to automating tasks with AI. Automating tasks can free up your time to do other things, such as marketing or customer service. Also, since you won't have to pay someone to complete the activity for you, it can help you save money. AI can also assist you in monitoring your progress and ensuring that you are accomplishing your objectives.
On the other hand, there are a few cons to using AI to automate tasks. First, AI can be less accurate than human workers. Second, it can be difficult to teach AI how to do a task correctly. Third, AI can be disruptive if it's not used properly. For example, if an AI system is used to automate a task that is currently done by a human, that human may lose their job.
The Cons of Automating Tasks with AI
There are many pros to using AI to automate tasks, but there are also a few cons to consider.
The biggest con to using AI to automate tasks is that it can lead to a loss of human interaction. For example, if you are a doctor and you use AI to automate tasks such as billing and scheduling, you may lose the opportunity to connect with patients on a personal level.
Patients may have a bad experience, and they may lose faith in the doctor's office as a result.
Another con to using AI to automate tasks is that it can lead to a loss of accuracy. If you are automating tasks that are important to the accuracy of your business, you may lose the opportunity to have human error. This can be a negative experience for customers, as well as for the business itself.
AI can also lead to a loss of privacy. If you are using AI to automate tasks, it may be able to learn about your personal preferences and use that information to automate tasks in a way that is not comfortable for you.
The Best Ways to Use AI to Automate Tasks
The use of artificial intelligence (AI) to automate processes has various benefits and drawbacks. Overall, the pros of using AI to automate tasks are that it can save time and boost productivity. However, there are also a few cons to using AI to automate tasks.
The biggest con to using AI to automate tasks is that it can lead to a loss of job security for human workers. Additionally, AI can also lead to a loss of privacy if not used correctly.
How to Automate Tasks with AI
Using artificial intelligence (AI) to automate jobs has both benefits and drawbacks. Using AI in your company has many advantages, but there are also some hazards. Here are some of the pros and cons of using AI to automate tasks:
Pros of AI-driven automation:
AI can improve workflow and efficiency.
AI can save you time and money.
AI can help you to automate tasks that are repetitive or time-consuming.
Cons of AI-driven automation:
AI can lead to the automation of tasks that are not important.
AI can lead to the automation of tasks that are dangerous or hazardous.
AI can lead to the automation of tasks that are unethical.
The Worst Ways to Use AI to Automate Tasks
There are many benefits to using AI to automate tasks and boost productivity. But there are also many ways in which AI can be used poorly, leading to a decrease in productivity and even job losses. Here are five of the worst ways to use AI to automate tasks.
AI is used to replace human workers.
This is the most common way to misuse AI. When AI is used to replace human workers, the human workers are either lost permanently or are reduced to a very low level of work.
This is frequently accomplished by employing AI to complete activities that are either too complex for humans to complete or that automation can now complete more rapidly and effectively than humans could.
AI is used to do the work of multiple workers.
This is also common, but it's often done in a way that is not productive. For example, a company might use AI to do the work of two or three workers, but this will often mean that the workers are required to do more work than they used to do.
Or the workers might be required to do the same amount of work but with more complexity.
AI is used to replace human managers.
This is also a common misuse of AI. When AI is used to replace human managers, the company may find that the AI system is not able to make the correct decisions.
This can lead to a loss of money or a loss of jobs.
AI is used to make decisions that are not in the best interest of the company.
This is also a common misuse of AI. AI can be used to make business decisions like which items to produce or which marketing campaigns to conduct that are not in the company's best interests.
AI is used to make decisions that are not in the best interest of the customers.
This is also a common misuse of AI. AI can be used to make decisions about which clients to serve or which things to sell that are not in the best interests of the customers.
The Top 5 Benefits of Automating Tasks with AI
There are many pros to using artificial intelligence (AI) to automate tasks and boost productivity.
Here are the top five benefits:
Improved Efficiency: AI can help you to complete tasks more quickly and with less effort. This can help you to save time and money.
Improved Accuracy: AI can help you to achieve higher accuracy when completing tasks. This can help you to avoid mistakes and correct them more quickly, which can save you time and money.
Increased Productivity: AI can help you to work more productively, which can boost your efficiency and help you to save time and money.
Reduced Stress: AI can help to reduce the amount of stress you feel when completing tasks.
Increased Confidence: AI can help you to feel more confident when completing tasks. This can boost your morale and help you to work more productively.
The Top 5 Benefits of Using AI to boost Productivity
There are a lot of benefits to using artificial intelligence (AI) to automate tasks and boost productivity.
Here are five of the top benefits:
Reduced Time Wasted on Tasks That Are Slow or Difficult
With AI, you can quickly and easily automate tasks that are slow or difficult to do manually. This can save you a lot of time and energy, allowing you to focus on more important tasks.
Increased Efficiency and Accuracy
With AI, you can achieve a high level of accuracy and efficiency when performing tasks. This can help you to get the most out of your time and resources, and to ensure that your product or service is of the highest quality.
Greater Productivity and Efficiency Across the Organization
AI can help to boost productivity and efficiency across an organization, helping to reduce costs and increase the speed of execution.
Reduced Risk of Errors and Missteps
With AI, you can reduce the risk of errors and missteps by automating tasks. This can help to ensure that your product or service is of the highest quality and that you meet customer expectations.
Increased Customer Satisfaction and Loyalty
With AI helping to automate tasks, you can increase customer satisfaction and loyalty by ensuring that your product or service is delivered on time and with the highest level of quality.
Summary of the Pros and Cons of Automating Tasks with AI
There are many pros and cons to using AI to automate tasks. Here are the key points to consider:
PRO:
-Reduced stress and time spent on repetitive tasks.
-Achieved faster results than manual work.
-Can be used to improve customer service and support.
-Improved accuracy and consistency in work.
-Can help to improve product quality and efficiency.
CON:
-May lead to increased workload for humans.
-May not be suitable for all tasks.
-May require more training than automated systems.
-May create a feeling of dependence on AI.
Conclusion
We hope you enjoyed our blog post about the pros and cons of using AI to automate tasks and boost productivity.
In today's fast-paced world, many people are looking for ways to streamline their lives and increase their productivity.
AI can play a big role in this by automating tasks and making your work life easier. While there are many benefits to using AI to automate tasks, there are also some risks.
We hope that our post has helped you to make an informed decision about whether or not to use AI to automate your work life.
Thanks for reading!
| 2023-02-24T00:00:00 |
https://cubo.to/blog/the-pros-and-cons-of-using-ai-to-automate-tasks-and-boost-productivity/
|
[
{
"date": "2023/02/24",
"position": 32,
"query": "AI job losses"
}
] |
|
Power on: How we can supercharge an equitable digital ...
|
Power on: How we can supercharge an equitable digital future
|
https://www.unwomen.org
|
[] |
... job losses. Stereotypes about who is, and isn't, well suited to STEM play a ... A global analysis of 133 AI systems from 1988 to today found that 44.2 ...
|
Today, women remain a minority in both STEM education and careers, representing only 28 per cent of engineering graduates, 22 per cent of artificial intelligence workers and less than one third of tech sector employees globally. Without equal representation in these fields, women’s participation in shaping technology, research, investments and policy will remain critically limited. The same challenges apply to their access to fast-growing and high-paying careers—an inequality compounded by the fact that, as tech and digital innovation disrupt industries, women will bear the brunt of job losses.
Stereotypes about who is, and isn’t, well suited to STEM play a major role in discouraging girls from entering these fields. These beliefs become a self-perpetuating cycle: without encouragement in tech fields, girls end up lacking necessary knowledge—thus making them less likely to express interest.
Those who do make it into tech often face an actively hostile environment, with a significant pay gap (21 per cent) and considerably lower rates of promotion (52 women for every 100 men). Nearly half (48 per cent) report experiencing workplace harassment. A whopping 22 per cent say they are considering leaving the workforce altogether due to the treatment they’ve received in the sector.
Past efforts to increase women’s representation have often focused on women’s supposed disinterest in STEM fields, rather than on the systems that exclude them. That messaging has actually backfired, fueling the idea that women don’t have real interest or talent in STEM. Effective solutions must target both the barriers that force women out of STEM jobs and those that keep girls from pursuing them in the first place.
Providing universal broadband access for teachers, students and schools—and ensuring digital literacy for its users—can increase girls’ exposure to STEM, particularly those from less privileged backgrounds. Digital learning provides new opportunities to adapt educational environments and curricula to the needs of girls and students from marginalized groups.
Working to eliminate gender biases from schools is also key, as is ensuring that girls have access to women mentors in STEM fields with whom they can identify. And connecting STEM to other disciplines—as well as emphasizing its potential applications to societal challenges, which research shows is a main driver of girls’ career choices—can help increase girls’ interest as well.
To help women succeed in a changing labour market, targeted reskilling and upskilling programmes should be created, focusing especially on groups most in danger of being left behind. And expanded labour regulations are needed to ensure that labour market transitions improve the position of women, rather than simply reproducing existing inequalities. This includes a living minimum wage, regulations against pay discrimination, and social protection systems that address, for example, discrepancies between the unpaid care burdens of women and men.
| 2023-02-24T00:00:00 |
https://www.unwomen.org/en/news-stories/explainer/2023/02/power-on-how-we-can-supercharge-an-equitable-digital-future
|
[
{
"date": "2023/02/24",
"position": 78,
"query": "AI job losses"
}
] |
|
What to do after a layoff: Everything you need to know
|
What to do after a layoff: Everything you need to know
|
https://www.techtarget.com
|
[
"Site Editor",
"Published"
] |
A job provides necessities. If you've been recently laid off, you should do the following: Register for unemployment. Unemployment benefits are generally slow ...
|
Layoffs often occur during times of economic volatility beyond any one company's control.
The American economy has been especially volatile in recent years, in part due to the COVID-19 pandemic and resulting fallout. In the first 44 days of 2023 alone, more than 100,000 employees were laid off, according to Layoffs.fyi. In that time, 345 of the companies with layoffs were tech companies.
Some economists have dubbed the recent economic volatility a rolling recession, where some pockets of the U.S. economy remain unaffected while others experience strife. Not every industry experiences a recession at once, meaning that mass layoffs and job growth can be happening simultaneously.
But if you are laid off, here are some next steps to take.
Get organized Take stock of final pay and benefits to get from your employer before leaving: Request a severance letter. Request a letter that explains the exact reason for being terminated. This will probably already be part of a severance package, but request one if it is not. Have HR forward the letter and any other communications regarding the layoff to a personal email since you will likely no longer have access to company email once you have left. The severance letter should include all the details of the separation, such as the date of your last day and when benefits end. Having this document will be useful in the event of legal issues.
Request a letter that explains the exact reason for being terminated. This will probably already be part of a severance package, but request one if it is not. Have HR forward the letter and any other communications regarding the layoff to a personal email since you will likely no longer have access to company email once you have left. The severance letter should include all the details of the separation, such as the date of your last day and when benefits end. Having this document will be useful in the event of legal issues. Collect severance pay. Collect your final paycheck and make sure that it is the correct amount.
Collect your final paycheck and make sure that it is the correct amount. Account for paid time off. Some companies pay out unused vacation and sick days when an employee is laid off. Consult your employee handbook regarding the company's PTO policy.
Some companies pay out unused vacation and sick days when an employee is laid off. Consult your employee handbook regarding the company's PTO policy. Review 401(k) and pension plans. Ask HR if the old 401(k) can be consolidated with a new one at your next job. If it can't, open a rollover IRA to reinvest the old 401(k). Another option is to cash out the old 401(k), but this comes with significant penalties.
Ask HR if the old 401(k) can be consolidated with a new one at your next job. If it can't, open a rollover IRA to reinvest the old 401(k). Another option is to cash out the old 401(k), but this comes with significant penalties. Review insurance benefits. Look at which insurance benefits will be removed and in what time frame. And don't be afraid to ask your employer to clarify anything you don't understand. Insurance benefits typically last as long as the premiums are paid. Many companies pay a month in advance. In the event of a mass layoff, the federal Worker Adjustment and Retraining Notification Act requires that all employers provide 60 days' notice in advance of plant closings and mass layoffs. Benefits and pay are received as normal until the end of that 60 days when the final check is administered. Many big tech companies had layoffs in the beginning of 2023.
Remain calm Layoffs are not personal, and they are not a result of poor performance -- they are systemic decisions. They generally occur because of restructuring, economic recession, mergers and buyouts. Still, they can be jarring and cause a lot of negative emotions. It's important not to act on these. Handle the departure courteously and professionally so that your reputation remains intact and no bridges are burned. Professional connections from an old job remain valuable even if you're terminated. Maintaining these can only help your chances of being hired in the future. You can also try the following: Ask about outplacement. Outplacement gives ex-employees counseling and access to staffing agencies that can help you get your next job.
Outplacement gives ex-employees counseling and access to staffing agencies that can help you get your next job. Negotiate severance. Some severance packages are negotiable. You should compare your severance package to others in the industry to see if you're able to get more. Some negotiable points include how long you will continue to be paid and when your benefits expire.
Some severance packages are negotiable. You should compare your severance package to others in the industry to see if you're able to get more. Some negotiable points include how long you will continue to be paid and when your benefits expire. Seek legal advice. You might want advice to determine if the decision to terminate you was discriminatory, retaliatory or in violation of the employment agreement.
You might want advice to determine if the decision to terminate you was discriminatory, retaliatory or in violation of the employment agreement. Tell colleagues. Openly tell old connections that you are looking for another job.
Meet basic needs Anything previously covered by your employer will need to come from somewhere else. A job provides necessities. If you've been recently laid off, you should do the following: Register for unemployment. Unemployment benefits are generally slow to kick in, so apply as soon as possible. Eligibility, amount and duration of benefits all depend on individual state laws, so check those to confirm what you are entitled to. Unemployment benefits are based on what you earned at your last job. Each state also has a maximum and minimum benefit amount.
Unemployment benefits are generally slow to kick in, so apply as soon as possible. Eligibility, amount and duration of benefits all depend on individual state laws, so check those to confirm what you are entitled to. Unemployment benefits are based on what you earned at your last job. Each state also has a maximum and minimum benefit amount. Register for health insurance. Once health benefits end, you have a few choices. You can go without health insurance, dependent on state laws; enroll in coverage under the Consolidated Omnibus Budget Reconciliation Act (COBRA); or shop for an individual health plan on the Affordable Care Act's health exchange. COBRA allows you to continue coverage for up to 18 months if you were laid off by a company with 20 or more employees. The health exchange provides a variety of health plan choices, and you can register outside of open enrollment time because being laid off is considered an unforeseen life event. If possible, you might be able to join a family member's or spouse's plan.
Once health benefits end, you have a few choices. You can go without health insurance, dependent on state laws; enroll in coverage under the Consolidated Omnibus Budget Reconciliation Act (COBRA); or shop for an individual health plan on the Affordable Care Act's health exchange. COBRA allows you to continue coverage for up to 18 months if you were laid off by a company with 20 or more employees. The health exchange provides a variety of health plan choices, and you can register outside of open enrollment time because being laid off is considered an unforeseen life event. If possible, you might be able to join a family member's or spouse's plan. Stick to a daily routine. Jobs provide a structure. It's good to retain this daily structure to remain organized and motivated -- and for general wellness. Dedicate the time you used for work to looking for jobs or other organized activities.
Prepare for the future Now that the old job is in the rearview, it's time to move forward. Write down accomplishments. Take stock of your skills and write them down. This helps reconfigure your perspective and reinforces that layoffs are not skill or performance based. This also helps you prepare for interviews that ask about these qualities.
Take stock of your skills and write them down. This helps reconfigure your perspective and reinforces that layoffs are not skill or performance based. This also helps you prepare for interviews that ask about these qualities. Write down what you want. Decide what is important in your next move. Although a layoff is a loss, it can also be an opportunity for a new start. Define your values and use them to evaluate new employers. Some example values include location, company size, role type and pay. Sticking to these values will support success in the next job.
Decide what is important in your next move. Although a layoff is a loss, it can also be an opportunity for a new start. Define your values and use them to evaluate new employers. Some example values include location, company size, role type and pay. Sticking to these values will support success in the next job. Create a schedule. Determine a process for job hunting and stick to it. Set a goal or intention for each day. Some items to consider in your job search program include the following: When will you network? Who do you want to network with? How often will you update your resume and cover letter? What platforms will you use to search for jobs? How often will you practice interview questions?
Determine a process for job hunting and stick to it. Set a goal or intention for each day. Some items to consider in your job search program include the following: The schedule can be augmented as you embark further on your job search journey, but answering these questions initially helps get the ball rolling.
| 2023-02-24T00:00:00 |
https://www.techtarget.com/whatis/feature/What-to-do-after-a-layoff-Everything-you-need-to-know
|
[
{
"date": "2023/02/24",
"position": 90,
"query": "AI job losses"
},
{
"date": "2023/02/24",
"position": 32,
"query": "artificial intelligence layoffs"
}
] |
|
Machine Learning Engineer: The 2023 Guide With 15 ...
|
Machine Learning Engineer: The 2023 Guide With 15+ Examples & Samples
|
https://www.hiration.com
|
[] |
The demand for machine learning engineers is rapidly increasing across industries to automate products with technological advancements. A machine learning ...
|
Click here to directly go to the complete Machine Learning Engineer Resume Sample.
How to become a machine learning engineer?
Machine learning and artificial intelligence are contributing immensely to empowering businesses and brands in this digital era. It can be a promising career for you if you have a knack for data, automation, and algorithms.
The market for machine learning is projected to grow to $152.24 billion in 2028 at a CAGR of 38.6%. If you are looking forward to becoming a machine learning engineer, you must brush up on programming and algorithms to advance professional growth in your career.
Read the blog to know all the aspects of the job and the machine learning engineer skills required to become a machine learning engineer.
Following are the summary points of our blog:
The demand for machine learning engineers is rapidly increasing across industries to automate products with technological advancements.
A machine learning engineer designs algorithms, develops systems, performs statistical analysis, etc., to deliver compelling business value.
Proficiency in programming languages, machine learning platforms, and analytical skills are essential to becoming a machine learning engineer.
Drafting an ATS-friendly machine learning engineer resume is required to present your skills and experience in the right manner for bagging the desired job.
Possessing machine learning engineer certification and experience in real-world projects will give you an edge over the competition.
In our machine learning engineer resume guide, we have answered a few frequently asked questions:
Machine Learning Engineer Salary
According to a trusted source Indeed, the average salary for a machine learning engineer is $141,712 per year in the United States.
According to Payscale, the average machine learning engineer salary is $113,358 per year.
According to Salary.com, the average Machine Learning Engineer salary in the United States is $121,233.
Also read: How much should a machine learning engineer be paid?
What is Machine Learning and What Do Machine Learning Engineers Do?
What is machine learning?
Machine learning is a branch of artificial intelligence that facilitates systems to operate by using data and algorithms.
ML applications focus on enhancing user experience without being explicitly programmed.
Machine learning develops algorithms to allow computers to learn their functions automatically without human interventions by accessing data, gradually improving its accuracy and meeting business needs.
What does a machine learning engineer do?
A machine learning engineer assesses, analyzes, and organizes complex datasets while designing & optimizing artificial intelligence systems, machine learning models, and algorithms.
Machine learning engineering is a rewarding career for anybody who is an analytical thinker and can solve technical problems.
Roles and responsibilities of a machine learning engineer:
Design Machine Learning (ML) systems
Create and implement ML models and algorithms
Select and verify data sets while choosing suitable data representation methods
Develop machine learning applications as per client requirements
Perform statistical analysis
Develop deep learning systems adhering to business requirements
The roles and responsibilities of a machine learning engineer will vary across industries & organizations and can take different forms depending on the project type.
Fresher Machine Learning Engineer Resume Sample
How to Become a Machine Learning Engineer?
What are the skills and qualifications required to be a machine learning engineer?
A machine learning engineer is expected to possess a master's degree and sometimes a Ph.D. in machine learning or a related field.
A professional with a minimum of 1 year experience and a Bachelor’s degree in computer science or related field can also pursue their career in machine learning.
A deep understanding of advanced statistical modeling, analytical methods, deep learning, etc., is a critical component to become a successful machine learning engineer.
We have mentioned the machine learning engineer job description for your reference:
Proficient in machine learning programming languages such as Python, Java, R, etc.
Adept at using machine learning platforms such as Microsoft Azure, IBM Watson, Amazon, etc.
Expertise in probability, data modeling, and strong problem-solving ability
Ph.D. or MS degree in Computer Science, Statistics, Applied Math, Econometrics, or other related fields.
Source: Atlexsoft.com
Bagging the first job or finding new machine learning engineer jobs can be nerve-wracking. Years of professional experience, certification, and projects can go in vain if you fail to present them at their best in your machine learning engineer resume.
Senior Machine Learning Engineer Resume Sample
Machine Learning Engineer Certifications to Pursue in 2023
Technological advancements have exponentially increased the demand for machine learning engineers. Businesses are implementing ML features in their products to provide tremendous business value to their customers.
To ascend your career ladder, from entry-level to junior and then to senior ranks, you need to challenge yourself every day to pick up new skills and stay updated.
Pursuing Andrew Ng’ courses or any machine learning engineer certifications will showcase your curiosity in the field and showcase how updated you are with the latest industry trends to potential employers.
Here are the top 5 high-ranked machine learning engineer certifications to help you uplift your career and bag a high-paying job:
How to display machine learning certification in your resume?
Create a 'Certifications' section in your machine learning resume and list the following details:
Name of the certification/course name
name Name of the certified authority
Location of the institute of affiliation
of the institute of affiliation Date of both enrollment and course completion
Make a bulleted list and add your machine learning engineer certification in the format mentioned below:
Certifications | Certifying Authority | Time
Also read: When to add certifications on a resume?
Possessing machine learning engineer certification can give you an edge over others. Therefore you must present them flawlessly.
5 Machine Learning Engineer Project Ideas to Get You Started
In a saturated job market, it is crucial to stand out from the crowd. Having machine learning projects in your portfolio is convincing evidence of your talent and interest in machine learning. The employer knows why they should hire you over other potential candidates.
This project can be great to work on for beginners. You can use linear regression techniques to build the model or an advanced approach like random forest regressor or gradient boosting.
Sales forecasts can be used to plan out resources and project budgets w.r.t expected demand. For predicting sales, you can use ARIMA, Vector Autoregression, or deep learning.
You can analyze the team performance graphically via Plotly library in Python to interpret team players' performance efficiently.
With advancements in technology and data collection methods, you can now predict heart disease via machine learning algorithms. You can utilize logistic regression machine-learning algorithms to predict heart disease.
If you are looking for a machine learning engineer job in the marketing industry, this can be a great project to work on. You can utilize K-Means clustering or hierarchical clustering to divide customers to render business value.
Junior Machine Learning Engineer Resume Sample
Jackie Jackson Machine Learning Engineer Skilled machine learning professional with 3+ years of experience in designing and developing ML models and systems across diverse industries. Possesses a diverse experience in collating & analyzing data, enhancing existing models, and revamping businessprocesses as part of providing compelling value to key clients. Proficient in collaborating with teams of high-performing professionals for developing ML frameworks and solutions for slashing costs & optimizing time for catapulting business growth. • Machine Learning Model Development • Data Collation & Analysis • Predictive Modeling • System Design & Development • Model Enhancement • Customer Behavior Analysis • Dataset Building • Dashboard Creation • Cost Reduction • Time Optimization • Solution Delivery • Process Improvement • Cross-functional Coordination • Recruitment & Training Tools & Languages : Pandas, scikit-learn, Neo4j, PostgreSQL, Hive, Spark, Python
Statistics/Machine Learning: Statistical Analysis, Linear/Logistic Regression, Clustering, k-means clustering PROFESSIONAL EXPERIENCE Key Achievements Honoured with Employee of the Year Award for surpassing the assigned targets by 35%
Increased market share by 25% as a result of developing customer segmentation algorithm in R
Performed an instrumental role in revamping algorithms for the company's application with 3M+ users System Design & Product Improvement Designing and developing analysis systems as part of extracting valuable information from large scale databases
Researching and developing analysis, forecasting & optimizing methods to improve the quality of 5+ user-facing products
Designed graph database via Neo4j for recommending real-time products to users via a smaller codebase ML Model Development & Cost Optimization Creating synthetic datasets as part of developing models and slashing data acquisition costs by 18%
Developing OpenCV machine learning solutions for senior management as part of facilitating smooth decision making
Building ML models and pipelines for use cases across facets spanning e-commerce, consumer data, markets, logistics, etc. Process Improvement & Cross-functional Coordination Establishing seamless interactions between edge machine learning modules and cloud-based learning systems
Scrutinizing existing Machine Learning (ML) models to identify key areas of modifications and deliver optimal solutions
Developing and implementing Machine learning operations ( MLOps) framework by liaising with a team of 10+ encompassing
Data Engineers, Data Scientists and DevOps engineers INTERNSHIP Predictive Modeling & Data Integrity Developed SQL stored procedures, functions, and style sheets for reducing data retrieval time by 40%
Liaised with the product team of 10+ professionals to integrate ideas into products and develop Machine Learning solutions
Employed decision trees to build predictive models as part of anticipating customers' behaviour
Performed a key role in enhancing data integrity by revamping schemas with 150+ tables Key Project 1: Customer Segmentation
Utilized k-means clustering algorithm to divide customers based on their purchase history, gender, age, interest, etc.
Key Achievement: Increased sales by 25% by running user-specific campaigns
Key Project 2: Housing Prices Prediction
Gathered and analyzed data to forecast house prices in Boston based on crime rate, number of rooms, etc.
Key Project 3: Heart Disease Prediction
Predicted the 10-year risk of Heart Disease w.r.t. diabetes, smoking, high blood pressure, and high cholesterol levels Certificate Program in Machine Learning & Artificial Intelligence | eCornell | Jan '21
Deep Learning Specialization | Coursera | Aug '19
Data Science: Foundations using R Specialization | Coursera | May '19 Master of Science in Machine Learning | Georgetown University | Washington, D.C. | Sep '16 - Nov '19
Bachelor of Science in Computer Science | University of San Francisco | SF, CA | Jun '11 - Aug '15
Key Takeaways
Create an ATS-friendly machine learning engineer resume with the right keywords to beat the bots and get shortlisted.
with the right keywords to beat the bots and get shortlisted. Gain expertise in programming languages like Python and R & operate machine learning tools & software to reach a higher and better position.
like Python and R & operate machine learning tools & software to reach a higher and better position. Pursue machine learning certification , attend online courses, work on machine learning projects to stay updated with the latest industry standards.
, attend online courses, work on machine learning to stay updated with the latest industry standards. A Ph.D. or MS degree in Statistics, Computer Science, Applied Math, Econometrics, or any related field is essential to bag a machine learning engineer job.
Go to Hiration career platform which has 24/7 chat support and get professional assistance with all your job & career-related queries. You can also write to us at [email protected].
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.hiration.com/blog/machine-learning-engineer/
|
[
{
"date": "2023/02/24",
"position": 8,
"query": "machine learning job market"
}
] |
The COST of not adopting AI into your workplace
|
The COST of not adopting AI into your workplace
|
https://aicadium.ai
|
[] |
The costs of not embracing AI are far-reaching, from increased operational costs and missed opportunities to difficulty attracting and retaining top talent and ...
|
In today’s rapidly changing business landscape, companies that don’t incorporate Artificial Intelligence (AI) into their processes are at a significant disadvantage. AI is fast becoming an indispensable tool for organisations seeking to optimise their operations and maintain a competitive edge. AI has the potential to revolutionise the way companies operate, providing them with valuable insights and enabling them to make better, more informed decisions. However, despite its many benefits, many companies still haven’t embraced AI, instead sticking with traditional methods.
There are many factors inhibiting the adoption of AI, and some of the most cited are as follows:
Cost: AI technology and solutions can be expensive, making it difficult for businesses to adopt them. Technical skills: Implementing and maintaining AI technology often requires specialised technical skills, which can be hard to find and costly to acquire. Data quality and availability: AI systems generally require large amounts of data to function accurately. In many cases, data is unavailable, or the quality is poor. Resistance to change: Companies may hesitate to adopt AI due to a lack of understanding of its capabilities and resistance to change traditional business practices and processes. Regulatory and ethical concerns: Data privacy, bias, and transparency are ethical, and, in many cases, regulatory hurdles (both perceived and actual) make some companies hesitant to adopt AI.
The Cost of Not Adopting AI
These are all valid concerns about the difficulty of AI adoption. But what is the price of not adopting AI in your workplace? Let’s explore the cost of not adopting AI and why companies must invest in this technology.
Decreased efficiency and productivity:
A study by McKinsey & Company, AI has the potential to increase labor productivity by up to 40%. AI can automate repetitive tasks, allowing employees to focus on more complex, higher-value work, which can increase overall efficiency and productivity. Missed opportunities:
Another cost of not adopting AI is the missed opportunities for growth and innovation. AI can provide companies with valuable insights to help them make better decisions and grow their business. Companies that don’t embrace AI miss out on these opportunities and will likely fall behind their competitors. A Gartner survey showed that by 2020, 90% of large organisations will have adopted AI in some form, leaving companies that don’t embrace the technology at a disadvantage.
Reduce operational cost
By automating repetitive and manual tasks, AI can help to reduce operational costs by improving efficiency, reducing errors, and streamlining processes. This can result in cost savings by reducing labor costs, reducing the need for overtime pay, and increasing productivity. An Accenture report found that AI can reduce operational costs by up to 60%. By not taking advantage of AI, a business will see increased operating expenses compared to its AI-using competitors. Difficulty attracting and retaining top talent:
A study by Deloitte found that companies that invest in AI and other cutting-edge technologies are more likely to attract and retain top talent within their industries. If your company isn’t investing in AI, you could miss out on top talent and sacrifice your ability to compete with other companies in your industry.
The various costs of not adopting AI in your company are significant. However, the costs of not embracing AI are far-reaching, from increased operational costs and missed opportunities to difficulty attracting and retaining top talent and decreased productivity. Companies that want to stay competitive and remain relevant in today’s fast-paced business environment must invest in AI and other cutting-edge technologies.
Bringing SaaS to AI to Increase Adoption
The exciting news for companies who have yet to embrace AI in their business practices is that a whole new class of AI-driven products are now available that reduce the time and cost of onboarding AI-driven business solutions. Often called the “democratisation of AI,” this trend infuses SaaS (Software as a Service) principles. Typically, SaaS products are easy to use and deploy and provide an enjoyable user experience. Instead of requiring specialised skills, SaaS products are widely useable by people without a software engineering background. By applying SaaS principles to AI, algorithms and models that were once only available to large tech companies with a team of data scientists become available to smaller companies across industries. This democratisation allows AI to bring value to companies where, up until now, it has been out of reach.
Some benefits of the democratisation of AI include:
The ability of smaller companies to compete with larger ones by implementing AI-powered tools for predictive maintenance, process optimisation, quality control, cost reduction, and increased productivity.
Improved safety and reduced risk of accidents by detecting potential safety hazards and providing real-time feedback.
Increased profitability through reduced waste, improved efficiency, and the ability to implement other Lean manufacturing principles.
Better environmental outcomes through reduced energy consumption and more efficient supply chain management across an industry value chain.
Aicadium View
Aicadium View is addressing the democratisation of AI through improved safety and productivity. The tools available in Aicadium View detect visuals, objects, and actions in videos and images to provide workplace insights that create better products and safer, more productive industrial environments. Using cameras within facilities and delivered as an easy-to-use enterprise software tool, Aicadium View empowers individuals and teams to make proactive, data-driven decisions, seamlessly integrating into daily work routines, providing tools for asset inspection, personal protective equipment detection (PPE), and measuring productivity.
Learn more about Aicadium View and how it can transform your company’s operations.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://aicadium.ai/the-cost-of-not-adopting-ai-into-your-workplace/
|
[
{
"date": "2023/02/24",
"position": 1,
"query": "workplace AI adoption"
}
] |
How AI Is Revolutionizing Workplace Safety
|
Artificial Intelligence for Occupational Health and Safety — Kreo
|
https://www.kreo.net
|
[] |
Many companies are turning to artificial intelligence (AI) and automation in an effort to restore workplace safety and combat rising employee stress levels.
|
Increased work demands, lack of employee support, and the adoption of new technologies are driving rising concerns about workplace safety. More than one-third of business leaders believe that workplace safety will become more difficult to maintain thanks to shifts in employee mental health and talent retention.
Many companies are turning to artificial intelligence (AI) and automation in an effort to restore workplace safety and combat rising employee stress levels. The right combination of automation and AI can help improve workplace safety by reducing human error, providing early warning detection, and improving operations.
How Artificial Intelligence Can Improve Worker Safety
Among other fields, the construction industry has already found ways to integrate automation and AI into daily business practices. Construction organizations of all sizes are using technology to estimate costs, predict maintenance patterns, improve safety monitoring, and track the construction takeoff process. This technology keeps employees away from dangerous tasks, helps them avoid burnout, and allows for automatic hazard detection.
Automating Dangerous Tasks
In hazardous work environments like a construction workplace, automation can handle hazardous work traditionally completed by workers. Automating potentially hazardous tasks can help remove workers from dangerous situations and reduce overall risk.
Construction leaders can automate dangerous tasks in a variety of ways. For example, some construction managers use technologies that can automate painting, bricklaying, or other repetitive tasks. Other construction sites use drone technology to inspect construction sites without the need to walk through potentially unsafe environments.
Avoiding Overwork
Overwork and fatigue can be hazardous in any line of work. In a construction environment, they can lead to serious bodily harm to yourself, to others, or to the structures you’re building.
Some construction sites are already deploying technology to help combat the effects of overwork and fatigue. For example, construction companies can provide employees with wearable devices that automatically monitor vitals like heart rate, skin temperature, or other physical movements. These devices help managers identify potential fatigue, removing workers from hazardous work environments before they create additional risks.
Other technologies can help project leaders track where workers spend time while onsite. These programs can help increase accountability and productivity, particularly when workers know their managers are tracking where time is spent. AI-enabled time-tracking programs also help managers ensure that workers are spending time on the most relevant tasks.
Hazard Detection
Computer vision technology can automatically monitor a video feed to detect potential hazards. These programs are trained to monitor the live feed of a single camera or camera network, identifying risks and notifying project leaders before those risks worsen. The same programs can often monitor pre-recorded video sessions, for training purposes.
Hazard detection programs help protect against a variety of different threats. These risks can include unsafe working conditions like exposed chemicals, workers without protective clothing, and other compliance issues. Computer vision can also spot misuse of tools and equipment, trip and fall hazards, unattended vehicles, and equipment out of place.
Security Surveillance
Security systems in a construction workplace can also benefit from automation and AI integration. Some AI algorithms improve hazard detection or object recognition programs, information that triggers alerts whenever the program identifies a potential safety risk. The same AI can also offer facial recognition and motion detection technologies, helping security surveillance programs identify unauthorized personnel or workers that enter a restricted area.
Some automation programs improve the analytical side of security surveillance. For example, video compression AI helps optimize video compression, reducing the amount of data that’s stored and transmitted from one device to the next. This compression improves video feed quality and can accelerate data transfer speeds.
Safety Training
AI is often combined with virtual reality (VR) or augmented reality (AR), to improve the quality of safety training programs. Together, AI and other technologies enhance several aspects of a construction organization’s safety programs, from emergency response training to hazardous waste removal.
Already improving outcomes in the firefighting space, AI and VR provide several key benefits to safety training regimens for construction workers. Combined, these technologies allow workers to experience hands-on training without the need to enter a potentially hazardous construction setting. Workers can navigate virtual environments, make decisions, and analyze those decisions without any risk of actual danger.
Predictive Insights
AI also contributes to the construction planning process, helping workers make accurate calculations and reduce errors. The predictive insights that AI provides can accelerate many stages of pre-construction, including materials inventory, measurements, safety planning and training, and risk assessment.
Situational prediction is a powerful benefit that AI provides. Automated prediction programs allow construction employees to minimize errors during calculation, errors that could have created real risk during the building process. The same tools also allow workers to communicate more effectively, collectively contributing measurements, materials estimates, and cost forecasts to the construction takeoff process. This means contractors can collaborate with clients and laborers, effectively projecting and delegating tasks for a project.
Predicting costs, timelines, and other project details does more than eliminate risk; it also helps save valuable time in the workplace. With reduced potential for accidents, workers can operate confidently and quickly with the support of a data-driven insights program.
Challenges for Artificial Intelligence in the Workplace
Implementing artificial intelligence can also lead to some challenges, particularly if the technology is used incorrectly. Here are some of the challenges AI and automation might face in the workplace:
Employees hesitant to implement technology, particularly workers worried that AI might replace their job;
Difficulties in programming the AI or troubleshooting its issues;
Eventual overreliance on technology that can create a decline in workplace productivity and decision-making;
Security risks when AI and automation require access to sensitive information;
Bias or discrimination in AI, based on the materials the program was trained to understand;
High costs to implement or use automation programs.
Despite hesitations, construction companies are already finding ways to overcome concerns related to AI and automation. For example, companies are providing training for employees unfamiliar with AI — and recognizing when employees use AI to become even more productive. Automation platforms are increasingly trained with a focus on diversity during development, to avoid the possibility of bias during deployment.
The Future of AI for Workplace Safety
AI and automation are already improving the modern construction workplace. They’re creating smarter, safer work environments where employees can spend less time on repetitive tasks and more time making high-level decisions. AI can make better cost and measurement estimations and reduce hazards for employees exposed to potential health and safety risks.
Technology will continue to make construction worksites safer and more secure. For example, autonomous construction equipment can reduce the risk of human error and injury, while new software tools help reduce errors when workers estimate costs, take measurements, or forecast project completion times. AI can also help construction leaders proactively identify and mitigate workplace risks before they materialize.
| 2023-02-24T00:00:00 |
https://www.kreo.net/news-2d-takeoff/how-ai-is-revolutionizing-workplace-safety
|
[
{
"date": "2023/02/24",
"position": 4,
"query": "workplace AI adoption"
},
{
"date": "2023/02/24",
"position": 28,
"query": "AI workers"
}
] |
|
Future of AI in HR: Latest Trends and Tools
|
Future of AI in HR: Latest Trends and Tools
|
https://blog.darwinbox.com
|
[
"Chaitanya Peddi",
"Co-Founder Of Darwinbox",
"Dhrishni Thakuria"
] |
AI frameworks become available in the open-source domain to help HR technology developers; Organizations get more digitally mature to support AI in HR adoption.
|
In HR, artificial intelligence (AI) has multiple, diverse applications. It’s used for self-learning technologies, for HR data processing in order to gain insights, or automate processes. Read on to learn about the latest developments in AI in HR, the common practices and processes where companies use AI, and the prospects for AI in HR.
2022 research shows that nearly 1 in 4 organizations are using automation and AI in HR. It also shows that the benefits of artificial intelligence in human resources range from time savings (85%) to better hiring (64%). Which some of these applications have been around for a few years now, things are evolving, and quite rapidly at that. We’re seeing a lot of new trends in HR practices using AI, and things will continue to change.
What Will the Future of AI in HR Look Like?
Today, AI in HR refers to the use of advanced, self-learning algorithms for HR data analysis, predominantly to generate insights and recommendations or automate tasks
As AI evolves, HR systems that use it can also get increasingly powerful. For example, five years ago, AI-based HR systems could possibly auto-recommend the top 10 candidates for a job. Now, it can generate scores that indicate exactly how aligned the candidate is with the role’s requirements. The future of AI in HR looks promising.
For instance, technology has already advanced to the stage where:
AI algorithms get more accurate and provide smarter insights
Data hosting to feed AI engines gets more affordable
AI frameworks become available in the open-source domain to help HR technology developers
Organizations get more digitally mature to support AI in HR adoption
In the future, we can expect advancements in AI technology that it will not only shortlist candidates, but it will also select and automatically hire and onboard the right person for the job, at least for routine, entry-level roles. And this is just one example of what AI can do at scale. AI’s impact extends to nearly every field of HR, from employee engagement to performance management and data-related activities.
Learn more: Is the Metaverse Workplace the Future of Work?
Applications of AI in HR: 10 Emerging Trends
The future of AI in HR will be shaped by the following 10 trends.
AI-driven hiring will become the default mode of recruitment
For any HR department, the most time-consuming activity in the hiring process continues to be the review of resumes. Identifying the perfect candidate with the required abilities and experience amongst hundreds of resumes is the most difficult aspect of recruitment. Using AI, these repetitious manual screening processes are automated, at least partially.
Resumes can be screened automatically using machine learning (ML) algorithms, and the system can then shortlist those that are most relevant to every position. Standardized job matching will undoubtedly save HR professionals time, and enhance the quality of their hiring. This is already being used in a few organizations and is one of the biggest benefits of artificial intelligence in human resources. In the next few years, we will see this trend grow, and scale such that every organization has the option to automate a large part of the recruitment and hiring process.
Employee onboarding processes will be predominantly automated
Onboarding and inducting new employees is typically a tiresome and repetitive process, as anyone who has managed an onboarding program can attest. The problem gets worse in large, distributed enterprises, particularly now after remote hiring is becoming the norm. Using AI, the HR team can configure and automate an onboarding procedure in a way that it is more structured, efficient, and individualized. AI technology can, for instance, automate the following stages of the new employee onboarding process:
Verifying documents
Induction and orientation
Organizing meetings with new employees
Handling administrative tasks like creating ID cards and other such documents
Handling IT device and network access requests
Learning and development (L&D) platforms will integrate AI
Training and development for employees is another function that can very easily and efficiently leverage AI technology. AI tools and AI-based software can be use to design and customize learning programs for individuals based on their unique requirements and competencies, enabling employees to learn more efficiently and enhance their skills.
AI-based products will give companies the power to offer several levels of training materials to workers based on their specific skills, work roles, and interests. There could, for instance, be a tool that recommends the most appropriate training programs based on the employee's current skills and the skills gap that must be filled. Further, these AI systems could provide individuals who have finished a course with additional courses that will help them update their abilities. Organizations can also use AI to set up self-service portals so employees have easy access to internal resources as well. The benefits of artificial intelligence for HR are obvious particularly with talent development, upskilling, or reskilling.
Employee referrals will be more accurate and predictable
Streamlining referrals is among the new trends in HR practices using AI. This refers to using AI to assist HR departments in gaining a better understanding of employee recommendations or referrals, and make the employee referral process more efficient. The software can examine the types of applicants referred by employees and offer information as to who recommends the most successful prospects. It can also be used to analyse performance data from prior referrals and identify when candidates similar to high-performing employees are being recommended. This becomes particularly important in a tight talent market, and when companies wish to hire employees who will fit into the organizational culture.
Learn more: Chatbots In HR Tech - The Best Is Yet To Come
Human resource information systems (HRIS) will be more effective and beneficial
The dynamic relationship of AI with data management systems offers significant implications for large-scale HRIS installations. By integrating AI across the data management system, database query efficiency and precision may be boosted, while also optimizing how you allocate human efforts. This is among the top benefits of artificial intelligence in human resources.
HR leaders will have to develop unique, high-quality skills as AI gains popularity
As stated in the Future of Jobs Report by the World Economic Forum, the demand for uniquely human capabilities will steadily increase. The World Economic Forum predicts that 75 million manual jobs will be lost due to the automation of everyday tasks and the use of AI. However, 133 million new positions will be generated, and emotional and scientific/technical intelligence, like technological design and programming, will be vital. Alongside the benefits of artificial intelligence in human resources, organizations will also have to consider these new requirements that will arise in the future.
AI will improve employee productivity and performance management
Every individual brings unique abilities, interests, and attitudes to his position. They all want growth, but managers seldom have the opportunity to individually present their employees with a variety of tips for enhancing their abilities and performance. AI can be used to ease this process, thanks to new trends in HR practices using AI technology.
By collecting personalized data on each individual, their role, and their talents, AI and ML algorithms may offer suggestions on the activities that other employees in comparable situations have undertaken to progress in other organizations. A strong trend we are seeing in the industry today isusing AI tooffer tailored learning advice and performance goals depending on employee abilities and positions by analyzing prior performance patterns.
AI will also assist with performance management programs like monitoring team productivity, and finding areas for improvement.
Attrition will fall, thanks to the use of AI in HR
Employee engagement is based on several organizational variables. Various workers demand different perks, incentives, inspiration, and guidance.
AI systems are capable of learning from past patterns and establishing a benchmark for interaction variables for each collection of attributes. It may then identify a pattern of employee turnover based on employee expectations and discontent. AI will be able to aid HR managers in identifying possible retention risks and preventing top employees from leaving the organization – a massive benefit of using artificial intelligence in human resources.
HR chatbots will become commonplace
Employee engagement is a discipline unto itself, and monitoring and evaluating worker sentiment on a daily basis is a component of this science. With insight from sentiment analysis of data around employee queries, AI-powered chatbots can ensure that the employee engagement process is a continuous, fruitful one.
Chatbots can be nearly realistic, human-like, and always-available, and involves the user in personalized interactions. These dialogues can then be examined and used to address the employee's unique issues, desires, and requirements. In addition to using AI in HR though, a human must be in the feedback loop, something commonly referred to now as "HITL” or Human in the Loop".
AI will drive almost all HR decisions
An automation tool cannot totally replace human decision-making, but a well-implemented AI system can provide you with the necessary analytics and data to make smarter, more effective, fact-based choices.
AI technology can be used to conduct surveys, collect feedback, and evaluate diverse business-related data such as productivity levels, employee engagement, performance, and areas for improvement. With vast, important, and specialized information at hand, HR directors would be able to make sound, more-informed decisions.
In the future, AI will enable true prescriptive HR analytics – i.e., systems and dashboards that auto-generate actionable recommendations in a natural language.
Learn more: Switch to Comprehensive HR Solutions for a Powerful Digital Workforce
Want to Get Started With AI in HR? Start Using these 4 Tools
In many ways, the future of AI in HR is already here. There are several HR technology solutions that offer powerful in-built features driven by artificial intelligence, so you do not have to invest in complex AI training, algorithm development, or hosting data.
To fast-track your journey toward the future of AI in HR, here are five tools you can start exploring right now:
AI-powered robotic process automation (RPA)
Organizations that are taking their first steps with using AI for HR could start with RPA, that automates and eases several manual tasks. It can relieve workers of mundane, repetitive tasks so they may focus on more strategic and meaningful work.
Employee onboarding is a fantastic example of how RPA powered by artificial intelligence can simplify processes. According to their department and position, multiple qualifications and documentation may be required from each employee. The RPA system can quickly identify and obtain the relevant paperwork for each employee based on predefined criteria.
Unified HR Tech suites powered by AI
This type of software is an all-inclusive HR solution. It will assist you right from the start of the employment process, with responsibilities such as assessing the best applicant referral sources. It can provide predictive data and interaction strategies to keep applicants and employees engaged throughout the employment lifecycle. It might also involve workers with a training chatbot as a retention management strategy. Artificial intelligence, here, is seamlessly interwoven into the HR technology suite and makes every feature better.
Learn more: Transform Your Recruitment Operations With Technology
Social experiences in the workplace powered by AI
There are several employee social media platforms that help in engagement, recognition, and rewards. Just like regular social media, these platforms use AI algorithms to boost relevant posts, highlight available communities, and nudge users toward greater engagement. This is among the top new trends in HR practices using AI, which uses machine intelligence to build human connections.
Artificial intelligence in payroll
The most sophisticated payroll tools today already use AI. It helps in continuous data ingestion and validation. The AI can perform automated compliance checks, and if there is any error, the AI knows who to approach for approval. This type of HR technology gives you a headstart on the future of AI in HR by paving the way for salary benchmarking, pay equality, etc.
Learn more: 3 Talent Management Challenges That Can Be Solved With Technology
The potential for AI in shaping the future of HR is limitless. HR tech companies are building this future by investing in emerging neural technologies, intuitive voice bots, touchless interfaces, and prediction engines.
Given all the new trends in HR practices using AI, modern, unified HRMS platforms such as Darwinbox can help ramp up your digital transformation journey. Schedule a demo today!
| 2023-02-24T00:00:00 |
https://blog.darwinbox.com/future-of-ai-in-hr-tech
|
[
{
"date": "2023/02/24",
"position": 33,
"query": "workplace AI adoption"
},
{
"date": "2023/02/24",
"position": 20,
"query": "AI labor market trends"
},
{
"date": "2023/02/24",
"position": 96,
"query": "AI workers"
}
] |
|
Licensing and AI: Understanding the Challenges of ...
|
Licensing and AI: Understanding the Challenges of Licensing AI Models
|
https://www.velaw.com
|
[] |
AI model licenses begin like any other software agreement, but negotiating those licenses requires a careful eye on AI-specific issues.
|
Artificial intelligence (AI) models are transforming industries and the workplace. While few companies will create AI models from scratch, most will find themselves licensing AI models from others. Negotiating those licenses requires a keen understanding of the risks and rewards of AI licensing. AI model licenses begin like any other software agreement, but negotiating those licenses requires a careful eye on AI-specific issues. AI models can be creative, have an enormous need for training data, and vendors often oversell the model’s capabilities. As a result, licensees should consider these challenges during negotiations. Below is a brief introduction to some of these issues.
Intellectual Property
What intellectual property (IP) rights exist in the output of an AI model? Can AI models create trade secrets, copyrights, or even inventive subject matter? If so, who owns the associated IP rights? The owner could be the licensor or licensee (or maybe the model itself?). The answers to these questions are not clearly defined, however, the U.S. Court of Appeals for the Federal Circuit recently confirmed that U.S. patent law requires an “inventor” to be “a human being,” and upheld the U.S. Patent Office’s rejection of patent applications for AI generated inventions. Nevertheless, a licensee can at least define its rights as against the AI model licensor in the license. Licensees should ask that all IP rights created by the AI be assigned to the licensee. For example, the makers of ChatGPT assign all rights to model outputs to their users. If a licensor refuses a similar grant, a licensee should at least ensure that it retains adequate rights to support its business, even after termination. Examples of these rights include, but are not limited to, the rights to reproduce the output, make derivative works of the output, and distribute the output. Otherwise, the licensor could use its rights as bargaining leverage against the licensee.
Performance and Liability
Despite the promise of AI systems, many are still experimental, and AI vendors may over-promise and under-deliver. Licensees should insist on minimum performance metrics to ensure that the licensed model provides adequate accuracy, reliability, and robustness. If the model does not perform as expected, the business consequences may be severe, and could lead to litigation. Licensees should craft warranties and indemnities to ensure that they do not unreasonably bear the risk of underperformance. The licensee should also insist on thorough testing and validation, ideally in advance of the license and on an ongoing basis. Licensees may benefit from a “trial period” to see how the system performs in their business.
Data Protection and Confidentiality
Data is essential to the development of artificial intelligence. As a result, AI vendors often seek to utilize their licensee’s data to improve their products and services. However, many of these vendors lack significant experience or sophistication in privacy and cybersecurity, making data protection and confidentiality even more critical. While data transfers are a standard component of software licenses, using licensee data to improve AI products presents additional privacy and cybersecurity concerns beyond those of a typical software agreement.
Licensees should ensure that any uses of data are consistent with applicable privacy laws and consistent with the privacy notices provided to their users. Numerous states are adopting laws relating to AI and automated decision-making, so licensees will need to stay updated on developments in this area to ensure ongoing compliance.
Further, any transfer of licensee data to the licensor is potentially vulnerable to theft while in the licensor’s hands. Licensees should ensure that licensors take adequate measures to protect licensee data. Some types of data, like protected health information (PHI) and payment card data require specific protections be included in agreements sharing such data. Licensees should consider their own compliance requirements when negotiating the license and ensure the license is consistent with those uses.
What This Means for You
The popularization of AI models brings a complex landscape of legal considerations. As AI becomes commonplace, companies need a solid grasp of these considerations. By staying up to date on AI regulation and seeking the advice of legal counsel, companies can responsibly harness the power of AI technology.
| 2023-02-24T00:00:00 |
https://www.velaw.com/insights/licensing-and-ai-understanding-the-challenges-of-licensing-ai-models/
|
[
{
"date": "2023/02/24",
"position": 35,
"query": "workplace AI adoption"
}
] |
|
Artificial Intelligence (AI) in Supply Chain and Logistics
|
Artificial Intelligence (AI) in Supply Chain and Logistics
|
https://throughput.world
|
[] |
AI-based automated tools can ensure smarter planning and efficient warehouse management, which can, in turn, enhance worker and material safety. AI can analyze ...
|
Speed in decision-making. Speed in reducing cycle-times. Speed in operations. And, speed in continuous improvement. The use of Artificial Intelligence (AI) in the supply chain is here to stay and will make huge waves in the years to come.
According to Gartner, supply chain organizations expect the level of machine automation in their supply chain processes to double in the next five years.
At the same time, global spending on IIoT Platforms is predicted to grow from $1.67B in 2018 to $17.41 Billion in 2025, attaining a 40% compound annual growth rate (CAGR) in seven years.
In today’s connected digital world, maximizing productivity by reducing uncertainties is the top priority across industries. Plus, mounting expectations of supersonic speed and operational efficiencies further underscore the need to leverage the prowess of Artificial Intelligence (AI) in supply chains and logistics.
Accelerating Supply Chain Success with Artificial Intelligence (AI) in Supply Chains & Logistics
AI in supply chains can deliver the powerful optimization capabilities required for more accurate capacity planning, improved demand forecasting, enhanced productivity, lower supply chain costs, and greater output, all while fostering safer working conditions.
The pandemic and the subsequent disruptions has demonstrated the dramatic impact of uncertainties on supply chains and has established the need for smart contingency plans to help companies deal with these uncertainties in the right way.
But is AI the answer? What are the AI use cases for supply chains as they struggle to get their logistics back on track? Let’s find out.
AI in Supply Chains – The Business Advantage
Accurate Supply Chain Inventory Management
Accurate inventory management can ensure the right flow of items in and out of a warehouse. Simply put, it can help prevent overstocking, inadequate stocking and unexpected stock-outs.
But the inventory management process involves multiple inventory related variables (order processing, picking and packing) that can make the process both, time consuming and highly prone to errors.
Here is where AI driven supply chain planning process and tools, with their ability to handle mass data, can prove to be highly effective. These intelligent systems can analyze and interpret huge datasets quickly, providing timely guidance on forecasting supply and demand.
Some of the AI systems are so advanced that they can even predict and discover new consumer habits and forecast seasonal demand. This level of AI application can help anticipate future customer demand trends while minimizing the costs of overstocking unwanted inventory.
Warehousing Efficienty
An efficient warehouse is an integral part of the supply chain. AI in inventory management can assist in the timely retrieval of an item from a warehouse and ensure a smooth journey to the customer.
AI systems can also solve several warehouse issues, more quickly and accurately than a human can, and also simplify complex procedures and speed up work. Also, along with saving valuable time, AI-driven automation efforts can significantly reduce the need for, and cost of, warehouse staff.use
Enhanced Safety
AI-based automated tools can ensure smarter planning and efficient warehouse management, which can, in turn, enhance worker and material safety.
AI can analyze workplace safety data and inform manufacturers about any possible risks. It can record stocking parameters and update operations along with necessary feedback loops and proactive maintenance.
This helps companies react swiftly and decisively to keep warehouses secure and compliant with safety standards.
Reduced Operations Costs
Here’s one benefit of AI systems for the supply chain that one simply can’t ignore. From customer service to the warehouse, automated intelligent operations can work error-free for a longer duration, reducing the number of human oversight-led errors and workplace incidents.
Additionally, warehouse robots can provide greater speed and accuracy, achieving higher levels of productivity – all of which will reflect in reduced operations costs.
On-time Delivery
As we discussed above, AI systems help reduce dependency on manual efforts, thus making the entire process faster, safer and smarter. This helps facilitate timely delivery to the customer as per the commitment.
Automated systems accelerate traditional warehouse procedures, removing operational bottlenecks along the value chain with minimal effort to achieve delivery targets.
Challenges of AI in Supply Chain
The potential of AI-driven supply chain and logistics is undisputed. However, to say that the path to become AI-powered is without challenges would be a lie.
To build successful supply chains, you must also be aware of the challenges of AI in supply chain that you might encounter along the way.
System Complexities
AI systems are usually cloud-based, and require expansive bandwidth. Sometimes, operators also need specialized hardware to access these AI capabilities and the cost of this AI-specific hardware can turn out to be a huge initial investment for many supply chain partners.
The Scalability Factor
Since most AI and cloud-based systems are quite scalable, the level of initial start-up users/systems that may be needed to be more impactful and effective could be higher.
Since all AI systems are unique and different, this is something that supply chain partners will have to discuss in depth with their AI service providers.
The Cost of Training
Like any other new technology solution, adoption of AI and its effective use will require personnel training, which is another aspect that’ll need significant investment in terms of time and money.
This can impact business efficiency as supply chain partners will need to work closely with the AI providers to create a training solution that is impactful and at the same time, affordable during the integration phase.
The Operational Costs Involved
An AI-operated machine has an exceptional network of individual processors and each of these parts need maintenance and replacement from time-to-time.
The challenge here is that due to the possible cost and energy involved, the operational investment could be quite high. When the time comes to replace some of these parts, the utility bills could shoot up and could directly impact the overhead expenses.
Scouting for the Needle in the Supply Chain Haystack
Data was once the barrier to effective use of AI. Not anymore. There is no dearth of data at most organizations. Smart investments in technologies like Artificial Intelligence (AI) are helping companies capture huge amounts of previously disaggregated data, but there arises a bigger question:
Is there a way to detect business bottlenecks sooner, given this ever-exploding pile of mashed-up data?
To guarantee results, supply chain managers need to be able to cut through the data noise with a powerful tool. A tool that can make use of this vast amount of data with targeted operational analytics to detect, quantify and rank the bottlenecks building-up in business processes early on.
What is an Example of AI in Supply Chains
Considering that supply chain is a multi-functional department, there are a number of examples for successful application of AI.
Faster and More Accurate Decision Making
In ai supply chain management, decisions need to be made every minute at strategic, operational, and tactical levels. It is impossible for humans to make all these decisions accurately and consistently.
This is where supply chain decision intelligence comes into play.
Driven by powerful advanced supply chain analytics, decision intelligence provides end-to-end visibility and insightful recommendations to drive improvements within the supply chain.
Take the case of a global retailer, for example.
The pressure to maintain high customer service levels led this company to incur enormous logistics costs due to poor demand planning and last-minute expedited shipments.
By utilizing ThroughPut’s supply chain intelligence capabilities, the company was able to prioritize their top-performing SKUs using a value-demand matrix and manage allocations accordingly.
This approach reduced unplanned logistics costs, saving up to €3.5 million per year in logistics expenses.
Precise Near-term Demand Sensing
Demand-driven supply chain management can significantly enhance the responsiveness of supply chains. However, one of the greatest challenges for most businesses is dealing with fluctuating demand due to seasonality and other variables.
AI enables real-time demand sensing, allowing businesses to predict near-term demand fluctuations and manage upstream activities with greater agility.
Church Brothers Farms, a company specializing in fresh farm produce, faced significant challenges due to the perishability of their products. Accurate demand forecasting was essential to ensure product quality and minimize wastage.
By leveraging ThroughPut’s Demand Sensing capabilities, Church Brothers Farms was able to:
Analyze Multiple Variables: Incorporate various factors affecting demand, such as seasonality, weather conditions, and market trends.
Enhance Forecast Accuracy: Achieve a higher precision in demand forecasting, leading to better inventory management.
Reduce Product Wastage: Minimize wastage by aligning production and distribution more closely with actual demand.
As a result, Church Brothers Farms improved order fulfillment and reduced product wastage, demonstrating the effectiveness of AI in demand-driven supply chain management.
Dynamic Inventory Management
The costs associated with overstocking or understocking are significant concerns for many businesses.
AI-driven dynamic inventory management systems can help address these challenges by:
Real-Time Inventory Tracking: Utilizing real-time data to monitor inventory levels and sales trends.
Predictive Analytics: Applying advanced analytics to forecast demand accurately and adjust inventory levels accordingly.
Automated Replenishment: Automatically triggering replenishment orders based on real-time inventory data and predictive demand signals.
Take the example of a fast-growing coffee retail chain.
Their cafe business was struggling because, in their quest to meet ever-growing and shifting customer demands, they were stockpiling raw materials needed to prepare items on their menu.
As a result, their inventory costs were rising, and product wastage was becoming a growing concern.
By leveraging ThroughPut’s AI-powered inventory management, the coffee chain gained SKU-level visibility of product demand and studied inventory turnover rates to optimize stock levels.
This enabled them to reduce their inventory by 15%, lowering overall costs and minimizing wastage.
Through AI-driven dynamic inventory management, the coffee chain was able to balance inventory levels more effectively, resulting in cost savings and improved operational efficiency.
Supplier Lead Times and Logistics Management
Supplier lead times can greatly impact a company’s ability to meet customer demands and maintain optimal inventory levels. By using AI, businesses can gain better visibility into supplier performance and lead times. This allows them to:
Monitor Supplier Performance: Track and analyze supplier lead times in real-time, identifying patterns and potential delays.
Predict Delays: Use predictive analytics to anticipate potential delays and proactively address them.
Optimize Ordering: Adjust ordering schedules based on real-time data and predictive insights to ensure timely replenishment.
Metro Railroad North is a standout example of effective supplier lead time and logistics management.
As a transportation service that keeps New York moving, downtime due to parts unavailability can become a major operational issue for the MTA.
To stay on top of supplier performance and use predictive analytics to mitigate potential downtime, ThroughPut engaged with the brand and drove significant results.
By partnering with ThroughPut, Metro Railroad North was able to:
Gain Real-Time Visibility: Monitor supplier lead times and logistics performance in real-time, allowing for quicker responses to potential issues.
Use Predictive Analytics: Leverage predictive analytics to forecast potential downtime and proactively manage supplier performance.
Improve Operational Efficiency: Ensure timely availability of parts, reducing downtime and maintaining smooth operations.
Day-to-day Benefits of AI-Powered Supply Chains
Studies suggest that AI and Machine Learning (ML) technologies can deliver unprecedented value to supply chain and logistics operations.
From cost savings, reduced operational redundancies, risk mitigation, to enhanced supply chain forecasting, speedy deliveries, more optimized routes and improved customer service, AI in the supply chain is being preferred by several top companies globally.
According to McKinsey, 61% of manufacturing executives report decreased costs, and 53% report increased revenues as a direct result of introducing AI in the supply chain.
Further, more than one-third suggested a total revenue bounce of more than 5%. Some of the high impact areas in supply chain management include planning and scheduling, forecasting, spend analytics, logistics network optimization and more, further discussed below.
Bolstering Planning and Scheduling Activities
Most often, supply chain managers struggle to establish an end-to-end process to plan for profitable supply network accounting, especially while being faced daily with increasing globalization, expanding product portfolios, greater complexity, and fluctuating customer demand.
Lack of complete visibility into existing product portfolios due to unplanned events, plant shutdowns, or transportation problems makes this task even more convoluted.
A typical smart supply chain framework includes multiple products, spare parts, and critical components, which are responsible for accurate outcomes. In many supply chain industries, these products or parts can be defined using multiple characteristics that take a range of values.
This can result in a high number of product configurations and applications. Also, in many cases, products and parts are also phased-in and phased-out regularly, which can cause proliferation leading to uncertainties and the bullwhip-effects up and down the supply chain.
By implementing AI in supply chain and logistics, supply chain managers can enhance their decision making by predicting building-up bottlenecks, unforeseen abnormalities, and solutions in order to streamline production scheduling that otherwise tends to be highly variable.
Furthermore, AI in supply chain can also lead to accurate predictions and quantification of expected outcomes across different stages of the schedule enabling the scheduling of more optimal alternatives as and when such interruptions occur during execution.
Intelligent Decision-making
AI-lead supply chain optimization software amplifies important decisions by using cognitive predictions and recommendations on optimal actions.
This can help enhance overall supply chain performance. It also uncovers possible implications across various scenarios in terms of time, cost, and revenue. Also, by constantly learning over time, it continuously improves on these recommendations as relative conditions change.
End-to-end Visibility
With the complex network of supply chains that exist today, it is critical for manufacturers to get complete visibility of the entire supply value chain, with minimal effort.
Having a cognitive AI-driven automated platform offers a single virtualized data layer to reveal the cause and effect, to eliminate bottleneck operations, and pick opportunities for improvement. All of this using real-time data instead of redundant historical data.
Actionable Analytical Insights
Several companies today lack key actionable insights to drive timely decisions that meet expectations with speed and agility. Cognitive automation that uses the power of AI has the ability to sift through large amounts of scattered information to detect patterns and quantify tradeoffs at a scale, much better than what’s possible with conventional systems.
Inventory and Demand Management
One of the biggest challenges faced by supply chain companies is maintaining optimum stock levels to avoid ‘stock-out’ issues. At the same time overstocking can lead to high storage costs, which on the contrary, don’t lead to revenue generation either.
Bringing in the perfect balance here is mastering the art of inventory and warehouse management.
When applied to demand forecasting methods, AI & ML principles create highly accurate predictions of future demand. For example, forecasting the decline and end-of-life of a product accurately on a sales channel, along with the growth of the market introduction of a new product, is easily achievable.
Similarly, ML & AI in supply chain forecasting ensures material bills and PO data are structured and accurate predictions are made on time. This empowers field operators to maintain the optimum levels required to meet current (and near-term) demand.
Boosting Operational Efficiencies
Besides the treasures still largely trapped in disaggregated data system silos at most corporations, IoT-enabled physical sensors across supply chains now also provide a goldmine of information to monitor and manipulate supply chain planning processes too.
With billions of sensors and devices, analyzing this pot of gold manually can create huge operational resource wastage and delayed production cycles. This is where intelligent analytics powered by ai in supply chain and logistics delivers immense value.
When supply chain components become the critical nodes to tap data and power the machine learning algorithms, radical efficiencies can be achieved. The value is realized through the application of machine learning in price planning.
The increase or decrease in the price is governed by on-demand trends, product life cycles, and stacking the product against the competition. This data is priceless and can be used to optimize the supply chain planning process for even greater efficiencies.
Unlocking Fleet Management Efficiencies
One of the most underrated aspects of the supply chain is the fleet management process. Fleet managers orchestrate the vital link between the supplier and the consumer and are responsible for the uninterrupted flow of commerce.
Along with rising fuel costs and labor shortages, fleet managers constantly face data overload issues. Managing a large fleet can easily seem like a daunting task more akin to an air traffic controller.
If you can’t find the information you need quickly, or properly utilize the data you collect, you may find your data pool quickly turning into an unproductive swamp.
AI in supply chain and logistics provides real-time tracking mechanisms to gain timely insights including the optimal times by where, when, and how deliveries must and should be made.
Such powerful multi-dimensional data analytics further aids in reducing unplanned fleet downtime, optimizing fuel efficiencies, detecting and avoiding bottlenecks. It provides fleet managers with the intelligent armor to battle against the otherwise unrelenting fleet management issues that occur on a daily basis.
Streamlining Enterprise Resource Planning (ERP)
A study by Panorama Consulting determined that “63% of manufacturing companies exceed their ERP budgets with average implementation costs overrun rising to $3 million.” Because supply chain managers deal with heterogeneous purchasing, procurement, and logistics across global supply chains, they tend to have more complex business processes than what a traditional software can handle.
AI in supply chain and logistics helps streamline the ERP framework to make it future-ready and connect people, processes, and data in an intelligent way. Finally, when AI is correctly implemented on ERP and related data systems, data becomes more receptive and event-driven over time, while processing greater amounts of data, to intelligently learn, quantify, rank, and prescribe remedies proactively and more frequently over time.
AI in Supply Chain: a Future Full of Promises
Gartner predicts that “The rise of IIoT will allow supply chains to provide more differentiated services to customers, more efficiently”.
As supply chain companies shift their focus from products to outcomes, traditional business models will become dated and then obsolete altogether, with the bodies and brands of the laggards and losers scattered along the way.
With global supply chains strengthening their roots, competitive pressures will force firms to extract every possible ounce of cost from their respective operations.
This is even more pronounced for local, regional, and national firms that are limited in their economies of scale, currency hedge capabilities, market concentration, with limited technology and operational budgets.
In such cases, looking at and embracing the winning SaaS and cloud solutions is a strategy for keeping up, and getting ahead of, the international conglomerates with massive IT and OT budgets, and greater margins of error in the near-term for making poor and expensive supply chain optimization technology mistakes with expensive consultants.
With all these influences coming to bear simultaneously, we are about to see a paradigm shift from simple reactive intelligence to predictive, adaptive and continuous learning systems that drive better decisions for continuous improvements using ML and AI in supply chain and ML on your existing data sources.
According to PwC, AI applications have the power to transform the way business is done and contribute up to $15.7 trillion to the global economy by 2030.
Today, AI can seed in the much needed agility and precision in supply chain optimization. It can also trigger a transformational increase in operational and supply chain efficiencies and a decrease in costs where repetitive manual tasks can be automated.
Readying Your Supply Chain for Artificial Intelligence: What You Need To Do First
Before investing heavily in new technologies, you must first assess your state of digital readiness. This assessment involves three steps:
How to get your supply chain ready for AI
1. Set Realistic Expectations
Every organization must conduct a self-awareness test before committing to AI implementation. Gather key internal stakeholders and ask thoughtful questions that scrutinize the targets and goals of a proposed implementation.
If you haven’t yet had formal discussions about new technology integrations, decide what these integrations might help you achieve.
Quantify your broad expectations for the short and long term. Weigh those against the hypothetical costs of implementation — including technology-acquisition expenses; the effects of temporary productivity disruption; and the labor costs of installation, setup and training.
At this stage, it can be useful to establish new KPIs to measure the impact of integrating AI in supply chain management. These should be related to the company’s traditional high-level goals. At a more granular level, professionals should understand how AI and automation will contribute to specific company operations.
Digital transformation doesn’t occur in a vacuum —existing personnel and processes across the organization will be impacted, even if the implementation is on a relatively small scale.
Once you have (1) an idea of the expected ROI of AI, (2) the potential impacts of digital transformation and (3) an estimate of costs, start thinking about your project timeline. Here, your focus should be on long-term efficiency gains, rather than immediate fixes.
Your investment is not going to pay off right away. The benefits of AI-powered supply chain management are cumulative in nature, and you’ll likely have to make near-term sacrifices to achieve significant future advantages.
2. Know How the Company Uses Technology
After understanding what you hope to gain from AI in supply chain, from a broader operational standpoint, assess your organization’s technology readiness. That assessment should be focused on three components: people, skills and tools.
Start by consulting with human resources staff to gain an understanding of the potential personnel impacts of technological transformation. Chances are good that you’ll need to bring in specialized personnel to fill new roles in your organization, so you’ll need a plan for identifying and recruiting those people. You may also need to train existing employees and ensure they understand how their responsibilities and workflows will change during and after implementation.
Examine your existing technology stack and discuss its advantages and limitations with relevant stakeholders. Interoperability is a critical measure of tech readiness, so try to get a sense of how well your various technologies are working together now.
Do this by asking questions: What is the language used for this application, and is it used for any others? How efficient are the data collection and storage tools, and how easy is it to retrieve data on demand? To what extent are we leveraging open-source technologies?
Are our critical applications closed and dependent on vendor services and customization, or are they interoperable and application programming interface (API)-ready?
Looking ahead, you’ll also want to think about where your new tech stack will be located —on-site; in a data warehouse; in a private, hybrid or public cloud; or some combination of those.
Who will need access to it (and from where) to keep operations running smoothly and KPI benchmarks met? In sum, this assessment requires a combination of meticulous planning at the personnel and application levels, and big-picture thinking about the state of the entire enterprise.
3. Dive Into Your Data
Data is the fuel that feeds AI, and you’ll need a lot of it to maximize your returns. Most business leaders know this, and they assume that they don’t have enough data to make an AI investment worthwhile. This is a common misconception.
Within most organizations, there is usually an abundance of data being generated, stored and forgotten. For these companies, the challenge isn’t collecting new data — it’s locating, consolidating and analyzing existing data. Often, most of the company’s data is collected for compliance purposes or used during audits.
Companies will want to consolidate their business and operations data — regardless of the amount — to assess overall data readiness. And your organization probably has more data than you think.
When stakeholders claim there isn’t enough data, that it isn’t clean, or that they’re unsure which data is relevant, they are succumbing to a common fallacy. They assume scarcity when availability is the real issue. Siloed data isn’t helpful to most operations, so it might as well not even exist.
Before implementing ai in scm (supply chain management), organizations might have to spend considerable time and effort breaking down silos, which often are intertwined with company culture and deeply embedded business processes.
A lack of commonality between different personnel types, such as information technology, operations technology, and operations and business, is also a culprit. Each of these teams has a different core objective and looks at data differently.
What may be immensely valuable to one department is often just noise to another, and in many organizations, a lack of regular interaction among teams leads to a lack of communication about important things like data.
Digital transformations can force internal teams to overcome silos and even restructure to facilitate increased collaboration. Ideally, however, a company should remove silos before beginning a digital transformation.
Doing so will not only make the transition process easier and more effective, but provide insights on whether the business is ready for such a transformation. If you can’t compel teams to work together and share important business information as a matter of course, you might not be ready.
AI is already beginning to transform and revolutionize supply management. If your organization hasn’t yet begun its digital transformation journey, and you’re feeling left behind, don’t worry: Machine learning is still in its nascent stage, and AI won’t disappear.
That’s not to say you should wait for AI technologies to fully mature before exploring their usefulness to your organization. Instead, follow the steps above to determine your company’s digital readiness. That exercise should inform your next steps.
If you’re not ready for transformation, start by preparing a plan to implement ai in supply chain. If you are ready already, start creating and executing your implementation plan.
What No one Tells You about Implementing AI Integration
Today’s supply chain executives are short on time, and having multiple meetings to discuss solution implementation is a burden they can’t afford. Integrated AI tools provide actionable insights that eliminate bottlenecks and unlock real-time value. That’s important because supply chain companies need more execution — not more analysis.
Implementing a full AI solution might seem daunting and cost-prohibitive, and it’s true that costs can range from millions to tens of millions of dollars, depending on the size of the organization. Businesses must first undergo a full digitization process and then implement an analytics program before they can integrate AI tools.
Oftentimes, companies waste significant resources in this process because they don’t incorporate the end user feedback and end up having to backtrack to address unanticipated problems.
But there is an alternative. An agile approach enables organizations to begin implementing AI in cost-effective ways. By integrating third-party vendors, they can start where they are, learn what works for their businesses, and scale up as needed.
This tactic allows for much faster AI integration than building a new platform from the ground up or building on top of legacy solutions.
Benefits Associated with Agile Cloud-based AI Strategies
1. Maximised Data
Supply chain companies excel at managing the flow of goods and services, and legacy platforms were designed to handle the data associated with these processes. But because they were built before AI and machine learning, they’re not equipped for the demands of today’s supply chain industries.
Newer platforms are built with technology stacks that can handle data capture, storage, processing, analysis, and visualization, and they’re designed for quick integration. Rather than wait for legacy vendors to build machine learning algorithms into their platforms, supply chain companies can take advantage of new tools immediately.
2. Automated Critical Analyses
Supply chain operations are complex, and it’s difficult for a human to recognizse patterns in inefficiencies, even with the aid of traditional business intelligence solutions.
Operations teams can reduce the amount of time it takes to analyze data by leveraging AI tools. AI works 24/7, and its sole job is to analyze inputs and highlight trends. Analysts can use those insights to identify potential areas of improvement, forecast demand and inventory levels, schedule maintenance and downtime activities, and predict potential equipment failures.
As an example of how this is working, consider AI’s role in agriculture. Weather forecasting and smart image processing enable growers to identify pests, weeds, and disease early on so they can protect their healthy crops.
Predictive analytics enable them to gauge how environmental factors will influence their crop yields, and real-time soil monitoring helps them adjust water levels to optimize growth. Supply chain companies can enjoy similar real-time and predictive benefits through AI solutions.
3. Enhanced Competitiveness
AI is not just a nice-to-have; it’s an imperative to stay competitive. These tools reduce processing time and facilitate smarter, faster decision-making.
AI provides a view into market trends and even weather patterns that might impact operations, and that data can make all the difference in maintaining strong customer relationships and industry credibility.
Having a view into when, where, and why bottlenecks occur can transform a company’s workflows and radically improve a supply chain company’s profitability.
By partnering with third-party AI vendors, supply chain businesses can move away from the cumbersome old model of waiting for legacy platforms to catch up with new technologies. The most successful businesses will be those that apply scalable, easily integrated solutions to their existing processes.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://throughput.world/blog/ai-in-supply-chain-and-logistics/
|
[
{
"date": "2023/02/24",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2023/02/24",
"position": 44,
"query": "AI labor market trends"
},
{
"date": "2023/02/24",
"position": 80,
"query": "AI workers"
}
] |
Gary Vaynerchuk compares the rise of AI like ChatGPT to ...
|
Gary Vaynerchuk compares the rise of AI like ChatGPT to the way the internet revolutionized work: 'AI is coming for our jobs and that's ok'
|
https://www.businessinsider.com
|
[
"Jason Lalljee"
] |
Gary Vaynerchuk predicts that AI technology is going to eliminate many roles, but is confident that workers will be able to find complementary jobs.
|
Entrepreneur and internet personality Gary Vaynerchuk is optimistic that workers will survive the rise of AI, although some experts are more ambivalent.
Entrepreneur and internet personality Gary Vaynerchuk is optimistic that workers will survive the rise of AI, although some experts are more ambivalent. Eric Gaillard/Reuters
Entrepreneur and internet personality Gary Vaynerchuk is optimistic that workers will survive the rise of AI, although some experts are more ambivalent. Eric Gaillard/Reuters
This story is available exclusively to Business Insider subscribers. Become an Insider and start reading now.
The entrepreneur and internet personality Gary Vaynerchuk isn't panicking over the quick rise of AI technology like ChatGPT — in fact, he welcomes the change.
Vaynerchuk, an early investor in companies like Facebook and Uber, posted a video on TikTok this week encouraging others to embrace the disruptions the chatbots might bring, even as many speculate that AI will bring upheaval to some industries. Anxieties about current widespread layoffs in the tech industry aren't helping, with the added irony that AI sometimes helps employers make decisions about who gets cut.
"What do I think of AI? I think it's coming, and it's coming fast. And it's going to be awesome," he said. "Humans have proven to me that they have the ability to adjust to the new reality and deal with it."
ChatGPT, which produces responses to user prompts that appear as if they're written by a human being, is only a few months old, but it's already demonstrated its potential to disrupt several industries. Insider's Aaron Mok and Jacob Zinkula reported this month that tech, media, teaching, and legal jobs, among others, are "amenable" to AI technologies, as Anu Madgavkar, a partner at the McKinsey Global Institute, phrased it.
Customer service is another industry that's getting increasingly automated — one study published last year by the tech research company Gartner projected that chatbots will be the main customer service channel for roughly 25% of companies by 2027.
Bloomberg's MLIV Pulse survey from early February, which surveys investors, finds that the consensus is that AI tech will eventually replace some jobs in finance, media, and tech, even as most investors didn't perceive their own jobs as at risk.
On the flip side, many workers are finding that they can use AI tools to enhance their productivity at work: it's useful for research, analyzing large amounts of data, and scheduling tasks, for instance. On the other side of the employment fence, people have also been using ChatGPT to write cover letters and resumes for them, which one recruiter told Insider is a productive and ethical use of the software.
Related stories Business Insider tells the innovative stories you want to know Business Insider tells the innovative stories you want to know
History says there's some reason to be optimistic about new technology, but AI is new terrain
Vaynerchuk is optimistic about AI technology — and about workers' ability to adapt to it, even if their current roles might end up on the chopping block.
"Most people worked on farms back in the day," he said. "And then a tractor came out. And everyone's like, 'fuck that. We're all out of fucking jobs.' And then people found new jobs."
Like Vaynerchuk points out, there's some reason to be optimistic long-term about the job shake ups technology can cause.
In 2018, for instance, the World Economic Forum projected that although more than 75 million jobs would be lost to automation in the next four years, 133 million would be created.
A report last year from the Brookings Institution said that technology "often creates as many jobs as it destroys over time," and that the cycle of automation can be good for the economy: people who can work with technology are more productive than their peers, reducing the cost of goods and services, which means people can buy more goods and services. And that leads to the creation of even more new jobs.
But workers directly replaced by the new technology lose out, Harry J. Holzer, a senior fellow at Brookings wrote in that report, adding that digital automation over the last four decades has added to labor market inequality, with production and clerical workers losing their jobs or seeing shrunk wages. And while some new jobs that were created pay more, others pay less.
"AI will increase the challenges many workers will face from automation, while still contributing to higher standards of living due to higher worker productivity," Holzer said, predicting that AI has greater potential for inequality than previous automation, and can potentially affect college graduates and professionals more than technology changes did in the past. "At the same time, we will need a much more robust set of policy responses to make sure that workers can adapt, so that the benefits of automation are broadly shared."
But Vaynerchuk is more convinced that AI represents the status quo for automation.
"Do you understand that I gave this same keynote in 1997?" he said. "The analogy I used then was, 'look, if you're the top salesman or saleswoman for the Yellow Pages, you might want to consider what Yahoo and Google are doing.'"
| 2023-02-24T00:00:00 |
https://www.businessinsider.com/gary-vaynerchuk-ai-chatgpt-chatbot-microsoft-google-job-labor-trends-2023-2
|
[
{
"date": "2023/02/24",
"position": 39,
"query": "AI labor market trends"
}
] |
|
The Future of Human Agency
|
The Future of Human Agency
|
https://www.pewresearch.org
|
[
"Janna Anderson",
"Lee Rainie",
".Wp-Block-Prc-Block-Bylines-Display Background Inherit Box-Sizing Inherit Color Inherit Color Var --Wp--Preset--Color--Text-Color",
"Font-Family Var --Wp--Preset--Font-Family--Sans-Serif",
"Font-Size Font-Weight Gap Important Line-Height",
"Margin-Bottom Text-Transform Uppercase .Wp-Block-Prc-Block-Bylines-Display A Text-Decoration None Important .Wp-Block-Prc-Block-Bylines-Display A Hover Text-Decoration Underline Important .Wp-Block-Prc-Block-Bylines-Display .Prc-Platform-Staff-Bylines__Separator Margin-Left"
] |
... labor, markets and other humans. They will also operate with the presumption ... information is shared with the AI system. This type of user control is ...
|
How we did this This report covers results from the 15th “Future of the Internet” canvassing that Pew Research Center and Elon University’s Imagining the Internet Center have conducted together to gather expert views about important digital issues. This is a nonscientific canvassing based on a nonrandom sample; this broad array of opinions about the potential influence of current trends may lead between 2022 and 2035 represents only the points of view of the individuals who responded to the queries. Pew Research Center and Elon’s Imagining the Internet Center sampled from a database of experts to canvass from a wide range of fields, inviting entrepreneurs, professionals and policy people based in government bodies, nonprofits and foundations, technology businesses and think tanks, as well as interested academics and technology innovators. The predictions reported here came in response to a set of questions in an online canvassing conducted between June 29 and Aug. 8, 2022. In all, 540 technology innovators and developers, business and policy leaders, researchers and activists responded in some way to the question covered in this report. More on the methodology underlying this canvassing and the participants can be found in the section titled “About this canvassing of experts.”
Advances in the internet, artificial intelligence (AI) and online applications have allowed humans to vastly expand their capabilities and increase their capacity to tackle complex problems. These advances have given people the ability to instantly access and share knowledge and amplified their personal and collective power to understand and shape their surroundings. Today there is general agreement that smart machines, bots and systems powered mostly by machine learning and artificial intelligence will quickly increase in speed and sophistication between now and 2035.
As individuals more deeply embrace these technologies to augment, improve and streamline their lives, they are continuously invited to outsource more decision-making and personal autonomy to digital tools.
Some analysts have concerns about how business, government and social systems are becoming more automated. They fear humans are losing the ability to exercise judgment and make decisions independent of these systems.
Others optimistically assert that throughout history humans have generally benefited from technological advances. They say that when problems arise, new regulations, norms and literacies help ameliorate the technology’s shortcomings. And they believe these harnessing forces will take hold, even as automated digital systems become more deeply woven into daily life.
Thus the question: What is the future of human agency? Pew Research Center and Elon University’s Imagining the Internet Center asked experts to share their insights on this; 540 technology innovators, developers, business and policy leaders, researchers, academics and activists responded. Specifically, they were asked:
By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives?
The results of this nonscientific canvassing:
56% of these experts agreed with the statement that by 2035 smart machines, bots and systems will not be designed to allow humans to easily be in control of most tech-aided decision-making.
of these experts agreed with the statement that by 2035 smart machines, bots and systems will not be designed to allow humans to easily be in control of most tech-aided decision-making. 44% said they agreed with the statement that by 2035 smart machines, bots and systems will be designed to allow humans to easily be in control of most tech-aided decision-making.
It should be noted that in explaining their answers, many of these experts said the future of these technologies will have both positive and negative consequences for human agency. They also noted that through the ages, people have either allowed other entities to make decisions for them or have been forced to do so by tribal and national authorities, religious leaders, government bureaucrats, experts and even technology tools themselves.
In addition, these experts largely agree that digital technology tools will increasingly become an integral part of people’s decision-making. The tools will provide ever-larger volumes of information to people that, at minimum, will assist them in exploring choices and tapping into expertise as they navigate the world.
At the same time, experts on both sides of the issue also agree that the current moment is a turning point that will determine a great deal about the authority, autonomy and agency of humans as the use 0f digital technology spreads into more aspects of daily life. Collectively, people will face questions such as: What are the things humans really want agency over? When will they be comfortable turning to AI to help them make decisions? And under what circumstances will they be willing to outsource decisions altogether to digital systems? Some outlined the stakes:
Alf Rehn, professor of innovation, design and management at the University of Southern Denmark, observed, “The future will clearly cut both ways. On the one hand, better information technologies and better data have improved and will continue to improve human decision-making. On the other, black box systems and non-transparent AI can whittle away at human agency, doing so without us even knowing it is happening. The real challenge will lie in knowing which dynamic is playing out strongest in any given situation and what the longer-term impact might be.”
Barry Chudakov, founder and principal, Sertain Research, predicted, “By 2035, the relationship between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence will look like an argument with one side shouting and the other side smiling smugly. The relationship is effectively a struggle between the determined fantasy of humans to resist (‘I’m independent and in charge and no, I won’t give up my agency!’) and the seductive power of technology designed to undermine that fantasy (‘I’m fast, convenient, entertaining! Pay attention to me!’)”
Kathryn Bouskill, anthropologist and AI expert at the Rand Corporation, said, “Some very basic functions of everyday life are now completely elusive to us. People have little idea how we build AI systems, control them and fix them. Many are grasping for control, but there is opaqueness in terms of how these technologies have been created and deployed by creators who oversell their promises. Right now, there is a huge chasm between the public and AI developers. We need to ignite real public conversations to help people fully understand the stakes of these developments.”
The experts replying to this canvassing sounded several broad themes in their answers. Among those who said that evolving digital systems will not be designed to allow humans to easily be in control of most tech-aided decision-making, the main themes are cited here:
Here is a small selection of expert answers that touch on those themes:
Greg Sherwin, a leader in digital experimentation with Singularity University, predicted, “Decision-making and human agency will continue to follow the historical pattern to date: It will allow a subset of people with ownership and control of the algorithms to exert exploitative powers over labor, markets and other humans. They will also operate with the presumption of guilt with the lack of algorithmic flagging as a kind of machine-generated alibi.”
J. Nathan Matias, leader of the Citizens and Technology Lab at Cornell University, said, “Because the world will become no less complex in 2035, society will continue to delegate important decision-making to complex systems involving bureaucracy, digital record-keeping and automated decision rules. In 2035 as in 2022, society will not be asking whether humans are in control, but which humans are in control, whether those humans understand the consequences of the systems they operate, whether they do anything to mitigate the harms of their systems and whether they will be held accountable for failures.”
Alan Mutter, consultant and former Silicon Valley CEO, observed, “Successive generations of AI and iterations of applications will improve future outcomes, however, the machines – and the people who run them – will be in control of those outcomes. AI is only as good as the people underlying the algorithms and the datasets underlying the systems. AI, by definition, equips machines with agency to make judgments using large and imperfect databases. Because AI systems are designed to operate more or less autonomously, it is difficult to see how such systems could be controlled by the public, who for the most part are unlikely to know who built the systems, how the systems operate, what inputs they rely on, how the system was trained and how it may have been manipulated to produce certain desired and perhaps unknown outcomes.”
Christopher W. Savage, a leading expert in legal and regulatory issues based in Washington, D.C., wrote, “In theory, a well-deployed AI/ML [machine learning] system could help people make rational decisions in their own best interest under conditions of risk and involving stochastic processes. But I suspect that in practice most AI/ML systems made available to most people will be developed and deployed by entities that have no interest in encouraging such decisions. They will instead be made available by entities that have an interest in steering people’s decisions in particular ways.”
Alejandro Pisanty, Internet Hall of Fame member, longtime leader in the Internet Society and professor of internet and information society at the National Autonomous University of Mexico, predicted, “There are two obstacles to human agency triumphing: enterprise and government. Control over the technologies will be more and more a combination of cooperation and struggle between those two forces, with citizens left very little chance to influence choices. … The trends indicate that the future design of decision-making tech will most likely not be determined by the application of science and well-reasoned, well-intended debate. Instead, the future is to be determined by the agendas of commercial interests and governments, to our chagrin.”
Heather Roff, nonresident fellow in the law, policy and ethics of emerging military technologies at the Brookings Institution and senior research scientist at the University of Colorado-Boulder, wrote, “Most users are just not that fluent in AI or how autonomous systems utilizing AI work, and they don’t really care. Looking at the studies on human factors, human systems integration, etc., humans become pretty lazy when it comes to being vigilant over the technology. Humans’ cognitive systems are just not geared to ‘think like’ these systems. So, when one has a lack of literacy and a lazy attitude toward the use of such systems, bad things tend to happen. People put too much trust in these systems, they do not understand the limitations of such systems and/or they do not recognize how they actually may need to be more involved than they currently are.”
Paul Jones, emeritus professor of information science at the University of North Carolina-Chapel Hill, said, “How automation takes over can be subtle. Compare searching with Google to searching CD-ROM databases in the 1990s. Yes, humans can override search defaults, but all evidence shows they don’t and for the most part they won’t.
“In information science, we’ve known this for some time. Zipf’s Law tells us that least effort is a strong predictor of behavior – and not just in humans. We once learned how to form elegant search queries. Now we shout ‘Alexa’ or ‘OK, Google’ across the room in a decidedly inelegant fashion with highly simplified queries. And we take what we get for the most part. The more often automated results please us, the more we trust the automation. While such assistance in cooking, math, money-management, driving routes, question-answering, etc., may seem benign, there are problems lurking in plain sight.
“As Cory Doctorow dramatizes in ‘Unauthorized Bread,’ complicated access, ownership agreements and other controls will and do put the users of even the most-simple networked technologies in a kind of centralized control that threatens both individual autonomy and social cohesion. The question you didn’t ask is: ‘Is this a good thing for humans?’ That’s a more complicated and interesting question. I hope that one will be asked of the designers of any automated control system heading for 2035 and beyond.”
A top editor for an international online news organization wrote, “At present, many people on Earth have already effectively outsourced – knowingly or unknowingly – their tech-aided decisions to these systems. Many of these people do not give extensive thought to the reality of their personal agency in such matters. In many cases this is because they do not fully understand such processes. Perhaps they have fully invested their faith into them, or they simply do not have the time nor inclination to care. Save a most unlikely paramount event that causes society to radically reevaluate its relationship to these systems, there is no reason to conclude at present that these common prevailing attitudes will change in any revolutionary way.
“For all intents and purposes, many people’s tech-aided decision-making is largely out of their control, or they do not know how to more-capably direct such systems themselves. Many of the most critical tech-aided decisions in practice today do not lend themselves to clear control through the conscious agency of the individual.
“The way in which automated recurring billing is designed often does not clearly inform people that they have agreed to pay for a given service. Many people do not understand the impact of sharing their personal information or preferences to set up algorithm-generated recommendations on streaming services based on their viewing behavior, or other such seemingly simple sharing of bits of their background, wants or needs. They may not know of their invariable sacrifice of personal privacy due to their use of verbally controlled user interfaces on smart devices, or of the fact that they are giving over free control over their personal data when using any aspect of the internet.
“For better or worse, such trends are showing no clear signs of changing, and in all likelihood are unlikely to change over the span of the next 13 years. The sheer convenience these systems provide often does not invite deeper scrutiny. It is fair to say tech design often gives the seeming appearance of such control, the reality of which is often dubious.”
Several main themes also emerged among those who said that evolving digital systems will be designed to allow humans to easily be in control of most tech-aided decision-making. They are cited here:
Here is a small selection of expert answers that touch on those themes:
Marc Rotenberg, founder and president of the Center for AI and Digital Policy, said, “Over the next decade, laws will be enacted to regulate the use of AI systems that impact fundamental rights and public safety. High standards will be established for human oversight, impact assessments, transparency, fairness and accountability. Systems that do not meet these standards will be shut down. This is the essence of human-centric, trustworthy AI.”
Jeremy Foote, a computational social scientist studying cooperation and collaboration in online communities, said, “People are incredibly creative at finding ways to express and expand their agency. It is difficult to imagine a world where they simply relinquish it. Rather, the contours of where and how we express our agency will change, and new kinds of decisions will be possible. In current systems, algorithms implement the goals of their designers. Sometimes those goals are somewhat open-ended, and often the routes that AI/ML systems take to get to those goals are unexpected or even unintelligible. However, at their core, the systems are designed to do things that we want them to do, and human agency is deeply involved in designing the systems, selecting parameters and pruning or tweaking them to produce outputs that are related to what the designer wants.”
Jon Lebkowsky, CEO, founder and digital strategist at Polycot Associates, wrote, “At levels where AI is developed and deployed, I believe there’s an understanding of its limitations. I believe that the emphasis going forward, at least where decisions have critical consequences, will be on decision support vs. decision-making. Anyone who knows enough to develop AI algorithms will also be aware of how hard it is to substitute for human judgment. I submit that we really don’t know all the parameters of ‘good judgment,’ and the AI we develop will always be limited in the ability to grasp tone, nuance, priority, etc. We might be able to effectively automate decisions about market selection, cosmetics, program offerings (but less so selection), etc. But consequential decisions that impact life and health, that require nuanced perception and judgment, will not be offloaded wholly to AI systems, however much we depend on their support. The evolution of digital tech’s ‘broadening and accelerating rollout’ will depend on the evolution of our sophistication about and understanding of the technology. That evolution could result in disaster in cases where we offload the wrong kinds of decisions to autonomous technical systems.”
Robert D. Atkinson, founder and president of the Information Technology and Innovation Foundation, said, “In terms of risks to human autonomy, we should not be very concerned. Technology always has been a tool that humans controlled, and there is no reason to believe otherwise going forward. To the extent autonomous decision-making systems make important decisions, they will 1) on average be more accurate and timely decisions than humans make (or else they wouldn’t be used); 2) in most cases they will be able to be overridden by humans. If a company or other organization implements such a system and it does not improve people’s lives, the company will not be able to sell the system because people will not use it.”
Melissa R. Michelson, dean of arts and sciences and professor of political science at Menlo College, wrote, “The trend I see in terms of AI-assisted life is that AI makes recommendations, while humans retain ultimate control. While AI is likely to improve its ability to predict our needs by 2035, based on tracking of our behavior, there is still a need for a human to make final decisions, or to correct AI assumptions. In part, this is due to the inherent nature of human behavior: It is not always consistent or predictable, and AI is thus unable to always accurately predict what decision or action is appropriate to the moment. It is also due to the undermining of AI tracking that individuals engage in, either deliberately or unintentionally, as when they log in using another person’s account or share an email address, or when they engage in offline behavior. I expect that by 2035 there will be more automation of many routine activities, but only at the edges of our daily lives. Complex activities will still require direct human input. A shortcoming of AI is the persistent issue of racism and discrimination perpetuated by processes programmed under a system of white supremacy. Until those making the programming decisions become anti-racists, we will need direct human input to control and minimize the harm that might result from automated systems based on programming overwhelmingly generated by white men.”
Chris Labash, associate professor of communication and innovation at Carnegie Mellon University, wrote, “It’s not so much a question of ‘will we assign our agency to these machines, systems and bots?’ but ‘what will we’ assign to them? If, philosophically, the best decisions are those based on intelligence and humanity, what happens when humanity takes a back seat to intelligence? What happens when agency gives way to comfort? If you are a human without agency, are you still human?’ The data I have read suggests that our future won’t be so much one where humans will not have agency, but one where humans offload some decisions to autonomous and artificial intelligence. We already trust making requests to bots, automated intelligence and voice assistants, and this will only increase. Five years ago a 2018 PwC study on voice assistants indicated that usage, trust and variety of commands were increasing, and customer satisfaction was in the 90% range. There is likely to be a considerable broadening of dependence on decisions by autonomous and artificial intelligence by 2035. My guess is although many important decisions will be made by autonomous and artificial intelligence, they will be willingly delegated to non-human intelligence, but we will still keep the decision of what decisions to offload to ourselves.”
Steve Sawyer, professor of information studies at Syracuse University, wrote, “We are bumping through a great deal of learning about how to use data-driven AI. In 15 years, we’ll have much better guidance for what is possible. And the price point for leveraging AI will have dropped – the range of consumer and personal guidance where AI can help will grow.”
Several said the trend will continue toward broader use of publicly accepted autonomous decisions.
Sam Lehman-Wilzig, author of “Virtuality and Humanity” and professor at Bar-Ilan University, Israel, said, “On the micro, personal level, AI ‘brands’ will be competing in the marketplace for our use – much like Instagram, Facebook, Twitter, TikTok compete today – designing their AI ‘partners’ for us to be highly personalized, with our ability to input our values, ethics, mores, lifestyle, etc., so that the AI’s personalized ‘recommendations’ will fit our goals to a large extent. But on the macro level humans will not be in charge of decisions/policy. Once we can be relatively assured that AI decision-making algorithms/systems have no more (and usually fewer) inherent biases than human policymakers we will be happy to have them ‘run’ society on the macro level – in the public sphere. There, AI-directed decisions will be autonomous; we will not be in control. Indeed, one can even posit that many (perhaps most) people throughout history have been perfectly happy to enable a ‘higher authority’ (God, monarch/dictator, experts, technocrats, etc.) to make important decisions for them (see Erich Fromm’s ‘Escape from Freedom’).”
An author whose writing has focused on digital and post-digital humanity asked, “Is it clear that humans are in control even now? They are not in control on Wall Street, not in control over what they see on the internet, not in control piloting airplanes, not in control in interacting with customer service of corporate providers of everyday services, etc.
“Are we in a period of coevolution with these systems and how long might that last? Humans do better with AI assistance. AI does better with human assistance. The word ‘automation’ sounds very 20th century. It is about configuring machines to do something that humans formerly did or figured out they could do better when assisted by the strength, precision or predictability of machines. Yet the more profound applications of AI already seem to be moving toward the things that human beings might never think of doing.
“Could even the idea of ‘decisions’ eventually seem dated? Doesn’t adaptive learning operate much more based on tendencies, probabilities, continual refactorings, etc.? The point of coevolution is to coach, witness and selectively nourish these adaptions. By 2035 what are the prospects of something much more meta that might make Google seem as much an old-fashioned industry as it itself once did to Microsoft?
“This does not imply the looming technological singularity as popular doomsayers seem to expect. Instead, the drift is already on. Like a good butler, as they say, software anticipates needs and actions before you do. Thus, even the usability of everyday software might be unrecognizable to the expectations of 10 years ago. This is coevolution.
“Meanwhile Google is feeding and mining the proceedings of entire organizations. For instance, in my university, they own the mail, the calendars, the shared documents, the citation networks and ever more courseware. In other words, the university is no longer at the top of the knowledge food chain. No humans are at the top. They just provide the feed to the learning. The results tend to be useful. This, too, is coevolution.”
Brad Templeton, internet pioneer, futurist and activist, chair emeritus of the Electronic Frontier Foundation, wrote, “The answer is both. Some systems will be designed for more individual agency, others will not. However, absent artificial general intelligence with its own agency, the systems which make decisions will be designed or deployed by some humans according to their will, and that’s not necessarily the will of the person using the system or affected by the system. This exists today even with human customer-service agents, who are given orders and even scripts to use in dealing with the public. They are close to robots with little agency of their own – which is why we always want to ‘talk to a supervisor’ who has agency. Expect the work of these people to be replaced by AI systems when it is cost-effective and the systems are capable enough.”
A number of the experts responding here made the argument that issues tied to this question will likely be battlegrounds in the future as human autonomy is debated. They asked, “What elements define human agency?” They noted that even small-scale decisions such as where people meet, how they move from place to place or how they might complete a written sentence can be consequential. They also said there are vastly varied points of view in regard to how and when human intervention in automated decision-making should be exercised. Some predicted these kinds of subtle issues will produce strong debates about what people should outsource to tech and what should be preserved as the essential domains in which humans should decide for themselves. Here is how one respondent tackled this:
Henry E. Brady, professor and former dean of the school of public policy, University of California, Berkeley, wrote, “My sense is that there will be a tremendous demand for having methods that will ensure that most important decisions are curated and controlled by humans. Thus, there will be a lot of support, using AI, text-processing and other methods, and there will be ways developed to control these processes to ensure that they are performing as desired.
“One of the areas in which I expect a lot of work will be done is in precisely defining ‘key decisions.’ Clearly there is already a recognition that bail, parole and other decisions in the criminal justice system are key decisions that must be approached carefully to avoid bias. Even for decisions that are less key, such as using a dating app or Uber, there is a recognition that some features are key: There must be some security regarding the identity of the parties involved and their trustworthiness. Indeed, developing trustworthy methods will be a major growth industry.
“One of the trade-offs will be allowing a broader range of choices and opportunities versus verifying the authenticity of these as real choices that can deliver what they promise. So far technology has done a better job of broadening choices than assuring their authenticity. Hence the need for methods to ensure trustworthiness.”
This is a nonscientific canvassing, based on a nonrandom sample. The results represent only the opinions of the individuals who responded to the queries and are not projectable to any other population.
In the next section, we highlight the remarks of experts who gave some of the most wide-ranging yet incisive responses to our request for them to discuss human agency in digital systems in 2035. Following, we offer a set of longer, broader essays written by leading expert participants. And that is followed with additional sections covering respondents’ comments organized under the sets of themes set out in the tables above. The remarks made by the respondents to this canvassing reflect their personal positions and are not the positions of their employers. The descriptions of their leadership roles help identify their background and the locus of their expertise. Some responses are lightly edited for style and readability.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.pewresearch.org/internet/2023/02/24/the-future-of-human-agency/
|
[
{
"date": "2023/02/24",
"position": 82,
"query": "AI labor market trends"
}
] |
How Popular Job Search Sites Use AI for Recruitment
|
How Popular Job Search Sites Use AI for Recruitment
|
https://www.talentprise.com
|
[] |
With AI, recruitment efforts become more efficient and effective; job seekers can get better matches for relevant jobs and employers can choose from a deeper ...
|
Job search sites have incorporated Artificial Intelligence (AI) into their recruitment processes so as to more efficiently and accurately match job seekers with employers.
AI-based technologies have been developed to analyze the skills and qualifications of job seekers, scour hundreds of job postings and websites, and even perform automated audio and video interviews to help companies identify suitable job candidates. It has overall drastically reduced the hiring process time.
AI is able to perform the highly tedious and time consuming job of reviewing applications quickly, accurately, and quite often at a lower cost than traditional methods.
AI can also help employers identify gaps in their staff, offering them a more efficient way to find the right employees.
Let’s discuss how AI is changing the way job search sites recruit applicants. Also, learn how businesses can take advantage of this technology for improved hiring results.
AI Algorithms and Their Role in Recruitment
You’ve probably noticed that job recruitment platforms have become increasingly sophisticated. That’s because AI algorithms are helping many companies find candidates more accurately. Take applicant tracking systems (ATS). These algorithms automatically sort through thousands of resumes and applications to narrow down the potential pool of candidates.
ATS uses a range of criteria—skill sets, education, years of experience—to identify which applicants are the best fit for a role.
An Applicant Tracking System (ATS) is a technology used by organizations to efficiently manage the recruiting process.
It helps recruiters to source, track, and manage job applicants and applicants’ data across all stages of the hiring process, from initial contact to post-hiring follow-up.
ATS also automates many tasks associated with recruitment, such as posting job openings to job boards, screening resumes, auto-replying to applicants, scheduling interviews with selected candidates, and collecting feedback from interviewers.
With this powerful and efficient technology, organizations can reduce manual effort, increase recruitment speed, and hire the best talent for their organization.
Benefits of Using Artificial Intelligence (AI) in Recruitment Process
The use of Artificial Intelligence in the recruitment process offers an unparalleled level of efficiency and accuracy in the selection process.
AI tools can easily parse through a large number of resumes and job applications quickly and accurately, eliminating the need for manual review.
It can also systematically identify the best candidates based on skill sets, qualifications, and potential without any human bias.
AI technology makes it easier to track analytics related to hiring performance such as how long it took to fill a job, potential salary savings, quality of hire, and the success rate of a particular candidate.
By using AI tools, companies can easily search through their vast databases of candidate information to identify potential candidates or quickly build candidate profiles related to a given project.
Another benefit is that AI can help to ensure an equitable hiring process eliminating any unintended biases that may exist when reviewing resumes and applications manually.
Popular Job Search Sites and Their Use of AI for Recruitment
A report indicates that 6 in 10 businesses are spending money on automated processes in hiring. They believe it will boost efficiency and allow for data-driven decisions.
Most popular job search sites and social media sites use AI for recruitment.
Such companies include LinkedIn, Indeed, and even Facebook. They use AI algorithms to learn your preferences, past experiences, and skills. It helps them to find the jobs that fit you best.
Understanding Your Preferences
AI algorithms can recognize patterns in data. It makes it easier for job search sites to understand what kind of job candidates you’re looking for. Thereafter, matching them with the right job opportunities.
Automating Job Postings
AI algorithms are also used for automating job postings on popular websites. AI can scan hundreds of resumes in record time. It can identify the most suitable candidates for specific roles.
This means companies don’t have to spend time manually sifting through candidates. AI does it all for them!
Recognizing Skills
AI algorithms can also help with talent sourcing. This is done by recognizing certain skills in your profile that are applicable to a certain job role.
For example, if you have worked with a particular software or technology before, you may be matched with job postings that require those same skills.
This makes it faster and easier for recruiters to find the best talent. This is done without having to comb through resumes manually.
How to Best Leverage a Job Search Site’s AI Capabilities? You might be wondering, how can I best leverage a job search site’s AI capabilities to recruit the best applicants? First, companies should make sure they craft their job postings with AI in mind. This helps the search engine to be able to better understand the role and bring in quality candidates. You can also include related keywords in the description which will help to optimize it. It ensures easier discovery from potential applicants.
Track Applications
Popular job search sites have advanced analytics tools that allow you to track your applications. These tools also help to measure the success of each campaign.
This is beneficial when it comes to recruitment planning. It allows you to easily identify which job descriptions are performing better. Also, it helps to adjust them accordingly, maximizing conversions.
Personalization
AI can also help recruiters customize their communication with applicants. It can even automate certain tasks such as scheduling interviews or sending follow-up emails.
Using AI-powered automation tools allows recruiters to focus their energy on more pressing tasks. This is done by streamlining the application process for a smoother experience.
These are just a few of the many ways that AI is helping companies recruit top talent more efficiently. By improving candidate search outcomes and managing applications with personalized touchpoints, companies can employ the best.
Challenges of Using AI for Recruitment
For starters, AI bias is a major concern when it comes to using machine-learning algorithms. This can occur when an algorithm is only trained on a certain demographic, leading it to favor certain types of candidates over others.
Other issues include a lack of transparency, inadequate data from past hires, a lack of legal framework and regulations, and difficulties in predicting learner performance in the long term.
Despite these challenges, AI can still offer invaluable insights and process efficiencies that companies can leverage in the recruitment process.
Here are some of the common challenges when it comes to using AI for recruitment:
Complicated Algorithms
AI algorithms can get fairly complicated. It requires companies to create detailed job descriptions. If done incorrectly, they could filter out the wrong candidates. This may be due to oversights in their job criteria and qualifications.
Costly Processes
The cost of developing, maintaining, and monitoring AI systems can be extremely expensive. Depending on how much automation is involved in the recruitment process, the more costly it might become.
Time Management
AI systems require constant oversight. This involves maintenance in order to ensure accuracy. It also requires up-to-date information when considering applicants’ qualifications and experiences.
Not only that but ensuring the system operates properly in a timely fashion. This and others are a few of the concerns many companies that implement AI systems face
Conclusion
AI is improving crucial hiring processes to increase efficiency and effectiveness. It has become a delight for both recruiters and job applicants.
The immense benefit of using AI in the recruitment process are enormous. It helps to reduce time spent in the manual recruitment process. It makes it easy to find the perfect applicant for the job.
AI platforms are changing the way job search sites function and operate. With AI, recruitment efforts become more efficient and effective; job seekers can get better matches for relevant jobs and employers can choose from a deeper selection of qualified applicants.
In short, AI is allowing job search sites to optimize their recruitment efforts and better serve their customers with speed and accuracy.
About Talentprise
Talentprise is a skill-driven AI recruiting platform for employers to find top-fit candidates, while helping job seekers land jobs they deserve.
Let’s help you fast-track your next hire with Talentprise’s AI-powered job posting. Register an account today and post your jobs online.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.talentprise.com/how-job-search-sites-use-ai-for-recruitment/
|
[
{
"date": "2023/02/24",
"position": 96,
"query": "AI labor market trends"
},
{
"date": "2023/02/24",
"position": 21,
"query": "artificial intelligence hiring"
}
] |
The parallels between Vonnegut's science fiction and our ...
|
The parallels between Vonnegut's science fiction and our modern-day world
|
https://www.npr.org
|
[
"Alejandra Marquez Janse Christopher Intagliata Mary Louise Kelly",
"Alejandra Marquez Janse",
"Christopher Intagliata",
"Mary Louise Kelly"
] |
There have been some experiments with universal basic income in various places in the world. Do you see that gaining more traction as robots and AI gain more ...
|
The parallels between Vonnegut's science fiction and our modern-day world
NPR's Mary Louise Kelly speaks with Robin Murphy, professor at Texas A&M University, about the through line between a science fiction novel and the current state of AI and automation.
MARY LOUISE KELLY, HOST:
Seventy-one years ago, Kurt Vonnegut published his first novel. It was titled "Player Piano." The book was based, in part, on Vonnegut's time working at General Electric, and it tells a dystopian tale of a society whose workers have been completely replaced by machines. Well, as the workers' discontent grows, they revolt. They destroy the machines, only to rebuild them because the workers miss them, the convenience, the quality of life they provide.
Well, if this plot summary has got you thinking about any parallels between Vonnegut's fiction and our modern-day world, Robin Murphy is one step ahead of you. Murphy is a roboticist who writes in a piece out this week in the journal Science Robotics, quote, "the overarching theme in "Player Piano" is that individual intelligence and creativity is a comforting lie that we tell ourselves about why we are irreplaceable by machines." Robin Murphy, welcome to ALL THINGS CONSIDERED.
ROBIN MURPHY: Well, thank you.
KELLY: I want to ask how you stumbled upon this book. And what about it got you thinking?
MURPHY: Well, a few years ago, I had - of course, I had read "Slaughterhouse-Five," but somebody had said something - oh, Vonnegut, yeah, his first book, "Player Piano," has automation robots. And I was like, what? And so I went back and reread it and said, holy cow. He saw a lot of things coming.
KELLY: Like what? And start maybe with the character named Rudy. Just describe briefly what happens to him and how that may have - we may be seeing some of that play out today.
MURPHY: Well, Rudy is an interesting character. He's a minor character, but he shows up at key moments. And he used to be, or still is, the best machinist there in Ilium, N.Y. But he lost his job, being very proud of how he lost his job because they had a robot learn by demonstration. He showed the robot how he did it. They were able to record his motions, learn from it, and now they didn't need him anymore. So he was very, very proud. But on the other hand, he's very distraught, you know?
KELLY: Superfluous, yeah. He's superfluous now because he's trained the robot to do what he does but even better.
MURPHY: Yeah. And he's got a universal basic income. So Vonnegut had that going through there. And another nice point about - so Rudy is talking to a couple of the engineers who are kind of in this protected class of people, right? You know, you're only replacing the skilled workers. But toward the middle of the book, Paul, the lead engineer, begins to realize that the engineers are getting replaced by automation as well, that nobody is really that irreplaceable.
KELLY: Go back to the universal basic income point. This is, why would you pay a human to do something if they have rendered themselves superfluous, if you don't need them to do any more of their work because the robot can do it? I mean, that is something we've seen play out. There have been some experiments with universal basic income in various places in the world. Do you see that gaining more traction as robots and AI gain more traction?
MURPHY: Well, it certainly comes up, you know, as an ethical thing about, well, robot displacement versus robot replacement of workers and the impact on society. And wouldn't it be great if everybody had universal basic income? And Vonnegut was definitely not in the category that that was a win-win situation; that work added dignity, added purpose, added a great outlet for creativity. And he somewhat implies that we may - there would be, like, eventually the innovation would tap out. If we kept just replacing people with automation, we wouldn't go to the next step beyond.
KELLY: So in the end, do you think Kurt Vonnegut was unusually prescient, or was the writing always on the wall for some of these things?
MURPHY: I personally think he was remarkably prescient. This was the first time we really saw this level of detail about robots replacing people. And yet in a positive way, it's nobody's doing it to subjugate people or to put them out of work deliberately. They're trying to raise the standard of living. But how trying to make the world a better place, sometimes we can trip over ourselves doing that.
KELLY: Robin Murphy, professor of computer science and engineering at Texas A&M University, thank you.
MURPHY: Thank you for having me.
Copyright © 2023 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.
Accuracy and availability of NPR transcripts may vary. Transcript text may be revised to correct errors or match updates to audio. Audio on npr.org may be edited after its original broadcast or publication. The authoritative record of NPR’s programming is the audio record.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.npr.org/2023/02/24/1159423016/the-parallels-between-vonneguts-science-fiction-and-our-modern-day-world
|
[
{
"date": "2023/02/24",
"position": 25,
"query": "universal basic income AI"
}
] |
Credited Responses: The Future of Human Agency in 2035
|
Credited Responses: The Future of Human Agency in 2035
|
https://www.elon.edu
|
[] |
The reigning paradigm for both basic research and industrial product design in AI ... “If social changes can be made through social advances like universal basic ...
|
This page holds hundreds of predictions and opinions expressed by experts who agreed to have their comments credited in a canvassing conducted from late June to early August 2022 by Elon University’s Imagining the Internet Center and Pew Research Center. These experts were asked to respond with their thoughts about the likely evolution of human agency and human decision-making as automated systems rapidly evolve in the digital age.
Results released February 24, 2023 – Internet experts and highly engaged netizens participated in answering a survey fielded by Elon University and the Pew Internet Project from late June through early August 2022. Some respondents chose to identify themselves, some chose to be anonymous. We share the for-credit respondents’ written elaborations on this page. Workplaces are attributed for the purpose of indicating a level of expertise; statements reflect personal views. This page does not hold the full report, which includes analysis, research findings and methodology. Click here or click the image to read the full report.
In order, this page contains: 1) the research question; 2) a brief outline of the most common themes found among both anonymous and credited experts’ remarks; 3) the submissions from respondents to this canvassing who agreed to take credit for their remarks.
This survey question asked respondents to share their answer to the following prompt and query:
Digital tools and human agency: Advances in the internet and online applications have allowed humans to vastly expand their capabilities, increased their capacity to tackle complex problems, allowed them to share and access knowledge nearly instantly, helped them become more efficient and amplified their personal and collective power to understand and shape their surroundings. Smart machines, bots and systems powered mostly by autonomous and artificial intelligence (AI), will continue those advances. As people more deeply embrace these technologies to augment, improve and streamline their lives, they are outsourcing some decision-making and autonomy to digital tools. That’s the issue we explore in this survey. Some worry that humans are going to turn the keys to nearly everything – including life-and-death decisions – over to technology. Some argue these systems will be designed in ways to better-include human input on decisions, assuring that people remain in charge of the most relevant parts of their own lives and their own choices.
Our primary question: By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives?
Yes, by 2035 smart machines, bots and systems powered by artificial intelligence WILL be designed to allow humans to easily be in control of most tech-aided decision-making relevant to their lives.
No, by 2035 smart machines, bots and systems powered by artificial intelligence WILL NOT be designed to allow humans to easily be in control over most tech-aided decision-making relevant to their lives.
Results for this question regarding the evolution of human-machine design in regard to human agency by 2035:
56% of these experts selected that by 2035 smart machines, bots and systems will not be designed to allow humans to easily be in control of most tech-aided decision-making.
44% said they hope or expect that by 2035 smart machines, bots and systems will be designed to allow humans to easily be in control of most tech-aided decision-making.
Follow-up qualitative question: Why do you think humans will or will not be in control of important decision-making in the year 2035? We invite you to consider addressing one or more of these related questions in your reply. When it comes to decision-making and human agency, what will the relationship look like between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence? What key decisions will be mostly automated? What key decisions should require direct human input? How might the broadening and accelerating rollout of tech-abetted, often autonomous decision-making change human society?
Click here to download the print version of the “Future of Human Agency” report
Click here to read the full “Future of Agency” report online
Click here to read anonymous responses to this research question
Common themes found among the experts qualitative responses:
*Powerful interests have little incentive to honor human agency – the dominant digital-intelligence tools and platforms the public depends upon are operated or influenced by powerful elites – both capitalist and authoritarian – that have little incentive to design them to allow individuals to exert more control over their tech-abetted daily activities. *Humans value convenience and will continue to allow black-box systems to make decisions for them – people already allow invisible algorithms to influence and even sometimes “decide” many if not most aspects of their daily lives and that won’t change. *AI technology’s scope, complexity, cost and rapid evolution are just too confusing and overwhelming to enable users to assert agency – it is designed for centralized control, not personalized control. It is not easy to allow the kind of customization that would hand essential decision-making power to individuals. And these systems can be too opaque even to their creators to allow for individual interventions. *Humans and tech always positively evolve – the natural evolution of humanity and its tools has always worked out to benefit most people most of the time, thus regulation of AI and tech companies, refined design ethics, newly developed social norms and a deepening of digital literacy will emerge. *Businesses will protect human agency because the marketplace demands it – tech firms will develop tools and systems in ways that will enhance human agency in the future in order to stay useful to customers, to stay ahead of competitors and to assist the public and retain its trust. *The future will feature both more and less human agency – tech will always allow a varying degree of human agency, depending upon its ownership, setting, uses and goals; some allow for more agency to easily be exercised by some people by 2035; some will not.
Responses from those preferring to take credit for their remarks. Some are longer versions of expert responses contained in shorter form in the survey report.
Following are the responses from survey participants who chose to take credit for their remarks in the survey; some are the longer versions of expert responses that are contained in shorter form in the official survey report. (Anonymous responses are published on a separate page.) The respondents were asked: “By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives? Why or why not?”
Some respondents chose not to provide a written elaboration, only choosing to respond to the closed-end Yes-No question. They are not included here. The statements are listed in random order. The written remarks are these respondents’ personal opinions; they do not represent their employers.
Rakesh Khurana, professor of sociology and professor of leadership development at Harvard University, responded, “People tend to be submissive to machines or any source of authority. Most people don’t like to think for themselves but rather like the illusion that they are thinking for themselves. Consider, for example, how often people follow GPS instructions even when instinct suggests they are going in the wrong direction. In politics or consumption, people often outsource their decision-making to what their friends ‘like’ on Facebook or the songs Pandora chooses, even if it is against their interests or might expose them to new ideas or music.
“In most instances, even without machines, there is a strong tendency among humans to rely on scripts and taken-for-granted unquestioned assumptions for their actions. Whether these scripts come from ‘society’ (a type of programmed machine) or an algorithm seems to be a difference of degree, not kind.
“For example, many people believe they have no agency in addressing problems linked to capitalism, human-caused climate change or any other ‘system’ that seems to exist outside of human control, even though these phenomena are designed and perpetuated by humans. It is easier for many people to imagine the end of the world than it is for them to imagine the end of capitalism.”
Mike Liebhold, distinguished fellow, retired, at the Institute for the Future, wrote, “By 2035 successful AI and robotic ‘full’ autonomous ‘control’ of ‘important’ decisions will be employed only in secure and well-managed and controlled applications of highly refined generations of applied machine intelligence, where any autonomous processes are managed and operated carefully, by high skilled workforces, with high degrees of systems literacies.
“While there will be gradually widespread adoption of AI augmentation (not necessarily replacement) of human decisions by applied AI and machine learning deeply embedded in hardware and digital services. In most cases down the long adoption curves uses of fully autonomous systems, will only gradually be successfully applied, still constrained by evolved versions of the same systemic vulnerabilities including pervasive digital security vulnerabilities, continued tensions between targeted personalization, and privacy surveillance.
“Finally, complexity is a continuing challenge, Computing technology is enabling way more capabilities than humans are capable of understanding and using effectively. It’s a form of cognitive dissonance like an impedance mismatch in electronic connections. Given the explosive availability of potentially useful data and structured knowledge resources and promising but immature, data fusion, AI and cloud computing capabilities, there’s years of work ahead to design systems that somehow systematise and simplify the complexity of AI machines to reliably summarise, explain and amplify capabilities to growing, but still limited useful sets for human cognitive capabilities and focused tasks.”
Paul Jones, emeritus professor of information science at the University of North Carolina-Chapel Hill, said, “Once I taught people to use computers. Later I taught computers how to use people. The computers are the better students. How automation takes over can be subtle. Compare searching with Google to searching CD-ROM databases in the 1990s. Yes, humans can override the search defaults, but all evidence shows that they don’t and for the most part they won’t.
“In information science, we’ve known this for some time. Zipf’s Law tells us that least effort is a strong predictor of behavior—and not just in humans (although I’ll stay with humans here).
“We once learned how to form elegant search queries. Now we shout ‘Alexa’ or ‘OK, Google’ across the room in a decidedly inelegant fashion with highly simplified queries. And we take what we get for the most part.
“Driving has changed completely since I learned to drive at 16. While the GPS and then Google Maps and for the scofflaw Waze, ‘suggest’ routes and ‘warn’ us of problems, we generally do as we are told. Airplanes and trains are for the most part already self-driving for the better parts of their trips. They can be overridden but are not.
“The more often automated results please us the more we trust the automation. So far (save for Teslas), so good. While such assistance with cooking, math, money-management, driving routes, question-answering, etc., may seem benign there are problems lurking in plain sight. As Cory Doctorow dramatizes in ‘Unauthorized Bread,’ complicated access, ownership agreements and other controls will and do put the users of even the most-simple networked technologies in a kind of centralized control that threatens both individual autonomy and social cohesion.
“The question you didn’t ask is: ‘Is this a good thing for humans?’ That’s a more complicated and interesting question than ‘Will humans be in control of important decision-making in the year 2035?’ I hope that one will be asked of the designers of any automated control system heading for 2035 and beyond.”
Henry E. Brady, professor and former dean of the school of public policy, University of California-Berkeley, wrote, “Many ‘decisions’ are already automated. My sense is that there will be a tremendous demand for having methods that will ensure that most important decisions are curated and controlled by humans. Thus, there will be a lot of support, using AI, text-processing and other methods, and there will be ways developed to control these processes to ensure that they are performing as desired.
“One of the areas in which I expect a lot of work will be done is in precisely defining ‘key decisions.’ Clearly there is already a recognition that bail, parole and other decisions in the criminal justice system are key decisions that must be approached carefully to avoid bias. Even for decisions that are less key such as using a dating app or Uber there is a recognition that some features are key: there must be some security regarding the identity of the parties involved and their trustworthiness. Indeed, developing trustworthy methods will be a major growth industry.
“One of the tradeoffs will be allowing a broader range of choices and opportunities versus verifying the authenticity of these as real choices that can deliver what they promise. So far technology has done a better job of broadening choices than assuring their authenticity. Hence the need for methods to ensure trustworthiness.”
Avi Bar-Zeev, founder and CTO of RealityPrime, an XR pioneer who helped develop the technology of HoloLens, Google Earth and Second Life and has worked with Microsoft, Google, Apple, Amazon and Disney, said, “Ad-tech is a business model designed to offset the apparent price of digital goods and services (down to “free”) by siphoning money from physical product purchases or app-store captive digital purchases through the ad-tech network.
“After decades of dominance, we’ve learned that nothing is free, and the cost of this approach is social harm. An individual price of this business model is in the loss of human agency, as ads always serve a remote master with an agenda, gradually perfecting its efficacy with more and more data and better and better prediction. The better they are, the less autonomy we have.
“By 2035, I expect ad-tech to finally diminish in dominance, with greater privacy controls. However, the most obvious replacement is “Personal AI,” which makes recommendations for our personal benefit. In fact, in a world full of content (think AR channels), we will either need the traditionally centralized filters and rankers, like Google, or we will need the intelligence to be distributed to our own devices, like personal firewalls and discovery engines.
“In either case, the algorithm still has the most control, because we only see what it shows us.
“We have to work harder to escape its natural bubble. The personal AI revolution has the potential to help AI make decisions the way we would, and thus do so to our benefit. But we will still rely on it, one way or another. The key question is whether we gain or lose by automating so much of our lives.”
Vint Cerf, pioneer innovator, co-inventor of the Internet Protocol and vice president at Google, wrote, “My thought, perhaps only hazily formed, is that we will have figured out how to take intuitive input from users and turn that into configuration information for many software-driven systems. You might imagine questionnaires that gather preference information (e.g., pick ‘this’ or ‘that’) and, from the resulting data, select a configuration that most closely approximates what the user wishes.
“Think about the Clifton StrengthsFinder questionnaire, a tool developed by the Gallup Organization that asks many questions that reveal preferences or strengths—sometimes multiple questions are asked in different ways to tease out real preferences/strengths.
“It’s also possible that users might select ‘popular’ constellations of settings based on ‘trend setters’ or ‘influencers’—that sounds somewhat less attractive (how do you know what behavior you will actually get?). Machine learning systems seem to be good at mapping multi-dimensional information to choices.”
Andre Brock, associate professor of literature, media and communication at Georgia Tech and advisor to the Center for Critical Race Digital Studies, wrote, “In 2035, automated decision-making will largely resemble the robo-signing foreclosure courts of the 2020’s, where algorithms tuned to the profit/governance models of extraction and exploitation are integrated into legal mechanisms for enhancing the profits of large corporations.
“My grounds for this extraordinary claim draw upon my observations about how governments have been captured by private/business entities, meaning that any pretense of equity based on the recognition of the ‘human’ has begun being supplanted by what Heidegger deemed humanity’s future as a ‘standing reserve’ of technology.
“Many decisions affecting everyday life for those in need of equity and justice already are framed through anti-blackness and extractive models; I’m specifically focused on the United States whose ‘democratic’ government was conceptualized by white men who worshiped property, owned Black folk, destroyed entire indigenous populations, and denied women the vote.
“Decision-making, from this perspective, largely benefits the political and economic interests of particular interests who fight savagely to retrench the gains made by Black folk, Asian folk, queer folk, women and the differently abled. There is no inherent democratic potential in information or algorithmic technologies designed to counter these interests, as the creators are themselves part of a propertied, monied, raced and sexualized elite.
“If anything, rolling out tech-abetted autonomous decision will further entrench the prevailing power structures, with possibilities for resistance or even equitable participation left to those who manage to construct alternate socialities and collectives on the margins.
“I’m intrigued by your question ‘what key decisions will be mostly automated?’ I feel that ‘key decisions’ is a phrase often understood as life-changing moments such as the purchase of a home, or what career one will pursue, or whether to become romantically involved with a possible life partner. Instead, I urge you to consider that key decisions are instead the banal choices made about us as we navigate society:
Whether a police officer will pull you over because you’re a Black driver of a late model vehicle
Whether a medical professional will improperly diagnose you because of phenotype/race/ethnicity/economic status
“These decisions currently rely upon human input, but the human point of contact is often culturally apprehended by the institutions through which these decisions are framed. I’m already uncomfortable with how these decisions are made; technology will not save us.”
Bill Woodcock, executive director, Packet Clearing House, commented, “The unholy trinity of the surveillance economy, pragmatic psychology and machine learning have dug us into a hole. They are convincing us to dig ever faster, and they are making us believe that it’s our own bright idea. I don’t see us getting out of this hole as long as the automated exploitation of human psychological weaknesses continues to be permitted.
“I’m very pessimistic about the balance of beneficial outcomes between humans and autonomous systems based on our track record thus far. For the first time in human history, we’ve created a stand-alone system which predates people and has its own self-contained positive feedback loops driving it toward increased scale. What’s particularly problematic is that the last 40 years of investigation of human psychology have revealed how easily people can be externally directed and how much work their brains will do to rationalize their actions as having been self-determined.
“Everyone wants to believe that they always have free will—that they always make their own choices based on rational processes—so they’ll do all of the work necessary to convince themselves of that while simultaneously opening their wallets to pay for more GPUs to further direct their own, and others,’ behavior.”
Douglas Rushkoff, digital theorist and host of the NPR One podcast “Team Human,” wrote, “The incentives structure of western civilization would have to be changed from profit to mutual flourishing in order for any technology development company to choose to design technologies that augment human control.
“I do believe we could easily shift the emphasis of technology development from control-over-others to augmentation of agency, but this would require a radical shift in our cultural value system. I don’t believe that billions of dollars will be spent on a counter-narrative until such a shift were to occur. It’s also hard to imagine scenarios years in the future without also taking into account mass migrations, the rise of authoritarianism, climate change and global health catastrophe.
“So, are we talking about the ‘key decisions’ of 6 billion climate refugees, or those of 200,000 corporate executives? My main reason for believing that human beings will not be in control of automation technology in the future is that human beings are in control of neither automated nor manual technologies in the present.
“I don’t see why the emergence of autonomous technologies would shift the trajectory away from using technology to control human behavior.”
Jamais Cascio, distinguished fellow at the Institute for the Future, predicted, “Several scenarios will likely co-exist in the future of agency by 2035:
1) Humans believe they are in control but they are not: The most commonly found scenario will be the one in which humans believe themselves to be in control of important decision-making in the year 2035, but they’re wrong. This will (largely) not be due to nefarious action on the part of rogue AI or evil programmers, but simply due to the narrowing of choice that will be part of the still-fairly-simple AI systems in 2035. Humans will have full control over which option to take, but the array of available options will be limited to those provided by the relevant systems. Sometimes choices will be absent because they’re ‘obviously wrong.’ Sometimes choices will be absent because they’re not readily translated into computer code. Sometimes choices will be absent because the systems designed to gather up information to offer the most relevant and useful options are insufficient.
“In this scenario, as long as the systems allow for human override to do something off-menu, the impact to agency can be minor. If it’s not clear (or not possible) that humans can do something else, partial agency may be little better than no agency at all.
2) Humans know they are not in control and they’re OK with that: Less common will be the scenario where humans do NOT believe themselves to be in control of important decision-making in the year 2035 and they like it that way. Humans are, as a general rule, terrible at making complex or long-term decisions. The list of cognitive biases is long, as is the list of historical examples of how bad decision-making by human actors have led to outright disaster. If a society has sufficient trust and experience with machine decision-making, it may decide to give the choices made by AI and autonomous systems greater weight.
“This would not be advisable with current autonomous and AI systems, but much can happen in a decade or so. There may be examples of AI systems giving warnings that go unheeded due to human cognitive errors or biases, or controlled situations where the outcomes of human vs. machine decisions can be compared, in this case to the AI’s benefit. Advocates of this scenario would argue that, in many ways, we already live in a world much like this—only the autonomous systems that make decisions for us are the emergent results of corporate rules, regulations and myriad minor choices that all add up to outcomes that do not reflect human agency. They just don’t yet have a digital face.
3) A limited number of AI-augmented humans have control: Last is a scenario that will somewhat muddy the story around human agency, as it’s a scenario in which humans do have control over important decision-making in the year 2035, but it’s a very small number of humans, likely with AI augmentations. Over the past few decades, technologies have vastly extended individuals’ power. Although this typically means extended in scale, where human capabilities become essentially superhuman, it can also mean extended in scope, where a single or small number of humans can do what once took dozens, hundreds, or even thousands of people. By 2035, we’ll likely see some development of wearable augmentations that work seamlessly in concert with their humans; whether or not we think of that person as a cyborg comes down to language fashion. Regardless, the number of people needed to make massive life-or-death decisions shrinks, and the humans who retain that power do so with significant machine backup.
“This may sound the most fantastical of the three, but we’re already seeing signals pointing to it. Information and communication systems make it easy to run critical decisions up the chain of command, taking the yes-or-no choice out of the hands of a low-ranking person and giving it to the person tasked with that level of responsibility. Asking the president for authorization to fire a weapon is just a text message away. Whether or not we go as far as cyborg augmentation, the humans-plus-AI model (as described by Kevin Kelly as ‘centaurs,’ his name for future people who use artificial intelligence to complement their thinking) will deeply enmesh decision-making processes. Advocates will say that it leads to better outcomes by taking the best parts of human and machine; critics will say that the reality is quite the opposite.
“For these scenarios, the canonical ‘important decision-making’ I’ve had in my head regards military operations, as that is the topic that gets the most attention (and triggers the most unrest). All three of the scenarios play out differently.
In Scenario 1, the information and communication systems that enable human choice potentially have a limited window on reality, so that the mediated human decisions may vary from what might have been chosen otherwise.
In Scenario 2, advocates would hope that carefully designed (or trained) systems may be seen as having ‘cooler heads’ in the midst of a crisis and be less-likely to engage in conflict over ego or ideology; if the system does decide to pull the trigger (literally or metaphorically), it will only be after deep consideration. One hopes that the advocates are right.
In Scenario 3, there’s the potential for both narrowed information with AI mediation and the ‘wise counsel’ that could come from a well-designed long-term thinking machine; in my view, the former is more plausible than the latter.
“Outside of these scenarios there are some key factors in common. The primary advantage to AI or autonomous decision-making is speed, with machines generally able to take action far faster than can a human (e.g., algorithmic trading). In competitive situations where first-mover advantage is overwhelming, there will be a continued bias towards AI taking charge, with likely diminishing amounts of human guidance over time.
“Another advantage of AI is an imperviousness to tedium, meaning that an AI can undertake the same repeated action indefinitely or pore over terabytes of low-content data to find patterns or anomalies, and give the final pass as much attention as the first. An amount or diversity of information that would be overwhelming to a human could easily be within the capacity of an intentionally-designed AI. When decisions can be made more precisely or accurately with more information, machine systems will likely become the decision-makers.
“The most unusual advantage of AI is ubiquity. If an AI system can make better (or at least useful) decisions, it does not need to be limited to the bowels of the Pentagon. Arguably, a military where every human soldier has AI ‘topsight’ that can see the larger dimensions of the conflict is more effective than one that has to rely on a chain-of-command or potentially biased human decision-making in the field. More broadly, a decision-making system that proves the most insightful or nuanced or aggressive or whatever can be replicated across all of the distributed AIs. If they’re learning systems, all the better—lessons learned by one can very rapidly become lessons learned by them all.
“I suggested at the outset that the conditions of 2045 will likely differ significantly from the world of 2035. The world of mid-century would be an evolution of the world we made in the previous couple of decades. By 2045, I suspect that our three scenarios would be the following:
No AI, No Cry: For many reasons, there are few if any real AIs left by 2045, and humans will be the default important decision-makers. This could be by choice (a conscious rejection of AI, possibly after some kind of global disaster) or by circumstance (the consequences of climate disaster are so massive that infrastructural technologies like power, parts and programmers are no longer available).
All Watched Over by Machines of Loving Grace: The full flowering of the second 2035 scenario, in which our machines/AIs do make significantly smarter and wiser decisions than do humans and that’s OK. We let our technology make the big choices for us because it will simply do a better job of it. It works out.
Digital Dictators: The full flowering of the third 2035 scenario. Here we see a massive consolidation of power in the hands of a very small number of ‘people,’ hybrids of AI top-sight and human biases. Maybe even a full digital duplication of a notorious authoritarian leader of years past, able to live on forever inside everyone’s devices.
“Of course, there’s always some aspects of the #1 scenario across issue areas—the Miserable Muddle. Stuff doesn’t work exactly as we’d like, but we can get enough done to carry on with it. People in power always change, but day-to-day demands (food, shelter, entertainment) don’t. Humans just keep going, no matter what.”
Ben Shneiderman, widely respected human-computer interaction pioneer and author of “Human-Centered AI,” wrote, “Increasing automation does not necessitate less human control. The growing recognition is that designers can increase automation of certain subtasks so as to give humans greater control over the outcomes. Computers can be used when they are reliable, safe and trustworthy while preserving human control over essential decisions, clarifying human responsibility for outcomes and enabling creative use by humans. This is the lesson of digital cameras, navigation and thousands of other apps. While rapid performance is needed in some tasks, meaningful human control remains the governing doctrine for design. As automation increases so does the need for audit trails for retrospective analysis of failures, independent oversight, and open reporting of incidents.”
For this study, Shneiderman also shared insights from an August 2022 interview he did with the Fidelity Center for Applied Technology: “The hopeful future we can continue to work toward is one in which AI systems augment, amplify and enhance our lives. Humans have agency over key decisions made while using a vast number of AI tools in use today. Digital cameras rely on high levels of AI for setting the focus, shutter speed and color balance while giving users control over the composition, zoom and decisive moment when they take the photo. Similarly, navigation systems let users set the departure and destination, transportation mode and departure time, then the AI algorithms provide recommended routes for users to select from as well as the capacity to change routes and destinations at will. Query completion, text auto-completion, spelling checkers and grammar checkers all ensure human control while providing algorithmic support in graceful ways.
“We must respect and value the remarkable capabilities that humans have for individual insight, team coordination and community building and seek to build technologies that support human self-efficacy, creativity, responsibility and social connectedness. Some advocates of artificial intelligence promote the goal of human-like computers that match or exceed the full range of human abilities from thinking to consciousness. This vision attracts journalists who are eager to write about humanoid robots and contests between humans and computers. I consider these scenarios as misleading and counterproductive, diverting resources and effort from meaningful projects that amplify, augment, empower, and enhance human performance.
“The past few years we have seen news stories about tragic failures of automated systems. The two Boeing 737 MAX crashes are a complex story, but one important aspect was the designers’ belief that they could create a fully autonomous system that was so reliable that the pilots were not even informed of its presence or activation. There was no obvious visual display to inform the pilots of the status, nor was there a control panel that would guide them to turn off the autonomous system. The lesson is that the excessive belief in machine autonomy can lead to deadly outcomes. When rapid performance is needed, high levels of automation are appropriate, but so are high levels of human independent oversight to track performance over the long-term and investigate failures.
“We can accelerate the wider, successful adoption of human-centered AI. it will take a long time to produce the changes that I envision, but our collective goals should be to reduce the time from 50 to 15 years. We can all begin by changing the terms and metaphors we use. Fresh sets of guidelines for writing about AI are emerging from several sources, but here is my draft offering:
1) Clarify human initiative and control.
2) Give people credit for accomplishments.
3) Emphasize that computers are different from people.
4) Remember that people use technology to accomplish goals.
5) Recognize that human-like physical robots may be misleading.
6) Avoid using human verbs to describe computers.
7) Be aware that metaphors matter.
8) Clarify that people are responsible for use of technology.”
Rob Reich, professor of political science and director of the Center for Ethics in Society at Stanford University, said, “No, systems powered by AI will not be designed to allow people to easily be in control over decision-making. The reigning paradigm for both basic research and industrial product design in AI is to strive to develop AI systems/models that meet or exceed human-level performance. This is the explicit and widely accepted goal of AGI, or artificial general intelligence. This approach sets AI on a course that leads inexorably to the diminishment or replacement of human agency.”
Sara M. Watson, writer, speaker and independent technology critic, replied with a scenario, writing, “The year is 2035. Intelligent agents act on our behalf, prioritizing collective and individual human interests above all else. Technological systems are optimized to maximize for democratically recognized values of dignity, care, well-being, justice, equity, inclusion and collective- and self-determination. We are equal stakeholders in socially and environmentally sustainable technological futures.
“Dialogic interfaces ask open questions to capture our intent and confirm that their actions align with stated needs and wants in virtuous, intelligent feedback loops. Environments are ambiently aware of our contextual preferences and expectations for engagement. Rather than paternalistic or exploitative defaults, smart homes nudge us toward our stated intentions and desired outcomes. We are no longer creeped out by the inferred false assumptions that our data doppelgängers perpetuate behind the uncanny shadows of our behavioral traces. This is not a utopian impossibility. It is an alternative liberatory future that is the result of collective action, care, investment and systems-thinking work. It is born out of the generative, constructive criticism of our existing and emergent relationship to technology.
“In order to achieve this:
Digital agents must act on stakeholders’ behalf with intention, rather than based on assumptions.
Technology must augment, rather than replace human decision-making and choice.
Stakeholders must trust technology.
“The stakes of privacy for our digital lives have always been about agency. Human agency and autonomy is the power and freedom of self-determination. Machine agency and autonomy are realized when systems have earned trust to act independently. Sociotechnical futures will rely on both in order for responsible technological innovation to progress.
“As interfaces become more intimate, seamless, and immersive, we will need new mechanisms and standards for establishing and maintaining trust. Examples:
Audio assistants and smart speakers present users not with a list of 10 search results but instead initiate a single command line action.
Augmented-reality glasses and wearable devices offer limited real estate for real time detail and guidance.
Virtual reality and metaverse immersion raise the stakes for connected, embodied safety.
Synthetic media like text and image generation are co-created through the creativity and curation of human artistry.
Neural interfaces’ input intimacy will demand confidence in maintaining control of our bodies and minds.
“Web3 principles and technical standards promise trustless mechanism solutions, but those standards have been quickly gobbled by rent seekers and zero-to-one platform logics before significant shifts in markets, norms and policy incentive structures can sustainably support their vision. Technology cannot afford to continue making assumptions based on users’ and consumers’ observed behaviors.
“Something akin to Lawrence Lessig’s four forces of regulatory influence over technology must be enacted: Code – Technology is built with agency by design. Markets – Awareness and demand for agency interfaces increases. Norms – Marginalized and youth communities are empowered to imagine what technology agency futures look like. Law – Regulators punish and disincentivize exploitative, extractive economic logics.”
Maja Vujovic, owner/director of Compass Communications, based in Belgrade, Serbia, wrote, “Whether we are ready or not, we must find ways to restore our control over our digital technology. If we don’t build user interfaces with a large button, simple keyword or short voice command for clearly separating what we agree to give out willingly (that which can be used) and what we don’t (which is off limits), then we’re just dumb. And doomed.
“Let’s look at the larger picture. We don’t need to wait for 2035 to automate our world. We can already patch a half a dozen applets, get our smart fridge to converse with our grocery app and link them both to our pay-enabled smart phone and a delivery service; they could restock our pantry on their own, every week. Yes, in the coming years, we will happily delegate such decisions in this interim period, when a sea of compute power will have to match an ocean of tiny parameters to just propose our next beach read or our late-night dinner-on-wheels.
“But wait! A nosy wearable will sound an alarm about that late-night meal intent and might even independently report it to our family doctor and to our health insurer. Our life insurance plan might also get ‘upgraded’ to a steeper premium, which our smart bank would automatically approve and honour every month. We might then also lose points on our gym score list, which could trigger a deserved bump of our next month’s membership fee, as a lesson.
“And just as we use our Lessons Learned app to proscribe late night-eating (because it makes us sick in more ways than one), we could see a popup flash before us, with a prompt: ‘Over three million of your look-alike peers voted for this candidate in the last election. She fights to protect our privacy, empowers disadvantaged groups and leads a healthy life—no late-night meals in her house! Would you join your peers now and cast your vote, quickly and confidentially?’
“All of this seems not implausible. The systems invoked above would work for each of us as users—we are their ‘Player One.’ Alas, there are also those systems that we are rarely aware of, where we are not users, but items. Any of those systems could—right now—be assessing our credit or dwelling application. Some applicant-tracking systems already blindly filter out certain job candidates or education seekers. Airbnb, hotels and casinos filter out unruly guests. In some countries of Europe, Middle East and Asia, authorities use facial recognition (de facto, though not always de jure) to keep tabs on their perceived opponents. It’s chilling to see the U.S. on the brink beyond which a patronizing governmental body or a cautious medical facility could filter out and penalize people based on their personal life choices.
“The technology to generate all kinds of recommendations already exists and is in use, often in ways that are not best for us. What is conspicuously lacking is real utilities, built for our benefit. Perhaps we might have a say in evaluating those who work for us: professors, civil servants, police officers, politicians, presidents. In fact, electoral voting systems might be equipped with a shrewd AI layer, Tinder-style: swipe left for impeachment; swipe right for second term.
“One reason more useful public-input recommender systems are not widely available is that they haven’t been successfully built and deployed. All other recommender systems have backers. We, the people, could try using Kickstarter to crowdfund our own.
“We can and will draft and pass laws that will limit the ability of technological solutions to decide too many things for us. In the coming decade, we will simply need to balance those two coding capacities of ours—one based on numbers, the other on letters. That’s a level of ‘programming’ that non-techies are able to do to put technology (or any unbridled power, for that matter) on a short leash. That interface has existed for several millennia; in fact, it was our first coding experience: regulation.
“There are already initiatives. An example is California’s ‘Kids’ Code’ (an age-appropriate-design code) that incorporates youth voices and energy. It shows that legislators and users possess impressive maturity around human-computer interaction and its risks, though the tech industry may appear unfazed, for now.”
R Ray Wang, founder, chairman and principal analyst at Constellation Research, wrote, “In almost every business process, journey or workflow, we have to ask four questions: 1) When do we fully intelligently automate? 2) When do we augment the machine with a human? 3) When do we augment the human with a machine? 4) When do we insert a human in the process? And these questions must also work with a framework that addresses five levels of AI Ethics: 1) Transparent. 2) Explainable. 3) Reversible. 4) Trainable. 1) Human-led.”
Richard Ashcroft, deputy dean and professor of bioethics at City University of London Law School, an expert on AI and ethics in healthcare, commented, “I am not optimistic because designing in human agency to AI/ML based systems is not easy from an engineering point of view, plus the industry and most of academia is mainly focussed on ‘quick wins,’ ‘low-hanging fruit’ and gaining competitive advantage in so doing.
“There’s also a strong tendency in the field to look for the advantages that ‘cutting out’ human agency, cognitive biases and other failures of ‘rationality’ bring, so I don’t think there is much appetite for designing human agency into these systems, outside the rather narrow field of ‘AI ethics,’ and the general debate in that area is more about assuring us that AI is safe, rather than looking for ways to make it so.
“A third point: Only some of these problems are specific to AI/ML systems; many of the issues were already built into complex sociotechnical systems, such as state bureaucracy, precisely to eliminate individual discretion because of issues around efficiency, avoidance of corruption and personal bias and so on.
“Also, any sufficiently complex system has ‘control problems’ that become problems of causal efficacy and epistemology. Humans have influence over such systems, but the effects of such influence are not always predictable or even desirable, from the point of view of the purposes built into such systems.”
Lillie Coney, chief of staff and policy director for a member of the U.S. House of Representatives, formerly associate director of the Electronic Privacy Information Center, said, “Agency and autonomy for one person may deny agency and autonomy to others. There will need to be norms, values and customs that alignment to transition to this state. There will likely be the ‘four walls rule’ that in one’s dwelling the person has full rights to exercise autonomy over technology, but even this will rely on Supreme Court decisions that uphold or strike down laws governing such matters.”
Ojelanki Ngwenyama, professor of global management and director of the Institute for Innovation and Technology Management at Toronto Metropolitan University, said, “It is pretty clear to me that it is not about the technology, but who controls it. Already tech firms determine what technologies we have and how we interact with them. Presently, we cannot even stop a mobile phone from recording our conversations and sending them to service providers, the makers of the technology, the developers of mobile operating systems, security agencies, etc.”
Paul Saffo, longtime Silicon Valley foresight guru, observed, “We have already turned the keys to nearly everything over to technology. The most important systems in our lives aren’t the ones we see, but the systems we never notice,—until they fail. This is not new: consider the failure of the Galaxy IV satellite a quarter century ago: puzzled consumers who never noticed the little dishes sprouting atop gas stations discovered they couldn’t fill their tank, get cash from ATMs, or watch their favorite cable TV programs.
“We have experienced 16 Moore’s Law doublings since then. Our everyday dependence on technology has grown with even greater exponentiality. We carry super-computers in our pockets, our homes have more smarts than a carrier battle group, and connectivity has become like oxygen—lose it for more than a few moments and we slip into digital unconsciousness, unable to so much as buy a latte, post a Tweet or text a selfie.
“Technologists are optimists. They promise that the next wave of technology will solve the failings of prior innovations and make glitches a thing of the past. Empowered by AI, Richard Brautigan’s ‘machines of loving grace’ will keep omniscient watch over our lives in a harmonious cybernetic meadow. There is no reason why the next technological wave can’t expand human agency, giving us greater satisfaction and control. It is just a matter of design. Or, rather, if it was just a matter of design, the now ubiquitous spell-checkers that so annoy us would actually be helpful—and come with an off switch to flick when they weren’t. This is just a minor example, but if we can’t make the small, simple stuff work for us, how will more complex systems ever live up to our expectations?
“But don’t blame the machines. No matter how brilliant AIs, avatars and bots become, they will never be truly autonomous. They will always work for someone—and that someone will be their boss and not you, the hapless user. Consider Uber or any of the other mobility services: in theory, their ever more brilliant algorithms should be working tirelessly to enhance the customer experience and driver income. Instead, they answer to their corporate minders, coldly calculating how far fares can be boosted before the customer walks—and how much can be salami-sliced off the driver’s margin before they refuse to drive.
“Nearly a century ago, Will Durant observed that ‘history reports that the men who can manage men manage the men who can manage only things, and the men who can manage money manage all.’ If Durant were here today, he would surely recognize that those who manage our synthetic intelligences will inevitably become the ones who manage all. And they will instruct their intelligences to grant you just enough agency to keep you from noticing your captivity.”
Nrupesh Soni, founder and owner of Facilit8, a digital agency located in Namibia, commented, “I fear that we have a whole generation of youth that is used to instant gratification, quick solutions and we do not have enough people who can think long-term and work on solutions. I do not think humans will be in-charge of the bots/AI decision-making, mainly because we are seeing a huge gap between the people who grew up with some understanding of programming and the basics motivations behind our digital technologies, and the next-gen that is used to using APIs provided to them without knowing the backend coding required to work on something new. There will be a time in the next 10 years when most of those who developed the core of these bots/AI will be aging out of the creative force, in their late 50s or 60s, and the younger generation will not know how to really innovate as they are used to plug-and-play systems.”
Maggie Jackson, award-winning journalist, social critic and author, commented, “Unless urgent steps are taken to protect human autonomy in our relations with AI, human agency in future will be seriously limited by increasingly powerful intelligences other than our own. I see the danger arising from both humanity’s innate weaknesses and from the unintended consequences of how AI is constructed.
“One point of vulnerability for human agency stems from how standard AI has been formulated. As AI pioneer Stuart Russell has brilliantly noted, we have created AI systems that have one overarching goal: to fulfill the objectives that humans specify. Through reinforcement learning, the machine is given a goal and must solve this objective however it can. As AI becomes more powerful, its foundational motivation becomes dangerous for two reasons.
People can’t know completely and perfectly what a good objective is; AI doesn’t account for a device or a person’s interactions within an unpredictable world. A machine that seeks to fulfill a specific objective however it can/will stop at nothing—even dismantling its off switch—in order to attain its goal, i.e., ‘reward.’ The implications are chilling.
“Consider the case of using AI to replace human-decision-making. AI is increasingly used to diagnose health problems such as tumors, to filter job candidates, and to filter and shape what people view on social media via recommender systems. While attention has rightly been drawn to the innate bias that is invested in AI, a larger danger is that AI has been created to solely to maximize click-through or other similarly narrow objectives.
“In order to maximize their goals, algorithms try to shape the world, i.e., the human user, to become more predictable and hence more willing to be shaped by the AI system.
“Social media and search engines, for instance, aren’t giving people what they want as much as modifying users with every click to bend to the goals they were created to pursue. And the more capable AI becomes, the more it ‘will be able to mess with the world’ in order to pursue its goals, write Russell and colleagues in a recent paper on AI’s future. ‘We are setting up a chess match between ourselves and the machines with the fate of the world as the prize. We don’t want to be in that chess match.’
“The result may be a form of chilling human enfeeblement, a dependence on powerful devices coupled with an indifference to this imbalance of power. It’s a mark of the seriousness of AI’s perils that leading scientists are openly discussing the possibility of this enfeeblement or ‘Wall-E problem’ (the movie of that name that portrayed humans as unwittingly infantilized by their all-powerful devices).
“A second point of vulnerability can be found in the rising use of caregiver robots. Simple robots are used mainly with vulnerable populations whose capacity to protect their cognitive and physical agency is already compromised. Robots now remind sick and elderly people to take their medicines; comfort sick children in hospitals; tutor autistic youth and provide companionship to seniors. Such ‘care’ seems like a promising use for what I call ‘AI with a face.’ But humanity’s proven willingness to attribute agency to and to develop intense social feelings for simple robots and even for faceless AI such as Siri is perilous. People mourn ‘sick’ Roombas, name and dress their healthcare-assistants and see reciprocity of social emotions such as care where none exists. As well, patients’ quick willingness to cede responsibility to a robot counters progress in creating patient-centered care.
“While studies show that a majority of Americans don’t want a robot caregiver, forces such as the for-profit model of the industry, the traditional myopia of designers, and the potential for people with less voice in healthcare to be coerced into accepting such care mean that public reservations likely will be ignored. In sum human autonomy is threatened by rising calls to use caregiver robots for the people whose freedom and dignity may be most threatened by their use.
“I am heartened by the urgent discussions concerning ethical AI ongoing around the world and by rising public skepticism—at least compared with a decade or so—of technology in general. But I am concerned that the current rapid devaluation of human agency inherent in AI as it is used today is largely absent from public conversation.
“We need to heed the creative thinkers such as Russell who are calling for a major reframing of standard models of AI to make AI better aligned with human values and preferences.
“We need to ignite serious public conversation on these topics—a tall order amidst rising numbness to seemingly ceaseless world crises.
“When it comes to human agency and survival, we are already deeply in play in the chess match of our lives—and we must not cede the next move and the next and the next to powerful intelligences that we have created but are increasingly unable to control.”
John Sniadowski, a systems architect based in the UK, said, “Our lack of agency has arrived. I suggest that the bias towards never challenging the machines is inevitable. Decision systems are generally based on opaque formulas with targeted outcomes the usually serve only the best interests of the AIs’ vendors. In most cases, the ultimate outcome from these automated, data-based decisions cannot be challenged and are, in fact, rarely challenged because the human belief is the system is correct often enough to be followed.
“Consider the financial industry today, in 2022. Lending decisions are based on smart systems that are nearly impossible to challenge. In addition, AI is frequently trained on data sets that are biased and may contain hidden anomalies that significantly alter the decision process.
“The vast majority of the population will be convinced by marketing, propaganda or other opinion-bending messages that these systems are right and any individual’s opinion is wrong. We already see that sort of behaviour in human-based systems operated by Big Pharma, where millions/billions of revenue could be lost if a significant outcome of a product/decision is successfully challenged.
“Life-and-death decisions should always require responsible human input, and they should have a set of criteria that the AI system must present in arriving at its decision that is transparent and capable of human interpretation. This should be enshrined in legislation with punitive consequences for vendors that do not comply with decision transparency. I would strongly suggest that this should be incorporated in a global human rights framework, that all humans have the right to challenge the outcome of an autonomous decision. This should be part of the UN charter and put in place as soon as possible.
“Given what we are experiencing on social media, where people can become captured by ‘echo chambers,’ there is a significant danger that AI and autonomous decision processes will exacerbate a broad range of societal inequalities. The vast array of data metrics now harvested from individuals’ internet activities will continue to categorize each person more and more towards an inescapable stereotype without the individual even being aware of the label unfairly applied to them.
“Companies will harvest information from ‘smart cities,’ and AI will build dossiers on each citizen that will be applied for a wide variety of decisions about a person completely without their personal consent. This is very dangerous, and we are already seeing this capability being subverted by some governments to tighten their authoritarian grip on their population.”
Ginger Paque, an expert in and teacher of internet governance with the Diplo Foundation, commented, “I note that the response to this question assumes that most conditions in the world will be on a predicted trajectory, following what is generally considered progress. I responded ‘no’ for two reasons. We are facing serious challenges today: pandemics, war, discrimination, polarizations, for example.
“It’s impossible to predict what kind of or level of civilization will prevail 13 years from now. I have no confidence in mathematical probabilities concerning our future on or off Earth. And while I think that coding, algorithms and machine learning will advance, I do not think they will be self-aware or reach sentience in the foreseeable future. That’s a belief, I guess, more than a well-founded scientific position. It leads me to think, then, that AI will continue to be designed, coded, and controlled by profit-seeking companies who have a vested interest in shaping and controlling our decision-making processes. So, it is not AI that controls our decisions; it is other humans who use the powerful resources of AI.
“What key decisions should be mostly automated? Those that each individual chooses to have automated based on clear and transparent settings. Which key decisions should require direct human input? Any that the individual chooses to have direct input on, and in particular any that affects the quality of life, education, privacy, health or characteristics unless clear options and alternatives are presented and evaluated for transparent choice.
“Autonomous decision-making is directed by some agency, most often a profit-making entity that logically has its profit as a priority. Whoever writes the code controls the decision-making and its effects on society. It’s not autonomous, and we should have clear and transparent options to ensure we do not continue to cede control to known or unknown entities without proper awareness and transparency. It’s not AI that’s going to take humans’ decision-making faculties away any more than phones and GPS ruin our memories. Humans choose—quite often without the proper awareness, information and training—to do so.”
Jean Seaton, director of the Orwell Foundation and professor of media history at the University of Westminster, said, “The questions you pose do not factor in political systems. Already we can see the impact of new apparently ‘democratic’ ways of communicating on political choices on political structures. The manipulability of apparently technical systems has already moved the world dramatically away from a wider human agency. The willingness—particularly of authoritarian states—to monitor but also ‘please’ people and manipulate understanding depends on these systems. The hostility towards expertise seen today, the politicization of every critical issue, and more—these are all manipulable. What political systems do well out of this? In future, very few people may have agency. How will they use it?
“Fear and anxiety are proper responses to the challenges we face. For one, the existential threat of climate extinction is about to be fogged by the initial waves of refugees from soon-to-be uninhabitable places—Delhi? Central and South Africa? Afghanistan and Pakistan? Mis-, dis- and malinformation succeed as distractions, and human agency is wasted on the small revenges rather than solving the long-term challenges that must be addressed now.”
Leah Lievrouw, professor of information studies at UCLA, wrote, “If the main point of this set of questions is agency, ‘will be designed’ is the fulcrum. Someone is designing these technologies for some purpose based on the assumptions of those who commission them. ‘Design’ and ‘designers’ seem to be presented here as passive processes, ‘manna from heaven’ in the old line from economics about the effects of technology.
“Who exactly has ‘agency’? According to the June 11, 2022, cover feature on AI in The Economist, the only ‘designers’—organizations? individuals?—with the cash and brute-force computing capabilities to do the newest ‘foundational AI’ are huge private, for-profits, with one or two non-profits like OpenAI being supported by the private firms; there are also a few new startups attempting ‘responsible’ or ‘accountable’ algorithms. So, there’s the agency of designers (will they design for user control?) and the agency of users (decision-making based on what AI presents them?).
“Decision-making may not be the only aspect of agency involved. The ‘machine-human’ relationship binary has been around in popular culture for ages, but I think the current thinking among AI designers goes way beyond the one-to-one picture. Rather, AI will be integrated into many different digital activities for lots of reasons, with ripple effects and crossovers likely. Thus, there’s unlikely to be a bright-line division between machine decisions and human decisions, both for technical reasons and because who, exactly, is going to declare where the line is? Employers? Insurers/finance? State agencies? Legislatures?
“Any entity deploying AI will want to use it to the greatest extent possible unless specifically enjoined from doing so, but right now (except maybe in the EU…?) it seems to me that few regulators or organizations are there yet. We already see some very worrisome outcomes, for example, algorithmic systems used in legal sentencing.”
Marti Hearst, professor and head of the school of information, University of California-Berkeley, said, “In general, interfaces to allow people to adjust settings do not work well because they are complicated and they are disfavored by users. Consider tools that aid people in what they are doing, such as search engines or machine translation. These tools use a lot of sophisticated computation under the hood, and they respond quickly and efficiently to people’s queries. Research shows that people do not want to adjust the settings of the underlying algorithms. They just want the algorithms to work as expected.
“Today’s machine translation tools work adequately for most uses. Research shows that translators do not want to expend a lot of effort correcting a poor translation. And users do not want to take the time to tweak the algorithm; they will use the results even if they are poor since there is often no other easy way to get translations. Alternatives interfaces might give users lots of choices directly in the interface rather than anticipating the users’ needs. This can be seen in faceted navigation for search, as in websites for browsing and searching for sporting goods and home decor products.
“Tools will continue make important decisions for people, whether they want this or not. This includes settings such as determining recidivism and bail, judging teacher performance and perhaps including push advertising and social media feeds. These tools will not allow for any user input since it is not in the interests of those imposing the decisions on others to do so.”
Laurie L. Putnam, educator and communications consultant, commented, “If you look at where we are now and plot the trajectory of digital ‘tools,’ it looks like we’re going to land in a pretty dark place.
“Already we would be hard-pressed to live our lives without using digital technologies, and already we cannot use those phones and apps and cars and credit cards without having every bit of data we generate—every action we take, every purchase we make, every place we go—hoovered up and monetized. There is no way to opt out. Already we are losing rather than gaining control over our personal data, our privacy, our lives.
“Yes, digital technologies can do a lot of good in the world, but when they are created to improve a bottom line at any cost, or to control people through surveillance, then that is what they will do. If we want to alter our course and land in a better place, we will need to reinvent the concept of consumer protection for the information age. That will require thoughtful, well-informed human decision-making—now, not years from now—in legislative policies, legal standards and business practices. These are the checks and balances that can help move us in the right direction.”
Kunle Olorundare, principal manager at the Nigerian Communications Commission, wrote, “Based on today’s trends in terms of the development of artificial intelligence, by 2035 the advancement of AI will have taken over most of the decisions that once were taken solely by humans. Bots with high-level intelligence will be manufactured for the sole purpose of solving complex tree decisions. These will take over most human decisions.
“Key decisions in engineering design, packaging in the manufacturing sector, arrangement of stock, logistics tracking, triggering of alarms will be done by bots, etc. However, human decisions will still be relevant even if relegated to the background. Ethical issues in engineering will still be taken on by humans because they require making relative arguments for and against.
“Our society will be changed for good, with integrated bots taking on most movement logistics decisions. Autonomous vehicles will lead to safer road practices because bots will always keep to the rules (except for occasional accidents that may occur due to bugs). There won’t be unreasonable competitive driving on our roads, in the sky or on the ocean.
“Those of us in the Internet Society—for which I am vice president of the Nigeria Chapter –believe in an open but secured internet. Autonomous systems will operate on a secured internet that allows for secure dissemination of relevant data for informed decisions based upon analytics. Due the increasing volume of vital data flowing through these systems, we must make continuous improvements in cyber security.
“Among the important places in which autonomous systems and the Internet of Things will play roles in resolving complex problems are in hospitals—for diagnosis and other tasks—and in agriculture, where data analytics and unmanned aerial vehicles will be useful in all aspects of farming and food distribution.”
Jeremy Foote, a computational social scientist studying cooperation and collaboration in online communities, said, “People are incredibly creative at finding ways to express and expand their agency. It is difficult to imagine a world where they simply relinquish it. Rather, the contours of where and how we express our agency will change, and new kinds of decisions will be possible. In current systems, algorithms implement the goals of their designers. Sometimes those goals are somewhat open-ended and often the routes that AI/ML systems take to get to those goals are unexpected or even unintelligible. However, at their core, the systems are designed to do things that we want them to do, and human agency is deeply involved in designing the systems, selecting parameters and pruning or tweaking them to produce outputs that are related to what the designer wants.
“AI and ML are already and will continue to be used to identify weaknesses in our processes. Through big data processing and causal inference approaches, we have recognized ways that judicial systems are racially biased, for example. I think that these sorts of opportunities to use data to recognize and correct for blind spots will become more common.
“Some systems, of course, will become more automated—driving, like flying, will likely be something that is primarily done by computers. There is great promise in human-machine collaborations. Already, tools like GPT-3 can act as on-demand sounding boards, providing new ways to think about a topic or writing up the results of research in ways that augment human authors.”
Gary A. Bolles, chair for the future of work at Singularity University and author of “The Next Rules of Work,” predicted, “Innovators will continue to create usable, flexible tools that will allow individuals to more easily make decisions about key aspects of their lives and about the technologies they use. There’s also a high probability that 1) many important decisions will be made for people, by technology, without their knowledge, and 2) the creators of media and information platforms will lead the arms race, creating tools that are increasingly better at hacking human attention and intention, making implicit decisions for people and reaping the data and revenue that comes from those activities.
“First, every human needs education in what tech-fueled decision-making is and what decisions tech can and does make on its own.
“Second, tech innovators need a stringent code of ethics that requires them to notify humans when decisions are made on their behalf, tells them the uses of related data and tells how the innovator benefits from the use of their tools. Finally, industry needs open protocols that allow users to manage dashboards of aggregated decisions and data to provide transparent information that allows users (and their tools) to know what decisions technology is making on their behalf, empowering them to make better decisions.”
Henning Schulzrinne, Internet Hall of Fame member and co-chair of the Internet Technical Committee of the IEEE, said, “Agency and recourse are privileges now and they are likely to become more so. By 2035, automated decision-making will affect all high-volume transactions—from hiring and firing to obtaining credit, renting apartments, gaining access to health care, and interactions with the criminal justice system. Wealth, income and social standing will determine the extent to which individuals will have the ability to contest and work around automated decisions. It doesn’t seem likely that any of this will change.
“This is not a new concept. An example is the scheduling of when and where you work; for many hourly workers and gig workers this is automated, with little ability to influence the hours and locations. Employment and termination are also already largely algorithmic (see Amazon warehouses and many gig platforms). High-income, higher-status individuals will likely still get interviewed, hired and evaluated individually, and have at least some leverage. This is also more trivially true for travel—economy class travelers book or rebook online; business class travelers get concierge service by a human. In 2035, the notion of talking to an airline representative, even after waiting for hours in a call center queue, will become a rarity.
“Areas that are currently ‘inefficient’ and still largely human-managed will become less so, particularly in regard to employment, rental housing and health care. Human input is only modestly useful if the input is a call center staff person who mainly follows the guidance of their automated systems. Human input requires recourse, rights and advocacy, i.e., the ability to address unfair, discriminatory or arbitrary decisions in employment, credit, housing and health care.”
Christian Huitema, 40-year veteran of the software and internet industries and former director of the Internet Architecture Board, wrote, “Past experience with technology deployment makes be dubious that all or even most developers will ‘do the right thing.’
“We see these two effects colliding today, in domains as different as camera auto-focus, speed-enforcement camera, and combat drones. To start with a most benign scenario, camera makers probably try to follow the operator’s desires when focusing on a part of an image, but a combination of time constraints and clumsy user-interaction design often proves frustrating. These same tensions will likely play in future automated systems.
“Nobody believes that combat drones are benign, and most deployed systems keep a human in the loop before shooting missiles or exploding bombs. I hope that this will continue, but for less-critical systems I believe designers are likely to take shortcuts, like they do today with cameras. Let’s hope that humans can get involved after the fact and have a process to review the machines’ decisions.
“Autonomous driving systems are a great example of future impact on society. Human drivers often take rules with a grain of salt, do rolling stops or drive a little bit above the speed limit. But authorities will very likely push back if a manufacturer rolls out a system that does not strictly conform with the law. Tesla already had to correct its ‘rolling stop’ feature after such push-back. Such mechanisms will drive society towards ‘full obedience to the laws,’ which could soon become scary.”
Richard Bennett, founder of the High Tech Forum and ethernet and WiFi standards cocreator, said, “While future AI systems will be designed to allow human override, most people will not take advantage of the feature. Just as we agree to privacy policies without reading them, we will happily defer to algorithmic judgments when it means saving a few minutes and avoiding the headaches of parsing complex policies. Policy advocates will continue to demand transparency and various other features, but the public will continue to value convenience over control.”
Laura Stockwell, executive VP for strategy, WundermanThompson, wrote, “When you look at the generation of people designing this technology—primarily Gen Z and Millennials—I do believe they have both the awareness of the implications of technology on society, along with the political leaning required to implement human-first design. Specifically, when you look at the development of Web3 and ownership of data you see proof of this approach already. We are also witnessing a generation of workers raised with DEI initiatives as well as the diversification of our population which are both positive steps forward in more inclusive design. I also believe that those in decision-making positions—primarily Gen X, will support these decisions. That said, I do believe legislation will be required to support large companies to take into account user autonomy and agency.”
Daniel Castro, vice president and director of the Center for Data Innovation at the Information Technology and Innovation Foundation, asks, “When you wake up to an alarm, is this a machine in control of a human or a human in control of a machine? Some would argue the machine is waking up the human, so therefore the machine is in control. Others would say the human set the alarm, so therefore the human is in control. Both sides have a point.
“What is exciting about AI is that we can move the debate to a new level—humans will have the option to use technology to better understand their entire sleep patterns, and how factors like diet, exercise, health, and behavior impact their sleep and what options are available to them to change. Some of this will be automated, some of this will involve direct human choice and input. But the net impact will be greater opportunities for control of one’s life than before.
“Some people may be happy putting their lives completely on autopilot. Others will want to have full control. Most will probably be somewhere in the middle, allowing algorithms to make many decisions but scheduling regular check-ins to make sure things are going right—the same way that people may check their credit card bills, even if they have autopay.”
danah boyd, founder of the Data & Society Research Institute and principal researcher at Microsoft, complained, “Of course there will be technologies that are designed to usurp human decision-making. This has already taken place. Many of the autopilot features utilized in aviation were designed for precisely this, starting in the 1970s; recent ones have presumed the pilot to be too stupid to take the system back. (See cultural anthropologist Madeleine Elish’s work on this.)
“We interface every day with systems that prevent us from making a range of decisions. Hell, the forced-choice, yes-no format of this survey question constrained my agency. Many tools in workplace contexts are designed to presume that managers should have power over workers; they exist to constrain human agency. What matters in all of these systems is power. Who has power over whom? Who has the power to shape technologies to reinforce that structure of power?
“But this does not mean that ALL systems will be designed to override human agency in important decisions. Automated systems will not control my decision to love, for example. That doesn’t mean that systems of power can’t constrain that. The state has long asserted power over marriage, and families have long constrained love in key ways.
“Any fantasy that all decisions will be determined by automated technologies is science fiction. To be clear, all decisions are shaped (not determined!) by social dynamics, including law, social norms, economics, politics, etc.
“Technologies are not deterministic. Technologies make certain futures easier and certain futures harder, but they do not determine those futures. Humans—especially humans with power—can leverage technology to increase or decrease the likelihood of certain futures by mixing technology and authority. But that does not eliminate resistance, even if it makes resistance more costly.
“Frankly, focusing on which decisions are automated misses the point. The key issue is who has power within a society and how can they leverage these technologies to maximize the likelihood that the futures they seek will come to pass.
“The questions for all of us are: 1) How do we feel about the futures defined by the powerful; and 2) How do we respond to those mechanisms of power? And, 3), more abstractly, what structures of governance do we want to invest in to help shape that configuration?”
Steve Sawyer, professor of information studies at Syracuse University, wrote, “We are bumping through a great deal of learning about how to use data-driven AI. In 15 years, we’ll have much better guidance for what is possible. And the price point for leveraging AI will have dropped—the range of consumer and personal guidance where AI can help will grow.”
Gillian Hadfield, professor of law and chair of the University of Toronto’s Institute for Technology and Society, said, “By 2035 I expect we will have exceedingly powerful AI systems available to us including some forms of artificial general intelligence. You asked for a ‘yes-no’ answer although the accurate one is ‘either is possible and what we do today will determine which it is.’
“If we succeed in developing the innovative regulatory regimes we will need–including new ideas about constitutions (power-controlling agreements), ownership of technology and access to technology by the public and regulators—then I believe we can build aligned AI that is responsive to human choice and agency. It is just a machine, after all, and we can decide how to build it. At the same time, it is important to recognize that we already live with powerful ‘artificially intelligent’ systems—markets, governments—and humans do not have abstract, ideal agency and choice within those systems.
“We live as collectives with collective decision-making and such highly decentralized decisions that constrain any individual’s options and paths. I expect we’ll see more automated decision-making in domains in which markets now make decisions—what to build, where to allocate resources and goods and services. Automated decision-making, assuming it is built to be respected and trusted by humans because it produces justifiable outcomes, could be used extensively in resolving claims and disputes. The major challenge is ensuring widespread support for decision-making; this is what democratic and rule-of-law processes are intended to do now.
“If machines become decision-makers, they need to be built in ways the earn that kind of respect and support—from winners and losers in the decision.
“The version of the future in which decisions are automated on the basis of choices made by tech owners and developers alone (i.e., implementing the idea that a public services decision should be made solely on the basis of a calculation of an expert’s assessment of costs and benefits) is one in which some humans are deciding for others and reducing the equal dignity and respect that is foundational to open and peaceful societies. That’s a bleak future, and one on which the current tensions between democratic and autocratic governance shed light. I believe democracy is ultimately more stable and that’s why I think powerful machines in 2035 will be built to integrate into and reflect democratic principles, not destroy them.”
Barry Chudakov, founder and principal, Sertain Research, wrote, “Before we address concerns about turning the keys to nearly everything over to technology, including life-and-death decisions, it is worthwhile to consider that humanity evolved only recently to its current state after hundreds of thousands of years of existence.”
“The Open Education Sociology Dictionary defines agency as ‘the capacity of an individual to actively and independently choose and to affect change; free will or self-determination.’ For much of human history, individual agency was not the norm. David Wengrow and David Graeber asked in ‘The Dawn of Everything’: ‘How did we come to treat eminence and subservience not as temporary expedients … but as inescapable elements of the human condition?’ In a review of that book, Timothy Burke argues, ‘An association between small-scale foraging societies and egalitarian norms is robust. If we are to understand human beings as active agents in shaping societies, then applying that concept to societies at any scale that have structures and practices of domination, hierarchy and aggression should be as important as noting that these societies are neither typical nor inevitable.’
“Much earlier, writing in the 1600s, the English philosopher Thomas Hobbes claimed in ‘Leviathan’ that without government life would be ‘solitary, poor, nasty, brutish and short.’ Yet by 1789, no country had a democratic government. As of 2021 (232 years later) only half of all countries were democracies and just 89 of the 179 countries for which data is available held meaningful free-and-fair, multi-party elections.
“Agency has been more a privilege than a reality for a broad swath of human history; humans did not possess the more-recent sense of agency in which they feel the freedom to be able to break out of an assigned role, advance or change their career or profession, or raise a voice in various ways on any issue. Technology tools have reformulated agency. In fact, to say they ‘reformulate’ it is not strong enough.
“Within the context of limited liberal democracies, human agency took a quantum leap with the advent of computers and the smartphone. Today via podcast, YouTube, Snap, TikTok or an appearance on CNN, a Greta Thunberg or Felix Finkbeiner can step out of the shadows to fight for climate change or any other issue. Today humans have a host of tools, from cell phones to laptops to Alexa and Siri to digital twins. These tools are still primitive compared to what’s coming. They don’t only provide opportunities. They can also usurp agency, as when a person driving looks down at a text ping and crashes the car, even ending their life.
“We cannot fully grasp the recency of the agency we have gained, nor the encroachments to that agency that new tools represent. In concert with understanding this, we come to the startling realization—the acknowledgement—that today we are not alone; our agency is now shared with our tools.
“In effect, shortly after about 20% of the world’s population (those living in liberal democracies) were afforded actual agency, things abruptly changed. Technology outpaced democracy. It also outpaced our awareness of the effects of technology gadgets and devices. For most of us who use them tools, agency today is impinged, compromised, usurped and ultimately blended with a host of tools. This is the new baseline.
“Seeing agency as shared compels response and responsibility. If people are to remain in charge of the most relevant parts of their own lives and their own choices, it is imperative to realize that as we more deeply embrace new technologies to augment, improve and streamline our lives, we are not outsourcing some decision-making and autonomy to digital tools; we are using tools—as we always have done—to extend our senses, to share our thinking and responses with these tools. We have done this with alphabets and cameras, computers and videos, cell phones and Siri.
“We are facing a huge paradigm shift with the advent of new technologies and AI and machine learning. We need to reconfigure our education and learning to teach and incorporate tool logic. Anticipating tool consequences must become as basic and foundational as reading or numeracy. We can no longer thoughtlessly pick up and use, or hand over to children, devices and technologies that have the ability (potential or actual) to alter how we think and behave.
“Agency has no meaning if we are unaware. There is no agency in blindness; agency entails seeing and understanding. From kindergarten to post-graduate studies, we need students and watchers who are monitoring surveillance capitalism, algorithm targeting, software tracking, user concentration and patterns and a host of other issues.”
“Considering agency from this perspective requires a rethink and re-examination of our natures, our behaviors and the subliminal forces that are at work when we pick up technology gadgets and devices. As Daniel Kahneman wrote, ‘Conflict between an automatic reaction and an intention to control it is common in our lives.’ We have little choice but to become more conscious of our reactions and responses when we engage with smart machines, bots and systems powered mostly by autonomous and artificial intelligence (AI).
Stephen Hawking said of AI and human agency, ‘The real risk with AI isn’t malice, but competence. A super-intelligent AI will be extremely good at accomplishing its goals, and if those goals aren’t aligned with ours we’re in trouble.’
“Our goals start with understanding how humans (mostly unconsciously) adopt the logic of tools and devices. Here is the truth about agency: no one escapes adhering to tool logic. We are not invincible when we engage with our gadgets and devices. The Marlboro Man notion of the cool, detached actor is defunct. We are now—and we will be much more so in the future—co-creators with our tools; we think with our tools; we act with our tools; we are monitored by them; we entrain with their logic. This is a re-statement of agency for those who claim the line from ‘Invictus,’ ‘I am the master of my fate: I am the captain of my soul.’ Actually, our technologies are at the helm with us.
“Rather than be offended by the intrusion of AI, or threatened by it, it would be far better to understand how AI affects agency in different dimensions, realize its potential and limitations and adjust our self-image accordingly. That adjustment starts with the understanding that we follow in the footsteps of our tools thus they will always affect our sense of self and our agency.
“What, then, does it mean to frame agency as a shared dynamic of the modern human condition? What does shared agency mean? It means that humans have willingly acceded a measure of their will and intent—their agency—to tools that augment (and often compete with) that will and intent; tools and software designed to involve human consciousness to such a considerable degree that humans can lose track of where they are, what they are doing, who they are with. Whether considered distraction or absorption, this is what agency looks like in 2022.
“Agency is not so simple. Like technology itself, agency is complicated. The short history of modern technology is the history of human agency encroached upon by tools that include ever greater ‘intelligence. The Kodak Brownie camera, a cardboard tool released in 1900, had no computing power built into it; today’s digital SLR has a raft of metadata that can ‘take over’ your camera, or simply inform you regarding many dimensions of light intensity, distance, aperture or shutter speed. In this instance, and in many others like it, humans choose the agency they wish to exert. That is true of computers, cell phones, video games or digital twins. We must now become more nuanced about that choice and shun simplistic encapsulations. As the website, AI Myths, notes:
‘No AI system, no matter how complex or ‘deep’ its architecture may be, pulls its predictions and outputs out of thin air. All AI systems are designed by humans, are programmed and calibrated to achieve certain results, and the outputs they provide are therefore the result of multiple human decisions.’
“But how many of us are aware of that programming or calibration? Unless we acknowledge how our agency is affected by a host of newer tools—and will be affected to an even greater extent by tools now in the works—our sense of agency is misguided. Our thinking about and assumptions of agency will be erroneous unless we acknowledge that we share agency with these new tools. We need to recognize that we share our consciousness with newer technology tools, we are no longer lone, independent agents.
“That’s not all. We are capable of creating new beings. Yuval Noah Harari says, ‘We are breaking out of the organic realm and starting to create the first inorganic beings in the history of life.’ These alt beings will further confound our sense of agency. Along with a question of our proprioception—where does our body start and end as we take ourselves into the metaverse or omniverse—inorganic beings will force us to ask, ‘what is real?’ and ‘what does real mean anymore?’ Will people opt for convenience, romanced by entertainment, and allow the gadgetry of technology to run roughshod over their intentions and eventually their rights?
“The answer to those questions becomes an issue of design informed by moral awareness. Technology must, at some level, be designed not to bypass human agency but to remind, encourage and reward it. Software and technology need to become self- and other-aware, to become consequence-aware.
“Technology seduction is a real issue; without engendering techno-nag, humans must confront AI with HI—human intelligence. Humans must step up to embrace and realize the potential and consequences of living in a world where AI can enhance and assist. Partnering with artificial intelligence should be an expansion of human intelligence, not an abdication of it.
“No, I do not expect that by 2035 smart machines, bots and systems powered by artificial intelligence will be designed to allow people to easily be in control over most tech-aided decision-making relevant to their lives. My rationale: In 13 years will we have completely revamped our educational systems to enable full understanding of the effects of technology and tech-aided decision-making? I doubt it.
“I believe the relationship between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence will look like an argument with one side shouting and the other side smiling smugly. The relationship is effectively a struggle between the determined fantasy of humans to resist (‘I’m independent and in charge and no, I won’t give up my agency!’) and the seductive power of technology (‘I’m fast, convenient, entertaining! Pay attention to me!’) designed to undermine that fantasy. However, this relationship is not doomed to be forever tense and unsatisfying.
“In a word, the relationship between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence will be fraught; it will still be unclear by 2035 that humans are now sharing their intelligence, their intentions, their motivations with these technological entities. Why? Because we have not built, nor do we have plans to build, awareness and teaching tools that retrain our populace or make people aware of the consequences of using newer technologies; and because in 13 years the social structures of educational systems—ground zero for any culture’s values—will not have been revamped, rethought, reimagined enough to enable humans to use these new entities wisely. Humans must come to understand and appreciate the complexity of the tools and technologies they have created, and then teach one another how to engage with and embrace that complexity.
“Some elaboration will clarify. Today most educational structures are centered around the older model of retention as the driver of matriculation. That is, students are tested on how much of the subject matter they are retaining, remembering. While it is important for students to understand, remembering has much less utility or meaning in a world where every fact is available at anyone’s fingertips via a host of devices, Alexa, Siri, etc. Instead, what is now supremely important is to understand the dynamics and logic of smart machines, bots and systems powered mostly by autonomous and artificial intelligence. This is the new foundation of learning.
“Further, instead of starting in kindergarten along with language and math skills, techno education is still siloed in “computer science”—which means much of our educated populace, unless they go to enlightened grammar schools or are computer science majors, are not trained in the languages of the future (JavaScript, Python, Go, etc.); or in the logic and grammar of quantum computing, digital twins, blockchain, algorithms, Internet of Things, or federated learning to name a few. This puts many students at a disadvantage when it comes to today’s most critical skill: learning to think through, question, test, and probe the moral and ethical dimensions of these new tools. In effect, questions of agency are off the table.
“Given the segregated hierarchical nature of today’s pedagogy, the issues of understanding the dynamics and logic of smart machines, bots and systems powered by autonomous and artificial intelligence is relegated—as mentioned—to the field of computer science. This means a university computer science major directly encounters these phenomena starting around the age of 18. That is utter nonsense. By that time, they have had their noses in devices at least since they were five, and many earlier as careless parents try to pacify toddlers with devices as early as two or three. Our devices as currently designed bypass agency, trick agency, deaden agency, lull agency—and these are the crude forerunners to the good stuff, to devices and technologies just around the corner in the metaverse and omniverse.
“Will we have entirely revamped educational structures K through university graduate school to enable necessary and powerful learning by 2035? Today we can’t even get large portions of our population to get vaccinated against a deadly virus; the population does not understand—or care about—disease vectors or communicable and mutating viruses. They think of them as conspiracies instead of DNA strings. What makes anyone think that in 13 years our educational system will revamp itself to address fundamental changes in the world and prepare students to coherently and ethically deal with smart tools, emerging technologies and their effects on agency?
“It will still be unclear to most by 2035 that humans are now sharing their intelligence, their intentions, their motivations with these technological entities. Why? Because we have not built, nor do we have plans to build, awareness and teaching tools that retrain our populace or make people aware of the consequences of using newer technologies; and because in 13 years the social structures of educational systems—ground zero for any culture’s values—will not have been revamped, rethought, reimagined enough to enable humans to use these new entities wisely.
“Humans must come to understand and appreciate the complexity of the tools and technologies they have created and then teach one another how to engage with and embrace that complexity. It is now supremely important is to understand the dynamics and logic of smart machines, bots and systems powered mostly by autonomous and artificial intelligence. This is the new foundation of learning. But most are at a disadvantage when it comes to today’s most critical skill: learning to think through, question, test and probe the moral and ethical dimensions of these new tools.
“The nature of consumer-focused smart tools is to keep the logic and dynamics of the tools hidden, or at least less noticeable, and to engage the user with features that are quick, convenient, pacifying. These can be the enemies of agency. The inside revolt of people in technology development is an enlightened push-back against the usurping of agency:
Steve Jobs wouldn’t let his kids use an iPad or iPhone.
Jaron Lanier has written extensively about the danger of treating humans as gadgets.
Former Google insider, Christian Harris, has railed against social media algorithms and how they amplify nonsense, creating the new propaganda, which he calls ‘amplifiganda.’
Stephen Hawking said that efforts to create thinking machines pose a threat to our very existence.
“Yet agency arrives in the smallest moments. Looking at your phone can be so addictive you don’t notice you’re ignoring a loved one; your attention can be compromised when driving, with deadly consequences. These are agency compromises. If you had full-awareness agency, you would notice that being alone together is not the purpose of togetherness; or that driving while texting is dangerous. But the device has usurped a measure of your agency.
“We would be wise to prepare for what shared consciousness means. Today that sharing is haphazard: We pick up a tool and once we are using how it is programmed, we see (and can be shocked by) how much agency the tool usurps. Instead, what we need is awareness of what technology-human sharing means and how much, if any, agency we are willing to share with a given tool. We will increasingly use AI to help us resolve wicked issues of climate change, pollution, hunger, soil erosion, vanishing shorelines, biodiversity, etc. In this sharing of agency, humans wil
| 2023-02-24T00:00:00 |
https://www.elon.edu/u/imagining/surveys/xv2023/the-future-of-human-agency-2035/credit/
|
[
{
"date": "2023/02/24",
"position": 50,
"query": "universal basic income AI"
}
] |
|
The Future of Human Agency | Imagining the Internet
|
The Future of Human Agency
|
https://www.elon.edu
|
[] |
The reigning paradigm for both basic research and industrial product design in AI ... income. Instead, they answer to their corporate minders, coldly ...
|
Experts are split about how much control people will retain over essential decision-making by 2035, as digital systems and AI spread. They agree that powerful corporate and government authorities will expand the role of AI in people’s daily lives in useful ways. But many worry these systems are diminishing individuals’ ability to control their choices
The content for this report was gathered in a canvassing conducted in summer 2022 by Elon University’s Imagining the Internet Center and Pew Research Center. The question asked: By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow people to easily be in control of most tech-aided decision-making that is relevant to their lives?
Results released February 24, 2023 – Pew Research Center and Elon University’s Imagining the Internet Center invited thousands of experts to share their opinions and predictions about the likely near future of human agency. More than 500 technology innovators, developers, business and policy leaders, researchers and activists responded to this canvassing, which took place between June 29 and Aug. 8, 2022. Several hundred of them wrote explanatory comments after responding to the study’s quantitative question on the topic. This report organizes and categorizes the most common themes expressed by these experts, and it provides thousands of intelligent insights about the likely future based on today’s trends.
This page carries the full 173-page report in one long scroll; you can also download a PDF by clicking on the related graphic. If you wish you can select a link below to read only the expert responses, with no sort or analysis:
– Read only the for-credit experts’ views on the future of human agency
– Read only the anonymous experts’ views on the future of human agency
– Download or read the print version of the report
This main report web page contains: 1) the research question; 2) a very brief outline of the most common themes found among these experts’ remarks; 3) the full report with analysis, which weaves together the experts’ written submissions in chapter form; 4) a detailed methodology section, which is located after the final chapter. The research question follows.
Prompt – Digital tools and human agency: Advances in the internet and online applications have allowed humans to vastly expand their capabilities, increased their capacity to tackle complex problems, allowed them to share and access knowledge nearly instantly, helped them become more efficient and amplified their personal and collective power to understand and shape their surroundings. Smart machines, bots and systems powered mostly by autonomous and artificial intelligence (AI), will continue those advances.
As people more deeply embrace these technologies to augment, improve and streamline their lives, they are outsourcing some decision-making and autonomy to digital tools. That’s the issue we explore in this survey. Some worry that humans are going to turn the keys to nearly everything – including life-and-death decisions – over to technology. Some argue these systems will be designed in ways to better-include human input on decisions, assuring that people remain in charge of the most relevant parts of their own lives and their own choices.
The question: By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives?
Yes, by 2035 smart machines, bots and systems powered by artificial intelligence WILL be designed to allow humans to easily be in control of most tech-aided decision-making relevant to their lives.
to allow humans to easily be in control of most tech-aided decision-making relevant to their lives. No, by 2035 smart machines, bots and systems powered by artificial intelligence WILL NOT be designed to allow humans to easily be in control over most tech-aided decision-making relevant to their lives.
Results for this question regarding the evolution of human agency by 2035:
56% of these experts selected that by 2035 smart machines, bots and systems will not be designed to allow humans to easily be in control of most tech-aided decision-making.
of these experts selected that by 2035 smart machines, bots and systems be designed to allow humans to easily be in control of most tech-aided decision-making. 44% said they hope or expect that by 2035 smart machines, bots and systems will be designed to allow humans to easily be in control of most tech-aided decision-making.
It should be noted that in explaining their answers most of these experts agreed that the future of digital systems is likely hold both positive and negative consequences for human agency. Most of the overall expert group also agreed that the current moment is a turning point that will determine a great deal about the authority, autonomy and agency of humans as the use of digital technology spreads inexorably into more aspects of daily life. The quantitative numbers alone do not tell the story. The question was asked to elicit respondents’ thought-provoking qualitative insights.
Follow-up qualitative question: Why do you think humans will or will not be in control of important decision-making in the year 2035? We invite you to consider addressing one or more of these related questions in your reply. When it comes to decision-making and human agency, what will the relationship look like between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence? What key decisions will be mostly automated? What key decisions should require direct human input? How might the broadening and accelerating rollout of tech-abetted, often autonomous decision-making change human society?
Common themes found among the experts qualitative responses:
Themes shared by those who say digital tools WILL NOT allow people to easily be in control:
*Powerful interests have little incentive to honor human agency – the dominant digital-intelligence tools and platforms the public depends upon are operated or influenced by powerful elites – both capitalist and authoritarian – that have little incentive to design them to allow individuals to exert more control over their tech-abetted daily activities.
*Humans value convenience and will continue to allow black-box systems to make decisions for them – people already allow invisible algorithms to influence and even sometimes “decide” many if not most aspects of their daily lives and that won’t change.
*AI technology’s scope, complexity, cost and rapid evolution are just too confusing and overwhelming to enable users to assert agency – it is designed for centralized control, not personalized control. It is not easy to allow the kind of customization that would hand essential decision-making power to individuals. And these systems can be too opaque even to their creators to allow for individual interventions.
Themes shared by those who say digital tools WILL allow people to easily be in control:
*Humans and tech always positively evolve – the natural evolution of humanity and its tools has always worked out to benefit most people most of the time, thus regulation of AI and tech companies, refined design ethics, newly developed social norms and a deepening of digital literacy will emerge.
*Businesses will protect human agency because the marketplace demands it – tech firms will develop tools and systems in ways that will enhance human agency in the future in order to stay useful to customers, to stay ahead of competitors and to assist the public and retain its trust.
*The future will feature both more and less human agency – tech will always allow a varying degree of human agency, depending upon its ownership, setting, uses and goals; some allow for more agency to easily be exercised by some people by 2035; some will not.
These themes are repeated in graphic form in two tables included below, in the full report.
Full Report with Complete Findings
The Future of Human Agency
Experts are split about how much control people will retain over essential decision-making as digital systems and AI spread. They agree that powerful corporate and government authorities will expand the role of AI in people’s daily lives in useful ways. But many worry these systems will further diminish individuals’ ability to control their choices
Advances in the internet, artificial intelligence (AI) and online applications have allowed humans to vastly expand their capabilities and increase their capacity to tackle complex problems. These advances have given people the ability to instantly access and share knowledge and amplified their personal and collective power to understand and shape their surroundings. Today there is general agreement that smart machines, bots and systems powered mostly by machine learning and artificial intelligence will quickly increase in speed and sophistication between now and 2035.
As individuals more deeply embrace these technologies to augment, improve and streamline their lives, they are continuously invited to outsource more decision-making and personal autonomy to digital tools.
Some analysts have concerns about how business, government and social systems are becoming more automated. They fear humans are losing the ability to exercise judgment and make decisions independent of these systems.
Others optimistically assert that throughout history humans have generally benefited from technological advances. They say that when problems arise, new regulations, norms and literacies help ameliorate the technology’s shortcomings. And they believe these harnessing forces will take hold, even as automated digital systems become more deeply woven into daily life.
Thus the question: What is the future of human agency? Pew Research Center and Elon University’s Imagining the Internet Center asked experts to share their insights on this; 540 technology innovators, developers, business and policy leaders, researchers, academics and activists responded. Specifically, they were asked:
By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives?
The results of this nonscientific canvassing:
56% of these experts agreed with the statement that by 2035 smart machines, bots and systems will not be designed to allow humans to easily be in control of most tech-aided decision-making.
of these experts agreed with the statement that by 2035 smart machines, bots and systems to allow humans to easily be in control of most tech-aided decision-making. 44% said they agreed with the statement that by 2035 smart machines, bots and systems will be designed to allow humans to easily be in control of most tech-aided decision-making.
It should be noted that in explaining their answers, many of these experts said the future of these technologies will have both positive and negative consequences for human agency. They also noted that through the ages, people have either allowed other entities to make decisions for them or have been forced to do so by tribal and national authorities, religious leaders, government bureaucrats, experts and even technology tools themselves.
In addition, these experts largely agree that digital technology tools will increasingly become an integral part of people’s decision-making. The tools will provide ever-larger volumes of information to people that, at minimum, will assist them in exploring choices and tapping into expertise as they navigate the world.
At the same time, experts on both sides of the issue also agree that the current moment is a turning point that will determine a great deal about the authority, autonomy and agency of humans as the use 0f digital technology spreads into more aspects of daily life. Collectively, people will face questions such as: What are the things humans really want agency over? When will they be comfortable turning to AI to help them make decisions? And under what circumstances will they be willing to outsource decisions altogether to digital systems? Some outlined the stakes:
Alf Rehn, professor of innovation, design and management at the University of Southern Denmark, observed, “The future will clearly cut both ways. On the one hand, better information technologies and better data have improved and will continue to improve human decision-making. On the other, black box systems and non-transparent AI can whittle away at human agency, doing so without us even knowing it is happening. The real challenge will lie in knowing which dynamic is playing out strongest in any given situation and what the longer-term impact might be.”
Barry Chudakov, founder and principal, Sertain Research, predicted, “By 2035, the relationship between humans and machines, bots and systems powered mostly by autonomous and artificial intelligence will look like an argument with one side shouting and the other side smiling smugly. The relationship is effectively a struggle between the determined fantasy of humans to resist (‘I’m independent and in charge and no, I won’t give up my agency!’) and the seductive power of technology designed to undermine that fantasy (‘I’m fast, convenient, entertaining! Pay attention to me!’)”
Kathryn Bouskill, anthropologist and AI expert at the Rand Corporation, said, “Some very basic functions of everyday life are now completely elusive to us. People have little idea how we build AI systems, control them and fix them. Many are grasping for control, but there is opaqueness in terms of how these technologies have been created and deployed by creators who oversell their promises. Right now, there is a huge chasm between the public and AI developers. We need to ignite real public conversations to help people fully understand the stakes of these developments.”
The experts replying to this canvassing sounded several broad themes in their answers. Among those who said that evolving digital systems will not be designed to allow humans to easily be in control of most tech-aided decision-making, the main themes are in the accompanying graphic.
Here is a small selection of expert answers that touch on those themes:
Alan Mutter, consultant and former Silicon Valley CEO, observed, “Successive generations of AI and iterations of applications will improve future outcomes, however, the machines – and the people who run them – will be in control of those outcomes. AI is only as good as the people underlying the algorithms and the datasets underlying the systems. AI, by definition, equips machines with agency to make judgments using large and imperfect databases. Because AI systems are designed to operate more or less autonomously, it is difficult to see how such systems could be controlled by the public, who for the most part are unlikely to know who built the systems, how the systems operate, what inputs they rely on, how the system was trained and how it may have been manipulated to produce certain desired and perhaps unknown outcomes.”
Christopher W. Savage, a leading expert in legal and regulatory issues based in Washington, D.C., wrote, “In theory, a well-deployed AI/ML [machine learning] system could help people make rational decisions in their own best interest under conditions of risk and involving stochastic processes. But I suspect that in practice most AI/ML systems made available to most people will be developed and deployed by entities that have no interest in encouraging such decisions. They will instead be made available by entities that have an interest in steering people’s decisions in particular ways.”
Greg Sherwin, a leader in digital experimentation with Singularity University, predicted, “Decision-making and human agency will continue to follow the historical pattern to date: It will allow a subset of people with ownership and control of the algorithms to exert exploitative powers over labor, markets and other humans. They will also operate with the presumption of guilt with the lack of algorithmic flagging as a kind of machine-generated alibi.”
J. Nathan Matias, leader of the Citizens and Technology Lab at Cornell University, said, “Because the world will become no less complex in 2035, society will continue to delegate important decision-making to complex systems involving bureaucracy, digital record-keeping and automated decision rules. In 2035 as in 2022, society will not be asking whether humans are in control, but which humans are in control, whether those humans understand the consequences of the systems they operate, whether they do anything to mitigate the harms of their systems and whether they will be held accountable for failures.”
Alejandro Pisanty, Internet Hall of Fame member, longtime leader in the Internet Society and professor of internet and information society at the National Autonomous University of Mexico, predicted, “There are two obstacles to human agency triumphing: enterprise and government. Control over the technologies will be more and more a combination of cooperation and struggle between those two forces, with citizens left very little chance to influence choices. … The trends indicate that the future design of decision-making tech will most likely not be determined by the application of science and well-reasoned, well-intended debate. Instead, the future is to be determined by the agendas of commercial interests and governments, to our chagrin.”
Heather Roff, nonresident fellow in the law, policy and ethics of emerging military technologies at the Brookings Institution and senior research scientist at the University of Colorado-Boulder, wrote, “Most users are just not that fluent in AI or how autonomous systems utilizing AI work, and they don’t really care. Looking at the studies on human factors, human systems integration, etc., humans become pretty lazy when it comes to being vigilant over the technology. Humans’ cognitive systems are just not geared to ‘think like’ these systems. So, when one has a lack of literacy and a lazy attitude toward the use of such systems, bad things tend to happen. People put too much trust in these systems, they do not understand the limitations of such systems and/or they do not recognize how they actually may need to be more involved than they currently are.”
Paul Jones, emeritus professor of information science at the University of North Carolina-Chapel Hill, said, “How automation takes over can be subtle. Compare searching with Google to searching CD-ROM databases in the 1990s. Yes, humans can override search defaults, but all evidence shows they don’t and for the most part they won’t.
“In information science, we’ve known this for some time. Zipf’s Law tells us that least effort is a strong predictor of behavior – and not just in humans. We once learned how to form elegant search queries. Now we shout ‘Alexa’ or ‘OK, Google’ across the room in a decidedly inelegant fashion with highly simplified queries. And we take what we get for the most part. The more often automated results please us, the more we trust the automation. While such assistance in cooking, math, money-management, driving routes, question-answering, etc., may seem benign, there are problems lurking in plain sight.
“As Cory Doctorow dramatizes in ‘Unauthorized Bread,’ complicated access, ownership agreements and other controls will and do put the users of even the most-simple networked technologies in a kind of centralized control that threatens both individual autonomy and social cohesion. The question you didn’t ask is: ‘Is this a good thing for humans?’ That’s a more complicated and interesting question. I hope that one will be asked of the designers of any automated control system heading for 2035 and beyond.”
A top editor for an international online news organization wrote, “At present, many people on Earth have already effectively outsourced – knowingly or unknowingly – their tech-aided decisions to these systems. Many of these people do not give extensive thought to the reality of their personal agency in such matters. In many cases this is because they do not fully understand such processes. Perhaps they have fully invested their faith into them, or they simply do not have the time nor inclination to care. Save a most unlikely paramount event that causes society to radically reevaluate its relationship to these systems, there is no reason to conclude at present that these common prevailing attitudes will change in any revolutionary way.
“For all intents and purposes, many people’s tech-aided decision-making is largely out of their control, or they do not know how to more-capably direct such systems themselves. Many of the most critical tech-aided decisions in practice today do not lend themselves to clear control through the conscious agency of the individual.
“The way in which automated recurring billing is designed often does not clearly inform people that they have agreed to pay for a given service. Many people do not understand the impact of sharing their personal information or preferences to set up algorithm-generated recommendations on streaming services based on their viewing behavior, or other such seemingly simple sharing of bits of their background, wants or needs. They may not know of their invariable sacrifice of personal privacy due to their use of verbally controlled user interfaces on smart devices, or of the fact that they are giving over free control over their personal data when using any aspect of the internet.
“For better or worse, such trends are showing no clear signs of changing, and in all likelihood are unlikely to change over the span of the next 13 years. The sheer convenience these systems provide often does not invite deeper scrutiny. It is fair to say tech design often gives the seeming appearance of such control, the reality of which is often dubious.”
Several main themes also emerged among those who said that evolving digital systems will be designed to allow humans to easily be in control of most tech-aided decision-making. They are cited in the accompanying graphic:
Following is a small selection of expert answers that touch on those themes:
Marc Rotenberg, founder and president of the Center for AI and Digital Policy, said, “Over the next decade, laws will be enacted to regulate the use of AI systems that impact fundamental rights and public safety. High standards will be established for human oversight, impact assessments, transparency, fairness and accountability. Systems that do not meet these standards will be shut down. This is the essence of human-centric, trustworthy AI.”
Jeremy Foote, a computational social scientist studying cooperation and collaboration in online communities, said, “People are incredibly creative at finding ways to express and expand their agency. It is difficult to imagine a world where they simply relinquish it. Rather, the contours of where and how we express our agency will change, and new kinds of decisions will be possible. In current systems, algorithms implement the goals of their designers. Sometimes those goals are somewhat open-ended, and often the routes that AI/ML systems take to get to those goals are unexpected or even unintelligible. However, at their core, the systems are designed to do things that we want them to do, and human agency is deeply involved in designing the systems, selecting parameters and pruning or tweaking them to produce outputs that are related to what the designer wants.”
Jon Lebkowsky, CEO, founder and digital strategist at Polycot Associates, wrote, “At levels where AI is developed and deployed, I believe there’s an understanding of its limitations. I believe that the emphasis going forward, at least where decisions have critical consequences, will be on decision support vs. decision-making. Anyone who knows enough to develop AI algorithms will also be aware of how hard it is to substitute for human judgment. I submit that we really don’t know all the parameters of ‘good judgment,’ and the AI we develop will always be limited in the ability to grasp tone, nuance, priority, etc. We might be able to effectively automate decisions about market selection, cosmetics, program offerings (but less so selection), etc. But consequential decisions that impact life and health, that require nuanced perception and judgment, will not be offloaded wholly to AI systems, however much we depend on their support. The evolution of digital tech’s ‘broadening and accelerating rollout’ will depend on the evolution of our sophistication about and understanding of the technology. That evolution could result in disaster in cases where we offload the wrong kinds of decisions to autonomous technical systems.”
Robert D. Atkinson, founder and president of the Information Technology and Innovation Foundation, said, “In terms of risks to human autonomy, we should not be very concerned. Technology always has been a tool that humans controlled, and there is no reason to believe otherwise going forward. To the extent autonomous decision-making systems make important decisions, they will 1) on average be more accurate and timely decisions than humans make (or else they wouldn’t be used); 2) in most cases they will be able to be overridden by humans. If a company or other organization implements such a system and it does not improve people’s lives, the company will not be able to sell the system because people will not use it.”
Melissa R. Michelson, dean of arts and sciences and professor of political science at Menlo College, wrote, “The trend I see in terms of AI-assisted life is that AI makes recommendations, while humans retain ultimate control. While AI is likely to improve its ability to predict our needs by 2035, based on tracking of our behavior, there is still a need for a human to make final decisions, or to correct AI assumptions. In part, this is due to the inherent nature of human behavior: It is not always consistent or predictable, and AI is thus unable to always accurately predict what decision or action is appropriate to the moment. It is also due to the undermining of AI tracking that individuals engage in, either deliberately or unintentionally, as when they log in using another person’s account or share an email address, or when they engage in offline behavior. I expect that by 2035 there will be more automation of many routine activities, but only at the edges of our daily lives. Complex activities will still require direct human input. A shortcoming of AI is the persistent issue of racism and discrimination perpetuated by processes programmed under a system of white supremacy. Until those making the programming decisions become anti-racists, we will need direct human input to control and minimize the harm that might result from automated systems based on programming overwhelmingly generated by white men.”
Chris Labash, associate professor of communication and innovation at Carnegie Mellon University, wrote, “It’s not so much a question of ‘will we assign our agency to these machines, systems and bots?’ but ‘what will we’ assign to them? If, philosophically, the best decisions are those based on intelligence and humanity, what happens when humanity takes a back seat to intelligence? What happens when agency gives way to comfort? If you are a human without agency, are you still human?’
“The data I have read suggests that our future won’t be so much one where humans will not have agency, but one where humans offload some decisions to autonomous and artificial intelligence. We already trust making requests to bots, automated intelligence and voice assistants, and this will only increase. Five years ago a 2018 PwC study on voice assistants indicated that usage, trust and variety of commands were increasing, and customer satisfaction was in the 90% range.
“There is likely to be a considerable broadening of dependence on decisions by autonomous and artificial intelligence by 2035. My guess is although many important decisions will be made by autonomous and artificial intelligence, they will be willingly delegated to non-human intelligence, but we will still keep the decision of what decisions to offload to ourselves.”
Steve Sawyer, professor of information studies at Syracuse University, wrote, “We are bumping through a great deal of learning about how to use data-driven AI. In 15 years, we’ll have much better guidance for what is possible. And the price point for leveraging AI will have dropped – the range of consumer and personal guidance where AI can help will grow.”
Several said the trend will continue toward broader use of publicly accepted autonomous decisions.
Sam Lehman-Wilzig, author of “Virtuality and Humanity” and professor at Bar-Ilan University, Israel, said, “On the micro, personal level, AI ‘brands’ will be competing in the marketplace for our use – much like Instagram, Facebook, Twitter, TikTok compete today – designing their AI ‘partners’ for us to be highly personalized, with our ability to input our values, ethics, mores, lifestyle, etc., so that the AI’s personalized ‘recommendations’ will fit our goals to a large extent. But on the macro level humans will not be in charge of decisions/policy. Once we can be relatively assured that AI decision-making algorithms/systems have no more (and usually fewer) inherent biases than human policymakers we will be happy to have them ‘run’ society on the macro level – in the public sphere. There, AI-directed decisions will be autonomous; we will not be in control. Indeed, one can even posit that many (perhaps most) people throughout history have been perfectly happy to enable a ‘higher authority’ (God, monarch/dictator, experts, technocrats, etc.) to make important decisions for them (see Erich Fromm’s ‘Escape from Freedom’).”
An author whose writing has focused on digital and post-digital humanity asked, “Is it clear that humans are in control even now? They are not in control on Wall Street, not in control over what they see on the internet, not in control piloting airplanes, not in control in interacting with customer service of corporate providers of everyday services, etc.
“Are we in a period of coevolution with these systems and how long might that last? Humans do better with AI assistance. AI does better with human assistance. The word ‘automation’ sounds very 20th century. It is about configuring machines to do something that humans formerly did or figured out they could do better when assisted by the strength, precision or predictability of machines. Yet the more profound applications of AI already seem to be moving toward the things that human beings might never think of doing.
“Could even the idea of ‘decisions’ eventually seem dated? Doesn’t adaptive learning operate much more based on tendencies, probabilities, continual refactorings, etc.? The point of coevolution is to coach, witness and selectively nourish these adaptions. By 2035 what are the prospects of something much more meta that might make Google seem as much an old-fashioned industry as it itself once did to Microsoft?
“This does not imply the looming technological singularity as popular doomsayers seem to expect. Instead, the drift is already on. Like a good butler, as they say, software anticipates needs and actions before you do. Thus, even the usability of everyday software might be unrecognizable to the expectations of 10 years ago. This is coevolution.
“Meanwhile Google is feeding and mining the proceedings of entire organizations. For instance, in my university, they own the mail, the calendars, the shared documents, the citation networks and ever more courseware. In other words, the university is no longer at the top of the knowledge food chain. No humans are at the top. They just provide the feed to the learning. The results tend to be useful. This, too, is coevolution.”
Brad Templeton, internet pioneer, futurist and activist, chair emeritus of the Electronic Frontier Foundation, wrote, “The answer is both. Some systems will be designed for more individual agency, others will not. However, absent artificial general intelligence with its own agency, the systems which make decisions will be designed or deployed by some humans according to their will, and that’s not necessarily the will of the person using the system or affected by the system. This exists today even with human customer-service agents, who are given orders and even scripts to use in dealing with the public. They are close to robots with little agency of their own – which is why we always want to ‘talk to a supervisor’ who has agency. Expect the work of these people to be replaced by AI systems when it is cost-effective and the systems are capable enough.”
A number of the experts responding here made the argument that issues tied to this question will likely be battlegrounds in the future as human autonomy is debated. They asked, “What elements define human agency?” They noted that even small-scale decisions such as where people meet, how they move from place to place or how they might complete a written sentence can be consequential. They also said there are vastly varied points of view in regard to how and when human intervention in automated decision-making should be exercised. Some predicted these kinds of subtle issues will produce strong debates about what people should outsource to tech and what should be preserved as the essential domains in which humans should decide for themselves. Here is how one respondent tackled this:
Henry E. Brady, professor and former dean of the school of public policy, University of California, Berkeley, wrote, “My sense is that there will be a tremendous demand for having methods that will ensure that most important decisions are curated and controlled by humans. Thus, there will be a lot of support, using AI, text-processing and other methods, and there will be ways developed to control these processes to ensure that they are performing as desired.
“One of the areas in which I expect a lot of work will be done is in precisely defining ‘key decisions.’ Clearly there is already a recognition that bail, parole and other decisions in the criminal justice system are key decisions that must be approached carefully to avoid bias. Even for decisions that are less key, such as using a dating app or Uber, there is a recognition that some features are key: There must be some security regarding the identity of the parties involved and their trustworthiness. Indeed, developing trustworthy methods will be a major growth industry.
“One of the trade-offs will be allowing a broader range of choices and opportunities versus verifying the authenticity of these as real choices that can deliver what they promise. So far technology has done a better job of broadening choices than assuring their authenticity. Hence the need for methods to ensure trustworthiness.”
This is a nonscientific canvassing, based on a nonrandom sample. The results represent only the opinions of the individuals who responded to the queries and are not projectable to any other population.
In the next section, we highlight the remarks of experts who gave some of the most wide-ranging yet incisive responses to our request for them to discuss human agency in digital systems in 2035. Following, we offer a set of longer, broader essays written by leading expert participants. And that is followed with additional sections covering respondents’ comments organized under the sets of themes set out in the tables above.
The remarks made by the respondents to this canvassing reflect their personal positions and are not the positions of their employers. The descriptions of their leadership roles help identify their background and the locus of their expertise. Some responses are lightly edited for style and readability.
1. A sampling of key, overarching views on human agency
The following incisive and informative responses to our questions about the evolution of human agency by 2035 represent some of the big ideas shared by a small selection of the hundreds of thought leaders who participated in this canvassing.
Success of AI systems will remain constrained due to their inherent complexity, security vulnerabilities and the tension between targeted personalization and privacy
Mike Liebhold, retired distinguished fellow at the Institute for the Future, wrote, “By 2035 successful AI and robotic ‘full’ autonomous ‘control’ of ‘important’ decisions will be employed only in secure and well-managed and controlled applications of highly refined generations of applied machine intelligence, where any autonomous processes are managed and operated carefully, by highly skilled workforces, with high degrees of systems literacies.
“While there will be gradually widespread adoption of AI augmentation (not necessarily replacement) of human decisions by applied AI and machine learning deeply embedded in hardware and digital services, in most cases [the use] of fully autonomous systems will only gradually be successfully applied. It will still be constrained by evolved versions of the same systemic vulnerabilities [of current systems], including pervasive digital security vulnerabilities and continued tensions of targeted personalization and privacy surveillance.
“Complexity is a continuing challenge. Computing technology is enabling far more capabilities than humans can understand and use effectively. It’s a form of cognitive dissonance like an impedance mismatch in electronic connections. Given the explosive availability of potentially useful data and structured knowledge resources and promising but immature data fusion, AI, and cloud computing capabilities, many years of work ahead will be needed to design systems that somehow systematise and simplify the complexity of AI machines to reliably summarise, explain and amplify capabilities to growing but still limited useful datasets for human cognitive capabilities and focused tasks.”
‘People tend to be submissive to machines or any source of authority. Most people don’t like to think for themselves but rather like the illusion that they are thinking for themselves’
Rakesh Khurana, professor of sociology and professor of leadership development at Harvard University, responded, “It is easier for many people to imagine the end of the world than it is for them to imagine the end of capitalism. People tend to be submissive to machines or any source of authority. Most people don’t like to think for themselves but rather like the illusion that they are thinking for themselves.
“Consider, for example, how often people follow GPS instructions even when instinct suggests they are going in the wrong direction. In politics or consumption, people often outsource their decision-making to what their friends ‘like’ on Facebook or the songs Pandora chooses, even if it is against their interests or might expose them to new ideas or music.
“In most instances, even without machines, there is a strong tendency among humans to rely on scripts and taken-for-granted unquestioned assumptions for their actions. Whether these scripts come from ‘society’ (a type of programmed machine) or an algorithm seems to be a difference of degree, not kind. For example, many people believe they have no agency in addressing problems linked to capitalism, human-caused climate change or any other ‘system’ that seems to exist outside of human control, even though these phenomena are designed and perpetuated by humans.”
‘Machines allow “guilt-free decision-making” along the lines of what the Nuremberg Trials revealed about armies’ chains of command’
Leiska Evanson, a Caribbean-based futurist and consultant, observed, “Machines allow ‘guilt-free decision-making’ along the lines of what the Nuremburg trials revealed about armies’ chains of command. Many will revel in such ‘freedom’ from decision burden and happily blame ‘the machine’ instead of their choice to trust the machine – much as they have blamed television, social media and videogames for human failings. Programmers and computer scientists do not trust humans. Humans do not trust humans.
“Very simply, human programming of AI currently relies on reducing specific human input points to reduce the fallacy of ‘organic beings’ – twitches, mistakes, miscalculations or bias. It has been known for at least a century how cameras, infrared and other visual/light-based technology do not capture darker skin tones well, yet this technology is being used for oxygen sensors, security cameras, facial recognition yielding the same mistakes and leading to incorrect incarceration, poor medical monitoring and death.”
Humans will be augmented by autonomous systems that resolve complex problems and provide relevant data for informed decisions
Kunle Olorundare, vice president of Nigeria’s Chapter of the Internet Society, wrote, “By 2035, bots with high-level intelligence will take over most human decisions – key decisions in engineering design, finance, logistics tracking, the triggering of alerts about threats to public safety/the environment and more. However, at the same time, human decisions will still be relevant even if seemingly relegated to the background. For example, ethical issues in engineering will still be taken on by humans because they require making relative arguments for and against. Our society will be changed for good with integrated bots taking on most movement logistics decisions. There will be safer traffic practices on our roads, in the sky and on the ocean.
“Other important places in which autonomous systems and the Internet of Things will play roles in resolving complex problems are in hospitals – for diagnosis and other tasks – and in agriculture, where data analytics and unmanned aerial vehicles will be useful in all aspects of farming and food distribution. These autonomous systems will operate on a secured internet that allows for secure dissemination of relevant data for informed decisions based on analytics.”
Machines that think could lead us to become humans who don’t think
Richard Watson, author of ‘Digital vs. Human: How We’ll Live, Love and Think in the Future,’ commented, “2035 is a bit early for humans to fall into deeper dependence on machine ‘intelligence’ – for that, 2045 is more likely. In 2035 humans will simply cooperate and collaborate with machines, and we will still trust human judgment ahead of AIs in important cases. This isn’t to say that the tech companies won’t try to remove individuals’ agency though, and the work of Shoshana Zuboff is interesting in this context. How might automated decision-making change human society? As Zuboff asks: Who decides? Who is making the machines and to what ends? Who is responsible when they go wrong? What biases will they contain? I think it was Sherry Turkle who asked whether machines that think could lead us to becoming humans who don’t. That’s a strong possibility, and we can see signs of it already.”
‘The bubble of algorithmically protected comfort will force us to have to find new ways to look beyond ourselves and roll the dice of life’
Sean McGregor, technical lead for the IBM Watson AI XPRIZE and machine learning architect at Syntiant, said, “The people in control of automated decision-making will not necessarily be the people subject to those decisions. The world in 2022 already has autonomous systems supervised by people at credit-rating agencies, car companies, police, corporate HR departments and more. How might the broadening and accelerating rollout of tech-abetted, often autonomous decision-making change human society? We will better appreciate the importance of random chance. Non-random computers mean you will not discover the unexpected, experience and learn from what you don’t prefer, and grow beyond the bubble of algorithmically protected comfort. We will need to find new ways to look beyond ourselves and roll the dice of life.”
‘Digital systems will let those willing to adopt them live a life of “luxury,” assuming subservient roles and freeing users of many tedious chores’
Michael Wollowski, professor of computer science, Rose-Hulman Institute of Technology, and associate editor of AI Magazine, said, “In order to ensure wide acceptability of digital systems, the users need to be in charge of any decision made, whether having a seemingly large impact or an apparent small impact. Those systems need to be engineered to work as a pleasant assistant to the user, just as a personal assistant might be, and a user must be able to override any decision for any reason. The system, just like the driving directions given by a navigation system, will continuously replan.
“Given that most humans are creatures of habit, all decisions that can be automated based on learning a human’s habits will be automated. Such systems should take into consideration human input, and they should ask the user whether they are sure they really want to go through with a decision that the system deems to have a significant impact. That type of decision depends on the person; what I consider a high-impact decision, my next-door neighbor may not care about.
“The system has to learn each user’s preferences. Digital systems will let those willing to adopt them live a life of ‘luxury.’ Just as people with means employ gardeners, nannies, housekeepers, pool boys, personal assistants, etc., these systems will assume many of those subservient roles and free users of many tedious chores.”
The goal for AI design is to ‘meet or exceed human-level performance … and this leads inexorably to the diminishment or replacement of human agency’
Rob Reich, professor of political science and director of the Center for Ethics in Society at Stanford University, said, “Systems powered by AI will not be designed to allow people to easily be in control over decision-making. The reigning paradigm for both basic research and industrial product design in AI is to strive to develop AI systems/models that meet or exceed human-level performance. This is the explicit and widely accepted goal of AGI, or artificial general intelligence. This approach sets AI on a course that leads inexorably to the diminishment or replacement of human agency.”
‘We need to reinvent the concept of consumer protection for the information age’ and create checks and balances that move us in the right direction
Laurie L. Putnam, educator and communications consultant, commented, “If you look at where we are now and plot the trajectory of digital ‘tools,’ it looks like we’re going to land in a pretty dark place. Yes, digital technologies can do a lot of good in the world, but when they are created to improve a bottom line at any cost, or to control people through surveillance, then that is what they will do.
“If we want to alter our course and land in a better place, we will need to reinvent the concept of consumer protection for the information age. That will require thoughtful, well-informed human decision-making – now, not years from now – in legislative policies, legal standards and business practices. These are the checks and balances that can help move us in the right direction. Already we would be hard-pressed to live our lives without using digital technologies, and already we cannot use those phones and apps and cars and credit cards without having every bit of data we generate – every action we take, every purchase we make, every place we go – hoovered up and monetized. There is no way to opt out. Already we are losing rather than gaining control over our personal data, our privacy, our lives.”
The manipulability of these systems has moved the world away from a wider human agency toward hostility toward expertise. ‘In the future, very few people may have agency’
Jean Seaton, director of the Orwell Foundation and professor of media history at the University of Westminster, said, “Already we can see the impact of new, apparently ‘democratic’ ways of communicating on political choices on political structures. The manipulability of apparently technical systems has already moved the world dramatically away from a wider human agency. The willingness – particularly of authoritarian states – to monitor but also ‘please’ people and manipulate understanding depends on these systems. The hostility toward expertise seen today, the politicization of every critical issue, and more – these are all manipulable. What political systems do well out of this?
“In the future, very few people may have agency. How will they use it? Fear and anxiety are proper responses to the challenges we face. For one, the existential threat of climate extinction is about to be fogged by the initial waves of refugees from soon-to-be uninhabitable places – Delhi? Central and South Africa? Afghanistan and Pakistan? Mis-, dis- and mal-information succeed as distractions, and human agency is wasted on small revenges rather than solving the long-term challenges that must be addressed now.”
The standardization of routine decisions as AI takes them over will make many of them more reliable, easy to justify and more consistent across people
Steven Sloman, a cognitive scientist at Brown University whose research focus is how people think, reason, make decisions and form attitudes and beliefs, commented, “The main changes I expect in human society are the standardization of routine decisions as AI takes them over and the uses of AI advice that make even unique decisions much more informed.
“Handing routine decisions over to AI will make many life decisions that are made repeatedly more reliable, easy to justify and more consistent across people. This approach could be applied everywhere in society, e.g., automating rulings in sports contests and other aspects of life. Should we interpret this type of radiology image as a tumor? Does a mechanic need to look at my car? Is it time for a new roof? Will student essays be graded automatically?
“My guess would be a bifurcation in class within society: Public schools with large demands will rely on automatic grading; private schools that demand a lot of tuition will not. Efficiency will trade off with cost, with the result that richer students will learn to express themselves with more freedom, less constrained by the less flexible, less insightful criteria of AI.
“Many difficult, unique decisions, though, involve large amounts of uncertainty and disagreement about objectives. Such decisions will never be handed over to AI. Doing so would reduce the justifiability of the decisions and put the responsible individuals in jeopardy. They will certainly be aided by AI, but I don’t see handing decision-making over to them entirely.
“Should my country go to war? Who should I vote for? Even, is it time to buy a new dishwasher? Or what TV show should I watch tonight? All of these questions involve either enormous uncertainty about outcomes or large disagreements about values, and people will always want to make the final decision.”
‘Digital tools to support decision-making are upgrades of old-fashioned bureaucracies; we turn over our agency to others to navigate our limitations’
Devin Fidler, futurist and founder of Rethinkery Labs, commented, “Turning over decisions to digital agents ultimately has the same downsides as turning over decisions to human agents and experts. In many ways, digital tools to support decision-making are upgrades of old-fashioned bureaucracies. For one thing, it can be easy to forget that, like digital systems, bureaucracies are built around tiered decision trees and step-by-step (algorithmic) processes.
“Indeed, the reason for both bureaucracy and digital agents is ultimately the same – humans have bounded attention, bounded time, bounded resources to support decision-making, and bounded information available. We turn over our agency to others to navigate these limitations. Importantly, however, we still need to establish the equivalent of a clear equivalent to the principle of ‘fiduciary duty’ that covers the majority of digital agents designed to act on our behalf.”
Society will no longer be human but instead socio-technical: ‘Without technology there would be no “society” as we know it’
David J. Krieger, director of the Institute for Communication and Leadership in Lucerne, Switzerland, predicted, “Individual agency is already a myth, and this will become increasingly obvious with time. The problem here is not technological, but ideological. Humanism attempts to preserve the myth of individual agency and enshrine it in law. Good design of socio-technical networks will need to be explicit about its post-humanist presuppositions in order to bring the issue into public debate. Humans will act in partnership – that is, distributed agency – with technologies of all kinds. Already this is so, and it will be more so in the future.
“In a data-driven society, all decisions on all levels and in all areas, business, health care, education, etc., will need to be evidence-based and not based on position in a hierarchy, or intuition, gut feeling, experience, etc. The degree of automation is secondary to the principle of evidence-based decision-making. When sufficient evidence is available, the level of automation will increase. Also, constraints of time and space will condition the level of automation.
“No decisions will be left to individual agency since there is no such thing. Even decisions about who to marry, what to study, what job to take, what therapy is appropriate, etc., will be assisted by automated data evaluation. Society will no longer be ‘human’ but instead ‘sociotechnical.’ Already there is no such thing as human society, for without technology there would be no society as we know it. The problem is that our current political and social ideologies do not acknowledge this fact and continue to portray a mythical version of the social and the human.”
When choice is diminished, we impede our ability to adapt and progress
Kenneth A. Grady, futurist and consultant on law and technology and editor of The Algorithmic Society newsletter, observed, “As we turn over more decisions to computers, we have seen choice diminish. Variety no longer is the spice of life. We have already reached a point where humans have relinquished important aspects of decision-making to computers.
“By broadening and accelerating the rollout of decision-making through computers rather than humans, we risk accelerating society’s movement toward the mean on a range of matters. We will drive out the unique, the outlier, the eccentric in favor of pattern behavior. The irony of this approach lies in its contradiction of nature and what got us to this point. Nature relies on mutations to drive adaptation and progress. We will retard our ability to adapt and progress. We have seen already the early indications of this problem.”
In order for Big Tech to choose to design technologies that augment human control, ‘the incentives structure would have to be changed from profit to mutual flourishing’
Douglas Rushkoff, digital theorist and host of the NPR One podcast “Team Human,” wrote, “The incentives structure of Western civilization would have to be changed from profit to mutual flourishing in order for any technology development company to choose to design technologies that augment human control.
“I do believe we could easily shift the emphasis of technology development from control-over-others to augmentation of agency, but this would require a radical shift in our cultural value system.
“I don’t believe that billions of dollars will be spent on a counter-narrative until such a shift were to occur. It’s also hard to imagine scenarios years in the future without also taking into account mass migrations, the rise of authoritarianism, climate change and global health catastrophe. So, are we talking about the ‘key decisions’ of 6 billion climate refugees, or those of 200,000 corporate executives?”
‘Everyone wants to believe they always have free will, and they will convince themselves of that while opening their wallets to pay for more GPUs that further direct human behavior’
Bill Woodcock, executive director of Packet Clearing House, commented, “The unholy trinity of the surveillance economy, pragmatic psychology and machine learning have dug us into a hole. They are convincing us to dig ever faster, and they are making us believe that it’s our own bright idea.
‘I don’t see us getting out of this hole as long as the automated exploitation of human psychological weaknesses continues to be permitted. I’m very pessimistic about the balance of beneficial outcomes between humans and autonomous systems based on our track record thus far.
“For the first time in human history, we’ve created a stand-alone system which predates people and has its own self-contained positive feedback loops driving it toward increased scale. What’s particularly problematic is that the last 40 years of investigation of human psychology have revealed how easily people can be externally directed and how much work their brains will do to rationalize their actions as having been self-determined.
“Everyone wants to believe that they always have free will – that they always make their own choices based on rational processes – so they’ll do all of the work necessary to convince themselves of that while simultaneously opening their wallets to pay for more GPUs that further direct their own, and others’ behavior.”
There’s a strong tendency in tech to look for the advantages that cutting out human agency, cognitive biases and other ‘failures of rationality’ bring to complex systems
Richard Ashcroft, deputy dean and professor of bioethics at City University of London Law School, an expert on AI and ethics in health care, commented, “I am not optimistic because designing in human agency to AI/ML [machine learning] based systems is not easy from an engineering point of view, plus the industry and most of academia is mainly focused on ‘quick wins,’ ‘low-hanging fruit’ and gaining competitive advantage in so doing.
“There’s also a strong tendency in the field to look for the advantages that ‘cutting out’ human agency, cognitive biases and other ‘failures of rationality’ bring, so I don’t think there is much appetite for designing human agency into these systems, outside the rather narrow field of ‘AI ethics,’ and the general debate in that area is more about assuring us that AI is safe, rather than looking for ways to make it so.
“A third point: Only some of these problems are specific to AI/ML systems; many of the issues were already built into complex socio-technical systems, such as state bureaucracy, precisely to eliminate individual discretion because of issues around efficiency, avoidance of corruption and personal bias and so on.
“Also, any sufficiently complex system has ‘control problems’ that become problems of causal efficacy and epistemology. Humans have influence over such systems, but the effects of such influence are not always predictable or even desirable, from the point of view of the purposes built into such systems.”
‘Industry needs open protocols that allow users to manage decisions and data to provide transparent information that empowers them to know what the tech is doing’
Gary A. Bolles, chair for the future of work at Singularity University and author of “The Next Rules of Work,” predicted, “Innovators will continue to create usable, flexible tools that will allow individuals to more easily make decisions about key aspects of their lives and about the technologies they use.
“There’s also a high probability that 1) many important decisions will be made for people, by technology, without their knowledge, and 2) the creators of media and information platforms will lead the arms race, creating tools that are increasingly better at hacking human attention and intention, making implicit decisions for people and reaping the data and revenue that comes from those activities.
“First, every human needs education in what tech-fueled decision-making is and what decisions tech can and does make on its own. Second, tech innovators need a stringent code of ethics that requires them to notify humans when decisions are made on their behalf, tells them the uses of related data and tells how the innovator benefits from the use of their tools.
“Finally, industry needs open protocols that allow users to manage dashboards of aggregated decisions and data to provide transparent information that allows users (and their tools) to know what decisions technology is making on their behalf, empowering them to make better decisions.”
‘Major tech-driven decisions affecting the rest of us are being made by smaller and smaller groups of humans’
Michael G. Dyer, professor emeritus of computer science at UCLA, wrote, “The smartest humans create the products of convenience that the rest of us use on a daily basis. A major goal of those smartest humans is to a product easily usable without the user having to understand how the product works or how it was constructed. I turn on a flat-screen TV and use its controls to navigate the internet without having to understand its internal structure or manufacture. I get into a car and drive it in similar fashion.
“Many extremely important decisions are being made without input from a majority of humans. Heads of major tech companies make key decisions about how their products will affect the public (examples: in terms of surveillance and info gathering on their consumers) without supplying much if anything in the way of human agency.
“While we will remain in control of products of convenience in 2035 (that’s what makes them convenient), we will continue to lose control in terms of major command-and-control systems of big tech and government. In fact, major tech-driven decisions affecting the rest of us are being made by smaller and smaller groups of humans.”
‘Whoever writes the code controls the decision-making and its effects on society’
Ginger Paque, an expert in and teacher of internet governance with the Diplo Foundation, commented, “We are facing serious challenges today: pandemics, war, discrimination, polarizations, for example. It’s impossible to predict what kind of or level of civilization will prevail 13 years from now.
“AI will continue to be designed, coded and controlled by profit-seeking companies who have a vested interest in shaping and controlling our decision-making processes. So, it is not AI that controls our decisions, it is other humans who use the powerful resources of AI. Autonomous decision-making is directed by some agency, most often a profit-making entity that logically has its profit as a priority. Whoever writes the code controls the decision-making and its effects on society. It’s not autonomous, and we should have clear and transparent options to ensure we do not continue to cede control to known or unknown entities without proper awareness and transparency.
“It’s not AI that’s going to take humans’ decision-making faculties away any more than phones and GPS ruin our memories. Humans choose – quite often without the proper awareness, information and training – to do so.”
AI will be built into so many systems that it will be hard to draw a line between machine decisions and human decisions
Leah Lievrouw, professor of information studies at UCLA, wrote, “Who exactly has ‘agency’? According to the June 11, 2022, cover feature on AI in The Economist, the only ‘designers’ – organizations? individuals? – with the cash and brute-force computing capabilities to create the newest ‘foundational AI’ are huge, private for-profits, and one or two ‘nonprofits’ like OpenAI being supported by the private firms; there are also a few new startups attempting ‘responsible’ or ‘accountable’ algorithms. So, there’s the agency of designers (will they design for user control?) and the agency of users (decision-making based on what AI presents them?).
“Decision-making may not be the only aspect of agency involved. The ‘machine-human’ relationship binary has been around in popular culture for ages, but I think the current thinking among AI designers goes way beyond the one-to-one picture. Rather, AI will be integrated into many different digital activities for lots of reasons, with ripple effects and crossovers likely.
“Thus, there’s unlikely to be a bright-line division between machine decisions and human decisions, both for technical reasons and because who, exactly, is going to declare where the line is? Employers? Insurers/finance? State agencies? Legislatures? Any entity deploying AI will want to use it to the greatest extent possible unless specifically enjoined from doing so, but right now (except maybe in the EU…?) it seems to me that few regulators or organizations are there yet.
“We already see some very worrisome outcomes, for example, algorithmic systems used in legal sentencing.”
‘Our sense of control is increasingly illusory; unless the machine stops, this will spread by 2035, and not just a little’
Jonathan Grudin, affiliate professor at the University of Washington Information School – a recently retired principal researcher at Microsoft – observed, “People won’t control a lot of important decision-making in the year 2035. We’re already losing control. A few current examples:
When Google exhibits the editorial control that has long been expected of publishers by removing 150,000 videos and turning off comments on more than 600,000 and removing ads from nearly 2 million videos and more than 50,000 channels, algorithms decide. Overall, this is a great service, but thousands of false alarms will elude correction.
When an algorithm error dropped a store from Amazon, humans were unable to understand and fix the problem.
A human resources system that enforces a rule where it shouldn’t apply can be too much trouble for a manager to contest, even if it may drive away valued employees.
Human agency is undermined by machine learning (ML) that finds effective approaches to convince almost any individual to buy something they don’t need and can’t afford.
“Our sense of control is increasingly illusory. Algorithms that support management and marketing decisions in some organizations operate on a scale too extensive for humans to validate specific decisions. Unless the machine stops, this will spread by 2035, and not just a little.”
Special insert: What would ChatGPT say if it were asked to participate in this canvassing?
ChatGPT is an AI-powered chatbot that was released to the general public by its inventors at OpenAI in November 2022, several months after we canvassed technology experts for this report about the future of human agency. It was programmed on large data sets of human writing with the goal of successfully producing human-like responses to prompts. It immediately drew broad public attention and has drawn a considerable amount of commentary about its effectiveness, its possible use cases and its potential impact on key parts of society. Early testing of the chatbot’s integration into Microsoft’s Bing search engine in February of 2023 generated responses that distressed and spooked users.
To see how ChatGPT might address the issues covered in this report, we asked it to write “three conversational paragraphs with examples” in response to the research question asked of the human experts in this survey: By 2035, will smart machines, bots and systems powered by artificial intelligence be designed to allow humans to easily be in control of most tech-aided decision-making that is relevant to their lives? Why do you think humans will or will not be in control of important decision-making in the year 2035?
ChatGPT’s answer, generated February 1, 2023:
“Yes, it is highly likely that by 2035, smart machines, bots, and AI systems will be designed to allow humans to easily control important tech-aided decision-making in their lives. As AI technology continues to advance, it will be important for developers to prioritize user control and transparency in their AI systems. This could include features such as adjustable privacy settings, the ability to explain AI decisions and recommendations and the option for human overrides.
“An example of this trend can already be seen in the development of voice assistants, such as Amazon’s Alexa or Google Home. These devices were designed to allow users to control their home environment with voice commands, but they also give users the ability to adjust their privacy settings and control what information is shared with the AI system. This type of user control is becoming increasingly important as AI is integrated into more aspects of our lives and decision-making.
“However, it is possible that some AI systems may not prioritize human control in the future. For example, in certain industries, AI systems may be designed to make autonomous decisions without human intervention for efficiency or safety reasons. In these cases, it will be important for developers to ensure that these AI systems are transparent in their decision-making and include oversight mechanisms to ensure that they are acting ethically. Overall, the extent to which humans will be in control of AI-powered decision-making will depend on the values and priorities of AI developers and the regulations put in place to govern AI use.”
To be clear, as far as we know, this is the only non-human generated response to this canvassing.
2. Expert essays on human agency and digital life
Most respondents wrote brief reactions to this research question. However, a number of them wrote multilayered responses in a longer essay format. This essay section of the report is quite lengthy, so first we offer a sampler of a some of these essayists’ comments.
Paul Saffo warned that it is likely that in the future, “those who manage our synthetic intelligences will grant you just enough agency to keep you from noticing your captivity.”
warned that it is likely that in the future, “those who manage our synthetic intelligences will grant you just enough agency to keep you from noticing your captivity.” Raymond Perrault predicted where the lines will be drawn on decisions made by autonomous systems vs. humans: “The higher the risk of the AI system being wrong and the higher the consequences of a bad decision, the more important it is for humans to be in control.
predicted where the lines will be drawn on decisions made by autonomous systems vs. humans: “The higher the risk of the AI system being wrong and the higher the consequences of a bad decision, the more important it is for humans to be in control. Jamais Cascio shared several compelling 2035 scenarios, ranging from humans benefiting greatly from “machines of loving grace” to a digital dictatorship that might even include “a full digital duplication of a notorious authoritarian leader of years past.”
shared several compelling 2035 scenarios, ranging from humans benefiting greatly from “machines of loving grace” to a digital dictatorship that might even include “a full digital duplication of a notorious authoritarian leader of years past.” Andre Brock said future automated decision-making will be further “tuned to the profit/governance models of extraction and exploitation integrated into legal mechanisms for enhancing the profits of large corporations.”
said future automated decision-making will be further “tuned to the profit/governance models of extraction and exploitation integrated into legal mechanisms for enhancing the profits of large corporations.” Alf Rehn wrote that if things play out well, algorithms can be as considerate to human needs as they are wise. “We need AIs that are less ‘Minority Report’ and more of a sage uncle, less decision-makers than they are reminders of what might be and what might go wrong.”
wrote that if things play out well, algorithms can be as considerate to human needs as they are wise. “We need AIs that are less ‘Minority Report’ and more of a sage uncle, less decision-makers than they are reminders of what might be and what might go wrong.” Barry Chudakov said society is facing a massive paradigm shift: “We cannot fully grasp the recency of the agency we have gained nor the encroachments to that agency that new tools represent. … We can no longer simply pick up and use, or hand over to children, devices and technologies that have the ability – potential or actual – to alter how we think and behave.”
said society is facing a massive paradigm shift: “We cannot fully grasp the recency of the agency we have gained nor the encroachments to that agency that new tools represent. … We can no longer simply pick up and use, or hand over to children, devices and technologies that have the ability – potential or actual – to alter how we think and behave.” danah boyd urged people to focus on the forces behind digital tools and systems and their goals. “What matters is power. Who has power over whom? Who has the power to shape technologies to reinforce that structure of power?”
urged people to focus on the forces behind digital tools and systems and their goals. “What matters is power. Who has power over whom? Who has the power to shape technologies to reinforce that structure of power?” Maggie Jackson predicted a damaging level of dependence on powerful devices could further evolve to eliminate most agency. “Human agency could be seriously limited by increasingly powerful intelligences other than our own due to humans’ innate weakness.”
predicted a damaging level of dependence on powerful devices could further evolve to eliminate most agency. “Human agency could be seriously limited by increasingly powerful intelligences other than our own due to humans’ innate weakness.” Maja Vujovic wished for uncomplicated decision-making user interfaces. “If we don’t build in a large button, simple keyword or short voice command for clearly separating what we agree to give out willingly … and what we don’t … then we’re just dumb. And doomed.”
wished for uncomplicated decision-making user interfaces. “If we don’t build in a large button, simple keyword or short voice command for clearly separating what we agree to give out willingly … and what we don’t … then we’re just dumb. And doomed.” Ben Shneiderman offered encouragement. “The hopeful future we can continue to work toward is one in which AI systems augment, amplify and enhance our lives. We must value humans’ capabilities and seek to build technologies that support human self-efficacy, creativity, responsibility and social connectedness.”
offered encouragement. “The hopeful future we can continue to work toward is one in which AI systems augment, amplify and enhance our lives. We must value humans’ capabilities and seek to build technologies that support human self-efficacy, creativity, responsibility and social connectedness.” David Weinberger touched on the light and dark sides of AI and ML decision-making. “As we delegate higher-order decisions to the machines, we may start to reassess the virtue of it. Autonomy posits an agent sitting astride a set of facts and functions. That agent formulates a desire and then implements. Go, autonomy! But this is a pretty corrupt concept.”
touched on the light and dark sides of AI and ML decision-making. “As we delegate higher-order decisions to the machines, we may start to reassess the virtue of it. Autonomy posits an agent sitting astride a set of facts and functions. That agent formulates a desire and then implements. Go, autonomy! But this is a pretty corrupt concept.” Claudia L’Amoreaux said the digital divide will widen, “creating two distinct classes with a huge gap between a techno-savvy class, and a techno-naive class. Techno-naive humans are easily duped and taken advantage of – for their data, for their eyeballs and engagement metrics and for political gain by the unscrupulous groups among the techno-savvy.”
said the digital divide will widen, “creating two distinct classes with a huge gap between a techno-savvy class, and a techno-naive class. Techno-naive humans are easily duped and taken advantage of – for their data, for their eyeballs and engagement metrics and for political gain by the unscrupulous groups among the techno-savvy.” Neil Davies commented, “One of the enduring problems of widescale, ubiquitous, autonomous systems is that mistakes get buried and failures aren’t shared; these things are prerequisites for people to learn from.”
commented, “One of the enduring problems of widescale, ubiquitous, autonomous systems is that mistakes get buried and failures aren’t shared; these things are prerequisites for people to learn from.” Marcus Foth said that, considering the many problems humanity and the planet are facing, “having the humans who are in control now not being in control of decision-making in 2035 is absolutely a good thing that we should aspire toward.”
said that, considering the many problems humanity and the planet are facing, “having the humans who are in control now not being in control of decision-making in 2035 is absolutely a good thing that we should aspire toward.” Gillian Hadfield optimistically declared, “Democracy is ultimately more stable than autocratic governance. That’s why powerful machines in 2035 will be built to integrate into and reflect democratic principles, not destroy them.”
optimistically declared, “Democracy is ultimately more stable than autocratic governance. That’s why powerful machines in 2035 will be built to integrate into and reflect democratic principles, not destroy them.” Gary Grossman worriedly predicted that humans will increasingly live their lives on autopilot. “The positive feedback loop presented by algorithms regurgitating our desires and preferences contributes information bubbles, reinforcing existing views, making us less open to different points of view, and it turns us into people we did not consciously intend to be.”
worriedly predicted that humans will increasingly live their lives on autopilot. “The positive feedback loop presented by algorithms regurgitating our desires and preferences contributes information bubbles, reinforcing existing views, making us less open to different points of view, and it turns us into people we did not consciously intend to be.” David Barnhizer warned, “The tech experimenters, government and military leaders, corporations, academics, etc., are engaged in running an incredible experiment over which they have virtually no control and no real understanding.”
warned, “The tech experimenters, government and military leaders, corporations, academics, etc., are engaged in running an incredible experiment over which they have virtually no control and no real understanding.” Lia DiBello pointed out that technology has always “shown itself to free human beings to focus on higher-order decision-making by taking over more practical or mundane cognitive processing,” from Global Positioning Systems to automated processes.
pointed out that technology has always “shown itself to free human beings to focus on higher-order decision-making by taking over more practical or mundane cognitive processing,” from Global Positioning Systems to automated processes. Russ White predicted, “Humans could lose the ability to make decisions, eventually becoming domesticated and under the control of a much smaller group of humans.”
predicted, “Humans could lose the ability to make decisions, eventually becoming domesticated and under the control of a much smaller group of humans.” Stephen Downes pointed out that AI is already shaping options, nudging individuals’ beliefs and activities in one direction or another and setting differential pricing. He predicted, “Where people will not have a sufficient range of control is in the choices that are available to us. … Companies have no incentive to allow individuals control.”
pointed out that AI is already shaping options, nudging individuals’ beliefs and activities in one direction or another and setting differential pricing. He predicted, “Where people will not have a sufficient range of control is in the choices that are available to us. … Companies have no incentive to allow individuals control.” Doc Searls noted the important work being done by tech designers in these early years of digital life. “Human agency and ingenuity are boundlessly capable. We need to create our own tools for exercising both. We will succeed in the long run because human agency in industrial and digital worlds is best expressed by humans using machines, not machines using humans.”
noted the important work being done by tech designers in these early years of digital life. “Human agency and ingenuity are boundlessly capable. We need to create our own tools for exercising both. We will succeed in the long run because human agency in industrial and digital worlds is best expressed by humans using machines, not machines using humans.” Sara M. Watson said in 2035 technology should “prioritize collective and individual human interests above all else, in systems optimized to maximize for the democratically recognized values of dignity, care, well-being, justice, equity, inclusion and collective- and self-determination.”
said in 2035 technology should “prioritize collective and individual human interests above all else, in systems optimized to maximize for the democratically recognized values of dignity, care, well-being, justice, equity, inclusion and collective- and self-determination.” Jim Dator spelled out the new contours of human agency, identity and intelligence, arguing, “Humanity can no longer be considered to be the measure of all things, the crown of creation. We are participants in an eternal evolutionary waltz that enabled us to strut and fret upon the Holocene stage.”
What follows is the full set of essays submitted by a number of leading experts responding to this survey.
‘Those who manage our synthetic intelligences will grant you just enough agency to keep you from noticing your captivity’
Paul Saffo, longtime Silicon Valley foresight guru, observed, “We have already turned the keys to nearly everything over to technology. The most important systems in our lives aren’t the ones we see, but the systems we never notice – until they fail. This is not new. Consider the failure of the Galaxy IV satellite a quarter century ago: puzzled consumers who never noticed the little dishes sprouting atop gas stations discovered they couldn’t fill their tank, get cash from ATMs, or watch their favorite cable TV programs.
“We have experienced 16 Moore’s Law doublings since then. Our everyday dependence on technology has grown with even greater exponentiality. We carry supercomputers in our pockets, our homes have more smarts than a carrier battle group, and connectivity has become like oxygen – lose it for more than a few moments and we slip into digital unconsciousness, unable to so much as buy a latte, post a tweet or text a selfie.
“Technologists are optimists. They promise that the next wave of technology will solve the failings of prior innovations and make glitches a thing of the past. Empowered by AI, Richard Brautigan’s ‘machines of loving grace’ will keep omniscient watch over our lives in a harmonious cybernetic meadow. There is no reason why the next technological wave can’t expand human agency, giving us greater satisfaction and control. It is just a matter of design. Or, rather, if it was just a matter of design, the now ubiquitous spell-checkers that so annoy us would actually be helpful – and come with an off switch to flick when they weren’t. This is just a minor example, but if we can’t make the small, simple stuff work for us, how will more complex systems ever live up to our expectations?
“But don’t blame the machines. No matter how brilliant AIs, avatars and bots become, they will never be truly autonomous. They will always work for someone – and that someone will be their boss and not you, the hapless user. Consider Uber or any of the other mobility services: In theory, their ever more brilliant algorithms should be working tirelessly to enhance the customer experience and driver income. Instead, they answer to their corporate minders, coldly calculating how far fares can be boosted before the customer walks – and how much can be salami-sliced off the driver’s margin before they refuse to drive.
“Nearly a century ago, Will Durant observed that ‘history reports that the men who can manage men manage the men who can manage only things, and the men who can manage money manage all.’ If Durant were here today, he would surely recognize that those who manage our synthetic intelligences will inevitably become the ones who manage all. And they will instruct their intelligences to grant you just enough agency to keep you from noticing your captivity.”
The higher the risk of the AI system being wrong and the higher the consequences of a bad decision, the more humans should be in control
Raymond Perrault, a distinguished computer scientist at SRI International (he directed the AI Center there from 1988-2017), wrote, “Current AI systems based on machine learning are showing continued improvement on tasks where large amounts of training data are available. However, they are still limited by their relative inability to incorporate and interact with symbolic information.
“The role of symbolic information and reasoning is one of the major outstanding questions in AI, and there are very different opinions as to whether and how integration should be achieved. I believe that robust, verifiable AI systems, needed for high-reliability systems such as self-driving cars, depend on progress in this area and that this technical problem will eventually be solved, though whether that will be sufficient to field high-reliability systems remains to be seen. I accept that it will, but I don’t know when.
“AI is and will continue to be used in two kinds of scenarios, those where the AI operates completely autonomously, as in recommender systems and those where humans are in ultimate control over the decisions suggested by the AI, and as in medical diagnostics and weapons. The higher the risk of the AI system being wrong and the higher the consequences of a bad decision, the more important it is for humans to be in control.
“Let’s look at a few of the main categories where that sorting will likely occur:
Major personal and life-and-death decisions (education, marriage, children, employment, residence, death): I don’t see full automation of decision-making in major personal decisions, though support of decisions could improve, e.g., with respect to choices in education and employment.
Financial decisions (buying a house, personal investments, more): Financial decisions will continue to get more support, and I could see significant delegation of investment decisions, especially of simple ones. But I can’t see an AI system ever deciding which house you should buy.
Use of major services (health care, transportation): AI support for health care and transportation will continue to increase, but I can’t see life-and-death health decisions ever being completely automated. I doubt that self-driving cars will operate at scale except in controlled conditions until the availability of highly reliable AI systems.
Social decisions (government, national security): Government faces enormous challenges on many fronts. We could save large amounts and improve fairness by streamlining and automating tax collection, but it is hard to see the will to do so as long as minimizing government remains a high priority of a large part of the population. I don’t see another 15 years changing this situation. The use of AI for national security will continue to increase and must continue to be under the control of humans, certainly in offensive situations. With appropriate controls, AI-based surveillance should actually be able to reduce the number of mistaken drone attacks, such as those recently reported by major news organizations.”
As with all of today’s technology, the rapid rollout of autonomous tools before they are ready (due to economic pressure) is likely and dangerous
Barrett S. Caldwell, professor of industrial engineering at Purdue University, responded, “I believe humans will be offered control of important decision-making technologies by 2035, but for several reasons, most will not utilize such control unless it is easy (and cost-effective) to do so. The role of agency for decision-making will look similar to the role of active ‘opt-in’ privacy: People will be offered the option, but due to the complexity of the EULAs (end-user license agreements), most people will not read all of them, or will select the default options (which may push them to a higher level of automation) rather than intelligently evaluate and ‘titrate’ their actual level of human-AI interaction.
“Tech-abetted and autonomous decision-making in driving, for example, includes both fairly simple features (lane following) and more-complex features (speed-sensitive cruise control) that are, in fact, user-adjustable. I do not know how many people actually modify or adjust those features.
“We have already seen the cases of people using the highest level of driver automation (which is nowhere close to true ‘Level 5’ driver automation) to abdicate driving decisions and trust that the technology can take care of all driving decisions for them. Cars such as Tesla are not inexpensive, and so we have a skewing of the use of more fully autonomous vehicles toward more affluent, more educated people who are making these decisions to let the tech take over.
“Key decisions should be automated only when the human’s strategic and tactical goals are clear (keep me safe, don’t injure others) and the primary role of the automation is to manage a large number of low-level functions without requiring the human’s attention or sensorimotor quickness. For example, I personally like automated coffee heating in the morning, and smart temperature management of my home while I’m at work.
“When goals are fluid or a change to pattern is required, direct human input will generally be incorporated in tech-aided decision-making if there is enough time for the human to assess the situation and make the decision. For example, I decide that I don’t want to go straight home today, I want to swing by the building where I’m having a meeting tomorrow morning. I can imagine informing the car’s system of this an hour before leaving; I don’t want to have to wrestle with the car 150 feet before an intersection while traveling in rush-hour traffic.
“I am really worried that this evolution will not turn out well. The technology designers (the engineers, more than the executives) really want to demonstrate how good they are at autonomous/AI operations and take the time to perfect it before having it publicly implemented. However, executives – who may not fully understand the brittleness of the technology– can be under pressure to rush the technological advancement into the marketplace.
“The public can’t even seem to manage simple data hygiene regarding privacy (don’t live-tweet that you won’t be home for a week, informing thieves that your home is easy to cherry pick and telling hackers that your account is easy to hack with non-local transactions), so I fully expect that people will not put the appropriate amount of effort into self-management in autonomous decision-making. If a system does not roll out well (I’m looking at Tesla’s full-self-driving or the use of drones in crowded airport zones), liability and blame will be sorted out by lawyers after the fact, which is not a robust or resilient version of systems design.”
‘The public and Big Tech must learn how to build equity into AI and know what levers to pull to assure that it works for the good of humanity’
Kathryn Bouskill, anthropologist and AI expert at the Rand Corporation, said, “Looking ahead, humanity will be challenged to redefine and reimagine itself. It must consider the unprecedented social and ethical responsibilities that the new speed of change is ushering into our lives – including crucial issues being raised by the spread of AI.
“The number of places in which individuals have agency and can take control in this era of swift technological speed is dwindling. Hitting the brakes is not an option. When life happens quickly, it can feel difficult to process change, create a purpose, hold our social ties together and feel a sense of place. This kind of uncertainty can induce anxiety, and anxiety can lead to isolationism, protectionism, fear, gridlock and lack of direction. …
“Is AI going to completely displace human autonomy? We may forget that humanity still has the opportunity to choose what is being developed. That can still be our decision to make. Most people are just passively watching the technology continue to rapidly roll out without being actively engaged as much as they should be with it.
“For now, I’m leaning toward the optimistic view that human autonomy will prevail. However, this requires the public implementation of educational components, so the black-box aspects of AI are explored and understood by more people. And the public and Big Tech must learn how to build equity into AI and know what levers to pull to assure that it works for the good of humanity. Smart regulation and robust data protection are also critically important.
“The greatest resource in the human toolkit is our ability to cooperate and creatively adapt to or change our surroundings. It will take a concerted effort across multiple stakeholders – citizens, consumers, employers, voters, tech developers and policymakers – to collectively devote attention to vetting and safeguarding technologies of the future to make the world safer.”
Focus on who has power over whom, and who has the power to shape technologies to reinforce that structure of power
danah boyd, founder of the Data & Society Research Institute and principal researcher at Microsoft, complained, “Of course there will be technologies that are designed to usurp human decision-making. This has already taken place. Many of the autopilot features utilized in aviation were designed for precisely this, starting in the 1970s; recent ones have presumed the pilot to be too stupid to take the system back. (See cultural anthropologist Madeleine Elish’s work on this.)
“We interface every day with systems that prevent us from making a range of decisions. Hell, the forced-choice, yes-no format of this survey question constrained my agency. Many tools in workplace contexts are designed to presume that managers should have power over workers; they exist to constrain human agency.
“What matters in all of these systems is power. Who has power over whom? Who has the power to shape technologies to reinforce that structure of power? But this does not mean that ALL systems will be designed to override human agency in important decisions. Automated systems will not control my decision to love, for example. That doesn’t mean that systems of power can’t constrain that. The state has long asserted power over marriage, and families have long constrained love in key ways.
“Any fantasy that all decisions will be determined by automated technologies is science fiction. To be clear, all decisions are shaped (not determined!) by social dynamics, including law, social norms, economics, politics, etc.
“Technologies are not deterministic. Technologies make certain futures easier and certain futures harder, but they do not determine those futures. Humans – especially humans with power – can leverage technology to increase or decrease the likelihood of certain futures by mixing technology and authority. But that does not eliminate resistance, even if it makes resistance more costly.
“Frankly, focusing on which decisions are automated misses the point. The key issue is who has power within a society and how can they leverage these technologies to maximize the likelihood that the futures they seek will come to pass.
“The questions for all of us are: 1) How do we feel about the futures defined by the powerful, and 2) How do we respond to those mechanisms of power? And, more abstractly: 3) What structures of governance do we want to invest in to help shape that configuration?”
Scenarios for 2035 and beyond are likely to range from humans benefiting from ‘machines of loving grace’ to being under the thumb of digital dictators
Jamais Cascio, distinguished fellow at the Institute for the Future, predicted, “Several scenarios will likely coexist in the future of agency by 2035.
1) “Humans believe they are in control but they are not: The most commonly found scenario will be the one in which humans believe themselves to be in control of important decision-making in the year 2035, but they’re wrong. This will (largely) not be due to nefarious action on the part of rogue AI or evil programmers, but simply due to the narrowing of choice that will be part of the still-fairly-simple AI systems in 2035. Humans will have full control over which option to take, but the array of available options will be limited to those provided by the relevant systems. Sometimes choices will be absent because they’re ‘obviously wrong.’ Sometimes choices will be absent because they’re not readily translated into computer code. Sometimes choices will be absent because the systems designed to gather up information to offer the most relevant and useful options are insufficient.
“In this scenario, as long as the systems allow for human override to do something off-menu, the impact to agency can be minor. If it’s not clear (or not possible) that humans can do something else, partial agency may be little better than no agency at all.
2) “Humans know they are not in control and they’re OK with that: Less common will be the scenario where humans do NOT believe themselves to be in control of important decision-making in the year 2035 and they like it that way. Humans are, as a general rule, terrible at making complex or long-term decisions. The list of cognitive biases is long, as is the list of historical examples of how bad decision-making by human actors have led to outright disaster. If a society has sufficient trust and experience with machine decision-making, it may decide to give the choices made by AI and autonomous systems greater weight.
“This would not be advisable with current autonomous and AI systems, but much can happen in a decade or so. There may be examples of AI systems giving warnings that go unheeded due to human cognitive errors or biases, or controlled situations where the outcomes of human vs. machine decisions can be compared, in this case to the AI’s benefit. Advocates of this scenario would argue that, in many ways, we already live in a world much like this – only the autonomous systems that make decisions for us are the emergent results of corporate rules, regulations and myriad minor choices that all add up to outcomes that do not reflect human agency. They just don’t yet have a digital face.
3) “A limited number of AI-augmented humans have control: Last is a scenario that will somewhat muddy the story around human agency, as it’s a scenario in which humans do have control over important decision-making in the year 2035, but it’s a very small number of humans, likely with AI augmentations. Over the past few decades, technologies have vastly extended individuals’ power. Although this typically means extended in scale, where human capabilities become essentially superhuman, it can also mean extended in scope, where a single or small number of humans can do what once took dozens, hundreds, or even thousands of peo
| 2023-02-24T00:00:00 |
https://www.elon.edu/u/imagining/surveys/xv2023/the-future-of-human-agency-2035/
|
[
{
"date": "2023/02/24",
"position": 85,
"query": "universal basic income AI"
},
{
"date": "2023/02/24",
"position": 63,
"query": "AI labor union"
}
] |
|
What Impact will Artificial Intelligence have on Productivity and ...
|
What Impact will Artificial Intelligence have on Productivity and the Economy?
|
https://ancora.net
|
[
"Ancora Editor"
] |
Artificial intelligence (AI) has the potential to greatly impact productivity and drive economic growth. ... ChatGPT in response to the same question posed in the ...
|
Published: 24 Feb 2023
Authors:
John Micklitsch, CFA CAIA, President & Chief Investment Officer
Artificial intelligence (AI) has the potential to greatly impact productivity and drive economic growth. By automating routine tasks and freeing up workers to focus on more complex and creative tasks, AI can improve overall efficiency and increase output. This can lead to higher profits for businesses, lower prices for consumers, and a more robust economy overall.
One of the primary ways AI will impact productivity is through process automation. AI algorithms can be trained to perform repetitive, time-consuming tasks, such as data entry and analysis, at a much faster pace and with higher accuracy than humans. This can free up workers to focus on higher value tasks, such as strategy development and problem solving, that cannot be easily automated. Additionally, AI algorithms can be programmed to learn from experience, constantly improving their performance over time. This means that businesses that adopt AI can expect to see increasing returns on investment as the technology becomes more sophisticated.
Another way AI will impact productivity is through the optimization of business processes. AI algorithms can be used to analyze vast amounts of data and identify areas of inefficiency in supply chain management, inventory control, and other key business processes. This information can then be used to streamline processes and eliminate waste, resulting in significant increases in productivity and cost savings. AI can also be used to automate decision-making, allowing businesses to make data-driven decisions in real-time, which can lead to more effective resource allocation and faster response times.
AI is also expected to have a major impact on the labor market. Some workers will be displaced by automation, but others will be trained for new jobs that require more advanced skills, such as data analysis and AI development. This will lead to a more highly skilled workforce and a more productive economy. Additionally, AI has the potential to create new industries and businesses that did not previously exist, leading to further job creation and economic growth.
In conclusion, AI has the potential to greatly impact productivity and drive economic growth in a variety of ways. From automating routine tasks to optimizing business processes and creating new industries, the applications of AI are numerous and far-reaching. As the technology continues to evolve, it is likely that we will see even more benefits to productivity and economic growth in the years to come.
Source: ChatGPT, February 10, 2023
Like a plot twist in a good movie, the plot twist here is that the above article was entirely written by ChatGPT in response to the same question posed in the article’s title. If you’re curious, it took less than two minutes for the system to generate the response to our query. The key takeaway from this experiment, in our view, is not so much the contents of the article, but that despite all the gloom and doom and short-termism thrown daily at investors, innovation is alive and well and will continue to drive the economy, industries and businesses forward in ways that we can’t even imagine yet. While we know that the outputs of such tools should still be taken with a grain of salt, artificial intelligence is a good example of another puff of wind on the global economic flywheel that will continue the world’s legacy of growth, innovation and improved living standards.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://ancora.net/what-impact-will-artificial-intelligence-have-on-productivity-and-the-economy/
|
[
{
"date": "2023/02/24",
"position": 92,
"query": "ChatGPT employment impact"
}
] |
How ChatGPT really works and will it change the field of IT ...
|
How ChatGPT really works and will it change the field of IT and AI? — a deep dive
|
https://blog.chatbotslife.com
|
[
"Aleksander Obuchowski"
] |
... ChatGPT and their impact on respected industries. We will discuss how models such as ChatGPT will affect the work of software engineers and ML engineers. We ...
|
How ChatGPT really works and will it change the field of IT and AI? — a deep dive Aleksander Obuchowski 27 min read · Feb 24, 2023 -- Listen Share
Unless you have been living under a rock for the last few months, you have probably heard about a new model from OpenAI called ChatGTP. The model has demonstrated extraordinary abilities in generating both code and textual responses that are not only coherent but most often factually correct and in line with the current human knowledge.
There are many articles describing the possible use cases of ChatGPT, however, they rarely go into the details about how the model works or discuss its border implications.
The goal of this article is to demystify ChatGPT showing how it works and why is it that effective, describing what are language modes, why are they so popular and what is their problem. As everything is explained from scratch but extensively I hope you will find it interesting whether you are NLP Expert or just want to know what all the fuss is about.
The second part of the article discusses the possible use cases of ChatGPT and their impact on respected industries. We will discuss how models such as ChatGPT will affect the work of software engineers and ML engineers. We will answer the question “Will you lose your job?” and we will also explain how GPT can create jobs.
Table of contents:
· What is ChatGPT?
· Why is ChatGPT so effective?
· What is ChatGPT capable of?
· Will ChatGPT replace software engineers?
· Will ChatGPT replace ML Engineers?
· Will ChatGPT replace your job?
· Will ChatGPT create jobs?
· Conclusions
What is ChatGPT?
In the first part of the article, we will try to demystify what ChatGPT is and discuss why it is so effective. Unfortunately, the model’s release wasn’t accompanied by a research paper, and its only official description can be found on the OpenAI blog.
Language Models
As we can read in the OpenAI article ChatGPT is a language model optimized for dialogue.
But what is a language model?
Formally, a language model is a probability distribution over words or word sequences. So given words in a sequence, the model tells us how probable the sequence is. In practice, we can ask a language model to continue the sequence with the word it thinks is the most probable.
There are many approaches to language modelling, we can for example ask the model to fill in the words in the middle of a sentence (as in the BERT model) or predict which words have been swapped for fake ones (as in the ELECTRA model). The most simple approach and the one used in the GPT family of models is in fact asking the model to predict the next word in a sequence. This is called casual language modelling. An input sequence that we feed to the model and ask it to complete is called a prompt.
So ChatGPT is nothing more and nothing less than a probabilistic model that predicts the next most probable words given an input string.
This task has however proven to be extremely effective, given a large training set and sufficient model size. Large Language models such as GPT can learn to generate sequences that are not only syntactically but also factually correct. They are able to generalize — meaning, they can generate responses to prompts they haven’t seen before by combining concepts from different examples from the training set. So the model is able to generate a poem about quantum physics because it has seen books about quantum physics and poems and is, therefore, able to generate a sequence that is both a probable explanation of quantum physics and a probable poem.
And as we could have already seen with the release of GPT-3 a few years ago casual language modelling can be used to perform various tasks and has proven to be universal. We can ask the model to generate a python function or a recipe for a cheesecake. We can ask it to translate from one language to another, extract key information from a given text and answer open-domain questions. All those various seemingly unrelated tasks such as Question Answering, Machine Translation, and Keyword Extraction, that are usually performed by specialized models can be represented as the text-to-text problem. Input sequence in form of the prompt and context is converted to the output sequence by casual language modelling.
But language modelling is not enough to create a universal model that answers all the questions of a user. Why? Because language models are jerks.
Chatathon by Chatbot Conference
Language models are jerks, InstructGPT isn’t
As we read next on the OpenAI blog :
ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response.
Fortunately, InstructGPT was released with a research paper, so we can shed some more light on the inner workings of the model.
In the introduction of the paper, the authors present a few major flaws of language models. Those models, trained to predict the next word in a sequence, are not good at following instructions. And why should they be? Language models are trained to predict the most probable sequence, not the most helpful one. This can lead to the models resenting unintended behaviours such as making up facts, generating biased or toxic text, or simply not following user instructions.
A solution to this problem presented by OpeanAI is reinforcement learning. Reinforcement learning is a machine learning training method based on rewarding desired behaviours and punishing undesired ones.
This approach with the rewards system based on human feedback is applied to GPT3 to create InstructGPT. Here is a brief description of the algorithm:
OpenAI collected prompts submitted by the users to the earlier versions of the model. Then they asked humans to generate their responses to those prompts and fine-tuned the GPT-3 model to match the style of human responses. This ensured the model generated responses in the form of instructions desired by the user rather than simple completions. Once the model generated a response in the desired format, the next thing to do was to teach it which responses are useful for the user. For this, the authors asked the model to generate a few responses to the same prompts. Those responses were then rated by humans from best to worst and used the train the reward model — an additional model that was able to classify the response as good or bad. The reward model was then used to fine-tune InstructGPT — it was taught to generate the best possible responses that scored the highest
So what is the difference between InstructGPT and ChatGPT?
As we can read in the article, the only difference between InstructGPT and ChatGPT is the fact that the annotators played both the user and AI assistant.
We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides — the user and an AI assistant.
The hypothesis as to why such training was particularly effective is explained in the next section.
To sum everything up we know that ChatGPT is:
A language model — a model trained to complete the sequence of words with the most probable continuation.
Trained with reinforcement learning to generate completions that are more desired by the user.
Why is ChatGPT so effective?
The bitter lesson and E2E models
In 2019 Rich Sutton wrote an essay called “The Bitter Lesson” explaining how in the long run end-to-end AI models that leverage computation always wins against human ones that leverage human expertise.
T he biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin ~ Rich Sutton, The Bitter Lesson
Recently ChatGPT has proven to follow this pattern and is perhaps the best example to support this thesis. Instead of relying on different models for each task, it is able to solve a variety of user problems by communicating with a user through a unified chat-like interface.
This end-to-end approach is partially efficient because it removes the human from the equation and leverages computational power and data instead.
E2e learning is nicely consistent with the general approach of machine learning to take the human expert out of the loop and to solve problems in a purely data-driven manner. ~ Tobias Glasmachers, “Limits of End-to-End Learning”
If we have used a separate model for each task (e.g. taught the system to tell jokes based on jokes datasets with premise and punchline, and taught it quantum physics based on a set of questions and answers in quantum physics) we would rely on human annotations limiting the reasoning of the model to those specific unrelated areas. However, by training a model in an unsupervised fashion we are able to use the abundance of data that humans have generated and leverage knowledge transfer between various tasks. The model can use the logic learned by analyzing quantum physics sources to generate twisted logic in a joke. It is simply more efficient to train one model for various NLP as knowledge from one task can be used in another one boosting the overall cognitive abilities of the model.
Recently, it has become increasingly common to pre-train the entire model on a data-rich task. Ideally, this pre-training causes the model to develop general purpose abilities and knowledge that can then be transferred to downstream tasks. (…) Crucially, the text-to-text framework allows us to directly apply the same model, objective, training procedure, and decoding process to every task we consider~ Raffel, Colin, et al. “Exploring the limits of transfer learning with a unified text-to-text transformer.”
To use one model for many different tasks we need a shared interface and a text-to-text approach seems like a good candidate. We can convert almost any NLP task to a text-to-text problem. And this gives us a framework to teach the model many things at once, free it of our limited perception of how a task should be formulated and let it figure out things on its own, where its only limit is computational power and data we can give it.
Text-to-text models
The idea of modelling different NLP tasks as a text-to-text approach is hardly a new one. The paper accompanying the release of GPT3 (a predecessor to GPT3.5 that ChatGPT was based on) was in fact called “Language Models are Few-Shot Learners”
For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.
The authors have shown that GPT3 is able to solve different problems in a zero-shot learning fashion. We give a model a description of the task we need it to perform in the prompt as an input and as an output, we will get the response. We can see e.g. that the model is able to solve translation tasks without being explicitly trained for machine translation.
This is due to the fact that the model is able to learn from analogous examples in its training dataset and generalize.
Such models can also learn from a set of few examples
The process of presenting a few examples is also called In-Context Learning, and it has been demonstrated that the process behaves similarly to supervised learning.
A similar approach was used in “Exploring the limits of transfer learning with a unified text-to-text transformer” which introduced a model called T5.
In this model, the authors used explicit unified prompts such as “summarize:” to train the model. We can see that even tasks that would normally be modelled as regression such as STBS (Semantic Textual Similarity) are instead performed in a text-to-text fashion where the model answers by generating a sequence of tokens corresponding to the desired number. This allows us to share knowledge across different tasks e.g. text understanding that is necessary for translation can be relevant for summarization.
But if such models existed before the question emerges:
How is ChatGPT different?
As we currently know very little about the exact process of training ChatGPT outside its minor differences from InstructGPT we can focus on the results distinguishing InstructGPT from other large language models and later hypothesize about the improvements made with ChatGPT over the InstructGPT.
In the paper, the authors compare IntructGPT training using reinforcement learning to GPT3 one of the largest language models trained without using reinforcement learning
What are the advantages of using reinforcement to align language models?
Better responses : InstructGPT outputs are preferred over GPT-3 outputs 85% of the time
: InstructGPT outputs are preferred over GPT-3 outputs 85% of the time Fewer hallucinations : InstructGPT models make up information not present in the input about half as often as GPT-3
: InstructGPT models make up information not present in the input about half as often as GPT-3 Less Toxicity : InstructGPT models generate about 25% fewer toxic outputs than GPT-3
: InstructGPT models generate about 25% fewer toxic outputs than GPT-3 Better Generalization: IntructGPT follows instructions for summarizing code, answers questions about code, and sometimes follows instructions in different languages, despite these instructions being very rare in the fine-tuning distribution
Comparison between InstructGPT (PPO) and GPT-3 (GPT)
Why is reinforcement learning so efficient?
As we can see in the previous section InstructGPT model fine-tuned using reinforcement learning can produce much better results than the GPT-3 model even if it was fine tunes using supervised learning (SFT). The SFT technique was based on training the model directly to produce responses submitted by the labellers given the same input as them, without the reinforcement learning process. The difference becomes even more apparent when we compare model sizes.
As we can see the InstructGPT model (PPO) is able to produce much better results than the GPT-3 model fine-tuned directly even if its size is 2 orders of magnitude smaller. But why is RL so efficient?
The cost of collecting data and the compute for training runs, including experimental runs is a fraction of what was spent to train GPT-3: training our 175B SFT model requires 4.9 petaflops/s-days and training our 175B PPO-ptx model requires 60 petaflops/s-days, compared to 3,640 petaflops/s-days for GPT-3
Firstly, the RL task is much easier to optimize than the text-to-text task. The reward model is just a simple regression model that takes a string as input and produces the score as output. This is a much simpler task than text-to-text as the output space is only a single number instead of thousands of possible tokens in the text-to-text task.
Secondly, the reward model can help the language model generalize. With a supervised text-to-text task the model only has as many reference points as the number of prompts and outputs. However, the RL model can extrapolate and hypnotize the usefulness of outputs that don’t have a gold standard prepared by humans. The signals coming from supervised learning are also very strong — each input has only one possible output that is seen by the model as 100% accurate during training. With RL the model can observe the variety of outputs and their usefulness as a spectrum.
How is ChatGPT different form InstructGPT?
As we established at the beginning of the article it isn’t really that different. We don’t have any quantitative experiments comparing ChatGPT to InstructGPT and there is no doubt that the phenomenon of ChatGPT is vastly attributed to the release of the open demo and its viral spread rather than major differences in the architecture of the model.
The one difference that we know about is that the human annotators played both sides — the user and an AI assistant. This could have provided the model with more diverse inputs and more aligned input and output pairs as labellers knew what they were expecting from the model when writing prompts.
This difference is however as the OpenAI itself admits — slight. As we can see in the anecdotal evidence of ChatGPT’s superiority over InstructGPT provided in the article, over the 3 examples one is related to hallucinations (the model accepts the suggestion in the prompt that Christopher Columbus came to the US in 2015) and the other 2 are related to responses that can be seen as dangerous. However, an argument can be made that producing dangerous but factually correct responses does not denote the inferior cognitive abilities of the model and limiting such responses is strictly a safety measure taken by OpenAI to limit their liability connected with broader usage of the model.
What is ChatGPT capable of?
As there already exist several good articles describing possible usages of ChatGPT I will not go into great detail explaining every single use case.
If you are looking for a detailed description of ChatGPT usage with examples, I highly recommend an article by Sophia Yang:
Or this one by Damir Yalalov:
There also exists a collection of awesome ChatGPT prompts on hugging face datasets.
But let’s give a brief description of what ChatGPT is capable of and what are the implications.
Create Content and ART
ChatGPT can create a variety of texts ranging from copies and blog articles to highly artistic forms such as poems. This definitely streamlines the process of content creation, especially for small companies and individuals that can’t afford a dedicated content writer not having the time to skill up in content creation.
Some people have also shown that it is possible to use ChatGPT for DMing D&D games.
This opens entirely new possibilities for AI-mediated games and storytelling, showing that ChatGPT can also be used for entertainment.
Of course, this also extends the discussion about the ethics of using AI to generate, recently sparked by Stable Diffusion and DALL-E to the text field.
However, as writing is both a skill and a talent, AI-mediated content generation can help those who have the talent but lack the skill, resulting in the creation of work that wouldn't otherwise see the light of the day. AI artists can be compared to directors that guide the model through their prompts. If you want to read more on that subject check out this excellent article by Kevin Kelly.
Answer Questions, Explain and Tutor
ChatGPT can answer a variety of questions related to specific fields and provide a detailed explanation of complex subjects. This made some academics really worried about their jobs but also present an unprecedented opportunity to lower the educational barriers, giving everyone equal access to advanced knowledge. Of course, as ChatGPT is not perfect giving students unsupervised access to it also creates a danger of them learning inaccurate information and propagating bias. Educators of the future could take on the role of supervisors and consultants rather than ex-cathedra lecturers.
A lot of students have also shown that it is possible to use ChatGPT for completing assignments and performing tests. This challenges the standard educational model focused on memorization and autonomous work. Addressing those fears a tool called GPTZero has been released that helps to identify AI-generated content allowing educators if students have been using such models in their work.
However, a point can be made that if such tools are present in our everyday life, can we really ban them in education? After all, we all know how the argument “You won’t always have a calculator in your pocket” aged.
With the rising popularity and accessibility of generational models, educators will have to think about how to incorporate those models into the academic world, maintaining a balance between giving students knowledge and the ability to think critically, while also allowing them to use modern tools.
Write and Debug Code
One of the most prominent capabilities of ChatGPT is the ability to write functions and even full modules given the textual explanation of what the program should do. This made some people make far-going conclusions that ChatGPT will replace programmers. However, we have to remember that the possibilities of the model are limited by maximum context length and output size (more about that is explained in the next section). This makes the model useful for writing standalone functions or modules but doesn’t make it suitable for writing complex applications. ChatGPT capabilities can be compared to the ones of GitHub Copilot however the model can also correct bugs in existing code and provide reasoning behind the generated code. This makes the tool extremely useful as a software engineer's assistant.
Perform various NLP tasks such as Summarization, Named Entity Recognition, Translation, Guided Text Generation
As shown in the previous sections almost any NLP task can be converted to Text-to-text format. For example Named Entity Recognition can be modelled as question answering. This makes ChatGPT especially useful for performing various NLP tasks that were previously modelled by custom models. More importantly, those tasks can be performed in zero-shot scenarios, where the user doesn’t need to provide any additionally labelled datasets. The task can be defined by a self-contained prompt with all the instructions and, if necessary, the examples. It will be harder and harder to justify developing proprietary models, while similar or better results can be achieved with a few cents per input.
Take on different personas such as travel guide, doctor or life coach
ChagGPT can take on the role of different personas presenting not only the specific domain knowledge associated with different jobs but also personality traits based on the guidelines specified by the user. Although the model acts as a highly-skilled, the profession definitely carries a lot of risks. It also, if uses consciously, allows the users to access a variety of services. After all, there is little harm in getting travel destination suggestions from ChatGPT by giving it your preferences, however, it acting as your doctor could be dangerous.
This also means a lot of low-risk consulting services will have to step up their game and think about their unique value proposition over models such as ChatGPT.
What ChatGPT isn’t capable of?
Mistakes of ChatGPT
There are many examples of mistakes done by ChatGPT in open domain questions and specific tasks such as code generations alike. The model is by no means perfect. We won’t focus on the specific mistakes but rather assume that the model can make, with some degree of probability, a mistake in any scenario and discuss its implications.
What is most important, in its current state, ChatGPT isn’t capable of identifying its own mistakes. There is no confidence score system for the user to see, and quite frequently ChatGPT doubles down on the mistakes it makes. This is perhaps the greatest restriction for using the model in a production environment. While we can accept the fact that the model might not know an answer to every question, what isn’t acceptable is the fact that it will always provide one. If we were to use ChatGPT as a medical assistant, we would have no way of knowing if the provided responses are current or not. Even if the model is correct 90% of the time that 10% could prove fatal. If human doctor encounters a question they don’t know the answer to, they will consult their colleagues, perform additional tests, read the latest research articles or, in the worst-case scenarios, simply restrain from giving a diagnosis. ChatGPT on the other hand will always utmost confidence even if it is completely wrong.
The real question you have to ask yourself is: “Are you willing to take the risk?”. And the answer is not always “NO”. While you might not accept a doctor that is incorrect 10% of the time, you might accept a translator or a florist.
ChatGPT is offline (at least for now)
In its current state, the system is entirely offline meaning it can only use information from its training dataset and can’t perform any queries or scrape the internet for new information. The most recent training data is of ChatGPT from 2021 September. This severely limits the capabilities of the model as it can’t use any information produced after that date. Although some fundamental truths about the universe might not have changed since 2021 there are some fields (like medicine) that are evolving rapidly and presenting users with information from several years ago might be dangerous. If the system were to serve as a modern search engine taking the place of e.g. Google, its functionality would have to be extended to performing live queries from the relevant fields or at least the training dataset would have to be updated frequently.
ChatGPT has no memory
The capabilities of any generational model (and ChatGPT is no exception) are limited by the maximum context length — the size of the input we can provide to the model. Although we don’t know the exact context length of ChatGPT some people have hypothesized that it is 8,192 tokens. This is quite impressive as it is 4 times the context length of GPT-3. Although the number of words we can input to ChatGPT is smaller as some rare words are split into sub-word tokens (you can check out the mechanism here) we have to remember that the entire US constitution is 4,543 words and this article is 6,554 words meaning both could be fully generated by ChatGPT)
However, this limit is still…limiting as ChatGPT won’t remember anything after 8192 tokens. The system has no persistent internal memory and it will eventually forget relevant information. This severally limits the capabilities of the model as e.g full-fledged coding projects have thousands of lines of code. This necessitates the creation of external systems that store information and decide which information might be relevant to the current query. For example, if we were to use ChatGPT as a doctor we would first have to decide which parts of the medical documentation we want to give the model as a context as some information from 10 years ago might still be relevant while an unrelated condition from a few months ago might not.
ChatGPT doesn’t perform reasoning
As the evidence has shown ChatGPT struggles with tasks such as common sense reasoning.
This question, while trivial for most adults, can’t be correctly answered by ChatGPT. Why? Because there is no actual reasoning in language models.
We have to remember that although the capabilities of ChatGPT are impressive it is just a language model that completes the prompt with the most probable sequence of words based on the training data. The training is essential as large enough models can just remember information instead of generalizing. This not only makes the system extremely biased by also makes it more of an intelligent search algorithm than a truly intelligent system. Recently the term stochastic parrot has been used to describe large language models reflecting on their true nature — repeating information instead of producing one.
No actual language understanding is taking place in LM-driven approaches to these tasks (…) languages are systems of signs, i.e. pairings of form and meaning. But the training data for LMs is only form; they do not have access to meaning. ~Bender et al.“On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜”
Of course, this doesn’t make the work of OpenAI any less impressive, however, we have to remember that the system does not act logically and instead acts probabilistically, and for large language models a lie repeated a thousand times really becomes the truth.
Will ChatGPT replace software engineers?
This question has been asked numerous times following the release of ChatGPT and might even be the reason you decided to read this article. But the answer is not straightforward.
Software engineers are translators
To answer the question if ChatGPT will replace software engineers, we first have to answer the question of what a software engineer’s job is really about. From a high-level point of view, a software engineer can be seen as a translator that translates the vision of a client or product manager into code. The type of code changed over the years, from machine code to low-level languages and then to high-level languages. It appears that with the rise of large language models, we have moved again by one layer of abstraction where the translation result might be a natural language. Software engineers of the future will most probably not write every single function on their own, and instead, use tools like ChatGPT to convert natural language inputs to machine-interpretable code. But someone will conceptualize client requirements, break them down into small pieces interpretable by ChatGPT and then connect those pieces into a larger infrastructure.
Another parallel that can be drawn is that the current situation of software engineers is similar to the translators back when machine translation was introduced. Back then a lot of people were scared about their jobs too, but the profession of a translator didn’t disappear and is still standing strong. Sure, a small piece of text might be translated by Google Translator, but humans still translate important legal documents. Even if those humans use machine translation to speed up the process, someone still has to correct the mistakes and sign off on the quality of the translation. A similar thing might happen with software engineers. People might use ChatGPT to generate simple functions, but the large-scale important project will still require human supervision.
No-code platforms already exist
The idea that not every single lie of code has to be written from scratch is nothing new and is in fact one of the fundamental good practices of programming. Moreover, no-code and low-code platforms have existed for several years and the field of IT is still standing strong. In fact, recent research shows low-code developers are actually happier and make more money on average than high-code developers (72% of low-code users make over $100K USD (compared to 64% of high-code users), 42% of low-code users vs. 31% of high-code users say they are “highly satisfied” with their jobs.)
Language models can’t exist in a vacuum
As we have already mentioned in its current state language models can’t be used on their own mainly because of the context length limit and their offline status. This necessitated the presence of humans or an external system that decides what information to provide to ChatGPT as input. This means that even if the language model is perfect, we still need at least databases, user interfaces and search engines. But the language models are not perfect, which means we also need an external vaidatator that knows the domain well and is able to interpret and judge the results. And, as mentioned before. this means that language models are just a higher level of abstraction for the developers.
Will ChatGPT replace ML Engineers?
ML Engineers are translators too
So what is it that makes the ML Engineer fundamentally different from the software engineer? One could argue that the job is different because it requires conducting experiments, and testing hypotheses or training models, which is beyond the scope of a typical software engineer. But most companies don’t care about the research, they care about the results. So from a high-level point of view, ML engineers are also translators as they also translate business requirements into code. The road might be different, but the destination is the same.
Prompt Engineering
As mentioned above we can use ChatGPT to perform a number of different NLP tasks. This means that the company might decide to pay for the subscription for ChatGPT instead of hiring ML Engineers to create custom modules. However, the process of turning other NLP tasks to text-to-text problems is not trivial and the results might vary depending on how we formulate the prompt. Let’s imagine that we want to perform Named Entity Recognition and identify names that appear in a given text (e. g. an invoice) we might ask the model: “Which people are mentioned in the text: x?” but we might also ask it “What names appear in the passage: x” and get different results. This opens up a new field of prompt engineering, and NLP teams of the future might focus on optimizing the language model input for a different task. The topic of prompt engineering is in fact already present in the field of AI and a lot of research has already been made in this area.
Language models can’t exist in a vacuum (again)
While large language models such as ChatGPT might live at the heart of your AI system there is still a need for pre and post-processing. For example, if your input is an invoice, you might use ChatGPT to identify key information but if the user submits an image, you still need an OCR system to convert this image to text first. Or, if your input is a voice, you might use ChatGPT for NLP but still need an ASR and a speech synthesis system. Or the document understanding and voice processing can be a separate end2end system that is better than ChatGPT, as we have established that end2end systems win in the long run. Either way, language models, like ChatGPT. will definitely be more relevant in the field of AI even in seemingly unrelated fields such as image processing but, in their current state, they can’t replace all AI models.
Will ChatGPT replace your job?
So far we have given 2 examples of jobs that will change because of ChatGPT. But what about other jobs? After all, ChatGPT can act as a doctor, content writer, tutor or, to some extent, any profession that doesn’t involve interaction with the physical world. Will your job be replaced by ChatGPT?
This question is perhaps best answered by this quote:
“AI won’t replace radiologists, but radiologists who use AI will replace radiologists who don’t,” ~Curt Langlotz, Director @StanfordAIMI
The same argument can be made for any profession.
Let’s say you are a content writer and your boss decided to use ChatGPT instead of you. A few questions emerge: is ChatGPT the best tool for this? After all other language models exist, maybe some of them are better than ChatGPT in your use case. How to tell ChatGPT about your company and its values? How to make sure the spirit of the article follows the message you want to send? How to correct its mistakes?
Who will have an answer to these questions? Your boss? Do you think he will spend more of his time researching those topics?
No, but you can.
And do you think medical directors will keep up with the latest research on medical language models?
No, but you can.
Your job might become harder (or easier), your job might have fewer openings, and your job will definitely change, it might be completely different in a few years, but it’s a process, and you can also change. If you don’t disappear, your job won’t disappear.
ChatGPT won’t replace people, but people who use tools like ChatGPT will replace those who don’t.
Will ChatGPT create jobs?
Prompt Engineers
As we have established, deciding which prompt to use for the language model is not a trivial thing. The results may vary drastically depending on the specific wording, order of words and semantics given if the intention stays the same.
In the future, prompt engineering can be both a useful skill and a form of artistic expression. If fact we can already see companies offering certified courses in prompt engineering.
Testers
ChatGPT and other language models are by no means perfect and their behaviour is often hard to predict. Using such a system in a production environment is a challenge and requires a lot of testing to be done beforehand. This might increase the demand for testers specialized in AI models, both manual and automatic as many aspects of the output, such as profanity, semantics, intention and emotion, could be tested automatically or with the help of other AI models
Domain Experts
As we have established, letting models such as ChatGPT roam freely carries a lot of danger, as users can be presented with wrong and potentially harmful information. This means that AI and product teams using ChatGPT will have to work closely with domain experts that could help validate and correct the models. In the future, perhaps one of the standard career paths of a doctor will be, instead of becoming a practitioner, working in AI teams as a domain expert.
AI Ethicists and Compliance Managers
As AI models affect more and more aspects of our life, more and more ethical questions arise that can’t be answered solely by technical teams.
We can also expect an increase in regulations concerning the usage of AI.
In the future, each company might have their own dedicated AI Compliance managers and the job might be as common as GPDR Compliance manager.
Conclusions
ChatGPT is a language model that is optimized for following user instructions with reinforcement learning.
ChatGPT and other language models will definitely affect many fields, such as content creation, art, programming and consulting.
ChatGPT cannot be currently used in most production environments without external validation systems.
In order for ChatGPT to be widely accepted, the authors have to incorporate confidence scores or a similar system to identify the mistakes of ChatGPT and make the model online or at least frequently update the training set.
ChatGPT will definitely affect a lot of jobs but it is up to you if it will replace you.
ChatGPT will definitely create a lot of new jobs, as the model not only answers questions but also raises a lot of new ones.
Don't forget to leave your thoughts
If you liked the article don’t forget to give it a 👏 If you have any thoughts about ChatGPT or want to share your perspective, leave a comment!
About the author
Hello, my name is Aleksander Obuchowski, I am passionate about Natural Language Processing and AI in Medicine. Follow me on LinkedIn if you like my stories.
Get Certified in ChatGPT + Conversational UX + Dialogflow
Are you ready for Godmode?
| 2023-05-12T00:00:00 |
2023/05/12
|
https://blog.chatbotslife.com/how-chatgpt-really-works-and-will-it-change-the-field-of-it-and-ai-a-deep-dive-bd1efdb9053e
|
[
{
"date": "2023/02/24",
"position": 96,
"query": "ChatGPT employment impact"
}
] |
U.S. and EU Announce Plans to Develop AI Standards
|
U.S. and EU Announce Plans to Develop AI Standards
|
https://spectrum.ieee.org
|
[
"Rahul Rao"
] |
Civil servants in the United States and European Union promised that the two would join forces and support development of AI models in five socially critical ...
|
In late January, civil servants in the United States and European Union promised that the two would join forces and support development of AI models in five socially critical areas, including health care and the climate.
However, their agreement has yet to translate into concrete action. “In my opinion, it’s a statement of intent,” says Nicolas Moës, a Brussels-based AI policy researcher at the Future Society think tank. “We do not have, yet, a lot of understanding of how that is going to be executed.”
But if the agreement’s models do materialize, the developers’ actions could set a precedent for handling data in a world where two sides of the Atlantic paint very different regulatory pictures.
The agreement is a product of the EU-US Trade and Technology Council (TTC), a body of civil servants created at a diplomatic summit in July 2021. AI isn’t the TTC’s only concern; it handles a wide variety of trade-related issues, including security, international standards, data governance, and supply chains.
But right at its inception, the TTC stated its intention to establish AI standards. Since then, its AI interest has only grown: At its most recent meeting, in December 2022, the council agreed on several AI items, including a promise to develop international AI governance standards and a joint study on AI’s ripples in the workforce. The TTC also promised to “explore collaboration” on more scientific AI work.
The details of that collaboration came a month later. Officials announced that U.S. and EU researchers would develop “joint models” in five designated fields: extreme weather and climate forecasting; emergency-response management; health and medicine improvements; electric grid optimization; and agriculture optimization.
This list is a departure from earlier joint projects, which tended to focus narrowly on data privacy.
Priya Donti , the executive director of Climate Change AI, a nonprofit that supports climate-related machine-learning research, believes the agreement is a good omen for her organization’s work. “The larger the extent to which we can share knowledge and best practices and data and all of that kind of thing, the more quickly we as a society will make progress,” Donti says.
Furthermore, the agreement eschews AI’s traditional haunts, such as text generation and image recognition, in favor of putting AI to work in socially relevant domains. “This collaboration emphasizes the priority that the directions of AI should be shaped by some of the more pressing societal problems we’re facing…and also chooses application areas that have a huge bearing on climate action,” Donti says.
It’s not clear who would develop the joint models or who would use them. One possibility is that they become public goods that U.S. or EU users could take and adapt for their own needs.
What is very clear, however, is that joint models don’t mean joint data. “The U.S. data stays in the U.S. and European data stays there, but we can build a model that talks to the European and the U.S. data,” a U.S. official told Reuters.
Officials didn’t clarify what exactly that means, but it could look like this: Imagine building a model that forecasts power-grid loads with a training set of real-world electrical consumption data (which could include personal information, if the data are household level). EU researchers might train a model with European data, then send the model across the sea for U.S. researchers to further train or fine-tune it with U.S. data.
Alternatively, researchers might set up some form of data-exchange system that allows models to access data from abroad. A climate-forecasting model, for instance, might be able to query data from European weather satellites even if researchers trained it in the United States.
Whatever the case, researchers building the models may be in for a rocky learning experience. “I expect this to be one of the politicized issues coming up,” says Moës.
But if researchers succeed, then whatever steps they take could leave a lasting impact. Standards for health care data —how to share them across borders and, importantly, between disjointed regulatory landscapes—already exist.
If AI’s stewards are able to make the most of the TTC’s agreement, they could establish similar data-sharing and interoperability standards in some of the agreement’s other areas. Thanks to the United States’ and the EU’s economic might, other countries might pay attention.
“If the EU and the U.S. come together and they say, ‘this is exactly how we’re going to be sharing climate data’…that really will push, probably, other countries to say, ‘well, if we’re going to be collecting climate data, why don’t we do it in the same format as well?’ ” says Daniel Castro , vice president at the ITIF think tank in Washington, D.C.
What is clear is that the European Union and the United States, even if their approaches to regulating AI are wildly divergent, have a common reason to work together on AI. “They see China as a common threat,” says Castro.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://spectrum.ieee.org/ai-standards
|
[
{
"date": "2023/02/24",
"position": 33,
"query": "AI labor union"
}
] |
AI PAY Price (AI PAY)
|
AI PAY price now, Live AI PAY price, marketcap, chart, and info
|
https://www.coincarp.com
|
[] |
CoinCarp does not currently have price data for AI PAY as it has yet to be listed on any cryptocurrency exchanges (CEX or DEX).
|
What Is AI PAY(AI PAY)?
Creating the Payment Infrastructure for AI-commerce. We help AI builders accept payments and manage usage of their apps, agents and GPTs.
Where Can You Buy AI PAY(AI PAY)?
Investing in AI PAY can seem complicated, but it is much easier when you buy AI PAY through cryptocurrency exchange. Signing up for a cryptocurrency exchange will allow you to buy, sell, and hold AI PAY — both for fiat money and other cryptocurrencies. Some of the most popular AI PAY cryptocurrency exchange are:
Please check AI PAY(AI PAY) token address If you want to buy or sell AI PAY(AI PAY) on dex exchange. Beware of scams!
Click here to view AI PAY(AI PAY) price in different crypto exchanges.
AI PAY (AI PAY) Community
What is AI PAY (AI PAY) Contracts address?
| 2023-02-24T00:00:00 |
https://www.coincarp.com/currencies/aipay/
|
[
{
"date": "2023/02/24",
"position": 41,
"query": "AI wages"
}
] |
|
The Ethics of AI Art
|
The Ethics of AI Art - Center for Media Engagement
|
https://mediaengagement.org
|
[] |
These artificial pictures can cause reputational damage for professionals and celebrities, and it can present national security implications for politicians and ...
|
For thousands of years, art has been an endeavor of the human race. From Rembrandt to Basquiat, from the Benin Bronzes to the new wave cinema of Hong Kong, art has been recognized as creative expressions of human intelligence. With the public release of DALL-E 2, a neural network that generates images from phrases, the definition of art might be due for reevaluation to include media produced by artificial intelligence. Generative AI, like countless other technologies emerging in the cyber-physical realm, present numerous ethical challenges.
DALL-E 2, aptly named for the combinative surrealism of Salvador Dalí and the futurism of Pixar’s WALL-E, is a machine learning model developed by research company OpenAI. The program model allows users to render images from a description in natural language. Because it relies on information databases from web servers as reference points, the illustrations are seemingly boundless. DALL-E 2 has the capability to learn and apply artistic styles, like “impressionist watercolor painting,” too. Realistically, the limits of its potential depend on the creativity of its input phrases.
On September 28, 2022, DALL-E 2 became universally available. With its release, renewed debate about the merits of AI art came to the fore. Specifically, artists and graphic designers began to consider how this technology can facilitate their professions. Patrick Clair, Emmy-winning main title designer, said, “It’s like working with a really willful concept artist,” (Roose, 2022). Others in the visual arts scene worry that programs like DALL-E 2 might put them out of work in the same way that automated machinery shrunk the manufacturing workforce. For instance, it isn’t hard to imagine the cover art for an electronic dance album to be designed by AI rather than a human. Why would a rock band commission Andy Warhol, say, when DALL-E 2 can generate “rotting banana in pop art style” for free?
Just as manufacturing companies defend the utility of automation, some artists don’t denounce AI in the design sector. Many retail corporations argue that computerized self-checkout stations save money by allowing employees to do other work that can’t be automated. In the same vein, AI art can maximize the efficiency of artists by sparking creativity or inspiring someone’s first step in the final project. One interior designer said, “I think there’s an element of good design that requires the empathetic touch of a human … So I don’t feel like it will take my job away,” (Roose, 2022).
In addition to the ethics of employing AI art for commercial and professional use, the content DALL-E 2 and others produce is ripe for discussion. Dr. Eduardo Navas, an associate research professor at Pennsylvania State University who studies DALL-E 2, finds that it functions metaphorically “almost like God—all a person has to do is to state a prompt (the word) and it is.” Aside from some restrictions in the algorithm, such as pornography and hate symbols, there are limited guardrails for what prompts can generate. While an earlier version of DALL-E filtered out all images of people, the current model allows users to render public figures in positions and settings that could be deemed offensive or simply implausible. Further, even if the average person can distinguish AI renderings from real images, some people might think a meme generated by DALL-E 2 actually happened. These artificial pictures can cause reputational damage for professionals and celebrities, and it can present national security implications for politicians and leaders.
According to Dr. Navas, the progression from DALL-E 2 static images to AI-generated video clips isn’t a matter of “if, but when.” This raises significant ethical concerns related to credibility and accountability. For one, falsified videos of public figures saying and doing outrageous things, or deepfakes, can erode trust in institutions. One study shows that rather than misleading people, AI deepfakes make them feel uncertain, which “reduces trust in news on social media,” (Vaccari & Chadwick, 2020). It’s entirely possible for bad actors to deceive the media with a false video, leading to widespread circulation even after it gets flagged for misinformation and retracted. Another AI researcher said, “If I got [an image] off the BBC website, the Guardian website, I hope they’ve done their homework and I could be a bit more trusting than if I got it off Twitter,” (Taylor, 2022). Still, news websites regularly publish mistakes, and sometimes a redaction or correction isn’t enough to curb the spread of it.
As a consequence of AI coding and algorithms, the next dilemma stems from bias and stereotypes. One journalist said, “Ask Dall-E for a nurse, and it will produce women. Ask it for a lawyer, it will produce men,” (Hern, 2022). This is partly due to the web servers that provide the program with learning material. Some might argue that DALL-E 2 is still in its early phases, and the OpenAI programmers need time to work out the kinks. However, the algorithm likely can’t eliminate stereotypes on the users’ end. Dr. Navas, who is Latino, said that a colleague ran the prompt on DALL-E 2 to generate images of “the most beautiful woman in the world.” DALL-E 2 then created images of white women (DALL-E 2 gives four initial results). Dr. Navas ran the same prompt a few days later and got a different set of images—in this case, of women who appeared ethnically ambiguous and who might be perceived as Latina. In all instances, the women in the images were portrayed in Western-style dress. It is not clear if user data was accessed for running each prompt, but problems with diversity and user privacy arise if such information played some role in the different results.
Then there’s the complicated question of ownership: who should own the copyright to the generated images? One could make the case for the companies behind the coding, like OpenAI. After all, if it weren’t for the labor of the programmers, there wouldn’t be a final product. The terms and conditions for DALL-E 2 stipulate that OpenAI holds the copyright for images rendered, but the users retain ownership of the prompts they entered manually. This might be a fair compromise, but as Dr. Navas points out, the source material for the machine learning model isn’t owned by OpenAI either. With “1.5 million users generating more than two million images every day,” intellectual property laws will need to be reconsidered for AI art.
To conclude, DALL-E 2 and other text-to-image AI technology showcase myriad ethical challenges, and this article in no way intends to be exhaustive. As mentioned, AI art can pose risks to human artists and their opportunities to earn money. At the same time, the programs can aid designers by sparking creativity in the initial stages of a project. On the content side of AI art, the images can be offensive or harmful, and this danger is further exacerbated with the potential for AI deepfake videos. Then, because the code relies on human input and a vast repository of reference images, the generated content can be plagued with biases. Lastly, the realm of AI art is relatively new, so laws and policies related to ownership will require ethical reasoning to determine who or what owns the images. For better or worse, DALL-E 2 is now publicly available and gaining popularity. It’s no longer a question of whether AI should generate art, but rather how ethics can guide the answers to these complicated and unique challenges.
Discussion Questions:
Are there ethical problems when it comes to AI generating art? Which values are in conflict in this case study? If you were on the team that helped create DALL-E 2, what kinds of content, if any, would you restrict from appearing in the results? Why? In regard to copyright ownership, what would be an ethical way of determining which parties, if any, deserve the right of possession? What if the art is sold commercially? Should we classify AI-generated images as art? What are the qualifications for something to be considered art?
Further Information:
Hern, Alex. “TechScape: This cutting edge AI creates art on demand—why is it so contentious?” The Guardian, May 4, 2022. Available at: https://www.theguardian.com/technology/2022/may/04/techscape-openai-dall-e-2
Robertson, Adi. “The US Copyright Office says an AI can’t copyright its art.” The Verge, February 21, 2022. Available at: https://www.theverge.com/2022/2/21/22944335/us-copyright-office-reject-ai-generated-art-recent-entrance-to-paradise
Roose, Kevin. “A.I.-Generated Art Is Already Transforming Creative Work.” The New York Times, October 21, 2022. Available at: https://www.nytimes.com/2022/10/21/technology/ai-generated-art-jobs-dall-e-2.html
Taylor, Josh. “From Trump Nevermind babies to deep fakes: DALL-E and the ethics of AI art.” The Guardian, June 18, 2022. Available at: https://www.theguardian.com/technology/2022/jun/19/from-trump-nevermind-babies-to-deep-fakes-dall-e-and-the-ethics-of-ai-art
Vaccari, C., & Chadwick, A. (2020). “Deepfakes and Disinformation: Exploring the Impact of Synthetic Political Video on Deception, Uncertainty, and Trust in News.” Social Media + Society, 6(1). https://doi.org/10.1177/2056305120903408
Authors:
Dex Parra & Scott R. Stroud, Ph.D.
Media Ethics Initiative
Center for Media Engagement
University of Texas at Austin
February 24, 2023
Image: “Vibrant portrait painting of Salvador Dalí with a robotic half face” / OpenAI
This case was supported by funding from the John S. and James L. Knight Foundation. It can be used in unmodified PDF form in classroom or educational settings. For use in publications such as textbooks, readers, and other works, please contact the Center for Media Engagement.
Ethics Case Study © 2023 by Center for Media Engagement is licensed under CC BY-NC-SA 4.0
| 2023-02-24T00:00:00 |
2023/02/24
|
https://mediaengagement.org/research/the-ethics-of-ai-art/
|
[
{
"date": "2023/02/24",
"position": 33,
"query": "AI journalism"
},
{
"date": "2023/02/24",
"position": 68,
"query": "artificial intelligence graphic design"
}
] |
Editing audio for radio news
|
Editing audio for radio news
|
https://mediahelpingmedia.org
|
[
"Jaldeep Katwala",
"Jaldeep Katwala Has Been A Journalist Since He Has Worked For The Bbc",
"Channel News",
"Radio Netherlands As A Broadcaster. He Has Also Taught Journalism",
"Run Several Media Development Projects",
"Training Courses Around The World."
] |
Image of journalists looking at a computer screen created with Gemini Imagen 3 AI by Media. Good journalism has always been about data. Follow us on Facebook.
|
We edit audio because we do not always have the time on air to broadcast a whole interview. Before you start editing audio, always ask the editor or producer of the item how long the edited item should be.
Make sure you are familiar with editing software you are using.
Ask whether you need to edit a cut down of the whole interview including your questions or if you are to provide one or more clips of just the interviewee talking.
Listen to the whole interview all the way through once, taking note of key points and noting down a time code for each important point made by the interviewee.
Listen out for poor quality. If you can’t hear what’s being said, it’s unlikely your listeners will be able to.
There are two main ways to edit – amputation and filleting.
Amputation implies cutting short the whole interview or cutting out whole questions and answers.
Filleting means taking only the essential parts of each answer and cutting out a little of each answer.
Amputation risks leaving out relevant information while filleting can result in an interview which sounds disjointed and unnatural.
Allow interviewees to sound as if they are having a conversation. It is not your job to make the interviewee sound more fluent or more polished.
However if they interject with hesitations such as ‘um’ and ‘er’ or leave long pauses in their answers, you should consider editing some of these out if it helps the listener understand what is being said.
Be careful not to cut all the hesitations and pauses out because that can sound artificial and unnatural.
Never take one answer and edit it as a response to another question. This is unethical and unprofessional.
Radio is a medium that is based on your ears. That mean when you edit audio, try not to edit using just the screen. Pay more attention to how it sounds rather than how it looks on the screen.
When you have finished editing, always listen back to the finished edit to make sure you have fulfilled the brief you were given, that you have captured all the relevant points the interviewee made, and that you have represented the interviewees points fairly and accurately.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://mediahelpingmedia.org/advanced/editing-audio-for-radio-news/
|
[
{
"date": "2023/02/24",
"position": 89,
"query": "AI journalism"
}
] |
Interviewing with AI: The Pros and Cons - PSCI
|
Interviewing with AI: The Pros and Cons
|
https://www.psci.com
|
[] |
AI interviews can help companies to screen a large number of candidates quickly and cost-effectively, reducing the time and resources needed for the hiring ...
|
There are a multitude of reasons why organizations are choosing to adopt AI technology.
Artificial intelligence has the potential to transform the workplace by improving efficiency, productivity, and decision-making while reducing costs and risks.
As AI technology continues to advance, a growing number of companies are even using it to conduct interviews.
But while there are undeniable benefits associated with an AI interview, there are some serious drawbacks as well.
If you’re an IT leader considering using such technology in your hiring process, you’ll need to consider both.
In this blog post, we review the advantages and disadvantages of using AI in the interview process.
The Pros of an AI Interview
Consistency
Many versions of these interviews are referred to as AVIs (automated video interviews). These involve job candidates recording themselves on a video platform and answering questions within an allotted amount of time.
The video is then analyzed by the AI developer platform to determine visual (e.g. smile), verbal (e.g. key words used), and/or vocal (e.g. tone of voice) attributes, which it will use to either accept or reject a candidate.
Conducting initial screenings in this manner can provide a consistent and standardized experience for all candidates, ensuring that everyone is evaluated in the same way, with the same questions and criteria.
Efficiency
Chief among the reasons for adopting AI technology in the hiring process, though, is that it allows for an easier, less expensive way to interview candidates.
For companies that receive thousands of resumes, this can be very useful.
AI interviews can help companies to screen a large number of candidates quickly and cost-effectively, reducing the time and resources needed for the hiring process.
Objectivity
While AI technology, such as ChatGPT, is an amazing piece of technology, it’s still susceptible to discrimination.
When used to conduct interviews, however, it can help eliminate the bias that can arise from human recruiters, such as unconscious bias based on gender, race, or other factors.
In fact, one of the first companies to adopt AI interviews, Unilever, reported hiring their most diverse class ever (in terms of gender diversity, racial diversity, and ethnic diversity) after using the technology for an extended period of time.
The Cons of an AI Interview
Lack of Human Interaction
One large drawback of AI interviews is their lack of personal touch, which can lead to candidates feeling less engaged and/or valued.
When conducting interviews, a positive interview experience is vital.
Providing a positive candidate experience can help make a great first impression on top talent, which can increase their desire to work for you.
A negative experience, however, can turn off those candidates you desire and even tarnish your company’s reputation.
Technical Issues
Just as with any technology, AI interviews can be prone to technical issues such as bugs or connectivity problems. These can disrupt the interview process and lead to a negative experience for the candidate.
When technical issues arise in a typical interview, the two parties can find a way to get back in contact. When it occurs with a robot, the interview is more likely to just end.
Limited Assessment Capability
Soft skills are important because they help workers get along and achieve goals as a team.
And because even technical jobs require soft skills, employers are especially keen to hire and promote workers who have these abilities.
AI interviews, however, may not be able to assess soft skills such as emotional intelligence or interpersonal communication. Possibly costing you a shot at landing a star employee.
Ethical Concerns
AI interviews raise ethical concerns around the use of personal data, privacy, and fairness in the hiring process.
Since human programmers are the ones who write the code for these AI programs, their biases – whether intended or not – can be embedded in the algorithms.
A prime example of this is when Amazon used such technology. In this instance, the AI showed a total bias against women and failed to rate candidates for software developer jobs and other technical posts in a gender-neutral way.
Overall, while AI interviews offer some clear benefits such as consistency, efficiency, and objectivity, they may not be suitable for all types of roles or for all candidates. It is important to carefully consider the pros and cons before adopting AI interview technology and to ensure that they are used in an ethical and fair manner.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.psci.com/interviewing-with-ai-the-pros-and-cons/
|
[
{
"date": "2023/02/24",
"position": 40,
"query": "artificial intelligence hiring"
}
] |
AI: What Does it Mean for the Future of Work?
|
AI: What Does it Mean for the Future of Work?
|
https://careerprocanada.ca
|
[
"Cathy Milton",
"Muhammad Ashir"
] |
At the end of the day, humans hire humans. The human component in hiring, recruitment, selection, and retention must be balanced with technology to ensure ...
|
It is a well-established fact that artificial intelligence (AI) will impact the future of work. Oracle.com defines artificial intelligence as applications that conduct complex tasks that once needed human input. AI uses computers and machines to make judgments and decisions, solve problems, learn, and reason; basically, AI simulates human intelligence. It can spot patterns and receive large amounts of data; an area where most humans are limited. But, what does AI mean for the future of work?
The Reality of AI: Transforming Our Workplaces
By 2025, 85 million jobs may be displaced due to automation, while 97 million new roles will emerge as humans and AI learn to coexist. By 2030, between 10 to 800+ million workers worldwide will be displaced by machines/automated processes. The McKinsey Global Institute reports that only 5% of occupations can be fully automated, but in approximately 60% of jobs, at least one-third of the activities could be automated. So, jobseekers must learn to work alongside machines and use new technologies and processes.
The Irony Behind AI: A Part of Daily Life
We engage with AI constantly. It exists in the algorithms that shape our social media feeds, the virtual assistants that answer questions online or on the phone, and the face ID you use to unlock your computing devices. AI is used when you ask Siri or Google to do something. Its capabilities have enabled innovations such as self-driving vehicles, connected “Internet of Things” devices, and a brain-controlled robotic arm that can help a paralyzed person feel again through complex direct human-brain interfaces.
How AI Will Shape the Future of Work and Enhance Human Potential
Will robots and machines replace all our jobs? Not likely, at least not anytime soon. Some predict that AI can and will create more jobs
Although AI is designed to raise the economy and enhance the quality of life, a primary concern about it relates to what degree AI will force workers to shift careers and even alter their lives. Automation can replace many mundane tasks such as scheduling meetings, answering questions, and writing to-do lists. The good news is that this frees up time that can be devoted to critical or creative tasks and projects. Thus, organizations, employers, and employees can benefit immensely by merging AI with human potential to achieve augmented intelligence; using machines and deep learning to enhance human capabilities, rather than replacing humans entirely.
Technology is not driving innovation to substitute, but rather to enhance, human potential. While many of us may dread the rise of AI, there are ways that we can embrace it. AI can’t replace the human heart connection.
Ethical Considerations
Artificial intelligence or computers that are taught to “think” like humans, can improve our health and reduce stress through advancements in medicine, manufacturing, and more. However, there are risks and drawbacks that need to be addressed.
AI must be used responsibly and ethically. Five recommendations have been created to provide guidelines on its development and use:
Effective: Ensure AI is the right tool to address the problem/concern. While the improper use of a particular AI system may not directly pose harm, it may impact trust in other AI-based systems.
Ensure AI is the right tool to address the problem/concern. While the improper use of a particular AI system may not directly pose harm, it may impact trust in other AI-based systems. Explainable: The logical decisions produced by AI should be communicated to stakeholders succinctly and resourcefully to gauge critical risks.
The logical decisions produced by AI should be communicated to stakeholders succinctly and resourcefully to gauge critical risks. Accountable: Organizations and individuals must be responsible for the outcomes of the AI systems they develop and deploy.
Organizations and individuals must be responsible for the outcomes of the AI systems they develop and deploy. Secure: AI systems should be safe from external interference through strategic initiatives, regulations, and policies.
AI systems should be safe from external interference through strategic initiatives, regulations, and policies. Fair: AI systems should address potential discrimination and bias. Assessing and testing systems can ensure safer outcomes and enhance worker acceptance.
AI and Recruitment
At the end of the day, humans hire humans. The human component in hiring, recruitment, selection, and retention must be balanced with technology to ensure equitable hiring free from biases. Therefore, collaboration will be required by recruiters, hiring managers, and AI experts.
The caveat is that many people will be concerned about AI’s reliability and trustworthiness, privacy, security, and mitigation of biases. Transparency, equity, and accountability will be relevant during integration and usage. Therefore, reliable data, standards, validation, and verification are critical to successfully incorporating AI technologies into workplace processes.
The Implications of AI for Workers
Proponents of automation/augmentation argue that its implementation is not causing a decline in the number of human workers, but rather is responsible for creating potentially millions of new jobs. Among AI’s biggest benefits is its ability to save humans from having to perform tedious, repetitive tasks, thus freeing them up to focus on more complex and rewarding projects.
One thing many agree is a certainty; AI will require workers to acquire and/or strengthen their skills. Key among these are:
Digital literacy skills to work with and supervise the machines.
Technological skills, such as advanced programming.
Interpersonal skills, emotional intelligence (EI), problem-solving, decision-making, and creativity skills will be required to make complex or sensitive decisions and navigate human interactions.
In the next decade, the demand for artificial intelligence specialists is estimated to grow by 36%. Those interested in pursuing a career in AI may be interested to know that salaries in the field often exceed six figures, even for entry-level positions.
The Implications of AI for Career Professionals
As career professionals, we are undoubtedly already using AI tools to manage our small businesses and give our productivity a boost, but we’ll need to educate and prepare our clients to focus on higher-value, higher-touch tasks requiring interpersonal skills, creativity, strategic thinking, and entrepreneurialism. We need to help our clients keep an open mind and envision a future of work that integrates AI and meaningful human interaction, rather than resisting change.
AI tools lack emotional intelligence, which propels career professionals to improve and help clients optimize their EI for career success. However, AI can pose various workplace safety hazards, including mental health and well-being. Thus, further research will be needed to explore the impact of these hazards and mitigate further AI-related risks for workers’ safety and wellness.
Conclusion
AI is driving economic growth and productivity with life-changing breakthroughs. It is quickly becoming an integral part of life through process automation, technological advancements, and lower production costs while growing capabilities and speed of computing power. Yet, everyone will need to adapt to the changes brought on by AI. These changes will have a major impact on the workplace of the future. Workers will need to learn innovative and advanced skills to stay competitive. Jobseekers will require affordable and accessible learning and upskilling opportunities to remain relevant.
We will all benefit by learning about, and embracing, AI. As career professionals, we can harness robotics or automation to perform low-value, repetitive tasks that are necessary, but consume valuable time. This will create greater space for us to champion our clients to pursue their goals and authentic purpose.
Invest in CPC’s courses and certification programs, and position your clients to embrace the new world of work.
Lori Jazvac is a passionate, award-winning Master Certified Résumé Strategist and Certified Employment Strategist through Career Professionals of Canada. As a multi-certified Master Résumé Writer and Certified Career Transition Coach, she specializes in helping clients navigate challenging career transitions. In 2013, an empowering vision inspired Lori to launch Creative Horizons Communications, a holistic career services firm where she virtually supports jobseekers around the globe to embrace their next career milestone. In her spare time, Lori enjoys dance, blogging, watching comedies and reality shows, yoga, and taking long walks in nature.
Ksenia Lazoukova is a Certified Career Development Practitioner (CCDP), Certified Résumé Strategist, Certified Career Strategist, Certified Employment Strategist, Certified Interview Strategist, and Certified Work-Life Strategist. She is a proud member and volunteer with Career Professionals of Canada. Ksenia is a dynamic career development professional, case manager, program coordinator, adult educator, and learning developer working at the Immigrant Services Association of Nova Scotia where she helps newcomers to Nova Scotia achieve their employment and career goals. In her past role as a job coach, Ksenia provided a wide range of employment services to people with disabilities in the supported employment setting. Her passion is helping people of various backgrounds overcome multiple barriers, fulfill their life and career dreams and goals, and become more fully integrated into their communities.
Conny Lee is a Certified Holistic Narrative Career Practitioner, Online Business Manager for coaches, Certified Career (CCS), Employment (CES), and Résumé Strategist (CRS), Trauma of Money Facilitator, and Sacred Money Archetypes® Coach. She focuses on supporting people to create the career, business, and life they truly desire. To learn more, visit Conny’s website at connylee.com. When she isn’t working, Conny enjoys reading, listening, learning anything related to personal development, spending time with her family, and working out.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://careerprocanada.ca/ai-what-does-it-mean-for-the-future-of-work/
|
[
{
"date": "2023/02/24",
"position": 80,
"query": "artificial intelligence hiring"
}
] |
Alphabet closes Everyday Robots among layoffs
|
Alphabet closes Everyday Robots among layoffs
|
https://www.therobotreport.com
|
[
"Brianna Wessling"
] |
On January 20, 2023, Alphabet announced it would be laying off around 12,000 workers, 6% of its workforce, and Everyday Robots is one of the few projects ...
|
Alphabet, Google’s parent company, is shutting down its subsidiary Everyday Robots, according to reporting from Wired.
On January 20, 2023, Alphabet announced it would be laying off around 12,000 workers, 6% of its workforce, and Everyday Robots is one of the few projects disbanded as part of the budget cuts. Some of the technology and part of the Everyday Robots team will be consolidated into existing robotics projects within Google Research, Denise Gamboa, director of marketing and communications for Everyday Robots, told Wired.
The company graduated from Alphabet’s X moonshot lab just over a year ago. The company taught over a hundred wheeled, one-armed robots to clean cafeteria tables, separate trash from recycling and open doors.
Everyday Robots wanted to create flexible and adaptable robots that could be used outside of industrial environments. The company’s first prototype was unveiled in 2021, and in 2022, it was upgraded with Google’s AI language research to allow them to process natural language commands.
Robotics Summit (May 10-11) returns to Boston
While the company had ambitious goals for its robots, they didn’t seem to ever make the commercialization stage even a decade after Alphabet acquired the company, although the robots did do some cleaning around Alphabet’s offices. Some of Alphabet’s other moonshot projects, like Loon, which created internet-beaming balloons, have already shut down for this very reason.
Other previous moonshot projects, like Wing, a drone grocery delivery company, and Waymo, an autonomous driving company, still appear to be going strong. At the end of last year, Waymo announced that it would be expanding its service area in both San Francisco and Phoenix.
According to Wired‘s reporting, a former employee from Everyday Robots said that the company struggled to determine the company’s mission. The team couldn’t decide if they were aiming for an advanced research project or a commercially viable product.
Everyday Robots employed over 200 people, and Alphabet did not give any details about how many of those employees, or which, would be staying on with the company.
| 2023-02-25T00:00:00 |
2023/02/25
|
https://www.therobotreport.com/alphabet-closes-everyday-robots-among-layoffs/
|
[
{
"date": "2023/02/24",
"position": 42,
"query": "artificial intelligence layoffs"
}
] |
AI In Education: The Impact of ChatGPT in the Classroom
|
AI In Education: The Impact of ChatGPT in the Classroom
|
https://blog.acceleratelearning.com
|
[
"Stemscopes Staff"
] |
In this article, we will explore the potential of ChatGPT in education, as well as its limitations and risks, to better understand the impact of AI on the ...
|
ChatGPT, a language model that uses deep learning techniques to generate human-like responses, has garnered significant attention for its potential applications in education.
This AI-powered technology has been hailed as a game-changer for the education industry. Its ability to support personalized learning experiences, facilitate research and knowledge acquisition, and automate testing and assessment.
However, as with any emerging technology, there are concerns around the accuracy and biases of ChatGPT's responses, as well as potential privacy and ethical implications of using AI in education.
In this article, we will explore the potential of ChatGPT in education, as well as its limitations and risks, to better understand the impact of AI on the future of learning.
AI in Education
Artificial intelligence (AI) is usually defined as the theory and creation of computer systems capable of performing tasks that would typically require human intelligence.
In other words, getting computers to do things we used to assume computers would never be able to do or never be good at, such as recognizing objects visually, understanding and producing speech, and creating original content.
In recent years the initial technical difficulties of getting computers to accomplish these tasks have been gradually overcome, and the pace of progress is increasing.
As the technology of AI has improved, innovators have explored new ways to apply it to education.
One area of innovation is in educational assessment. Versions of AI that can process visual input can optically “read” a handwritten math equation and grade it.
Similarly, speech recognition has improved to the point that AI can evaluate spoken responses. In addition, when these systems integrate machine learning, they can improve their ability to do these assessments over time.
Natural Language Processing
As computers have become faster and more powerful, they still seem to lag in certain areas, such as language.
If you're like me, you’ve been a sci-fi fan for years and probably wondered, “Where are the computers we can talk to?”
We probably all know the frustration of trying to get Alexa to follow a simple command or have our patience interacting with the robot on the other end of a phone call.
Because the human brain is hard-wired for language, we often don’t realize how incredibly complex an enterprise it is.
Natural Language Processing (NLP), teaching computers to use written and spoken language the way humans do, began soon after the first computers were built.
The complexity of the task, however, has stymied professionals for decades. Real progress has been made in recent years, though, as the release of ChatGPT demonstrates.
What is ChatGPT?
Basically, ChatGPT (Chat Generative Pre-trained Transformer) is a chatbot, a computer application that can interact through text. You’ve likely dealt with one when you were on a website where no human customer service representative was available.
ChatGPT was developed by OpenAI, an American AI research facility. It was created using language models (think of them as mathematical models of how words work) and then trained over time by humans.
So is it any good? Can it produce decent, natural-sounding text based on a simple prompt?
I visited the ChatGPT website myself recently and typed in the prompt, “Give me an opening paragraph for an article on the effect of ChatGPT on education.”
What I got was the first paragraph of this article. Go back now and give it another look. The writing style does not perfectly match my own.
It’s a bit dry (and do I detect a hint of self-promotion?), but it's not bad. Certainly, it’s good enough to pass for original text composed by a human being, which is raising concerns.
ChatGPT in Education: Threat or a Benefit?
Much of the buzz around ChatGPT has been expressions of angst about the threat it poses to education. The concern is usually centered on the fear that students will hand in computer-generated material as their own if reports, essays, and even poems can be easily generated by typing in a few simple prompts.
“The College Essay is Dead” is a typical expression of this sentiment (Marche, 2023).
Reactions like this are to be expected. As new technology emerges, it brings with it the worry that students will come to rely on it, leading to the loss of essential skills.
I was in grade school when the first handheld calculators became widely available, and I remember how everyone wanted to ban them from classrooms for fear that my generation would no longer be able to do basic math.
Even Socrates railed against the innovation of the written word, fearing that literacy would result in forgetfulness (Socrates on the Forgetfulness that Comes with Writing, n.d.).
Those of us who have grown up with calculators can still do basic math, and being able to read has not substantially degraded my memory (The aging process has done that very nicely, thank you!).
Calculators and the written word have reshaped learning but not destroyed it.
That’s not to say that we should not be cautious about how we use new technologies in the classroom. We simply need to be aware of the tradeoffs. When television was the new technology, some thought it would be a great boon to education and others who thought it was a scourge.
The reality is that it turned out to be a tool that can be used well or poorly.
Making ChatGPT Your New Classroom Ally
Concerns about cheating or the loss of basic skills are valid, but the best approach can’t be simply to ban ChatGPT from classrooms or, worse yet, pretend it doesn’t exist.
Teachers are a dedicated and creative bunch and have found ways to make allies of former enemies such as calculators, television or Wikipedia.
Ignoring or banning a new technology is a strategy that not only won’t work but also fails to prepare students for the current reality. We live in a world with the internet, smartphones, and chatbots that can produce natural language text.
Surely the wisest approach is to find ways to integrate this new technology into teaching to the benefit of both students and teachers.
Generating Simple Content
First, let’s consider how teachers can use ChatGPT to make their lives easier. As any classroom teacher can tell you, they spend a lot of time generating content to use in their classrooms.
Much of this tedious and time-consuming work could easily be handed off to AI.
For example, I entered the following prompts into Chat GPT.
The results took only seconds and were surprisingly good. Think about the time a teacher could save by using ChatGPT to create this kind of content.
Of course, the system is limited, and the results are not always perfect. The story about planets had some vocabulary that was not grade-level appropriate and would have to be tweaked by the teacher.
On the other hand, I did learn something new about organic chemist Percy Julian.
ChatGPT as a Language Resource
The examples above use ChatGPT to generate content that might be used in a math, science, or social studies classroom. Remember, though, that the real power of a natural language generator is its ability to use language.
This can be especially helpful when the focus of teaching is language itself, as the prompts below illustrate.
The first prompt produced a brief bit of text with pretty egregious spelling errors (anumals) and more subtle grammatical errors (...examples includes…) but which would still be useful for having student hone their editing skills.
The response to the second prompt gave me not only three examples of errors but also the explanation and correct version of each.
How Students Can Use ChatGPT
If we avoid the initial impulse to ban students from using ChatGPT outright, we can focus on helping them use it in a way that’s not just reasonable but even helpful.
The internet is already full of examples, but here are a couple of prompts that demonstrate what I’m talking about.
The first prompt would work when the learning objective is less about creating outlines and more about the content. What the student who enters this prompt gets is, in effect, a list of topics they have to learn and write about.
In the case of the second prompt, the student can compose a sentence and get feedback on their use of language.
This could be especially helpful for English Language Learners (ELLs). It’s worth noting that the response I got to this prompt detected not only the spelling and grammar errors but also the factual error of confusing parallel and perpendicular lines.
This last example demonstrates the capability of the system not simply to generate content but also to analyze and evaluate it.
For teachers willing to invest time into teaching students to responsibly use this technology, the payoff could be an eventual lessening of their burden.
Remember the prompt for generating ten story problems?
Imagine if all the students in a math class entered that prompt. Every student would have their own unique set of story problems. That would be a nightmare to grade, you say.
Not so because the students can also ask ChatGPT to check their work. By simply asking the system if the answer they got is right, they will get feedback and an explanation of the problem.
The Future of ChatGPT
We will undoubtedly struggle with how to deal with ChatGPT for years to come, just as we have done for centuries at that particular intersection of technology and education.
It’s both exciting and a little frightening to think that, by the time we have devised an approach that works, the technology will have moved on already.
You may have read that another AI, called ChatGPT Zero, has already been developed to detect if something was written by ChatGPT. This may alleviate, temporarily, the fears of those who predict widespread cheating, but the arms race between technologies will never end.
The best plan of action is to try to keep up with the advances being made and to collaborate with other education professionals to devise a plan for working with technology rather than against it.
Having worked in education for decades, I am confident that the creativity and determination of professionals in the field can meet this challenge– and turn it to their advantage and the benefit of their students.
References
Alleyne, A., et al. (2022, June 15). Future of Testing in Education: Artificial intelligence. Center for American Progress. Retrieved February 16, 2023, from https://www.americanprogress.org/article/future-testing-education-artificial-intelligence/
Marche, S. (2022, December 16). The College Essay Is Dead. The Atlantic. Retrieved February 16, 2023, from https://www.theatlantic.com/technology/archive/2022/12/chatgpt-ai-writing-college-student-essays/672371/
Roose, K. (2023, January 12). Don't ban ChatGPT in Schools. Teach with it. The New York Times. Retrieved February 16, 2023, from https://www.nytimes.com/2023/01/12/technology/chatgpt-schools-teachers.html
Socrates on the Forgetfulness that Comes with Writing. (n.d.). Retrieved February 14, 2023, from https://newlearningonline.com/literacies/chapter-1/socrates-on-the-forgetfulness-that-comes-with-writing
What is Natural Language Processing? IBM. (n.d.). Retrieved February 16, 2023, from https://www.ibm.com/topics/natural-language-processing
| 2023-02-24T00:00:00 |
https://blog.acceleratelearning.com/ai-in-education-the-impact-of-chatgpt
|
[
{
"date": "2023/02/24",
"position": 8,
"query": "artificial intelligence education"
}
] |
|
Will AI replace graphic designers?
|
Will AI replace graphic designers?
|
https://sketchdeck.com
|
[] |
AI is a powerful, new tool that will make it easier to execute a design strategy, but we'll still need professional designers to develop and oversee that ...
|
The technical storage or access that is used exclusively for statistical purposes.
The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
| 2023-02-24T00:00:00 |
https://sketchdeck.com/blog/will-ai-replace-graphic-designers/
|
[
{
"date": "2023/02/24",
"position": 23,
"query": "artificial intelligence graphic design"
}
] |
|
The Copyright and Impact of AI
|
The Copyright and Impact of AI – PRINT Magazine
|
https://www.printmag.com
|
[] |
Currently, images made with AI are not copyrightable. Copyright (in the US, anyway) applies only to images “made by humans.”
|
If you have not read Part 1 of my AI series, please do so now, or some of this will not make sense to you.
I have mixed feelings about this statement. I do value the importance of copyright (unlike some people who feel that it only serves corporate interests and should be abolished). I have threatened to sue on three occasions and been compensated in all three instances. Two of those were clear and direct lifts of particular images, but one of them was merely a infringement of style, which my lawyer enumerated in 13 points. He expected that they would tell us to “fuck off back to Canada” (his exact words), but much to our surprise they paid up and destroyed remaining copies of the offending item.
We were surprised because “style” is not copyrightable in the US (where the infringement took place). Someone has to actually, demonstrably lift your image or unique part of your image for you to have a copyright infringement. But when they do it it makes me hopping mad.
There is a—sadly abandoned—Facebook group called “Copy/Anticopy” which I absolutely loved. In it they would post two or more images of design side-by-side and ask the question “Similarity, Copy or Not Copy?” And those few of us following would weigh in. The comparisons were fascinating. As I pointed out in some of the posts, other options to the question were “homage” and “parody.” Some were posters that used the same image—but that image might have been stock. I found the question endlessly fascinating. The group is still there, so take a look.
All this to say that unless your image has been specifically lifted and regurgitated (alterations and interpretations may or may not protect you: search “Shepard Fairey vs. Associated Press”), you are not protected by copyright—online outrage and accusations notwithstanding.
However, in tiny Canada:
Canadian copyright law takes its cue from a 2004 decision of the Supreme Court: CCH Canada Ltd. v. Law Society of Upper Canada. In it, the high court defined an “original work” in terms of effort — as a product of “an exercise of skill and judgment.” That exercise of skill and judgment, wrote then Chief Justice Beverley McLachlin, “must not be so trivial that it could be characterized as a purely mechanical exercise.” — CBA / ABC National: “The legal status of generative AI”
Super interesting! However, from the same source:
But because Canada is a little fish in a big copyright pond, said Lebrun, many decisions about the legal status of generative AI may be settled abroad. “The principal problem facing any artist in this situation is jurisdiction,” he said. “This isn’t happening in Quebec. It’s happening in California, mostly. This is an international issue. It’s international data.”
© 2008 Marian Bantjes.
From time to time someone would contact me to say that so-and-so had copied my work. I’d take a look and see something ornamental and say, “I don’t own ornament.” Or maybe it would be something that showed some influence, but so what? I have been influenced by those who came before me—we all know that’s how it works.
So when we look at other people’s work are we stealing something from them? What if we search for pictures of horses to figure out just what that hind leg looks like from a certain angle? What if we search #hotrod and use what we find as references to make our own drawings of hotrods? Is any of that theft?
Because that’s what AI is doing. And in fact, because it’s looking at and learning from absolutely everything, your (yes your) influence on it is far less than on the person who specifically looks at your images for “inspiration,” or whatever.
Image generated in Midjourney by Marian Bantjes.
Meanwhile, currently, images made with AI are not copyrightable. Copyright (in the US, anyway) applies only to images “made by humans.” I’m sure this will be challenged in the near future, but the law changes very slowly and technology moves very fast. But I’m fine with this; I think that’s fair for now until things get more sorted out. As mentioned in my previous post, I personally don’t feel authorship in the images I made, although I do feel ownership.
Turbulent waters
I’ve covered the basic usage of Midjourney, but it, and other AI image programs, have the ability to specifically request images “in the style of” an artist or photographer. Aside from the fact that style is not copyrightable, this does seem concerning—until you try it. I have tried it, and my dear designer/illustrator friends … it has no idea who you are. I have tried some of the most famous names in Illustration, and it doesn’t even give a hint of knowing who the fuck I’m after. As for myself? Oh, people have tried…
Har har har de hardy har har!
This may look like it’s making some association with me, but I would bet the results would be the same without my name in the prompt.
Again, it hasn’t got a clue. I’ve got maybe 500 images out there among billions. An artist has to have a massive level of fame (word-recognition by the masses) for this to affect them—if indeed it does. Below are a couple of experiments I made:
Image generated in Midjourney by Marian Bantjes using the prompt “Barber trimming a boys hair in the style of Norman Rockwell”
Image generated in Midjourney by Marian Bantjes using the prompt “David Hockney, swimming pool.”
Both of these are astonishing. They really had me wondering how close they were to actual paintings (except the bottom two “Hockney”s) but via online searches I could find nothing with the same compositions, although plenty, in both cases, with similar elements. The AI is extremely good at representing paintings by incredibly famous artists within the subject matter that is common to their work, but I wondered how transferable that imitation was to a subject not associated with the artist.
It would appear it has no idea how David Hockney might paint a rabbit:
Image created in Midjourney by Marian Bantjes using the prompt “David Hockney, rabbit”
Image generated in Midjourney by Marian Bantjes using the prompt “man with his hair on fire, waving his fist at passing cars, in the style of Norman Rockwell”
It’s an idiot! This is because it has no actual intelligence—it is riffing off of many thousands of artworks on the internet by those artists. But when presented with something they never made, it’s unable to apply any technique whatsoever to a new subject. It has no idea that Rockwell is associated with sweetness, innocence, and a particular era. So basic to a human, incomprehensible to it. And this aspect of understanding is not going to improve in the near future, possibly the distant future, or maybe never.
Nevertheless, an unscrupulous person might generate a Hockney (or Rockwell, Koons, Hirst …) similarities and put them on pillows or some shit and sell them. But the AI didn’t do that, the human did. That same human would think nothing of taking images from the internet and selling them on pillows. And guess what—here they are. AI won’t change bad behavior by humans.
Things get murkier the deeper you go
I was disturbed, however, to discover that you can point Midjourney to an online image in the prompt to include it in the algorithm. I do actually think this should not be legal, despite the less-than-stellar results, because it shows intent to copy. That’s an important point and comes up in this legal case against Jeff Koons.
However, I wanted to test it out, so I used some of my own work on the internet to include in a prompt.
My original piece, left, referenced by me in a Midjourney prompt produced the four images, right.
My original piece, left, referenced by me in a Midjourney prompt (plus the word “heart”) produced the four images at right.
While the first two examples are vaguely me-ish in a way that I might recognize if I saw them in the wild, they are no more concerning than any human-created messes that I have seen based on or influenced by my work. As for the third example, there’s barely any relationship. Only the 2nd version might give me pause, but otherwise, have at ’er.
While I maintain that AI is not going to improve in “intelligence” any time soon, this type of copying directly from an image will improve, and that really is something worth fighting/lobbying against.
But aside from that I think Illustrators and artists have little to worry about on the copyright front, unless your work looks like this.
In which case you should have been worried a long, long time ago, and not due to AI, but due to humans.
Meanwhile
If you’re seriously worried about your copyright, you might want to take a look at what you agree to when you use Facebook, Instagram or any number of other online platforms. Meta’s (FB, Insta) current policy is:
We do not claim ownership of your content, but you grant us a license to use it. Nothing is changing about your rights in your content. We do not claim ownership of your content that you post on or through the Service and you are free to share your content with anyone else, wherever you want. However, we need certain legal permissions from you (known as a “license”) to provide the Service. When you share, post, or upload content that is covered by intellectual property rights (like photos or videos) on or in connection with our Service, you hereby grant to us a non-exclusive, royalty-free, transferable, sub-licensable, worldwide license to host, use, distribute, modify, run, copy, publicly perform or display, translate, and create derivative works of your content (consistent with your privacy and application settings). This license will end when your content is deleted from our systems. You can delete content individually or all at once by deleting your account. [Emphasis mine.] — Copyrightlaws.com, “Instagram and Copyright — What Are the Terms of Use?”
And you might want to think twice about complaining about it all on social media while using animated gifs from movies etc. to express your feelings.
But there’s still lots worry about
Will people use AI instead of artists? Yes, and they already have. Ad agency BSSP used AI generated images for the fall 2022 production of The Nutcracker for the San Francisco Ballet. And I’m sure there are many more.
I think a lot of artists’ work will be lost to AI. Not from the likes of The New Yorker, or anywhere that has intelligent (there’s that word again), sensitive Art Directors—but we all know that kind of work is few and far between. So while I honestly don’t believe that an AD who would otherwise use, say, Anita Kunz, will instead try to get an Anita-Kunz-like-image out of AI (good fucking luck!), the types of people who just need something that they would have previously got from stock imagery, or stolen from the internet, will. Plus unimaginative, shit ADs.
David Holz, the founder of Midjourney, says:
Right now, our professional users are using the platform for concepting. The hardest part of [a commercial art project] is often at the beginning, when the stakeholder doesn’t know what they want and has to see some ideas to react to.
Oh my god. The day will come soon, if it hasn’t already, when you—yes you—will be presented with some piece of half-baked “concept art” generated in AI with the instructions “like this, sortof, only happier, with more “pop”, and no warrior king, and you-know—in your style.” This guy shows us how horrible it will be.
Some of us have the luxury of telling such people to fuck off. Others don’t. Welcome to the 1990s of graphic design when young designers had to take “direction” from people who just learned how to use InDesign, and people with two months of night classes in design were “stealing our jobs.”
In the immortal words of Michael Bierut, “Do good work.”
David Holz, again, says:
I think that some people will try to cut artists out. They will try to make something similar at a lower cost, and I think they will fail in the market. I think the market will go towards higher quality, more creativity, and vastly more sophisticated, diverse and deep content. And the people who actually are able to use like the artists and use the tools to do that are the ones who are going to win.
Image generated in Midjourney by Marian Bantjes.
I hope he’s right, and in certain areas AI cannot and never (in our lifetimes and, I bet, before the power grid goes down and we all have to live on nuts and berries) will be able to compete. It will never be able to read a story, understand its nuances and come up with a compelling image for it (although it could “read” a story and pick out repeating words like “girl, house, mother” and make some cliche out of that); and it will never have humor or wit (Christoph Niemann can totes relax).
But its use will impact you and other artists, and especially photographers, like stock photography and illustration did. I predict we will also see a big jump in the next year or two while everyone tries out the novelty of it.
But as someone who has used it obsessively over the past two weeks, I can tell you that it’s not as easy as people like to say it is, and I think ADs will tire of spending hours trying to get that “concept image” and revert to just telling you what they want.
Regarding Contests
So far, the Society of Illustrators New York, American Illustration, Communication Arts, Spectrum Fantastic Art, 3×3, Creative Quarterly, Society of Illustrators Los Angeles, World Illustration Awards, Applied Arts Awards and the AIGA have all stated that they will not allow AI images into their competitions, and for the moment, I support that, and think that’s fair.
I do believe, however, that AI like Midjourney, etc. are tools, and that creative people will find ways to use those tools in interesting and creative ways, and that these boundaries will become blurred.
For now, I believe that AI generated images should be clearly stated as such, wherever they are used, even if put in other photos or whatever. For the record, I also believe that digitally altered photos should also be stated as such. Much of the furor comes down to honesty. People should not claim work as their own that they did not make or that they stole from someone else, whatever the method, and such behaviour should not be tolerated.
Image generated in Midjourney by Marian Bantjes.
If you want to understand more about AI, please read this article about the difference between AI and babies.
For more about US copyright and AI, you can watch/listen to this annoying video.
That article about Canadian law (“The Legal Status of Generative AI”) is super interesting, and is here.
Next, in Part 3, Edel Rodriguez and I will talk about all of this.
This essay was originally published on Marian’s blog, Marian Bantjes is Writing Again. You can keep up with her work here, or look through her archives on Substack.
Header image generated in Midjourney by Marian Bantjes, including the prompt “in the style of Albrecht Dürer.”
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.printmag.com/web-interactive-design/the-copyright-and-impact-of-ai/
|
[
{
"date": "2023/02/24",
"position": 30,
"query": "artificial intelligence graphic design"
}
] |
How AI is Transforming UI/UX and Product Design
|
How AI is Transforming UI/UX and Product Design- GeekyAnts
|
https://geekyants.com
|
[] |
So How Can Designers Get Benefited from These AI-powered Tools? · Designers working with AI can create their designs faster and at a lower cost due to the ...
|
With the recent launch of ChatGPT by OpenAI on November 2022, there is a hubbub going on in the designer and developer communities. The critical questions being asked are — How does ChatGPT affect the future of UI/UX and product design? What will be the new workflow for designers and creators?
There is also a fear that artificial intelligence-powered platforms will replace designers, developers, and creators.
I wanted to test this theory out. So, I started exploring AI tools that are in the center stage, like ChatGPT, Midjourney, and DALL-E 2, for one of my recent projects. I found that a few of them augmented my process, but not without some hiccups. This blog is a summary of my observations.
| 2023-02-24T00:00:00 |
https://geekyants.com/en-us/blog/how-ai-is-transforming-uiux-and-product-design
|
[
{
"date": "2023/02/24",
"position": 90,
"query": "artificial intelligence graphic design"
}
] |
|
Using Artificial Intelligence For Animation A How to Guide
|
Using Artificial Intelligence For Animation A How to Guide
|
https://unmistakablecreative.com
|
[] |
From motion graphics and facial animation to 3D animations and virtual characters, these powerful tools offer a wide range of possibilities for bringing ideas ...
|
The future of animation is already here with the emergence of Artificial Intelligence (AI). AI is revolutionizing the animation industry and opening up new possibilities for creative expression. AI and machine learning are collaborating with animation studios, transforming the way we think about the animation process. Human animators can now produce a wide variety of high-quality animation videos with ease.
Traditional animation videos were time consuming and expensive to produce. Creating professional-looking animations required extensive experience with 3d computer animation and other animation technology.
As the animation industry and animation technology continues to evolve, animators are increasingly turning to AI-powered tools to create high-quality animations with fewer resources and at an accelerated speed. From motion graphics and facial animation to 3D animations and virtual characters, these powerful tools offer a wide range of possibilities for bringing ideas to life. Professional-level animators can use them to streamline the design process while creating professional animations with a AI-powered video creation tool. While first-time animators can use an animation software tool to create professional-looking animations.
2. Using Artificial Intelligence for Animation
In addition to these established software tools, Artificial Intelligence (AI) animation generators have also emerged as key players in the animation industry. AI-powered tools such as Adobe Character Animator and Autodesk Motion Builder allow animators to quickly create high-quality animations with minimal effort. They provide basic plans and limited features that enable novice animators to bring characters to life without the need for extensive training. These AI-powered programs usually have a simple interface that makes it easy for beginners to get started quickly. Additionally, they offer additional features such as facial tracking, motion capture, and lip sync capabilities which can be used to create realistic animations with little effort.
However, the game-changer in the animation arena is the emergence of AI animation generators.
Getting started with AI animation generators is surprisingly simple and straightforward. With an intuitive user interface, most of these programs require minimal setup or technical knowledge, offer a wide range of features, making them suitable for both first-time animators and professional-level animators alike.
All you need to do is select from a variety of animation video templates or upload your own design, add images or designs, and customize the output according to your own preferences. Once you have customized the animation, all that’s left to do is hit generate and you can start creating animated characters and all kinds of animations.
RunwayML is an excellent AI animation generator that can create realistic animations from text inputs and transform static images into animated ones. It offers animators a powerful resource and provides advanced features for creating realistic animations. Additionally, it offers editing tools for video editing, tons of animation effects,image modification, and applying different styles of animation among other features.
Genmo : This is an another ai-based animation tool specializes in generating lifelike human animations from text inputs, enabling users to animate their textual ideas swiftly. It I can also do things like edit diffferent styles of animation and change styles of existing images through a simple chat interface.
: This is an another ai-based animation tool specializes in generating lifelike human animations from text inputs, enabling users to animate their textual ideas swiftly. It I can also do things like edit diffferent styles of animation and change styles of existing images through a simple chat interface. Kaiber.AI is an animation generator that creates lifelike animaons based on text prompts. It also offers additional features for flipbook and motion animation, allowing users to create different styles of animation quickly.
Furthermore, there are a range of effective tools available, such as Stable Diffusion, that have a user-friendly interface, allowing individuals to produce high-quality designs and AI-generated images. Ther are also many popular whiteboard animation software tools that aloow yout to create Whiteboard-based AI animations, explainer videos, and educational animations.
Some of these tools offer limited features on their basic plan, while the higher priced plans offer more advanced features and tons of animation effects. While these tools aren’t perfect they are democratizing human creativity and enabling everyone to create professional-looking animations regardless of their design experience or animation skills, opening up a wide range of creative possibilities for everyone. Many offer simple to use animation video templates, making it much easier to create custom animation characters and lifelike animations.
Additionally, for professional animators many of those tools enable them to developa a vast library of concept designs, motion graphics, visual effects, high quality images, and stunning animations. The advanced features of many of these tools streamline the design process and post – production, and more for professional animators. And they eliminate many of the time consuming tasks of manual animation
Choose the animation software tool or AI-powered video creation tool that works for you, play with them to create a variety of animations. Animation technology is changing the game.
3. The Role of AI in Character Animation
The use of artificial intelligence and advanced animation software has revolutionized the animation industry, allowing animators to create highly realistic animations and custom animation characters with intricate details and high-quality visuals. Additionally, many of these tools also make 3d computer animation possible. No longer having to rely on manual animation is a lifesaver for first-time animators
The process begins with establishing a basic plan and understanding the features available in traditional animation software, such as the design process, motion graphics capabilities, facial animation features, intuitive interface options, and other aspects that are relevant.
The process of using artificial intelligence (AI) for animation begins with creating a basic plan. It is important to understand the features available in traditional animation software, such as the design process, motion graphics capabilities, facial animation features, intuitive interface options, and other elements that contribute to the development of a realistic and imaginative animation.
After finalizing the plan, research will be necessary on AI algorithms and tools that can aid in the production of the intended custom animation chararacters. This may require the utilization of machine learning models or neural networks that can be trained to generate animations based on specific input parameters.
Case Study: Creating Custom Animation Characters for a Rap Parody Cover
Adobe character animator is an animation software tool that uses AI and has a wide range of features and an easy-to-use interface for beginner animators. The software allowed me to create 3D animations, facial animations, motion graphics, and bring my characters to life. Because Adobe character animator offers tons of animation effects, I was able to make high-quality animations with little time and resources.
After establishing the initial plan, I began the animation process for my project. Utilizing the AI-powered facial animation feature, I successfully brought my nephew’s character to life by generating authentic facial expressions and movements that effectively conveyed emotion. I used facet.ai train an image model with a wide variety of his pictures so they would look realistic when I brought them into my animation software tool..
Furthermore, the tool’s voiceover feature facilitated the generation of lifelike character voices through the use of AI technology, allowing for the seamless realization of my ideas with precision and efficiency.
I utilized the visual effects feature of the software tool to incorporate a diverse range of post-production effects, including lighting, color correction, and others. This enabled me to complete my project with professional quality outcomes efficiently.
By utilizing artificial intelligence in animation projects, individuals can create realistic animated videos without the need for professional animation skills. If you are interested in beginning your own creative journey with animation, do not hesitate any further.
Step 1: Rewriting the Lyrics with ChatGPT
I used Chat GPT to rewrite the lyrics of the song “Fresh Prince of Bel Air”. The prompt was to generate rap cover lyrics for the song. With some customization, I made the lyrics more personal for my 3-month-old nephew. It took a few tries to get it right. According to Kevin Kelly in a Wired article, AI requires human input. AI generators work best when used in partnership with humans.
Step 2: Engaging a Freelance Rapper through Upwork
After completing the lyrics, I hired a freelance rapper on Upwork to create a rap cover of the song using the new lyrics. The rapper was responsible for producing a rendition that captured the essence of the original song while adding a modern twist. After a few hours and a payment of forty dollars, I received a customized cover of “Fresh Prince of Bel Air”.
Step 3: Generating Perfect Characters with AI
The capabilities of AI in animation extend beyond just creating realistic characters; they also include generating ‘perfect’ characters – characters that align with specific aesthetic or thematic needs. For instance, AI can be programmed to generate characters of a certain style, ethnicity, or age group, according to the project’s requirements.
With the lyrics and audio ready, the next step was to create the characters for the animation. I used an AI tool, facet.ai, where I had trained an image model with pictures of my nephew. This allowed me to generate Pixar-style 3d animations for the characters. I input each character suggestion into this AI tool and requested variations on a few images. This ability to customize characters according to specific needs paves the way for new possibilities for professional looking animation.
Step 4: Learning Character Animator and Design Scenes
To bring these characters to life, I had to become familiar with Adobe Character Animator, a powerful tool that enables anyone with creativity to create professional animations.
To create an animation with multiple scenes and characters in Adobe Character Animator, I created a 10-day self-study curriculum. Following Scott Young’s Accelerated Learning Process, I broke down the complex task into smaller parts. This allowed me to focus on mastering one skill at a time, gradually progressing towards the end goal. By studying advanced features and practicing regularly, I was able to build up my proficiency in the software.
I used Chat GPT for suggestions on scenes, timing, and other important elements in the animation. This AI-assisted process helped me visualize the final product and plan the necessary steps. I had clear learning goals, identified resources for learning, and created a learning plan. I tracked my progress and made adjustments as needed. This step was time-consuming but crucial in utilizing AI for animation. It was a combination of self-directed learning, AI technology, and creative execution that made the animation come alive.
You can watch the video below. While it’s nowhere near the caliber of what a professional animator could produce, it’s amazing what 40 dollars and a bit of imagination enables you to do.
4. How AI is Shaping the Future of Animation
Machine learning and animation technology is changing the animation industry. AI animation generators use algorithms to automate animation. These tools can create animations quickly based on user input. Animation that used to take weeks or months can now be done in minutes.
AI-based animation generators have practical applications in the animation industry. These generators are currently being used to automate tasks like in-betweening, which helps create intermediate frames. This use of AI technology significantly reduces the workload for animators and improves the efficiency of the animation process.
AI tools like Chat GPT and Dall-E have been utilized in various innovative ways outside of traditional animation studios. For both beginner-animators and professional-level animators this makes it much easier to create a variety of animations.
AI technology is constantly advancing, leading to more sophisticated generators that offer users advanced features, customization, and control. This transformation is not only changing the process of animation creation, but also expanding who can participate in the animation industry, making it more accessible and inclusive.
Game development, explainer videos, and the design of virtual characters are just the begining. It won’t be long before we see individual creators using 3d computer animation to produce feature length films. The AI revolution in animation is just starting, and there are many exciting possibilities for the future. The ability to create high quality animation videos will be accesible to beginner-animators like never before.
5. Conclusion
In the field of animation, we are on the verge of a revolution, a renaissance of creativity. The era of manual animation is coming to an end.The availability of free tools for animators, 2D animation tools, and advanced AI, and evolution of animation technology is empowering individual creators like never before.
With a bit of imagination and creativity anyone can create lifelike animations without the headaches involved in producing traditional animation videos.
Soon all of us will have the ability to produce high quality animation videos at a fraction of the time and effot that was required for producing traditional animation videos.
This represents a significant departure from the past, when labor costs, the animation process, and the difficulty of creating realistic animations posed major challenges for those with limited animation experience or skills.
Advanced AI technology has become an equalizing force, enabling individuals to create diverse digital characters and intricate animations quickly and efficiently. Previously, such a task would have required a team and substantial financial resources. Now, anyone with a creative vision and access to animation tools, AI voice generators, and AI-powered voiceover features can bring their ideas to life, even at the level of an animated show like South Park.
The advancements in animation technology are transforming the industry and allowing creators of all backgrounds to bring their creative visions to life through various forms of animation.
In this era, individual creators have the opportunity to create complex animations and works that resonate with audiences, leaving a lasting impact on the animation industry.
However, it is important to remember that technology should be seen as a supplement to the story, rather than a replacement for it. The core of any animation lies not in its technical aspects, but in its narrative, which is crucial for creating realistic animations.
Advanced features and a vast library of tools can aid in creating complex animations and realistic characters, but they don’t eliminate the need for a well-crafted narrative. It’s the heart and soul of any animation, the element that truly engages the audience and gives the characters life.
So, let’s take this leap into the future of animation together. Whether you’re a person with limited animation experience creating your first animation video or a seasoned professional pushing the boundaries of what’s possible, the time has never been better to dive in. Harness the power of AI, leverage the advanced animation software at your fingertips, and let your creativity soar.
The future of animation is here, and it’s waiting for you to make your mark. It’s time to create lifelike animations, complex character animations, graphic designs, live-action videos, virtual characters, explainer videos, video content, and even a blog post if you wish. The possibilities are endless in this post-production era of animated videos, and all you need is a deep understanding of your narrative and the right animation software tool.
Meta Description: Discover how artificial intelligence is revolutionizing the animation industry. This guide will show you step-by-step how to use AI for animation and create stunning visuals.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://unmistakablecreative.com/artificial-intelligence-for-animation/
|
[
{
"date": "2023/02/24",
"position": 99,
"query": "artificial intelligence graphic design"
}
] |
The future of the Czech labour market
|
The future of the Czech labour market
|
https://www.aspeninstitutece.org
|
[] |
Model worked with local factors, top 10 global tendencies and an analysis of 131 professions in 31 sectors. Study named “The Future of the Czech Labour Market” ...
|
The Boston Consulting Group and the Aspen Institute Central Europe, a non-profit organization, presented a unique model of the Czech labor market development on Wednesday, August 24, 2022, at a press conference. Model worked with local factors, top 10 global tendencies and an analysis of 131 professions in 31 sectors. Study named “The Future of the Czech Labour Market” predicts the development of the labour market till the year 2030 and highlights the main changes that will affect the next decade. The study also provides specific proposals for the state administration, companies and employees to ensure that the Czech Republic will successfully cope with the upcoming challenges.
The full study with a detailed outlook to 2030 and the main trends that will affect the labour market in the next decade can be downloaded in the link below.
Download the full study HERE
Official press release
The Czech economy, except for the year 2020, has been growing in the range of 3-6% per year. Further GDP growth will be hampered, in addition to the current high inflation, mainly by the lack of an effective labour force (in simple terms, a combination of the education/skills factor and the gross quantity of labour). Apart from the already existing shortage of workers, which will continue to increase due to demographic developments, the structure of the labour market will change significantly: some positions will disappear and new ones will appear.
Unless the government, employers and employees take active steps to adapt to these changes, the Czech economy risks losing competitiveness, increasing unemployment and slowing growth.
| 2023-02-25T00:00:00 |
https://www.aspeninstitutece.org/news-article/the-future-of-the-czech-labour-market/
|
[
{
"date": "2023/02/25",
"position": 61,
"query": "AI labor market trends"
}
] |
|
WAC 182-513-1350 Defining the resource standard and ...
|
WAC 182-513-1350 Defining the resource standard and determining resource eligibility for SSI-related long-term care (LTC) services.
|
https://www.hca.wa.gov
|
[] |
For LTC services provided under the categorically needy (CN) program: In a medical institution, excess resources and available income must be under the state ...
|
This is a reprint of the official rule as published by the Office of the Code Reviser. If there are previous versions of this rule, they can be found using the Legislative Search page.
| 2023-02-25T00:00:00 |
https://www.hca.wa.gov/free-or-low-cost-health-care/i-help-others-apply-and-access-apple-health/wac-182-513-1350-defining-resource-standard-and-determining-resource-eligibility-ssi-related-long-term-care-ltc-services
|
[
{
"date": "2023/02/25",
"position": 81,
"query": "universal basic income AI"
}
] |
|
How to Start a Union in Your Workplace in 7 Steps
|
How to Start a Union in Your Workplace in 7 Steps
|
https://www.themuse.com
|
[] |
To demystify the process of forming a union, we've broken it down in seven steps. Start small: Talk to your coworkers.
|
It was the summer of 2020, and Tori Tambellini was working at a Starbucks in downtown Pittsburgh. She’d returned to work in-person during the COVID-19 pandemic—before vaccines were available but after some public health precautions had been lifted.
She felt unprepared to handle circumstances involving patrons who were unhoused or struggling with mental illness or substance use issues—difficulties that were exacerbated in the fallout from COVID-19. Tambellini says she even had to administer naloxone to reverse an opioid overdose. On top of how Starbucks handled the pandemic, she felt the company “just saw us as numbers.”
Late the following year, Tambellini’s fellow Starbucks baristas in Buffalo formed a union. Within a matter of months, Starbucks Workers United’s victory electrified workers across hundreds of Starbucks locations across the U.S.—including Tambellini. When she saw the success in Buffalo, it was clear the answer was unionizing. By the spring, she and her coworkers voted to join Starbucks Workers United.
The coffee workers are far from being outliers. During the pandemic, thousands of essential workers triggered a new era of organizing, as they realized the power they hold when they work together to improve their workplaces. Beyond the front lines, office workers began rethinking their relationship to their work. Millions quit their jobs during what became known as the Great Resignation. Others resorted to “quiet quitting.” Whether they’ve stayed or left, workers have become more “toxic aware”—recognizing their workplaces as unhealthy and realizing they deserve better.
The choice to unionize has grown increasingly common as workers transform their anger, frustration, and burnout into action. Though union representation still remains historically low, its popularity is on the rise. The number of workers represented by a union went up by 200,000 from 2021 to 2022, according to the Economic Policy Institute. And union election petitions to the National Labor Review Board rose by 53% between fiscal years 2021 and 2022—the highest increase since 2016.
Why would you organize?
Tambellini says it simply: “If you have a boss, you need a union.”
A union is, in its simplest form, a group of workers who’ve decided to come together to bargain with their employer as a group rather than individually to leverage their collective power and make their jobs better. Traditionally, a group of workers works with an established union whose staff have expertise in labor organizing and how to negotiate with management, though that isn’t always the case.
The goal is to create a contract—known as a collective bargaining agreement. Through persistence and teamwork in the contract negotiation process, a union can help you secure job protections, higher wages, improved benefits, and other workplace improvements specific to you and your industry. The contract created by employees and the employer might include salary minimums, break requirements, or mandated annual raises, just to name a few examples.
Perhaps you’ve considered unionizing but are unsure how. Only one in 10 U.S. workers are repped by a union, according to 2017 survey data, but nearly half of nonunion workers would join a union if they could. The Economic Policy Institute suggests the number might be even higher, given that public approval of unions rose to 71% in 2022—a 57-year high.
7 simple steps to start a union
To demystify the process of forming a union, we’ve broken it down in seven steps.
1. Talk to your coworkers.
The first step is straightforward: Talk to your coworkers and find out what they think about the workplace.
“You have to go to the simplest of questions,” says Michelle Gonzalez, a nurse in the Bronx and member of the negotiating team of her union, the New York State Nurses Association. “What do workers want? What’s important to this group of people?” adds Gonzalez, who was among thousands of New York nurses who went on strike earlier this year. You won’t be able to pinpoint the problems to tackle without asking. “You can’t identify what people want unless you talk to them,” she says.
Start with a couple coworkers you trust, says Tim Dubnau, the deputy director of organizing at the Communications Workers of America. You don’t want to reach out to everyone in your workplace right away, since you’d risk management finding out before you’re prepared to go public.
2. Find a union and build an organizing committee.
Find the right job for you Let The Muse match you with a company culture that fits your goals and values. First, select your career path: Marketing Sales Data Human Resources Customer Service Software Engineering Product Management Education Design and UX Administration How many years of experience do you have? 0 - 1 years 1 - 5 years 5 - 10+ years What company benefits are most important to you? Health Insurance Paid Vacation Remote Work Opportunities Dental Insurance 401k With Matching Vision Insurance Promote From Within Flexible Work Hours Personal Sick Days Performance Bonus Calculating your job matches... skip
Dubnau recommends contacting a labor union that could represent you early in the process. A traditional union—sometimes called a trade union or labor union—will ideally have the staff, resources, and expertise to kickstart the process and represent you in negotiations. “Hopefully, the union will hook you up with a union organizer who can walk you through the steps,” Dubnau says.
Then, form an organizing committee—the group of workers who are committed to unionizing and spearhead building broader support. The workers who would be in the union—typically non-managerial workers—are what’s known as the bargaining unit. A union organizer can help you figure out who would be a part of the bargaining unit in your particular industry or company.
As you talk with coworkers, you’ll want to get to know workers from a variety of backgrounds to make sure the organizing committee reflects the bargaining unit as a whole, Dubnau says, in terms of race, ethnicity, seniority, title, department, shift, and more.
3. Build support.
At Tambellini’s store in Pittsburgh, lead organizers put together a list of all the workers at the store so they could make a plan to talk with everyone. Each person was given a general assessment of how enthusiastic they’d be to join the union—from joining the organizing committee to holding anti-union perspectives. This would inform how workers would approach conversations—often short exchanges while on breaks, but also off the clock and outside of work. Tambellini says it helped that the coworkers trusted each other already.
Dubnau says getting the green light to unionize from 30% of workers within a potential bargaining unit is enough to legally trigger an election with the National Labor Relations Board (NLRB)—the governmental body that oversees the formation of unions. But in reality, securing support from at least 70% of your coworkers prior to going public is much safer.
“We don’t want an election,” Dubnau says. “We want to win the election.”
Gonzalez advises pinpointing skill sets and expertise as you work to build support—perhaps someone excels at writing and another is good at one-on-one conversions to spread the word. “Part of organizing is identifying: What skills do you have and what can you bring to the rest of the group?” she says. “When you’re organizing, it doesn’t depend on just one person. It depends on your ability to work as a group,” she adds, “and what you can accomplish as a group. That’s the beauty of collective power.”
4. Sign cards, file for recognition, and hold an election.
Once you’ve built enough support to go public, the next step is to sign union cards indicating that you would like to be represented by the union you’re working with for the purposes of collective bargaining. You or your union representative then files the union cards with the NLRB, usually electronically.
But this step requires more than just signing a card. “You can’t win anything in secret,” Dubnau says. “You gotta put yourself out there publicly.”
Perhaps the day you file for recognition you decide among your coworkers to wear a T-shirt in support of the union or change your Slack avatar, or submit a letter to management announcing your intention to form a union and highlighting key grievances. At unionizing Starbucks stores, for instance, Tambellini says she and her coworkers call the public announcements about unionizing their “Dear Howard” letters—referring to the CEO of the coffee shop chain. Using the power of social media or speaking to journalists has increasingly become an element of building support.
“That shows power,” Dubnau says. “It takes away the fear. It really is a little taste of what it’s gonna be like to have a union card in your back pocket.”
A month or so after filing for recognition, the NLRB holds an election either in-person or through mail-in ballots. In lieu of an election, your company can voluntarily recognize the union if they choose. While this is growing in popularity, it remains rare.
5. Prepare yourselves for union busting and retaliation.
Once management knows you’re organizing, keep an eye out for union busting. Hired firms may train leaders and middle managers to spread misinformation about how unions operate or instill fear in workers through retaliatory tactics. “It’s very tired and well-worn and predictable,” Dubnau says.
Watch out for sudden mandatory meetings, or “captive audience meetings,” often used to speak negatively about unions or attempt to mislead workers. Companies rely on these meetings to contest union campaigns. Promises to make improvements or attempts to appease workers through small or symbolic changes are signs the company may be trying to persuade you that a union is unnecessary. Stricter rules or other unexpected changes in your workplace—like sudden schedule changes or surveillance of communications—are also signs of union busting. Management may also threaten to shut down the business—and some do.
Collective bargaining without fear of retaliation is protected under the National Labor Relations Act. If you think the law is being violated, you can file an unfair labor practice charge with the NLRB, which triggers a process that can lead to a trial. But the truth is the law won’t always protect you.
Sometimes retaliation can result in workers—especially organizers or key leaders within the union—getting fired. Although illegal, companies hope this level of retaliation will quash union activity.
When Tambellini was fired last summer, she was shocked. The company alleged she clocked in nine minutes before officially beginning work—but the timing was peculiar since she was among the union campaign leaders, she says. Now, she’s organizing with the union and fighting for reinstatement with other fired Starbucks workers in an unfair labor practice trial. (Starbucks has denied any discipline or firing for any workers who are “supporting, organizing or otherwise engaging in lawful union activity.”)
Though there are risks, Dubnau and Tambellini agree there’s power in numbers, and solidarity is crucial.
6. Form a bargaining committee and negotiate a contract.
Once you’ve won an election, it’s time to actually negotiate with your bosses about what changes you want to see. The bargaining unit—everyone who will be in the union—should first elect a bargaining committee. These rank-and-file workers will be the key group to represent the unit in meetings with management.
Dubnau recommends creating a bargaining survey. Find out the specifics of what workers want and rank what’s most important to guide priorities. For example, you and your coworkers may want to fight for an increased hourly wage, basic healthcare benefits, parental leave, mandated breaks, or minimum staffing requirements.
Gonzalez says gathering survey data from nurses on their priorities was critical to organizing effectively—even in an already-established union. One example Gonzalez shared: If several workers aren’t getting breaks and don’t have enough time to use the bathroom, resulting in frequent urinary tract infections, that’s a concrete problem organizing can solve. But you won’t be able to pinpoint the problems without asking. “A lot of the work is simply having conversations,” she adds.
When the bargaining committee and management determine a tentative agreement, a meeting is held to explain the contract to the rest of the unit. Then, the unit votes to approve the contract or send it back to the bargaining table.
A majority of collective bargaining agreements (a.k.a., contracts) last for three years, but could be one year or even five years, according to Dubnau. However, he considers agreements longer than three years “unsettling.” Why? High inflation could outweigh a 2% annual pay raise agreement, for example, meaning wages aren’t keeping up with the cost of living.
7. Make a plan to maintain momentum.
Prepare yourself for a potentially arduous process. You might spend months organizing, and then many more months negotiating before you reach that coveted contract. The average time it takes for employers and new union workers to finalize their first collective bargaining agreement is 465 days, according to a Bloomberg Law analysis.
“We’re really playing the long game here,” Tamebellini says of contract negotiations with Starbucks, where management and baristas are at odds over holding hybrid bargaining sessions. “Getting everyone to sign the card—that’s the first hard step. The next hard step is winning your election. But I think maybe the hardest step is keeping up the enthusiasm and keeping morale up while you are waiting for that contract.”
If management isn’t negotiating with you in good faith or receptive to the demands, you can escalate pressure with a variety of actions, such as sharing information on social media or staging internal actions to show bosses what you’re unwilling to compromise on. The unit can also organize walk-outs or, in a last resort, authorize a strike.
Dubnau notes strikes are exceedingly rare on a first contract. But they can be effective. Thousands of New York City nurses—including Gonzalez—went on strike earlier this year during a contract renewal negotiation. The three-day action culminated in major wins for the nurses: a nearly 20% pay increase and increased staffing. (Following the end of the strike, Montefiore’s president, Dr. Philip Ozuah, said the center is “grateful for the dedication and commitment of our nurses who have served through very challenging circumstances over the past several years.”)
But Gonzalez notes the lead-up to the strike took years, and, at times, momentum faded. “When it dies down, what do you do? You can’t just lie on the floor and say, ‘OK, no more workers’ rights.’ I think you have to come up with a new plan,” she says.
When the path forward seems impossible or exhausting, Tambellini adds, you have to “remind people what they’re fighting for. Keep them aware of the issues.” The journey is a long one. But forming a union can lead to a safer and more secure work environment—one that you, your current coworkers, and future employees deserve.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.themuse.com/advice/how-to-start-a-union
|
[
{
"date": "2023/02/25",
"position": 40,
"query": "AI labor union"
}
] |
Concerns rise over treatment of human workers behind AI ...
|
Concerns rise over treatment of human workers behind AI technology
|
https://www.pbs.org
|
[
"Lisa Desjardins",
"Andrew Corkery"
] |
Thought by many to be powered only by computers, AI often relies on a massive human workforce, and there are significant questions about the treatment of those ...
|
Lisa Desjardins:
Artificial intelligence comes in many forms, and whether you realize it or not, it is now woven into things we see and touch every day. Things like Googling anything or tagging a friend on Facebook, filing your taxes, using TurboTax, and even using your phone's speak to text feature.
AI also is all over the headlines these days as societies confront the growing technology. This week, the U.S. Copyright Office ruled that AI images cannot be legally protected. China launched a crackdown on the popular AI program ChatGPT. And the New York Times recently published a rant by Microsoft's new AI chat feature, which tried to convince the writer to leave his wife. Thought by many to be powered only by computers, AI often relies on a massive human workforce, and there are significant questions about the treatment of those workers.
Joining us now to discuss is Sonam Jindal with Partnership on AI, a nonprofit coalition committed to the responsible use of artificial intelligence.
I want to start with just understanding the basics here. What are these jobs exactly that people are doing that keep artificial intelligence working?
Sonam Jindal, Program Lead, Partnership on AI: Yeah, absolutely. Well, artificial intelligence products and models require massive amounts of data. So to make it very simplistic, a computer system or an AI algorithm doesn't know on its own whether or not something is a cat or a dog. It needs to be told what is a cat or a dog? So there are people who go through images and label them cat, cat, dog, dog and over time, the algorithm can understand it. And that is true of all AI models. All of them require data and humans to look at that data and classify it.
| 2023-02-25T00:00:00 |
2023/02/25
|
https://www.pbs.org/newshour/show/concerns-rise-over-treatment-of-human-workers-behind-ai-technology
|
[
{
"date": "2023/02/25",
"position": 1,
"query": "AI workers"
}
] |
It is the dawn of a new ai ART era - Art of Loving Italy
|
It is the dawn of a new ai ART era
|
https://www.artlovingitaly.com
|
[
"Melissa Muldoon"
] |
... designer has requested the AI to reproduce. Image Credit: Melissa and ... graphic design tool. Once again, new things are looming large on the horizon ...
|
Living in harmony with new technology
So, this designer/illustrator has concluded that she can live in harmony with DALL•E art creator. She realizes she is on the threshold of a new era. And just like the first time she turned on a Mac computer and booted up Adobe’s Illustrator and Photoshop programs, events that also changed her world forever (in a FANTASTIC way) DALL•E art creator has the same potential to be as important a graphic design tool.
Once again, new things are looming large on the horizon for artists. DALL•E art creator is the next step in the art world, and there will be no going back. It will be an innovative and cutting-edge design application for illustrators. Still, it cannot replace the unique combination of creativity, intuition, and technical skill that professional illustrators possess. This graphic designer is comforted by the thought and excited to see what will come next!
Artist’s note. Caution: Playing around with DALL•E art creator is an easy way to go down a deep rabbit hole and lose many hours of your life. The results are never quite perfect, and it takes a bit of a learning curve to give the proper instructions to “the machine” to produce the images you want. Still, I was amazed by the accuracy of the scene settings when I told the AI to create illustrations set in specific cities in Italy, Arezzo, Florence, Orvieto, Lucca, and Montepulciano. I downloaded the images I liked the best and took them into Adobe Illustrator and Photoshop, where I continued to manipulate the images to fine-tune them manually.
| 2023-02-26T00:00:00 |
2023/02/26
|
https://www.artlovingitaly.com/ai-generated-art-illustrations-graphic-design-effects-future-artists/
|
[
{
"date": "2023/02/25",
"position": 96,
"query": "artificial intelligence graphic design"
}
] |
25+ Incredible Machine Learning Statistics [2023]
|
25+ Incredible Machine Learning Statistics [2023]: Key Facts About The Future Of Technology
|
https://www.zippia.com
|
[
"Feb.",
"Fact Checked",
"Cite This Webpage"
] |
The U.S. machine learning market is projected to grow from $100 million in 2018 to $935 million in 2025. The demand for employees with AI and machine learning ...
|
Research Summary. Machine learning and artificial intelligence are transforming the world of technology both in the private world and in business. Here are the key statistics on machine learning in business:
61% of marketers say machine learning and AI are the number one priority in their data strategies.
While global employment of machine learning engineers is projected to grow at a rate of 22% between 2020 and 2030.
The global machine learning industry is projected to have a CAGR of 38.8% between 2022-2029.
73% of business leaders believe machine learning will double productivity for their employees.
For further analysis, we broke down the data in the following ways:
Adoption | Benefits | Trends and Projections | Customer Experience
The global CAGR of the machine learning industry is about 38.8%, and its value is anticipated to reach almost $209.91 billion by 2029.
As of 2022, the global machine learning industry is worth an estimated $21.17 billion.
In 2018, the U.S. machine learning market was worth only $100 million.
North America follows closely, however, with 44.05% of the market share. Asia-Pacific, Africa, and South America share the remaining 11.08%.
Generating customer insights and intelligence, increasing long-term customer engagement, and generating financial insights are the three next most popular uses.
Improving customer experience and automating processes are the top two uses of AI and machine learning.
Most use AI for product or service development (45%) or service operations (43%).
50% of companies use AI in at least one business function.
43% of these companies also said that AI and machine learning initiatives are more important than they initially thought, and about 25% said they wished they’d made them a priority earlier.
64% said that this was one of their top priorities in 2020. Many survey respondents pointed to the COVID-19 pandemic as one of the motivating factors for changing priorities.
In 2021, 76% of surveyed companies prioritize AI and machine learning over other IT initiatives.
More specifically, 73% of those business leaders believe that productivity will double by 2035 thanks to AI, and only 39% of employees also believe this.
However, only 55% of their employees share this belief.
89% of surveyed company leaders believe AI will increase their employees’ performance and productivity by 2035.
Marketing and sales saw the highest average increase at 79%, followed by strategy and corporate finance that saw a 73% average increase.
Companies that adopted AI in at least one business function saw an average revenue increase of 66% within those functions.
However, as far as making these beliefs a reality, only 50% of organizations have incentives to invest in machine learning and automation.
More specifically, 85% of executives believe that machine learning and automation will give their companies a competitive advantage.
74% of surveyed company leaders believe their organizations could better meet their goals if they invested more in machine learning and automation.
In addition, these systems also save human salespeople time and energy, allowing them to create even more revenue for the company.
These surveyed companies have also seen machine learning create 40-60% cost reductions and an increase of over 50% leads and appointments.
Companies report that AI and machine learning have reduced their sales call times by 60-70%.
The number of smartphone owners who use AI-powered voice assistants daily increased by 23% from 2018 to 2020.
AI-based startups received $18.5 billion in venture capital in 2019, and by 2023, total investments in this sector are expected to reach $100 billion.
The demand for employees with AI and machine learning skills is growing at a CAGR of 71% from 2020 to 2025.
The U.S. machine learning market is projected to grow from $100 million in 2018 to $935 million in 2025.
Another 34% say they’ve never interacted with AI, and 32% say they aren’t sure if they have or not.
84% of survey respondents have interacted with AI, but only 34% of them believe they’ve interacted with AI.
These respondents would prefer a hybrid over a system with only humans, as 35% of consumers, millennial or otherwise, are concerned about losing a human touch via shifting totally to AI. This is why so many are willing to pay for a hybrid system that gives them the benefits of both AI and humans.
AI can save sales representatives and customers time and energy by answering their questions and solving their problems quickly and efficiently, and companies are starting to take advantage of this by implementing more and more of this technology.
An estimated 85% of customers’ relationships with companies are handled without talking to a human.
What is machine learning used for? Machine learning is used for a variety of everyday digital tasks. These include: Email filters
Search engines
Personalized ads
Voice recognition
Voice assistants
Banking alert software Machine learning is simply an algorithm that allows programs to take in new information and produce a result based on that information. For example, in an email filter, if the machine learning system doesn’t recognize the sender and sees some suspicious links in it, it will automatically move it to the spam folder. Machine learning can also be used for more advanced artificial intelligence applications such as autonomous cars or robots.
What is the difference between AI and machine learning? The difference between AI and machine learning is that machine learning is a subset of AI. AI is the broad concept of a technological machine that simulates human intelligence, while machine learning is a type of AI where a machine learns from past data on its own. The result of these differences is that machine learning systems are designed to perform one data-based task on their own, and AI systems are designed to perform various tasks on their own. Examples of AI include voice assistants, online chatbots, and online gaming. Examples of machine learning include Google’s search algorithms, suggested posts on Facebook, and email filters.
Will machine learning replace statistics? No, machine learning will not replace statistics. Statisticians focus on taking a large amount of data and separating it into smaller sets of data, also known as “statistics.” Their goal is to figure out how to collect and translate data into usable information. The goal of machine learning, on the other hand, is to create predictions based on past data. These predictions include things like whether or not a bank transaction is legitimate or whether or not a customer is going to want to see a specific ad. While machine learning and statistics both use data, they use it for different things, which means one will not replace the other.
What are examples of machine learning? There are several examples of machine learning, as it’s become interwoven with our day-to-day lives. Some of the most well-known examples include: Image Recognition. If you’ve ever wondered how Facebook so accurately knows when someone tags you in a photo, the answer is machine learning. Over time, the software learned to identify your face through other images you were tagged in, as well as your profile photos.
Speech Recognition. The only reason Amazon Alexa or Apple Siri is able to understand you so well is through machine learning. With the use of talk-to-text programming, the system can better understand language over time.
Medical Diagnosis. Many bots are able to learn various symptom patterns and use image recognition to diagnose illnesses.
Extraction. Machine learning can be used to extract structured information from unstructured data. This can be useful for massive companies that need to extract useful information from their customers.
What programming languages are used for machine learning? There are at least five programming languages commonly used in machine learning. Each has its advantages and disadvantages, so it’s hard to claim any as being superior over the others. Here are the top five: Python. This is the most widely used programming language for machine learning. It has extensive libraries of information to work with, high code readability, and flexibility but can fall short in more complex scenarios.
R. This programming language is also common for machine learning, as its open-sourced nature makes it highly cost-effective. It’s also easy to learn, but with the downside of slow speed and potentially poor security.
Java and JavaScript. Mostly popular among those who already used Java prior to getting into machine learning, this programming language is good for starting new projects from scratch and has great third-party access. However, java can be slow and requires a lot of memory space.
Julia. This programming language is fairly new and has exceptionally high performance. However, it’s not as common and takes up a lot of memory.
LISP. By far the most efficient and flexible machine learning language for solving specific scenarios, LISP also comes with poor learnability and readability.
Is machine learning hard? Machine learning can be hard, depending on your skillset. First and foremost, programming can be difficult to learn no matter what type of code you’re going to work with, and machine learning adds another layer of complexity on top of that. Further, even for those who understand programming languages, creativity, experimentation, and tenacity are required. That makes it an unideal starting point for beginners. However, you shouldn’t be dissuaded from trying. The best thing you can do to improve your coding skills is to consistently practice machine learning techniques.
| 2023-02-26T00:00:00 |
2023/02/26
|
https://www.zippia.com/advice/machine-learning-statistics/
|
[
{
"date": "2023/02/26",
"position": 7,
"query": "machine learning job market"
}
] |
Paramount Roles of ChatGPT in Sustainable Business ...
|
PARAMOUNT ROLES OF CHATGPT IN SUSTAINABLE BUSINESS TRANSITION
|
https://paramountecologicalresources.com
|
[
"Egwumah Fa",
"Paramount Ecological Resources",
"Egwumah F.A."
] |
Inclusion, Diversity, and Equality (DEI):The development of AI is going to be a huge aid to HR managers in enhancing diversity and inclusion in the workplace, ...
|
This website uses cookies to ensure you get the best experience on our website.
Accept
| 2022-08-05T00:00:00 |
2022/08/05
|
https://paramountecologicalresources.com/paramount-roles-of-chatgpt-in-sustainable-business-transition.html
|
[
{
"date": "2023/02/26",
"position": 89,
"query": "workplace AI adoption"
}
] |
Report Recommends Transparency When Using AI in Hiring
|
Report Recommends Transparency When Using AI in Hiring
|
https://www.shrm.org
|
[
"Nicole Lewis"
] |
An organization run by AI is not a futuristic concept. Such technology is already a part of many workplaces and will continue to shape the labor market and HR.
|
Designed and delivered by HR experts to empower you with the knowledge and tools you need to drive lasting change in the workplace.
Demonstrate targeted competence and enhance credibility among peers and employers.
Gain a deeper understanding and develop critical skills.
| 2023-02-26T00:00:00 |
https://www.shrm.org/topics-tools/news/technology/report-recommends-transparency-using-ai-hiring
|
[
{
"date": "2023/02/26",
"position": 35,
"query": "AI labor market trends"
},
{
"date": "2023/02/26",
"position": 9,
"query": "artificial intelligence employers"
},
{
"date": "2023/02/26",
"position": 8,
"query": "artificial intelligence hiring"
}
] |
|
AI is Transforming Investing. What's in it For Investors?
|
AI is Transforming Investing. What's in it For Investors?
|
https://www.wealthenhancement.com
|
[] |
... labor market in 2023. Fed's grade on: Stabilizing inflation. Our advisors ... Get the latest wealth management tips and trends from our library of articles and ...
|
AI has been called a disruptor, a game-changer, and the next frontier in investment management. Every day, analysts use AI models to manage risk, inform credit decisions, and automatically detect fraud. One of the most popular uses of AI is in portfolio modeling, where algorithms use historical data to make predictions about the future performance of various asset classes.
AI is becoming increasingly important to financial firms for managing risk and improving operations and compliance. But what are AI’s potential benefits for individual investors?
AI's transformation of every industry will create innovative new companies and exciting opportunities for investors.
Financial advisors use AI tools to generate insights and customize client portfolios more effectively.
AI has great potential to help alpha-seeking investors manage risk and model long-term performance.
AI’s ability to analyze large, unstructured datasets is increasing our predictive power in several ways. While we can't predict the future, we can use AI to improve our predictive capabilities and decision-making. Wealth Enhancement Group has been exploring different types of AI designed to amplify human intelligence rather than replace it. Equipping our experienced financial advisors with more powerful predictive tools represents a unique opportunity, with an eye on improving returns, managing risk, and creating improved client experiences.
Enter the Swarm
Swarm AI is a class of AI that uses the collective behavior of swarm animals (such as ants, birds, and bees) as inspiration for its algorithms. These animals solve problems as a group, using their intelligence to implement agile solutions actively. Swarm AI, a collaborative platform developed by Unanimous AI, uses an algorithm trained by data informed by group behavioral dynamics. This technology allows individuals to answer questions collectively, with the AI reacting and facilitating the decision-making process to encourage an outcome. Then, another AI model assesses the group's behavior and assigns a "conviction score" to gauge their confidence in the decision.
Wealth Enhancement Group is always looking for ways to empower our advisors to provide more personalized, responsive service. To that end, we tested Swarm AI with a small team of our expert advisors. We asked them a series of questions about 2023's outlook, using the Swarm AI platform to collect insights. This article highlights our results.
2023 Economic Outlook
The first topic our advisors addressed was the general economic outlook for 2023. Through the following questions, we used AI to gauge our advisors' sentiments effectively and gleaned some insightful results. It is important to note that the decisions and answers presented in this article should not be relied on as financial advice. This article aims to demonstrate one way AI can help amplify human intelligence in financial advising and give our advisors the chance to express their opinions.
We asked our advisors, what is the biggest risk the stock market will face in the next six months?
Recession
Weak corporate profits
Inflation
Geopolitical turmoil
Employment
Federal Reserve intervention
To kick off our session, we asked members of our Roundtable™ team of advisors the biggest risk stocks would face in the first two quarters of 2023. Using Swarm AI software to track the group's collective sentiment, they answered with “Weak corporate profits.” The heat map below visualizes the amount of support each answer received.
Figure 1: Our panel speaks about weak corporate profits are the biggest challenge to stocks
Image
Interestingly, our advisors chose weak corporate profits as more impactful than inflation or employment. They ultimately suggested that weak corporate profits may lead to a decrease in investor confidence and a price decline. In a market environment like this, our advisors prioritize keeping a close eye on the companies' earnings reports in their client's portfolios.
What are the odds the U.S. will enter a recession in the next 12 months?
Given the unrelenting impacts of inflation, continued Federal Reserve rate hikes, and global geopolitical turmoil, our advisors collectively decided there is a 75% chance that the U.S. will enter a recession in 2023. Our team landed on this pessimistic outlook with a reasonable level of confidence, which indicates that investors should account for this possibility as we progress through the year.
If we do enter a recession in the next 12 months, how long is the recession most likely to last?
When we asked advisors how long a 2023 recession could last, they responded with a high conviction that the recession would last only up to 6 months. The graphical data of our advisors' deliberations show that the most popular responses were between 2 to 3 quarters.
Using GDP decline as our benchmark, we asked advisors, how severe will this potential recession would be?
Our advisors decided a shallow (1-2%) recession is most likely, as shown in the heat map below.
Figure 2: Our panel speaks that the recession will likely be shallow.
Image
Our advisors predicted a 75% chance that 2023 will yield a shallow (1-2%) recession lasting about two financial quarters.
How likely is a "stagflation" scenario for the U.S. economy in the next six months?
The dreaded "stagflation" scenario combines slow economic growth, high unemployment, and inflation. Our advisors said stagflation is unlikely during the first two quarters of 2023. While these conditions regularly occur at different times throughout economic cycles, it’s less common to see an alignment of all three, especially during a tight employment market.
Which major equity market will perform best in the next 12 months?
Our advisors initially needed help to reach a consensus when we asked this question. They were confident in their positions, to the point that they could not come to a clear answer as a group, highlighting the truth to the statement markets are unpredictable. When we asked the question again, they suggested Emerging Markets as the strongest performer but with only 30% conviction.
Figure 3: Our panel speaks, selecting Emerging Markets as the strongest performing market.
Image
Perhaps the uncertainty of our advisors' consensus reflects a fundamental belief in portfolio diversification and not overweighting any one market or region.
Fed Report Card
The Fed plays a crucial role in our economic system, and its policies significantly impact individual investor portfolios. In this series of questions, we asked our advisors to "grade" the Fed, from A through F, on its performance in driving the U.S. economy.
We asked our advisors…how would you grade the Fed’s efforts in managing the following issues?
Fed’s grade on: Employment
Our advisors' grade? A C+, with an 84% conviction rate, shows high confidence. While the unemployment rate may currently be relatively low, this grade may change along with the rate hikes we've recently experienced if the increases lead to a softer labor market in 2023.
Fed's grade on: Stabilizing inflation
Our advisors' grade? A D, with a 71% conviction rate. The Fed's rate hikes seem to be working to lower the blistering rate of inflation.
Fed’s grade on: Avoiding a Recession
Our advisors' grade? Another D, with an 89% conviction rate, is our experiment's highest conviction rate. Advisors needed to be more impressed with the Fed's actions to avoid a recession. The need to rein in inflation has forced the Fed to raise rates very quickly, negatively impacting investor portfolios and boosting the likelihood of a recession.
Wealth Enhancement Group: How It All Fits Together
We asked our advisors… what investors value most in their Financial Advisor?
Although most of the answers below received some level of support:
Inspire confidence
Clear communication & explanations
Professionalism
Personal attention
Detail-oriented
Since their time is valued
Our team of advisors landed on clear communication & explanations as their best answer. A financial advisor is responsible for analyzing and interpreting various financial information. Clear communication about their findings makes it easier for an advisor to help their client's financial plans stay on track.
Finally, we asked our advisors… which investor action should be the HIGHEST priority now?
Trim expenses
Pay down debt
Boost emergency fund
Avoid impulsive decisions
Explore alternative investments
Consider available tax efficiencies
In the uncertain macroeconomic environment, our advisors considered what investors should prioritize in 2023. While exploring alternative investments and considering tax efficiencies were popular among some of our advisors, the winning answer was to avoid impulsive decisions. Our advisors know it can be easy to make emotional and financial decisions in difficult times. It's of the utmost importance to avoid this type of decision-making. Fortunately, our experienced advisors are here to help with that!
About this research
Our goal in this exercise was to convene Wealth Enhancement Group advisors with Swarm AI technology to gather insights and unlock the group's collective intelligence. We evaluate this technology and others for its capabilities as predictive decisions and forecasting tools.
Swarm AI® technology, developed by Unanimous AI and used by our advisor teams for this article, employs real-time human input and AI algorithms modeled after swarms in nature. Nature shows us that groups can produce insights that greatly exceed the abilities of any individual member. Research indicates that Swarm AI technology enables human groups to amplify their intelligence, an intriguing proposition for financial services.
Swarms have generated insights for the Washington Post, TechCrunch, TIME, Forbes and a host of Fortune 500 companies. More published research using Swarm® is available on the Unanimous AI website.
For more information on leveraging the power of Wealth Enhancement Group's UniFi™ process and applying our collective intelligence to your financial plan, set up a free, no-obligation meeting with an advisor today.
| 2023-02-26T00:00:00 |
https://www.wealthenhancement.com/blog/ai-is-transforming-investing-what-s-in-it-for-investors
|
[
{
"date": "2023/02/26",
"position": 59,
"query": "AI labor market trends"
}
] |
|
AI Is Revolutionizing Recruiting Strategy. Here's How
|
AI Is Revolutionizing Recruiting Strategy. Here's How
|
https://jobiak.ai
|
[] |
What's more: recent developments in AI recruitment are revolutionizing job posting performance, further enabling Google to dominate the online recruitment space ...
|
It’s no secret that Google is positioning itself to disrupt the $200B recruiting strategy industry and become a job posting conglomerate.
By leveraging its vast resources and big-data reservoirs, Google is using its enormous job taxonomy and AI recruitment search algorithms to dramatically improve candidate traffic and relevancy for recruiters.
Today, seventy-three percent of job seekers start their job search on Google, totaling over 300 million monthly searches. For the world of HR, there is no central job listing location as powerful, comprehensive, and complex as Google for Jobs. It is unprecedented.
What’s more: recent developments in AI recruitment are revolutionizing job posting performance, further enabling Google to dominate the online recruitment space & recruiting strategy.
So recruiters must be racing to Google for Jobs to post their job listings and experiencing incredible results – right?
Not quite.
Google for Jobs hasn’t gotten as much attention as one might think in both the SEO and HR communities. And despite having spread to global markets, it remains largely unknown how vast of a resource Google’s job compilation database and SEO algorithms are.
The Mystery of Google for Jobs
How to get job postings to rank on Google is a mystery to many recruiters.
Recruiters who are rarely technical are now required to add complex HTML schema tags to their job posts, and without any technical resources on their team that knows code, this can be daunting.
For example, recruiter solutions to date have involved relying on restrictive Application Tracking Systems, expensive developer API integration tools, or even paying to post each job to an external job board that has integrated with Google for Jobs.
Each of these options are either cost-prohibitive at scale, or create a less-than-optimal candidate experience.
For many recruiters who have gone through the hurdles of figuring out how to post, they tend to not have much understanding of the complex SEO that goes on behind the scenes. Savvy talent acquisition pros know that optimizing the keywords and avoiding these mistakes in the job posting is essential.
Even then, jobs may not be showing up on the first pages of Google search results. Many HR teams just aren’t seeing value and are losing faith in Google for Jobs as a serious tool for sourcing candidates, despite the plethora of untapped opportunities and insights that can be found within it.
In this article, we’ll geek out on the SEO behind the scenes of Google’s complex job posting taxonomy, and how intelligent and disruptive hiring technologies such as Jobiak are using the power of Artificial Intelligence to address long-standing pain-points in candidate identification, engagement, and on-boarding.
There is a small, yet rapidly growing segment of recruiters who are arming themselves with the knowledge of how keyword optimization technologies work, and as a result are experiencing a 5x in job ranking improvement and relevancy.
Behind the Scenes of Google for Jobs SEO
When it comes to understanding the SEO and job posting taxonomy behind the scenes with Google, it is critical to understand what works and what doesn’t work within it.
One must know what job keywords are more effective, and to know what job titles are more common and efficient. This is a new area of job SEO that has yet to be fully understood or capitalized upon by recruiters.
So how does Google for Jobs work, exactly?
Google has built a “job family taxonomy” that aggregates similar job titles into families of jobs to build a truly useful, searchable, “universe” of jobs, organized by discipline and functional domain.
Google does an incredible job at understanding search terms & recruiting strategy, keeping track of all past searches to get smarter, and using smart NLP algorithms to decompose searches into meaningful queries and then pulling the best possible results.
Of course, applying this expertise to job search is a natural evolution. Under the covers of Google’s job taxonomy is an engine that tries to understand a job through it skills.
As the chart below shows, the engine actually reads through job descriptions and tries to find the job you’re looking for – rather than just look at the title (which is what most job searches do).
This results in a far better search experience.
| 2019-12-03T00:00:00 |
2019/12/03
|
https://jobiak.ai/ai-is-revolutionizing-online-recruitment-and-job-posting-performance/
|
[
{
"date": "2023/02/26",
"position": 98,
"query": "AI labor market trends"
},
{
"date": "2023/02/26",
"position": 35,
"query": "artificial intelligence hiring"
}
] |
Can ChatGPT become your new, free employee? -
|
Can ChatGPT become your new, free employee?
|
https://egn.com
|
[] |
The potential benefits of such a shift are numerous, including increased efficiency, reduced costs, and the ability to scale output in ways that would be ...
|
Better than most writers, ChatGPT is set to be the future of text production, but do not let it run unattended
Me, a human: “Hey ChatGPT Can you write an introduction to an article about ChatGPT replacing humans in text production?”
ChatGPT: “Sure!
As technology continues to advance, more and more industries are finding themselves disrupted by the rise of automation and artificial intelligence. One area that has seen significant advancements in recent years is natural language processing (NLP), and specifically, the use of advanced language models like chatGPT. These models, trained on massive amounts of data, can generate human-like text with remarkable accuracy and fluency.
With this progress in NLP, many experts are now asking whether chatGPT and similar models might soon be able to replace human writers in text production. The potential benefits of such a shift are numerous, including increased efficiency, reduced costs, and the ability to scale output in ways that would be impossible for humans. However, there are also concerns about the impact of automation on jobs and the potential for bias in the output of these models.”
It sounds great, right? The new ChatGPT is extremely hyped these days and for a reason. Because, as you can read above, it is able to produce texts that are both well-written and precise.
But what is this machine, what can we use it for, and will it eventually take our jobs? To answer these questions, I have interviewed Johannes Bjerva. He has a PhD in computer science and works as an Associate Professor at the Department of Computer Science at Aalborg University Copenhagen. His research focusses on Natural Language Processing (NLPs) such as OpenAI´s new ChatGPT, and he currently leads a large project on multilingual NLP funded by the Carlsberg Foundation.
Johannes, what is ChatGPT? And how does it work?
“ChatGPT is a piece of technology, that is based on what we call a language model. The AI has been taught everything by first reading billions of words, and next through interactions with humans. In the early stages of training, when asked about something, the responses would not have been natural at all, but after millions of interactions with humans, this quality as increased, to the point where interactions are deceivingly natural. While this might seem similar to how a child learns language, there are considerable differences – for instance, where a 13-year-old has a high command of language after only hearing about 100 million words, an artificial intelligence needs billions of words to reach anything resembling this level.”
What potential lies inside this machine for corporations?
“The obvious way to use it is in terms of text production. Almost every part of every corporation writes something at a daily basis. This might be e-mails, articles, SEO copywriting, customer service and internal communications. And especially in copywriting, ChatGPT can be useful.
Will it replace many people’s jobs already in the near future?
“Of that, I am not so sure. Because this machine needs to be supervised. You can not just let it write whatever it wants and let it be published or send. With earlier versions of ChatGPT we saw a lot of examples, where the robot wrote racist and abusive things. And it is still possible for this to happen. The creators from OpenAI are trying to fix these screw-ups when they notice them. But it is like a cat and mouse game, where new ways to trick it is constantly found. Until the robot becomes completely reliant, you will always need to include a human touch. Everything needs to be supervised, and you will have to ask yourself, if the time spend supervising exceeds the time it will take to write the text on your own.”
Is it even possible to recognize texts written by ChatGpt, when stumbling upon them on the internet? And if you use it to create SEO content, will Google punish you for having AI-generated texts?
“Well, the language model has become more complex, and the more complex it gets, the more human-like it gets. As long as the texts it generates are helpful to it´s readers, I don´t think Google has any problem with it.”
Does the arrival of the ChatGPT reveal the coming of a new era in technology?
I don´t think, it will cause a revolution right away. It won´t just take people´s jobs in an instant. Journalists, for example, their job of actually writing an article takes up maybe 20% of their time. The rest is research and other things. But it might become a factor, that will restructure many people´s jobs. I, personally, hope to do a lot more scientific research on this type of AI language models, and am open to industrial collaborations in this direction. It will especially be interesting to learn, how to integrate it with specific companies’ databases. This way it will be much more competent as an asset to the company.”
As any new technology, it takes time to adapt and understand it´s functions. If you want sparring and inspiration on how others might incorporate new inventions in their work, check out EGNs professional peer-groups.
| 2023-01-23T00:00:00 |
2023/01/23
|
https://egn.com/dk/chatgpt-a-new-era/
|
[
{
"date": "2023/02/26",
"position": 53,
"query": "ChatGPT employment impact"
}
] |
Daiki - Your AI Governance Platform built for Compliance
|
Your AI Governance Platform built for Compliance
|
https://dai.ki
|
[] |
At Daiki, we make AI work for you by centralizing the governance, monitoring ... organization stays aligned on AI adoption across the organization. AI ...
|
Functional Functional Always active
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
| 2023-02-26T00:00:00 |
https://dai.ki/
|
[
{
"date": "2023/02/26",
"position": 68,
"query": "AI labor union"
}
] |
|
YourGPT - The complete AI Platform for Business Automation
|
The complete AI Platform for Business Automation
|
https://yourgpt.ai
|
[] |
YourGPT AI helped us improved communication for government agencies and labor unions. The AI-powered chatbots efficiently handle inquiries, reducing ...
|
The ability to create customized workflows and choose from different LLMs has been incredibly useful for my business. It offers flexibility and adaptability, allowing us to tailor the AI to our needs. Ariel D.
I love the user-friendly dashboard and intuitive dashboard. It's so easy to navigate and get things done. And when I run into issues, the support team is there to guide me every step of the way. Michal .
YourGPT is incredibly easy to use and set up. Whether you need simple features or advanced customization, they have everything covered. And their customer support? Always friendly and ready to help – truly excellent service! Gianlucca D.
YourGPT provides accurate and human-like responses to customer queries. The multi-channel support integration with platforms like Messenger, WhatsApp, and Slack makes it easy for our support agents to connect with customers on their preferred platform. It's been a game-changer for our customer service. Achal G.
YourGPT AI has transformed how we handle customer interactions. With its no-code ai agent builder and quick integrations, we've improved response times and customer satisfaction. A game-changer for our support team! Trampth
YourGPT AI helped us improved communication for government agencies and labor unions. The AI-powered chatbots efficiently handle inquiries, reducing workload and improving service quality. Julian
We needed an AI assistant that could handle complex queries and integrate with multiple platforms—YourGPT AI delivered. The setup was smooth, and the results speak for themselves! Markus
I would like to thank the YourGPT team. With YourGPT AI, we improved our customer service, making responses faster and more accurate. The automation helps us handle more work without hiring new team members, and the AI understands our business needs perfectly. Eilon
YourGPT AI has saved us countless hours by automating routine support requests. The AI understands context better than anything we've used before, making customer interactions feel natural and engaging. Martin
We wanted a chatbot that could scale with our business, and YourGPT AI exceeded expectations. The advanced AI features and analytics tools give us deep insights into customer behavior, helping us improve continuously. Ronan
| 2023-02-26T00:00:00 |
https://yourgpt.ai/
|
[
{
"date": "2023/02/26",
"position": 69,
"query": "AI labor union"
}
] |
|
My new co-worker: Generative AI - Corporate Hacking
|
My new co-worker: Generative AI
|
https://www.corporatehacking.org
|
[
"Corporate Hacker"
] |
My new co-worker: Generative AI. How Artificial Intelligence (AI) will shape the future of the corporate world. Corporate Hacker's avatar. Corporate Hacker. Feb ...
|
In true “if you can’t beat them, join them” fashion I’ve been reflecting a lot on the impact of the latest AI trends, specially Generative AI (like ChatGPT or Dall-E), on the corporate world. Before thinking about the impact lets try to distil what’s happening underneath.
What doors are being opened?
From decision to creation
Until 2 months ago, AI was primarily associated with decision making. What is the optimal price for this product?, should I offer this product to my client?, is this picture from a cat? Decisions usually taken by humans with dozens of biases, replaced by a feelingless algorithm. Today we think about AI for creation. Yes-No becomes full stories and draft documents, OCR like image recognition becomes art and faces that don’t exist and we see an exponential growth of AI characters in movies and deep fake videos. This is my favourite so far.
From specific to general
Until 2 months ago, AI was thought to solve parts of a problem, like optimising the price for a product. Today, we envision an AI with the possibility to take over a full problem. Think about the creation of a website, where the AI understands the purpose of the site, designs it, choose and build the technology required and constantly conduct A/B type tests to maximise client engagement. The dream of a corporate businessman… not having to talk with those nasty tech guys.
From data to knowledge
Until 2 months ago, most AI algorithms were trained with an specific application in mind and with the limitations of the available data points. Today, we have seen a machine talking about everything, form hard facts to imaginary stories which provides an added feeling of realism and depth.
What could be the impact on my company?
Skyrocketing productivity… and layoffs
Internet reduced the need for physical sales. Automation (process robotics if you are lazy) reduced back-offices doing mundane tasks. With AI:
Designers and analysts will not only be replaced by algorithms doing 80-90% of the same work in seconds instead of days but will also iterate with hard data to optimise it. Developers are already accelerating with AI “companions” that autocomplete pieces of code and technical functions (e.g., store this over there) to later see end-to-end AI developers take over more straight forward developments (e.g., a website). Contact centres will replace 90% of their staff with conversational AI that will only route to humans on a few fancy cases. Monitoring and 24/7 support jobs will get replaced by AI monitoring massive data (e.g., security cameras, network traffic, factory sensors) with the ability to also optimise how they work.
Pressure for restructuring and layoffs will be higher than ever and countries with less ethics and social concerns will leap above the rest.
Rethinking corporate governance
A problem already, corporate decision making is based on processes built by and for humans. Even its most useless parts provide a sense of traceability and objectivity for someone. With AI:
Uncertainty will have to be accepted, especially in regulated industries, with humans not fully understanding the reasons behind each choice in exchange of the certainty that an optimal result. Employees will act like taxi drivers, constantly complaining that they can do a better job than the GPS to save their jobs… they cant. Automation will be the only way to trace and audit the decisions taken by machines with degrees of autonomy. Regulators and internal auditors will still fight back to leave some manual controls in place like a human pushing a button. Facts over feelings, people will no longer be able to lie, with AI “peers” raising the flag. Every decision will be benchmarked with its optimal value to the stakeholder and will have to be overriden by a human to justify any other purpose (e.g., politics, sustainability, equality).
More of everything
The perfect public image conveyed by most companies, solid, efficient, experienced, secure… will be harder and harder to keep. AI will:
Make big problems bigger like Security where the identity of a person will be blurred and machines will trick humans with perfect image and voice replicas. HR and educators will struggle with people fuelling their work with AI content. Competition will become fiercer, what started with smaller players taking advantage of a leveled technology playfield will expand to quality of service provided by hordes of “free” AI relationship managers. Expertise will be at everyone’s reach, with machines learning years of facts and decisions in minutes. Capital will only play a differential role in asset intensive industries (e.g., manufacture, transport), not for labor. External pressure will increase in an attempt to save jobs. Regulators will come up with artificial ways to compensate for higher competition masked as corporate greed. Politicians will promise to save jobs from “evil” corporations and public perception will be more important than ever, with the only remaining human in the equation, the client, more relevant than ever…
Like previous revolutions, Generative AI will smash the corporate world and the speed in which it will happen will be far more dramatic, demanding higher resiliency from employees, corporate owners and governments. It will not be easy to hack.
Share
| 2023-02-26T00:00:00 |
https://www.corporatehacking.org/p/my-new-co-worker-generative-ai
|
[
{
"date": "2023/02/26",
"position": 85,
"query": "AI workers"
}
] |
|
Chatbots Suck at Journalism
|
Chatbots suck at journalism. Why is journalism welcoming them?
|
https://slate.com
|
[
"Nitish Pahwa"
] |
Since 2014, plenty of newsrooms have tapped automated and even artificial-intelligence tech to aid their work: the Associated Press, Reuters, and the Washington ...
|
If there is one thing the boosters and cynics agree on about artificial intelligence, it’s that the tech is coming for white-collar jobs. One obvious target of text-generating tools like ChatGPT? Journalism. This is not speculation of a far-off future—it’s happening now.
It makes sense, from a cold business perspective, that text-based media would want to adopt A.I. in order to cut costs (humans, expensive) and speed up output (humans, slow). Just look at how BuzzFeed’s rock-bottom stock value jumped when it said last month that the site would use services from buzzy startup OpenAI to spiff up the site’s famed quizzes. As Damon Beres wrote in the Atlantic shortly after the announcement: “The bleak future of media is human-owned websites profiting from automated banner ads placed on bot-written content, crawled by search-engine bots, and occasionally served to bot visitors.”
This hype-and-fear cycle has persisted for months, generating an infinite scroll of warnings about the A.I. content we’ll all be subjected to in the future. The prophecies are well-taken. But recent examples demonstrate that it might not make business sense—at least, not just yet—for journalists to be displaced by tools like ChatGPT. In part because these artificial intelligence and machine learning services are very bad at journalism.
Since 2014, plenty of newsrooms have tapped automated and even artificial-intelligence tech to aid their work: the Associated Press, Reuters, and the Washington Post, for tallying corporate earnings and sports-game scores; Bloomberg, to personalize news feeds and search results for individual readers; the Los Angeles Times, for brief and speedy reporting on homicides and earthquakes; the Guardian, to track international political donations. Slate uses automated podcast transcription for accessibility purposes, and—for kicks—once tested whether ChatGPT could offer advice appropriate for Dear Prudence. (Hey, nothing wrong with a gimmick.) British publications like Press Association and the Times utilize the tech to extrapolate trend stories from mass data sets, and to personalize newsletters delivered to readers.
Advertisement
Advertisement
Advertisement
Advertisement
Those efforts all have something in common: They use software to take on drudging tasks like transcribing and initial data-gathering so that journalists have more time to do more intensive reporting. The difference now is that some outlets are trying to use ChatGPT and other A.I. tools as more than just a donkey carrying a heavy load.
In an already infamous example, the tech news and review site CNET tried using generative text programs to fully write articles, with little in the way of editorial oversight, internal or public transparency, or even plain accuracy. According to reporting last month by Futurism and the Verge, CNET began quietly publishing these service articles on its website back in November—for example, a daily article reporting the latest mortgage rates—originally attributing their authorship to “CNET Money Staff.” The articles noted that they were “generated using automated technology,” but the disclosure didn’t include any specifics. (Currently, the articles are attributed to “CNET Money” and feature newly worded disclosures: “This article was assisted by an AI engine and reviewed, fact-checked and edited by our editorial staff.”)
Advertisement
The site’s editor in chief, in response to the reporting, claimed that every piece was “reviewed, fact-checked and edited” before publication and framed the site’s experiment as an “assist” to her staffers. But Futurism soon found that CNET was using A.I. to rewrite some of its already published articles without due disclosure, while the Verge uncovered that nearly half the site’s A.I.-generated articles required substantive corrections. (They were also plagiarizing, a lot.) Human CNET employees became increasingly upset with both their new chatbot colleagues and the company’s response. As such, the experiment is now on pause, though Red Ventures is planning to update and relaunch the system soon, according a Futurism report published Friday.
Advertisement
Advertisement
“It seems like Cnet’s owner, Red Ventures, basically ordered the site’s leadership to start running A.I. articles, and then when they got caught they tried to invent a retroactive explanation that they’d been ‘testing and assessing new technology,’ ” wrote Futurism managing editor Jon Christian in an email. “If they’d owned their mistakes and written seriously about what they’d learned, it could have been a huge boon for the rest of the publishing industry.” Indeed, Red Ventures, which acquired CNET in 2020 and forced mass layoffs as a precondition, was definitely in a position to offer advice to the field. Two more of its subsidiary sites, Bankrate and CreditCards.com, were also regularly publishing (erroneous) A.I.-written articles for a while.
Advertisement
One reason for this commodity publishing strategy is, obviously, web traffic. And web traffic depends a lot on Google. So if every day, people are Googling about mortgage rates … why not autopublish an article that will bring their eyeballs to CNET?
CNET, already weakened by workforce reductions, had gradually lost visibility on Google Search results throughout 2022, according to a report from the SEO firm SISTRIX. A serious problem, considering search engine optimization is ever more important for digital publishers in the age of plummeting social media traffic. So, the idea is, quickly produced A.I.-written explainers might boost a site’s search rankings and traffic. Perhaps even if the A.I.-written and search-targeted posts are inaccurate, as was the case for Bankrate.
Advertisement
Advertisement
This is slightly counterintuitive; auto-generated content is associated with low-quality journalism, and that’s precisely what Google has tried to suppress in its search results. “Before this GPT conversation, Google was doubling down on content quality and what they call EEAT: experience, expertise, authority, and trust,” explained Lily Ray, senior SEO director at Amsive Digital and author of the SISTRIX report. “They want to know who created the content—they want to know that person’s an expert or has a lot of experience. They want to be able to trust that person—trust the brand, trust a website.” While that guidance may sound beneficent for the web at large, it’s also influenced by Google’s self-interest. “They want to make the internet a safe place—that people can trust Google’s results,” said Ray. “They’ve been on that mission for a long time, and that leads to elevating content that probably doesn’t use a lot of A.I.”
Advertisement
Advertisement
So ugly were the CNET and Bankrate belly-flops that Google clarified its policies for a GPT-3-written world. On Feb. 8, the search giant shared a blog post outlining how it would approach A.I.-penned information going forward. “Appropriate use of A.I. or automation is not against our guidelines. This means that it is not used to generate content primarily to manipulate search ranking,” Google explained, clarifying that “using AI doesn’t give content any special gains. It’s just content.” The company recommended that A.I. use in online writing be made clear to readers when appropriate, that A.I. not be made a primary author, and that accuracy and authority still be prioritized when publishing digital information. In an independent study, SEO consultant Gael Breton found that A.I. writing did not automatically reduce Google traffic, but that prolific human authors still commanded the larger share of search referrals in comparison.
Advertisement
Advertisement
For now, in other words, websites need not worry about a blanket ban on “CNET Money Staff”–style articles as long as generative-app use is made clear, accuracy is prioritized, and the content doesn’t consist of misleading “health, civic, or financial information.” And so publications keep trying to clear that very low bar. The publishing company the Arena Group—which hosts a portfolio of understaffed, struggling publications like Sports Illustrated—announced early this month it would employ OpenAI tech for assistive purposes, and then published a chatbot-penned advice piece in Men’s Journal that contained significant errors.
Here’s the thing about the newest generation of text-generative A.I. applications, like ChatGPT and Microsoft’s chaotic new Bing chatbot: They’re very good at having a conversation, which is to say these things can write. They’re also talented fabulists that will pass off inaccurate or hallucinated information with eerie confidence. If any human CNET staffers got caught pulling this crap, they’d be fired.
Advertisement
Advertisement
But a couple of possibilities loom. One is that the technology improves, or human guardrails advance, to the point that these things are capable of producing a kind of journalism at scale. Another is that they become so good that consumers skip visiting their formerly favorite tech website and direct their nagging, pressing questions to—and only to—their friendly neighborhood chatbots.
Advertisement
Advertisement
When it comes to chatbots, “there are so many queries that can cut into people needing to go to Google for anything,” said Ray, the SEO specialist, giving examples like simple recipes or code troubleshooting, both of which ChatGPT is well-versed in. As a result, should more consumers turn to GPT models for such answers, that could fuel “a huge decline in people feeling like they need to go Google something, and that cuts into [websites’] ad impressions.” ChatGPT famously does not link to any of the sources it relies on for its answers, nor does it provide a hint as to what may have informed its output. This has caused consternation among major digital publishers like CNN and the Wall Street Journal, whose work was scraped extensively, without their permission, in order to train ChatGPT’s current iteration; OpenAI has defended this practice as constituting fair use. (According to data compiled by former OpenAI executive Jack Clark, Slate was one of the most-utilized sources for training ChatGPT-2, an earlier iteration of the app.)
Advertisement
Major search engines, too—the ones that used to drive so much traffic to CNET—are starting to incorporate A.I. chatbots, with wild and unpredictable results. What that entails for digital journalism is similarly murky. “We have Neeva, we have Bing, and they’re clearly trying to set a good example by saying, We’re still going to send traffic to sites, we’re still going to say where we got this from,” said Ray. “There’s a new tool called Perplexity.ai that’s similar to ChatGPT but it cites all its sources. People really like that.” But just having these references available doesn’t guarantee that users will click them. As media-biz analyst Brian Morrissey wrote in his newsletter, “The change of the search interface to accommodate AI chat will make [referrals to publishers] less effective. Some will click on the citations, but many will find the answer good enough.”
Advertisement
Advertisement
Advertisement
And none of these search engines has the stature of Google, which isn’t following their lead on citations and links. The same week that it described its stance on A.I. and SEO, Google demonstrated its own rival chatbot, Bard. Not only did Bard spit out an inaccurate answer that appeared to throttle Google’s stock price, it showed that Google seems to be taking a ChatGPT-style lane when it comes to disclosing whence its answers, accurate or not, were sourced. “We’ve never quite seen a search result like the one they presented that just removes the answer from the place that the answer came from,” said Ray. “Almost every other type of Google search result has some type of attribution. That’s really bad for publishers and very scary.”
For such reasons, David Karpf, a George Washington University associate media professor who’s written about A.I. for years, doesn’t think journalism should count on Google’s dominance and purported idealism to aid the sector in staving off the business threats posed by ChatGPT-like tools. In an interview, he pointed to a prior example of an online upstart that threatened virtual publishing as we know it: Demand Media, the content-farms juggernaut whose potency was killed off when Google adjusted its algorithm to halt referrals to its properties. “I look at what CNET’s doing, and it feels so much like the Demand Media SEO-bait articles that they were trying to do as cheaply as possible,” said Karpf. “If the way that we imperfectly saved news a decade ago was the benevolence of the platform monopolist,” which began sifting out low-quality articles, “I’m not sure we can have faith in that this time, because the platform monopolist might also be the one who’s producing those tools.” After all, Google famously invented the “T” in ChatGPT: the Transformer, a neural network for automated language learning and processing. That very tech is what enabled OpenAI to present a competitive threat to Google when it comes to quick information reference.
Advertisement
Advertisement
Advertisement
Advertisement
The future of news outlets’ search viability may depend on which engines win the ongoing chatbot arms race: the ones that prominently link, credit, and encourage more in-depth discovery, versus the ones that do none of those things. Predictions for this space should expand beyond chatbots—news curators and aggregators are also training their own algorithms to personalize non–social media news feeds for users through easy-to-use apps. In that vein, it could be that news eventually gets decoupled from search altogether. Some publishers, like Mediaite, are backing out of SEO-tailored content to curate a direct, loyal audience, one that’s more likely to visit its homepage or to click on Mediaite articles surfaced to readers on apps like Flipboard and specialized feeds like Google News.
Google and Microsoft seem to be bracing for a future in which users abandon traditional web search for chatbots, which could reorder how people experience, and how organizations publish to, the web. We’re not there yet. But Karpf suggests it’s never too early for a backlash.
Advertisement
When it comes to A.I.-written articles on traditional news sites, “if advertisers don’t like it, if they want to take the extra step of saying, ‘no CNET articles at all,’ that requires organizing,” said Karpf. “Do readers eventually start signaling to the platforms, ‘I’m really annoyed that I keep getting served ChatGPT crap when I search for something or when I ask for something, and I would like to be able to trust this’?” We already know online misinformation is quite lucrative, and we don’t know yet whether the A.I. factor will affect this, unless there’s clear reputational damage at stake.
Advertisement
Part of that backlash may come from within news organizations. Labor reporter Hamilton Nolan has gone so far as to write that “if something did not come from a human mind, it is not journalism. Not because A.I. cannot spit out a convincing replica of the thing, but because journalism—unlike art or entertainment—requires accountability for it to be legitimate.” Some newsroom humans are already working to ensure standards for A.I. use are clear-cut, that writers are made aware of intent to use these tools, and that those projects do not muddy the definition of journalism, following in the steps of screenwriters and voice actors who are working to clarify terms of proper, ethical A.I. use in their own contracts. For example, Wirecutter’s editorial union stipulates that layoffs due to automated newsroom processes, as well as editorial work outsourced to automated systems, require advance notice and good-faith bargaining with the labor union. Two journalists who are currently organizing their newsroom through the Writers Guild of America, East—speaking on condition of anonymity—told me they’d been considering pushing for A.I. provisions in their contracts even before the CNET situation, thanks to the use of such tech in ever-present workplace surveillance apparatuses like Microsoft’s “productivity score.” Now, in the midst of ChatGPT hype, “the language we’re bargaining over is what materially affects journalists,” one of the journalists said. “Something A.I. is not very good at is taking a lot of disparate elements that are unrelated and qualitative and formulating something new and qualitative based off that.”
Advertisement
Advertisement
Advertisement
Advertisement
What’s more, chatbots can’t talk to people on the ground, learn to be extra careful and discerning with certain sources, describe situations and people firsthand with scrutiny or empathy, or come up with entirely new observations or arguments, at least not yet. Using ChatGPT for web articles “would make sense only if our goal is to repackage information that’s already available,” Ted Chiang wrote in the New Yorker. Copywriting and blogging and proofreading could be automated to an extent, provided that chatbots fix their myriad kinks, but the journalism process of reporting, discovery, sensible synthesis, fact-checking and double-checking, and accountability to a community (or the entire world) cannot be supplanted just yet. Rapid text output is not the same as reporting out truthful stories with a responsible paper trail. As Slate contributor John Warner, an author and professor, put it in his newsletter: “ChatGPT is not generating meaning. It is arranging word patterns.”
Advertisement
For these reasons, most of the sources I spoke with recommended that publishers take caution before throwing themselves into A.I. chaos. “They should probably move very slowly here,” Karpf said. “The instinct to say, ‘Oh good, we can use this for everything, let’s cut costs to the bone,’ carries more risk than they expect.” The Writers Guild–affiliated journalists concurred: “If we start relying on it too quickly, then you’re going to see a lot of errors, racial bias, unobjective journalism, or just copied-and-pasted press releases.” Michael King, an SEO expert who’s been experimenting with A.I. developments for years, mentioned that ChatGPT produces far more errors when prompted to produce a lengthy response as opposed to a shorter one, making clear its current utility for content generation: short, fact-checked text snippets at most. We’ll see how that changes when GPT-4 comes along.
All these shiny new apps far surpass any prior A.I. developments in terms of capability and training, and they presage some major changes in the field, as well as our lives. Still, it’s one thing to predict yet another technological reckoning for our embattled profession. It’s another to actually put it into practice and behold the results.
Future Tense is a partnership of Slate, New America, and Arizona State University that examines emerging technologies, public policy, and society.
| 2023-02-26T00:00:00 |
2023/02/26
|
https://slate.com/technology/2023/02/chatbots-suck-at-journalism-why-is-journalism-welcoming-them.html
|
[
{
"date": "2023/02/26",
"position": 40,
"query": "AI journalism"
}
] |
How AI will change recruitment - Recruidos
|
How AI will change recruitment
|
https://recruidos.com
|
[] |
AI-powered recruitment tools are designed to automate many of the repetitive and time-consuming tasks that are typically associated with recruitment. For ...
|
Artificial Intelligence (AI) is a rapidly advancing technology that has the potential to revolutionize the way we work, live, and interact with one another. One area in which AI is poised to make a significant impact is in the field of recruitment. The recruitment landscape is changing at a rapid pace, and AI is playing an increasingly important role in helping organizations to identify, attract, and hire the best candidates for open positions.
AI-powered recruitment tools are designed to automate many of the repetitive and time-consuming tasks that are typically associated with recruitment. For example, AI can be used to sort through resumes and identify the most relevant candidates for a given position. This can help organizations to quickly and efficiently identify the best candidates for open positions, reducing the time and resources that are typically required to fill a vacancy.
AI can also be used to conduct initial screenings of candidates, allowing organizations to quickly identify those who are most likely to be a good fit for a given position. This can be done by analyzing candidates’ resumes and cover letters, as well as by conducting initial interviews. By using AI to conduct these initial screenings, organizations can save time and resources while also ensuring that they are identifying the most qualified candidates for open positions.
Another way in which AI can change the recruitment landscape is by helping organizations to identify and attract top talent. AI can be used to analyze data on candidates’ skills, experience, and qualifications, as well as data on the types of positions and industries in which they are most likely to excel. This can help organizations to identify and attract top talent that may not have been previously considered for open positions.
AI can also be used to help organizations to identify potential candidates who may be a good fit for open positions, but who may not have actively applied for a job. For example, AI can be used to analyze data on candidates’ online presence, such as their social media profiles and activity on professional networking sites. This can help organizations to identify potential candidates who may be a good fit for open positions, but who may not have actively applied for a job.
AI-powered recruitment tools can also be used to help organizations to improve their recruitment processes and make them more efficient. For example, AI can be used to automate many of the repetitive and time-consuming tasks that are typically associated with recruitment, such as scheduling interviews and sending out follow-up emails. By automating these tasks, organizations can save time and resources while also improving the overall efficiency of their recruitment processes.
In conclusion, AI is changing the recruitment landscape in a big way. The technology can help organizations to quickly and efficiently identify the best candidates for open positions, reduce the time and resources required to fill a vacancy, identify and attract top talent and improve the overall efficiency of their recruitment processes. As the technology continues to advance, we can expect to see even more ways in which AI will change the way we recruit and hire new employees.
| 2023-02-26T00:00:00 |
2023/02/26
|
https://recruidos.com/how-ai-will-change-recruitment/
|
[
{
"date": "2023/02/26",
"position": 65,
"query": "artificial intelligence hiring"
}
] |
Global Humanities Institute 2024: Design Justice AI
|
Global Humanities Institute 2024: Design Justice AI
|
https://chcinetwork.org
|
[] |
DESIGN JUSTICE AI is a Global Humanities Institute that will explore community-centered, humanistic, and interdisciplinary engagement of “Generative AI,”
|
DESIGN JUSTICE AI is a Global Humanities Institute sponsored by the Consortium of Humanities Centers and Institutes and the Mellon Foundation. This institute will explore community-centered, humanistic, and interdisciplinary engagement of “Generative AI” (the statistical modeling of human languages, communication, arts, and cultures), and is a partnership involving four university-based centers:
The principal collaborators include Lead PI Lauren M. E. Goodlad (Distinguished Professor of English & Comparative Literature, Chair of the Critical AI @ Rutgers initiative, and editor of Critical AI) and Colin Jager (Director of the Center for Cultural Analysis at Rutgers) in conjunction with co-PIs at each of the partnering centers: Matthew Stone (Professor and Chair of Computer Science at Rutgers), Katherine Bode (Professor of Literary and Textual Studies at ANU), Vukosi Marivate (Chair of Data Science at the University of Pretoria and lead for the Data Science for Social Impact Group), and Michael P. Lynch (Board of Trustees Distinguished Professor of Philosophy and former director of the Humanities Institute). You may find a full list of their collaborators below. The main institute meeting in 2024 will involve an application process that funds up to 20 additional interdisciplinary scholars.
For this GHI's full institute website, please visit here. For questions, please write to [email protected].
University of Pretoria
Expected Timeline
The pre-institute meeting is tentatively scheduled for July 7-11, 2023 in Canberra at the campus of Australia National University. This initial meeting will put in place an application process to fund up to 20 interdisciplinary scholars, with special focus on early career and emerging scholars and community partners to join this group at the main institute meeting. We will announce the application process in July 2023.
The main institute meeting, DESIGN JUSTICE AI, will be held at the University of Pretoria from June 30 to July 13, 2024 and will include collaborators from all four centers along with the scholars chosen through the application process. The DESIGN JUSTICE AI meeting at Pretoria will be partly hybrid in order to welcome the participation of interested scholars, technologists, and community collaborators worldwide.
We plan to invite distinguished speakers to join us via hybrid or virtual lectures so as to prioritize in-person participation by emerging scholars.
A post-meeting event will be scheduled for Fall 2024 and will likely take the form of a hybrid event on the Rutgers campus.
Research Goals and Questions
By now many people have heard about ChatGPT and other “large language models.” What they may not know is that these are examples of the rapid diffusion of so-called generative AI: machine learning technologies that simulate human languages, communication, arts, and cultures through the statistical modeling of vast troves of “scraped” internet data. Our Global Humanities Institute is inspired by the work of the Design Justice Network, a hub for people committed to embodying and practicing the Design Justice Network Principles. Longstanding DJN member Sasha Costanza-Chock (former fellow of the Berkman-Klein Center for Internet & Society and Head of Research for OneProject.org) wrote Design Justice: Community-Led Practices to Build the Worlds We Need (2020) to advance community-led design practices. Our approach to these practices and topics combines interdisciplinary critique, public humanities, and best practices from data science and digital humanities (DH), with collaborative research that strives to center people and cultures that have been marginalized by design processes.
DESIGN JUSTICE AI will cross disciplinary divides and reach out to affected communities as we foster creative thinking, model new forms of research, and produce resources for scholars and the general public. As commercial technologies aim to simulate and mediate human expression and creativity at an unprecedented scale, our Global Humanities Institute will seek interdisciplinary standpoints and fertile alliances that produce knowledge “from below”: through creative collaborations between researchers, students, and community partners. Our goal is not only to “critique” these fast-developing technologies, but also to envision ML systems that work in the public interest: i.e., safe, accountable, and inclusive systems that are receptive to many voices.
Through publication of blogs, research templates, interviews, experimental datasets, recorded lectures, pedagogical practices, and peer-reviewed articles and special issues, our institute will share resources that help to diffuse these critical methods. In doing so, we hope to help any campus to develop nuanced understanding of and engagement with “generative AI,” including robust pedagogical strategies, and the potential for community-centered research projects informed by design justice principles.
Our guiding questions include:
What would be lost from human creativity and diversity if writers or visual artists come to rely on predictive models trained on selective datasets that exclude the majority of the world’s many cultures and languages?
What frameworks or evaluation practices might help to concretize what is meant by “intelligence,” “understanding,” or “creativity”–for machines as well as humans? How might such humanistic interventions help diverse citizens to participate in the design and implementation of generative technologies and the benchmarks that evaluate them?
What are the strengths and weaknesses of current statistical models–which generate outputs probabilistically (by privileging dominant patterns) and selectively (based on scraped data)–in modeling the lived knowledge, embodied cognition, and metareflection that informs human communication, art, and cultural production?
If evidence suggests that “generative AI” is harmful–and/or counter to the professed object of enhancing human lifeworlds–what alternatives might be forged through community participation in research that rearticulates goals, and reframes design from the bottom up? What kinds of teaching, research, community practices, and policies might sustain these humanist-inflected and justice-oriented design processes?
Although the DESIGN JUSTICE AI outlook will not reject the potential utility of “generative AI” out of hand, our research questions go to the heart of what inclusive collaborations can contribute to the study of resource-intensive technologies that aim to monetize and “disrupt” human communication and creativity.
Institute Participants
Rutgers University, Center for Cultural Analysis (CCA)
Brittney Cooper: Professor of Africana Studies/Women’s, Gender, & Sexuality Studies; a scholar of Black women’s intellectual history and race and gender politics, Cooper is currently working on sexism and racism in digital and social media contexts.
Alex Guerrerro: Professor of Philosophy; a J.D. who specializes in moral and political philosophy as well as African and Native American Philosophy, Guerrerro has taught a recent graduate seminar on the Ethics and Politics of AI.
Australian National University (ANU), Humanities Research Centre
University of Pretoria, Centre for Advancement of Scholarship
Abiodun Modupe: Lecturer in Computer Science and specialist in the modeling of local African languages, Modupe is currently implementing a degree program in “Big Data Science” for the Data Science department.
Brenda Nomadlozi Bokaba, Lecturer in African Languages and Literature, Bokaba is an activist for multilingualism across South Africa and works with community partners on local African languages.
Emma Ruttkamp-Bloem: Head of Philosophy, AI Ethics lead for the Centre for AI Research, and Chair of the Southern African Conference on AI Research (SACAIR), Ruttkamp-Bloem is an ethics policy researcher currently serving as a member of the UNESCO World Commission for Ethics of Scientific Knowledge and Technology (IUHPST).
University of Connecticut, Humanities Institute (UCHI)
Alexis L. Boylan: Director of Academic Affairs, UCHI and professor of Art and Art History and the Africana Studies Institute, Boylan works on the rights of visual artists in regard to “generative” technologies. Specifically, she is interested in how this tech will impact local art communities and markets globally.
Eleni Coundouriotis: Professor of English and Comparative Literary and Cultural Studies, Coundouriotis researches African literature and human rights.
Yohei Igarashi: Associate Professor of English and Coordinator of Digital Humanities and Media Studies for UCHI, Igarashi is working on collaborative projects with language models and has written on the relation between “generative” writing and literary history.
Design Justice Network (DJN) Wesley Taylor: Assistant Professor in the Department of Graphic Design at Virginia Commonwealth University, member of the Design Justice Steering Committee, Taylor is a print maker, graphic designer, musician, animator, educator, mentor and curator whose practice is rooted in social justice.
The institute organizers are grateful to all of the above faculty for their input as well as to CCA Business Manager Matt Leonaggeo, Rutgers Grants Specialist Justin Samolewicz, and the Critical AI @ Rutgers team (Kristin Rose, Jennifer Vilchez, Andi Craciun, Ang Li, and Jai Yadav).
For questions, please write to [email protected].
| 2023-02-26T00:00:00 |
https://chcinetwork.org/programs/ghi2024-ai
|
[
{
"date": "2023/02/26",
"position": 54,
"query": "artificial intelligence graphic design"
}
] |
|
Instance Segmentation: How adding masks improves ...
|
Instance Segmentation: How adding Masks improves Object Detection
|
https://www.thinkautonomous.ai
|
[] |
Two losses? If we are to understand how to add a segmentation head to an ... AI Skills. SDC App for iOS, Android and Browser. Interested in Autonomous ...
|
It was late, and I was going back from the office to get home to my newborn baby, when I saw a post on my LinkedIn feed: "YOLOv7 Instance segmentation & Pose Estimation running at 30 FPS!".
"What is this guy talking about?" I thought. "YOLO" isn't a segmentation algorithm! And it's even less a pose estimation algorithm! What is he talking about!"
I couldn't help but open the video, to see how much this post was wrong, but then I saw it: The Instance Segmentation model made from YOLO!
When I looked at the output, I noticed something: Not only was the algorithm predicting the objects and the segmentation masks, but it also assigned a specific color for each of the individual objects.
I was amazed. Because at this moment, I realized that with an object detector like YOLO, we could do multiple tasks. And we again entered a new era!
The Era of Multi-Task Learning everywhere!
In this post, I want to explore the different ways to do instance segmentation. I want to us to understand better the main idea behind it, but also the "how" it's done. We'll see the real-world applications, and how it's in reality, just a strong multi-task learning algorithm.
What is instance segmentation, and why is it needed?
A few years ago, if you need to run 2 tasks such as object detection and image segmentation in parallel, you needed 2 models. With two models, came two different training pipelines, two loss functions to deal with, two datasets to label, and of course, twice the computing power needed.
But then came Instance Segmentation, which is the fusion of semantic segmentation and object detection, and was doable with just one model!
Rather than building one network for each task, you have a network that builds both — or as I often call these types of networks, you have a Hydranet!
So here is my network at first:
Two Networks running Two Separate Tasks
But we don't need to have two networks. This is the main idea behind multi-task learning, and I have an entire course about it; because encoders are essentially the same and have the same purposes (to learn features), we can use the same encoder, and then add heads to the network.
Like this:
A Single Network Running 2 Tasks
Instance Segmentation is doing exactly this. Rather than doing simple image segmentation or object detection, it's about doing both tasks at once.
This type of application is needed everywhere where both semantic segmentation and object detection are needed, for example in scene understanding for robotics or autonomous driving.
So let's get to the 1,000,000 $ question:
How does instance segmentation work?
How to turn an object detection algorithm like YOLO into an instance segmentation model? Is this a process where we fuse two neural networks? Do we really just "add a segmentation head" and that's it? What does it mean for training? Is there one loss? Two losses?
If we are to understand how to add a segmentation head to an algorithm like Faster-RCNN, we must first understand how these models work.
Take an object detector like Faster-RCNN (2015), the general architecture looks like this:
The Faster-RCNN algorithm
The way I explain it in my MASTER OBSTACLE TRACKING course is through this image:
How Faster-RCNN works in 5 Steps
In short, we have two-stages:
Bounding Box Proposal : A stage made of the Encoder or Feature Extraction , the RPN (Region Proposal Network), that proposes Bounding Boxes, and the ROI Pooling that extracts a fixed-length feature vector from the proposed regions.
: A stage made of the Encoder or , the (Region Proposal Network), that proposes Bounding Boxes, and the that extracts a fixed-length feature vector from the proposed regions. Box Classification: For each proposed box, we have extracted a vector — and we now classify this vector using some fully-connected layers. This is done for every box and the classification allows to predict between multiple categories.
On the other hand, we also have One-Stage Networks, like YOLO or SSD. This time, the architecture is one stage, we directly learn the features, regress bounding boxes, and classify them:
How YOLO works from a super high-level
Whether it's Faster-RCNN or YOLO, the way to turn an object detector into an instance segmentation model is to add a mask prediction branch to the network. By the way, I invite you to read this article that explains the details of YOLOv4.
How to turn Faster-RCNN into Mask-RCNN?
Here is my simplification of the Mask-RCNN architecture that has been created to perform instance segmentation from Faster-RCNN:
How the Mask-RCNN Approach does segmentation
Once the boxes are "proposed", we can simply add a branch that will perform segmentation in parallel to the classification branch.
How? The output of the image segmentation branch is a set of binary masks, one for each object instance in the image.
Binary Mask Prediction in Mask-RCNN
How do we get these masks? The same way we do in any image segmentation task: we upsample the features learned for each ROI (proposed bounding box), and then build a decoder that classifies each pixel. For example, the Mask-RCNN model uses an FCN (Fully Convolutional Networks) — that is basically the first Deep Learning architecture for image segmentation.
YOLOv7 Mask and YOLOv7 Pose: How to turn YOLO into (almost) anything?
Why do I mention " YOLOv7"? Simply because this version from 2022 is the first to make multi-task directly possible. Mask-RCNN has for long been the go-to technique for instance segmentation. With YOLO, the architecture was different and harder to work on.
But in 2017, YOLOv7 shipped with new models heads, allowing for keypoints detection (pose estimation) , instance segmentation, and object detection .
Semantic Segmentation Head
YOLOv7 tweaked for instance segmentation (source)
The way it works for semantic segmentation is by integrating a segmentation paper called BlendMask. BlendMask is a state-of-the-art instance segmentation algorithm that uses a multi-level feature fusion module to generate high-quality instance segmentation masks. What happens is YOLO is fine-tuned on the MS COCO instance segmentation dataset and trained for 30 epochs.
Blending
FYI, "blending" is the idea of fusing predicted bases from FPN (row 1) with attention masks (row 2):
How Blending Works (explained in the BlendMask paper): "We illustrate an example of the learned bases and attentions. Four bases and attention maps are shown in different colors. The first row are the bases, and the second row are the attentions. Here ⊗ represents element-wise product and ⊕ is element-wise sum. Each basis multiplies its attention and then is summed to output the final mask"
Pose Estimation Head
Similarly, a model like YOLOv7 uses the YOLO-Pose algorithm that enhances YOLO by adding a keypoint detection output to each scale along the detections.
YOLOv7 tweaked for pose estimation (source)
Notice how in both cases, the architecture is similar to a feature pyramid network, where we run predictions at different scales.
Which approach works better? Results show YOLOv7 is one of the state-of-the-art papers in instance segmentation, but to be fair, Mask-RCNN has been released in 2018, which is 4 years before YOLOv7.
Training, and all the mess that comes with it
One of the biggest problem in multi-task learning is training. Let's say you're training a model to classify whether a person is a man or a woman, and at the same time, you want to predict the age of that person.
The simplest implementation would take a classification loss such as Binary-Cross Entropy, but the regression model can use the L2 Loss, or L1 Loss. These outputs would not be at the same scale at all, and tasks like regression would be alone influencing the network's weights.
Doing segmentation and detection in the same network brings similar problem. Many papers address the issue, often by applying an alpha coefficient to each loss. In my course on HydraNets, I discuss such issues and several techniques to solve them.
Examples of Instance Segmentation algorithms
Since we're talking about YOLO, MASK-RCNN and BlendMask, here are a summary of the most popular instance segmentation algorithms you can search for:
Mask-RCNN (2018): An extension of the Faster-RCNN algorithm thanks to the addition of a segmentation branch.
(2018): An extension of the Faster-RCNN algorithm thanks to the addition of a segmentation branch. CenterMask (2020): An anchor-free instance segmentation model that is based on the CenterNet algorithm (that predicts object centers rather than bounding boxes, and thus can also do 3D object detection)
(2020): An anchor-free instance segmentation model that is based on the CenterNet algorithm (that predicts object centers rather than bounding boxes, and thus can also do 3D object detection) BlendMask (2020): An algorithm that uses the attention mechanism and a feature pyramid network to dynamically combine features from different levels of a convolutional neural network, and achieves state-of-the-art performance on several benchmark datasets.
(2020): An algorithm that uses the attention mechanism and a feature pyramid network to dynamically combine features from different levels of a convolutional neural network, and achieves state-of-the-art performance on several benchmark datasets. YOLACT (2020): A real-time instance segmentation algorithm that combines the speed of object detection with the accuracy of instance segmentation by using a set of parallel convolutional layers to predict instance masks.
(2020): A real-time instance segmentation algorithm that combines the speed of object detection with the accuracy of instance segmentation by using a set of parallel convolutional layers to predict instance masks. SOLO (2020) : A fully convolutional instance segmentation algorithm that assigns instance labels and predicts pixel-wise segmentation masks in a single forward pass.
: A fully convolutional instance segmentation algorithm that assigns instance labels and predicts pixel-wise segmentation masks in a single forward pass. HTC (2020): A model that uses the cascade idea to combine predictions from multiple detections and segmentation streams.
Panoptic, Semantic, and Instance Segmentation
The world of image segmentation is actually much bigger than these two ideas. Many years ago, one of the most asked question was "semantic segmentation vs instance segmentation: which one is best?". And of course, the need is different for them both.
When semantic segmentation is the task of classifying every pixel of an image, instance segmentation is the task of classifying every pixel of an object.
Semantic segmentation vs Instance Segmentation (source)
But semantic segmentation cannot tell the difference between two objects of the same class. If two objects with the same category "car" are detected, the colors stay the same. With instance segmentation methods, we are able to get a richer output format, and thus differentiate between the different instances. But we still don't get the full picture.
So semantic segmentation vs instance segmentation is a lost fight: The only way to do both is to perform something called Panoptic Segmentation.
We get the better of both world: We can assigns a single semantic label to each pixel in an image based on its class, like "road", "car", "building", etc... but we also get to differentiate between separate instances of the same category.
Panoptic Segmentation is the fusion of semantic and instance segmentation
Summary, and learning Instance Segmentation
Here is a summary of what we've been through:
Instance Segmentation is the idea of augmenting object detection by adding a segmentation task to it . It brings many benefits, such as richer context understanding, as well as inference speed gains.
. It brings many benefits, such as richer context understanding, as well as inference speed gains. In Mask-RCNN, we simply add a segmentation head to the architecture , and this branch predicts binary masks using an FCN approach.
, and this branch predicts binary masks using an FCN approach. In an approach like YOLOv7, the segmentation branch is done using BlendMask , which is a model that uses the attention mechanism and fuses several masks together to perform the task.
, which is a model that uses the attention mechanism and fuses several masks together to perform the task. There are many methods for instance segmentation, the most common are Mask-RCNN, YOLO-Seg, YOLOACT, BlendMask, HTC, SOLO, and more.
the most common are Mask-RCNN, YOLO-Seg, YOLOACT, BlendMask, HTC, SOLO, and more. When we fuse instance with semantic segmentation, we get panoptic segmentation , which brings the better of both worlds.
, which brings the better of both worlds. We can use instance segmentation in many fields, from self-driving cars to robotics to satellite imagery.
There are many real-world applications of semantic segmentation, you can read my article about that here. Now if you also need to work at the object level, then there are additional use cases. One interesting example is the nuclei segmentation done for the 2018 data science bowl. When done right, it can also be integrated in surgery robots, as in this repo. Instance segmentation can be used with aerial images, target detection and tracking, agriculture, cinema, robotics, and many more...
Surgery Robot Instance Segmentation (source)
As a computer vision engineer, learning instance segmentation is not only a nice way to get deeper in Computer Vision, it's before anything an excellent way to get started with Multi-Task Learning. Too many engineers still think of neural nets as "one task", but history has proven many times how neural networks can be used for more than one task. It's the case with the instance segmentation models, but also with object detection (the models do both regression and classification), as well as models purely built for multi-task.
An example from my Hydranets course, where the students learn build a network that can do both semantic segmentation and depth estimation:
A HydraNet running both semantic segmentation and depth estimation
| 2023-02-27T00:00:00 |
2023/02/27
|
https://www.thinkautonomous.ai/blog/instance-segmentation/
|
[
{
"date": "2023/02/27",
"position": 93,
"query": "AI job losses"
}
] |
The AI-native telco: Radical transformation to thrive in ...
|
The AI-native telco: Radical transformation to thrive in turbulent times
|
https://www.mckinsey.com
|
[
"Joshan Abraham",
"Jorge Amar",
"Yuval Atsmon",
"Miguel Frade",
"Tomas Lajous"
] |
For workforce planning, AI tools enhance traditional applications by forecasting across supply-and-demand metrics for monthly, daily, and intraday time horizons ...
|
Artificial intelligence (AI) is unlocking use cases that are transforming industries across a wide swath of the world’s economy. From infrastructure that “self-heals” to radically reimagined (and touchless) customer service and experience; from large scale hyper-personalization to automatically created marketing messages and images leveraging Generative AI tools like ChatGPT—it is all a reality today. These AI solutions can powerfully augment and sometimes radically outperform most traditional business roles.
About the authors This article is a collaborative effort by Joshan Abraham, Jorge Amar, Yuval Atsmon, Miguel Frade, and Tomás Lajous, representing views from McKinsey’s Technology, Media & Telecommunications Practice.
The impact from these solutions is becoming evident. AI leaders—the top quintile of companies that have taken the McKinsey Analytics Quotient assessment—have experienced a five-year revenue CAGR that is 2.1 times higher than that of peers and a total return to shareholders that is 2.5 times larger.
Given the numerous challenges the telecom industry has faced in recent years, such as flagging revenues and ROIC, one might expect the industry would have already adopted a full transition to this technology. Yet, based on our experience with operators across the world, telcos have yet to fully embrace AI and an AI-focused mindset. Instead, models are developed once and not enhanced as the business context evolves. Machine learning (ML) is in name only, limiting the ability of the system to improve from experience. Most regrettably, AI investments are often not aligned with top-level management priorities; lacking that sponsorship, AI deployments stall, investment in technical talent withers, and the technology remains immature.
Contrast this disjointed state of affairs with an AI-native organization. Here, AI is viewed as a core competency that powers decision making across all departments and organization layers. AI investments are required to enable most C-level priorities such as more personalized recommendations for customers and faster speed of answer in call centers. Top executives serve as champions of critical AI initiatives. Data and AI capabilities are managed as products, built for scalability and reusability. AI product managers, even those working on foundational products, are celebrated for the benefits they generate for the organization.
Reaching this state of AI maturity is no easy task, but it is certainly within the reach of telcos. Indeed, with all the pressures they face, embracing large-scale deployment of AI and transitioning to being AI-native organizations could be key to driving growth and renewal. Telcos that are starting to recognize this is nonnegotiable are scaling AI investments as the business impact generated by the technology materializes.
While isolated applications of the technology can help individual departments improve, it’s AI connected holistically at all levels and departments that will be key to protecting core revenue and driving margin growth in even the most difficult of environments. Imagine the following not-so-distant scenarios:
Customer focused: Sarah, a New Yorker, is a high average revenue per user (ARPU) customer. Aware that Sarah spends half of her phone usage time on fitness apps, the AI creates an enticing customized upgrade offer that includes a six-month credit applicable to her favorite fitness subscription and NYC-specific perks, such as a ticket to an upcoming concert sponsored by the operator. Knowing Sarah’s high digital propensity, the AI makes the offer available to her as a digital-only promotion.
Employee focused: When Trevor, an associate in a telco mall store, logs in at the start of his shift, he receives a celebratory notification congratulating him on his high-quality interactions with customers the previous day. And because the AI detected that Trevor is underperforming peers in accessory and device protection attach rates, he receives a notification pointing him to coaching resources specifically created to enhance performance in those metrics.
Infrastructure focused: Lucile, director of a capital planning team, uses AI to inform highly targeted network investment decisions based on a granular understanding of customer-level network experience scores strongly correlated to commercial outcomes (for example, churn). The AI provides tactical recommendations of what and where to build based on where customers use the network and on automatically computed thresholds after which new investments have marginal impact on experience and commercial outcomes for the operator.
How these possibilities could become reality is critical to consider, especially given that most telcos currently deploy AI in limited ways that will not drive sustainable, at-scale success.
Why now? The case for becoming AI native
Factors supporting this move for telcos include the following:
Increasing accessibility of leading AI technology: AI-native organizations like Meta continue to grow the open-source ecosystem by making new programming languages, data sets, and algorithms widely available. In parallel, cloud providers have developed multiple quick-to-deploy machine-learning APIs like Google Cloud’s Natural Language API. Generative AI solutions, such as ChatGPT, that are capable of creating engaging responses to human queries are also accessible through API. These two factors, coupled with dropping costs of data processing and storage, make AI increasingly easier for organizations to leverage.
Rapid explosion of usable data: Operators can collect, structure, and use significantly more data directly than ever before. This information includes dataflows from individualized app usage patterns, site-specific customer experience scores, and what can be purchased or shared from partners or third parties. To answer privacy fears raised by consumers and regulators, telcos must also invest in building digital trust, including actively managing data privacy and having a robust cybersecurity strategy and a framework to guide ethical deployment of AI.
Proven use cases and outcomes: AI-Native organizations across industries have deployed AI to achieve four critical outcomes highly relevant to operators across the world: 1) drive revenue protection and growth through personalization, 2) transform the cost structure, 3) enable a frictionless customer experience, and 4) meet new workplace demands. Operators can learn from all of them. Streaming players, for example, have long been known for providing highly curated personalized content recommendations based on past user behavior. To optimize cost and deliver a seamless customer experience, one of the leading US insurance companies leverages AI assistants to reduce and even eliminate human interactions for users to obtain coverage or cancel policies with other carriers. In turn, some of the leading tech companies in the world are known for using AI to highlight the traits of great managers and high performing teams and use those insights to train company leaders.
Technology investments recognized as a business driver: In a post-pandemic world, there is broad consensus among investors and executives that technology investments are not a mere cost center but a fundamental business driver with profound impacts on the bottom line. Despite prospects of economic turmoil and recessionary fears, IT spending is expected to increase by more than 5 percent in 2023, with technology leaders under growing pressure to demonstrate impact on company financials.
Operator bets need hyper charging: As networks and products converge, operators are making bets on becoming cost and efficiency focused, experience-centric, or ecosystem players. AI use cases that are more relevant for each bet can give them a better chance to hypercharge and leapfrog competition.
For the greatest payoff, this shift requires telcos to embrace the concept of the AI-native organization—a structure where the technology is deeply embedded across the fabric of the entire enterprise.
Using AI to reimagine the core business
Telcos have been under relentless pressure over the past decade as traditional growth drivers eroded and economic value increasingly shifted to tech companies. By using AI to its fullest extent, operators can protect their core business from further erosion while improving margins.
As the industry looks to leverage the power of AI, we see six themes gaining prevalence in strategic agendas based on our experience working with telcos across the world.
Hyper-personalize and architect sales and engagement
Leveraging the breadth and depth of user-level data at their disposal, operators have been increasingly investing in AI-enabled personalization and channel steering.
For example, a hyper-personalized plan and device recommendation for each line holder could leverage granular behavioral data—such as number of and engagement with apps installed and device feature usage—to create individualized plan recommendations (superior network speed or streaming service add-ons), promos (“Receive unlimited prepaid data to be used for a music streaming service for only $5 per month”), and messaging for specific devices, locations, and events (“Upgrade to the latest device featuring built-in VR”). Subsequently, using audience segmentation tools, customers can be guided to channels that offer an engaging experience while driving the most profitable sales outcome for the telco. A subscriber, for example, with low-digital propensity, high ARPU, and high churn risk who is living within a few miles of a store, might be a good candidate to nudge to a device upgrade in-store, leading to better customer experience and potentially stronger loyalty for the operator. Or consider a different scenario: this subscriber uses an advanced 5G network in New York City and is a regular user of fitness apps who travels frequently outside the country. As a result, her telco offers a personalized plan recommendation with superior network access, top fitness app subscription perks, and an attractive international data plan.
Case study: An Asia–Pacific operator that launched a comprehensive customer value management transformation powered by AI (with personalization at the core) achieved a more than 10 percent reduction in customer churn and a 20 percent uptake in cross-sell.
Reimagine proactive service
Earlier investments in digital infrastructure combined with predictive and prescriptive AI capabilities enable operators to develop a personalized service experience based on autonomous resolution and proactive outreach.
With fully autonomous resolution, for example, the system can predict and resolve potential sources of customer dissatisfaction before they are even encountered. After noticing a customer is accruing roaming charges while traveling abroad, the AI system automatically applies the optimal roaming package to her monthly bill to minimize charges. It then follows up with a personalized bill explanation detailing the package optimization and resulting savings for the customer, leading to a surprising and positive CX moment.
Operators are also exploring the redesign of digital service journeys with the help of AI assistants serving as digital concierges. Generative AI technologies, including tools such as ChatGPT, have the potential to enhance existing bots through better understanding of more complex customer intents, more empathetic conversations, and better summarization capabilities (For example, when a bot needs to handover a customer interaction to a human rep). A single unified AI assistant will likely also represent a step change in speed, accuracy, and engagement compared to the interactive voice response systems of today.
An AI-powered service organization is a key ingredient to releasing the full capacity of specialized reps for high-value interactions while improving overall customer experience—one of the key battlegrounds for telcos around the world.
Case study: A leading telco is expected to achieve an approximately 10 percent decrease in device troubleshooting calls, powered by a proactive AI engine that considers the customer’s likelihood of calling and issue severity to decide whether to push the most effective resolution via SMS. This proactive engine is also a key element of the operator’s ambition to have the highest customer satisfaction scores among competitors.
Build the store of the future
In retail, AI is leading a revolution in the design and running of stores by streamlining operations and elevating the consumer experience.
Some telcos already use virtual retail assistants displayed on floor screens to conduct multiple transactions with customers, including adding balance to a prepaid account and selling prepaid cards and TV subscriptions. A leading European telco leverages AI tools for delivering more-accurate device grading and trade-ins in the store. The store of the near future includes the following components:
Front of house: Aisle layout and product placement are optimized based on browsing patterns analyzed by machine vision. Digital signage is made relevant to individual customers who are in-store and identified through biometric or geofencing technology. Interactive kiosks serve up personalized promos, service assistance, and wait-time forecasts. Customers are matched with reps who are given nudges with personalized info likely to spark the best interaction and lead to a truly seamless customer experience.
Back of house: Device SKUs are automatically managed to optimize inventory and sales. Stores stock curated assortments based on local preferences surfaced in sales analytics. AI tools such as computer-vision-based grading allows for immediate price guarantees on devices that are traded in.
Outside: Consumers walking near the store receive text or push notifications with a personalized promotion and an invitation to check the product in-store.
Case study: An Asian telco launched a 5G virtual retail assistant in unmanned pop-up stores. The digital human communicates with customers in a personal and friendly way with engaging facial expressions and body language. She supports customers across multiple transactions, from buying prepaid cards to getting SIM card replacements.
Deploy a self-healing, self-optimizing network
The AI-native telco will leverage technology to optimize decision making across the network life cycle stages, from planning and building to running and operating. In the planning and building stages, for example, AI can be used to prioritize site-level capacity investments based on granular data, such as customer-level network experience scores.
In the running and operating phases, AI can prioritize the dispatching of emergency crews based on potential revenue loss or impact on customer experience. AI can also enable a self-healing network, which automatically fixes faults—for example, auto-switching customers from one carrier frequency to another because the former was expected to become clogged. This frees up engineering resources for higher-value-added activities.
Case study: A telecom operator developed an AI-based customer network experience “score” to improve its understanding of how customers perceive their network and to inform network deployment decisions. The AI engine leveraged granular network-level information for every line (e.g., signal strength, throughput) with an ML model to create the score tailored to each customer’s individual network experience and expectations. The operator used the score, which directly correlated with impact metrics such as customer churn or network care tickets, to monitor network performance trending (how the score fluctuated in different regions), to identify opportunities to refine its buildout plan, and to improve how it managed its customer base.
The state of AI in 2022—and a half decade in review
Improve frontline productivity
The AI-native telco also uses AI-enabled tools to optimize workforce planning and coaching of frontline employees across multiple teams, including field force, customer service, and retail associates.
For workforce planning, AI tools enhance traditional applications by forecasting across supply-and-demand metrics for monthly, daily, and intraday time horizons with higher accuracy, more granularity, and full automation. Smart scheduling matches supply with demand, such as reps needed in a call center during particularly busy periods, to meet service level targets as well as customers’ expectations.
Acting as an intelligent coaching manager, an AI-enabled nudge engine provides personalized celebratory and improvement opportunity nudges to employees and their supervisors (Exhibit 1). Coupled with advancements in Generative AI, the impact of the AI nudge-engine might go even further by, for example, simulating customer responses under different scenarios to train reps.
Case study: A telco operator deployed an AI-enabled scheduling and coaching solution for technicians servicing copper and fiber customers. Resulting efficiency gains included 10 to 20 percent capacity generation and improved customer satisfaction scores.
Power intelligent internal operations
AI-powered insights will enhance decision making across business functions, beyond the automation of standardized or low-complexity tasks. In finance, for example, AI can flag outlier invoices for further inspection, while on the accounts receivable side it can predict customers likely to default, triggering mitigating actions. In HR, AI can help flag employees with high attrition or absenteeism risk and the respective drivers while also helping identify informal influencers who can lead change management efforts. Generative AI solutions can help with the development of product marketing copy, the synthesis of customer feedback for research purposes or even enable business users to write simple code to quickly adjust IT applications.
Overall, involving AI in decision making and execution results in higher speed and consistency. Its benefits can be felt everywhere, from contract management and supplier search to onboarding and IT maintenance.
Case study: A UK-based transportation company deployed AI to identify the main drivers of employee attrition and absenteeism. The company then developed targeted interventions for each of the drivers with an estimated 20 to 25 percent reduction in sick pay and attrition costs.
Success factors of AI-native transformation
The what of envisioning being AI native is the relatively easier part of this journey; the how of making the possibilities reality is the tougher challenge. Working on multiyear projects with operators across the world, we’ve identified critical best practices in three areas that are the hallmarks of a successful AI-native transformation: building AI, managing it, and driving its adoption.
Building AI best practices
Developing transformative AI requires a carefully-calibrated approach that follows these core guidelines:
Build core AI capabilities in a modular fashion and with reusability in mind, with the potential to be deployed across multiple contexts in the operator. A core forecasting engine, for instance, can be deployed both in a call center and in a retail setting. This will drive higher ROI for AI investments by decreasing time to deploy and preventing duplication of work.
Tightly integrate AI capabilities with one another based on a model architecture approach that interconnects different AI models to maximize value generation and promote reusability. For example, a digital propensity model will be built as a core model that becomes an input into multiple customer-facing models.
Use digital twins as the foundation for all AI. Digital twins—virtual representations of a physical asset, person, or process with a data product at its core—are the key to unlocking reusable AI. The data in a digital twin is intentionally structured and modeled to enable easy, reusable consumption and governance across needs, and to serve as the single source of truth for all models (Exhibit 2).
Implement machine learning operations (MLOps) best practices to shorten the analytics development life cycle and increase model stability. MLOps typically involve automating the integration and deployment of code underlying AI capabilities.
Rethink the tech talent strategy holistically. Without a deep bench of engineering talent, an AI-native ambition will remain a mirage. Employers should consider expanding their sourcing net to a wider range of universities and learning environments. It’s also critical to improve conditions that developers work under, because developer experience is a top factor in determining an employer’s attractiveness. Constraints on which programming languages and cloud providers’ tools can be used, for example, can have meaningful impact on a developer’s decision to recruit for and stay with an organization, as well as on the developer’s productivity. Because tech talent needs are multifaceted, operators should launch a comprehensive list of initiatives across the employee life cycle.
Managing AI best practices
Maintaining and improving AI capabilities depends on an experimental, iterative mindset focused squarely on product and tech innovation.
Treat AI capabilities as true products by assigning dedicated product managers to oversee them. PMs act as translators between the technical and business teams and are mandated to own the product continuously and develop opportunities to improve it. They ensure that it’s never built as a onetime solution.
Set up AI labs for fast experimentation. Dedicated teams of PMs and data scientists or engineers are granted expedited approval to experiment with new models, test for feasibility, and validate business value before scaling.
Refresh the AI tech stack at least annually to take advantage of new developments. In recent years, there have been significant enhancements in tooling that drastically transformed AI workflows.
Speed up IT and Data Modernization efforts (the complexity of which often slows down AI transformations) by leveraging reference architectures that have been road-tested in multiple transformations across industries. Moreover, build the target cloud-native data architecture following an iterative approach, focused on enhancing the components required for the priority AI use cases first (e.g., data streaming might be key to unlock fraud detection use cases).
Driving AI adoption best practices
Taking a comprehensive approach focused on both what goes into and comes out of models is critical for fostering growing usage of AI:
Ensure AI solutions are considered trustworthy AI, including dimensions such as model explainability, accountability for the outcomes of AI models, and technical robustness.
Make change management a day one focus. Operators need to involve end users of AI-enabled insights through all the stages of the model development life cycle and invest in formal and informal capability building. Operators will also need to take a hard look at replacing and revamping existing processes as well as management practices and roles to be centered around AI.
Next steps toward building the AI-native telco
In many industries, companies have used AI to make their operations more efficient, drive material enhancements in customer experience, and ultimately used it to bring innovative products and services to market more quickly. Operators can learn from these industries and invest in AI to improve their competitiveness in the coming years of economic uncertainty and competitive turmoil. Many operators have already started to do so.
Organizations that talk about adopting AI but move at a slow pace, hoping that a few innovation projects developed at the fringes of the organization and in silos that will come together to create a snowball effect to holistically change how technology informs business decision making, are likely to fail.
Ultimately, the biggest drivers of AI adoption will be CEO-level sponsorship and full executive alignment throughout the AI-native transformation. The art of the possible with the technology has long surpassed what companies have been able to absorb. Without active support from the top level to proactively address organizational inertia, communicate an engaging change story, model new behavior, promote capability building, and make commitments on the required long-term technological investments, AI-native transformation efforts will not succeed.
The journey to becoming AI native will require operators to create a strategic vision and road map that excites and mobilizes the organization, build priority AI capabilities to gain momentum, and bring everyone together to ensure operating model and change management are set up to drive adoption. Embracing large-scale AI deployment across the organization will follow.
The journey is long and requires commitment, but operators that embrace the path to becoming AI native are more likely to emerge as leaders in the next horizon of transformation.
This article was revised on December 19, 2023 to include a new case study on deploying a self-healing, self-optimizing network.
| 2023-02-27T00:00:00 |
https://www.mckinsey.com/industries/technology-media-and-telecommunications/our-insights/the-ai-native-telco-radical-transformation-to-thrive-in-turbulent-times
|
[
{
"date": "2023/02/27",
"position": 58,
"query": "workplace AI adoption"
}
] |
|
Digital Employees and Digital Influencers are About To ...
|
Digital Employees and Digital Influencers are About To Change Everything
|
https://williameveryweek.com
|
[
"William Anderson"
] |
The Ethics of Digital Humans in the Workplace and Online ... Since then, we have seen rapid adoption of AI technology through the software we already use.
|
Digital Employees and Digital Influencers are About To Change Everything
The Ethics of Digital Humans in the Workplace and Online William Anderson 5 min read · Feb 27, 2023 -- Share
DALL·E 2023–02–27 15.05.40 — various prompts and editing
Michael Keaton’s character in Robocop (2014) is Raymond Sellars. He was supposed to be a villain. Still, watching this movie nearly a decade later, he feels more like a hero by contemporary yardsticks. He’s a successful billionaire leading a massive tech company, doing whatever it takes to increase the stock price. If the story was real, we would all be talking about his upcoming Netflix dramatization.
For those unfamiliar with the movie (the original or the remake), the premise is that an injured cop named Alex Murphy is mostly rebuilt as a robot to fight crime. Initially, Murphy is the decision maker, but Sellars, the head of the company behind the rebuild, keeps reducing his will until it becomes questionable whether there is any “human” left inside Robocop.
My favorite line from the movie comes after Sellars is confronted with the fact that it’s illegal to build a robot that thinks it’s a human. He responds, “No. No, no, no. It’s a machine that thinks it’s Alex Murphy. And in my book, that’s legal.”
The Impact of AI Technology On Desire
| 2023-02-28T00:00:00 |
2023/02/28
|
https://williameveryweek.com/is-your-coworker-a-robot-digital-people-are-here-1aa1b4cbbb28
|
[
{
"date": "2023/02/27",
"position": 98,
"query": "workplace AI adoption"
}
] |
Artificial Intelligence in Education. 2023 Survey Insights
|
Artificial Intelligence in Education. 2023 Survey Insights
|
https://www.holoniq.com
|
[] |
25% report successful investment and deployment of AI in 2022, compared to 14% in 2019. AI is gradually shifting from consideration to action; 44% of ...
|
Organizational adoption and applications of AI
Organizations are picking up the pace in their planning and adoption of Artificial Intelligence. 25% report successful investment and deployment of AI in 2022, compared to 14% in 2019. AI is gradually shifting from consideration to action; 44% of respondents have included AI in their short to medium term plans, and although pilots are still happening, these have decreased since 2019. Likewise, those who consider AI to be 'on the radar' but are not planning action have decreased from 24% in 2019 to 14% in 2022.
Figure 3. Organizational planning for AI: 2019 vs 2022
"Like many institutions we are in the planning stage. There are not many solutions out there apart from reporting and analysis of data. Solutions with learning analytics that are predictive are limited."
Looking at specific technologies, education organizations appear to have made most progress embedding Machine Learning into their education operations (38%), compared to 29% in NLP and 24% in Vision.
Reports vary for Vision and Voice applications, with more than a third of respondents having no current plans in place for AI application. These technologies are still relatively new for many organizations, and many tools and applications are still in stages of development or piloting use in different contexts.
AI adoption rationale and expected value creation
The most common reason for adopting AI among our respondents was to improve customer outcomes. 75% of our sample noted this as a priority, compared with 45% who cited cost reduction, and 43% looking to disrupt the market.
The accelerated shift to online learning over the last few years has placed the customer (student) experience in sharp focus for education institutions. Some AI-driven solutions aim to improve student satisfaction and outcomes with personalized learning and support, for example, as well as enabling teachers to design and deliver learning in more efficient and innovative ways.
Overall, there is optimism among both institutions and digital providers for the potential of AI to drive innovation, improve agility and disrupt established ways of operating in education markets and institutions.
Figure 4. Reasons for adopting AI in education
"AI has the potential to transform and optimise the way we work in higher education and our students' learning experiences. It's still in its very early stages at my university, but there is planning in place and leaders who understand the value."
As stakeholders consider the emerging value AI may create, there are high expectations for areas of education where assessment and feedback is central to operations. Around a third of our sample expect significant impact here, and a further 31% expect moderate impact on value.
Figure 5. Where is AI expected to create value?
AI technologies are also expected to bring improved value to Learning Processes and Customer Support, pointing to different parts of the learner experience and lifecycle. AI in Customer Support may bring improvements in marketing, recruitment and enrolment, as well as student support throughout their learning experience. Learning Processes are likely to deploy AI across learning design and learner experience, bringing potential efficiencies but also new ways of designing and delivering learning in different educational contexts.
"AI affects every aspect of student journeys as well as teachers day-to-day lives, scaled to millions of students."
Enablers and barriers to AI adoption
To take advantage of AI’s potential, many organizations have started to include core AI practices and tools that enable them to realize the value of AI at scale. 43% report that senior leaders have shown significant commitment to adopt AI initiatives, and a further 47% note that their organizations are using data effectively to support goals of AI work.
Figure 6. AI practices to enable adoption
Whilst some of these enabling practices are similar to those reported in 2019, others have shifted. There has been an increase, for example, in organizations reporting that they have mapped where all potential AI opportunities lie (40% in 2022, compared to 27% in 2019). On the other hand, fewer are likely to feel that they have access to the talent and skill sets to support AI work now (28% in 2022, vs. 37% in 2019); this may be due to several factors, include global labor shortages in digital skills, as well as increasing complexity and capabilities of the AI tools themselves, which demand new and different talent from within and outside the organisation.
Figure 7. Barriers to adoption
As companies invest and transition towards an AI-driven education ecosystem, they are finding it increasingly hard to recruit the right talent to work on these key technology challenges. 54% reported this as the leading barrier limiting AI adoption plans, compared to 44% in 2019. The second biggest barrier (50% of respondents) was cited as 'under-resourcing for AI', which has risen sharply as an issue since 2019 and is likely compounding the issue of recruiting skilled talent.
"One of the biggest challenges for adopting AI insights in operations is the lack of data literacy across the organization."
Another common and rising theme is a lack of clear organizational strategy in AI, noted by 47% of respondents as a barrier restricting AI adoption. Uncertain/ low expectations on investment returns (25%) and significant infrastructure and other functional costs (31%) are some of the additional challenges limiting adoption of AI in education.
| 2023-02-27T00:00:00 |
https://www.holoniq.com/notes/artificial-intelligence-in-education-2023-survey-insights
|
[
{
"date": "2023/02/27",
"position": 37,
"query": "AI labor market trends"
},
{
"date": "2023/02/27",
"position": 1,
"query": "AI education"
},
{
"date": "2023/02/27",
"position": 1,
"query": "artificial intelligence education"
}
] |
|
Mapped: IMF unemployment forecasts by country for 2023
|
This infographic maps unemployment forecasts by country for 2023
|
https://www.weforum.org
|
[
"This Article Is Published In Collaboration With",
"Visual Capitalist"
] |
Across many countries, the pandemic has made entrenched labor trends worse. It has also altered job market conditions. South Africa is projected to see the ...
|
The IMF's World Economic Outlook projects that South Africa will have the highest jobless rate globally in 2023, estimated at 35.6%.
The US is forecast to have an unemployment rate of 4.6%, which is 1.2% higher than current levels.
The job market is one of the strongest areas of the global economy, but this poses a challenge for central bankers, as it contributes to high inflation.
Mapped: Unemployment Forecasts, by Country in 2023
As 2022 clearly illustrated, the global job market can surprise expectations.
So far, this year is no different. The unemployment rate in six of the G7 countries hovers near the lowest in a century. With an unemployment rate of 3.4%, the U.S. jobless rate hasn’t fallen this low since 1969.
But as some economies navigate a strong labor market against high inflation and hawkish monetary policy, others are facing more challenging conditions. In the above graphic, we map unemployment forecasts in 2023 using data from the IMF’s World Economic Outlook.
In the above graphic, we map unemployment forecasts in 2023 using data from the IMF’s World Economic Outlook. Image: Visual Capitalist / IMF
Uncertainty Clouds the Surface
Across many countries, the pandemic has made entrenched labor trends worse. It has also altered job market conditions.
South Africa is projected to see the highest jobless rate globally. As the most industrialized nation on the continent, unemployment is estimated to hit 35.6% in 2023. Together, slow economic growth and stringent labor laws have prevented firms from hiring workers. Over the last two decades, unemployment has hovered around 20%.
South Africa has the highest unemployment rate Image: Visual Capitalist
In Europe, Bosnia and Herzegovina is estimated to see the highest unemployment rate, at over 17%. It is followed by North Macedonia (15.0%) and Spain (12.7%). These jobless rates are more than double the projections for advanced economies in Europe.
The U.S. is forecast to see an unemployment rate of 4.6%, or 1.2% higher than current levels.
This suggests that today’s labor market strength will ease as U.S. economic indicators weaken. One marker is the Conference Board’s Leading Economic Index, which fell for its tenth straight month in December. Lower manufacturing orders, declining consumer expectations, and shorter work weeks are among the indicators it tracks.
Like the U.S., many advanced countries are witnessing labor market strength, especially in the United Kingdom, Asia, and Europe, although how long it will last is unknown.
A Closer Look at U.S. Numbers
Unlike some declining economic indicators mentioned above, the job market is one of the strongest areas of the global economy. Even as the tech sector reports mass layoffs, unemployment claims in the U.S. fall below recent averages. (It’s worth noting the tech sector makes up just 4% of the workforce).
In 2022, 4.8 million jobs were added, more than double the average seen between 2015-2019. Of course, the pandemic recovery has impacted these figures.
Some analysts suggest that despite a bleaker economic outlook, companies are hesitant to conduct layoffs. At the same time, the labor market is absorbing workers who have lost employment.
Consider the manufacturing sector. Even as the January ISM Purchasing Managers Index posted lower readings, hitting 47.4—a level of 48.7 and below generally indicates a recession—factories are not laying off many workers. Instead, manufacturers are saying they are confident conditions will improve in the second half of the year.
Containing Aftershocks
Today, strong labor markets pose a key challenge for central bankers globally.
This is because the robust job market is contributing to high inflation numbers. Yet despite recent rate increases, the impact has yet to prompt major waves in unemployment. Typically, monetary policy moves like these takes about a year to take peak effect. To combat inflation, monetary policy has been shown to take over three or even four years.
The good news is that inflation can potentially be tamed by other means. Fixing supply-side dynamics, such as preventing supply shortages and improving transportation systems and infrastructure could cool inflation.
As investors closely watch economic data, rising unemployment could come on the heels of higher interest rates, but so far this has yet to unravel.
| 2023-02-27T00:00:00 |
https://www.weforum.org/stories/2023/02/unemployment-forecast-work-country/
|
[
{
"date": "2023/02/27",
"position": 76,
"query": "AI labor market trends"
}
] |
|
Life Sciences AI Use Cases and Trends - An Executive Brief
|
Emerj Artificial Intelligence Research
|
https://emerj.com
|
[] |
In a 2021 survey of life science organizations published by the International Data Corporation (IDC), respondents cited a 65% average increase in AI spending in ...
|
Like many other economic and industrial sectors, AI is beginning to transform operations across life sciences. In a 2021 survey of life science organizations published by the International Data Corporation (IDC), respondents cited a 65% average increase in AI spending in their organizations over the next year.
Life sciences is an enormous umbrella that covers numerous scientific disciplines. This article will present leaders with three overarching trends of AI adoption within the life sciences space, primarily focusing on for-profit companies in pharmaceuticals (pharma) and biomedicine:
AI-driven drug R&D is taking off
Data sharing is driving AI innovation
Many firms could be gauging AI ROI poorly
We then will examine three use cases directly related to these trends:
Drug research and development: Reducing the oncological drug development process by several years through reviewing drug performance and patient outcomes with natural language processing and predictive analytics.
Automated diagnostics: Developing interactive apps using models trained in diagnostic data that lets patients perform their own screenings and answer essential questions on symptoms.
Supply chain management: Reducing waste in manufacturing active pharmaceutical ingredients using deep learning techniques and transformer anomaly detection models to identify critical insights from temporal patterns in the production data.
AI Adoption Trends in Life Sciences
We’ll first look into these trends and their concomitant effects on life science investments in AI solutions.
Trend 1: AI-driven Drug Research and Development is Taking Off
Drug research and development (R&D) is perhaps a biopharmaceutical enterprise’s most common and promising use case. The reason is that the process is so arduous, expensive, and uncertain. According to a 2021 report by the Congressional Budget Office (CBO):
In 2019, the pharmaceutical industry spent $83 billion on R&D, ten times the per-year amount in the 1980s.
The cost of developing a new drug – including capital costs and expenditures on failed drugs – is estimated to be anywhere from less than $1 billion to more than $2 billion. (Independent, mostly non-profit sources such as the American Chemical Society tend to estimate costs on the lower end of this $1-2 billion scale, while research from within the industry may exaggerate expenses. For example, PhRMA, a big pharma trade association, estimates an average development cost of $2.6 billion.)
Companies are already investing big in end-to-end AI for R&D. Per a press release by the American Chemical Society (ACS), “… companies are committing to R&D-wide AI for support along the entire continuum of drug discovery, from identifying targets to designing drugs to analyzing clinical trials.”
The release lists companies that have invested heavily in related AI tech. Some of them have exceeded billions of dollars.
This “continuum of drug discovery” encompasses:
Biology: target discovery and disease modeling
Chemistry: retrosynthesis, small molecule generation, virtual screening
Clinical development: clinical trial design, patient stratification, prediction of trial outcomes
Experts state that AI is not yet mature enough to serve as a fully functional, end-to-end solution. “Much AI has focused on chemistry, whereas biology is a far more complex, difficult-to-predict field,” the release reads. However, the end goal remains the same: use machine learning to analyze vast data stores and develop models capable of autonomous improvement.
Trend 2: Data Sharing is Driving AI Innovation
While drug and vaccine development is perhaps the most ubiquitous application of AI, it is far from the only one. There exist many potential applications of AI across the life sciences value chain, including:
Clinical setup: e.g., designing the trial protocol, trial planning, trial setup, and management
Manufacturing and supply chain: e.g., defect management, order and inventory management, packaging and labeling
Marketing: e.g., market research, advertising and promotion, product lifecycle management
Medical affairs (department tasked with communicating accurate information to clients): e.g., literature research, medical queries, regulatory filing, scientific documentation
Research: e.g., developing novel compounds, molecule identification, and targeting, lab data management
Figure 1: AI Applications Across Life Sciences. (Source: InfoSys)
IDC estimates that computers will have stored approximately 270 gigabytes of healthcare and life sciences data on every person worldwide by 2020. This data trove drives many insights and innovations in healthcare and life sciences.
According to a Deloitte 2022 report, life science enterprises are sharing non-competitive, HIPAA-compliant data. Moreover, these enterprises are supposedly able to do so without concerns for data privacy. Deloitte states that this is possible through an application programming interface (API)-centered data strategy.
Enterprises anticipate the more open sharing of this data, particularly by younger digital natives, resulting in a valuable stream of actionable data points. The intended result is interoperable data sharing across the organization and in collaboration with partners, patients, payers, and providers.
According to a report [pdf] by the U.S. Department of Health and Human Services (DHHS), the sharing and utilization of copious health data has fueled the development of algorithms and machine learning and has accelerated the development of AI applications. The DHHS report cites six major health data types that can be used for AI development:
Administrative and claims data
Clinical data
Clinical trials data
EHR data
Genomic data Patient-generated data
IoT data
Social media data
Social determinants of health data ( defined as “the conditions in the environments where people are born, live, learn, work, play, worship, and age that affect a wide range of health, functioning, and quality-of-life outcomes and risks.”
Trend 3: Many Firms Could Be Substandardly Gauging AI ROI
The IDC survey respondents report the three most popular AI uses in their life science firms as:
Improving employee productivity Developing new products Improving risk management
However, aside from improved risk management, these uses are not those with the highest ROI. Per the survey respondents, the use cases delivering maximum returns were:
Gaining competitive intelligence (i.e., market research) Improving customer experience (CX) Increasing margins Improving risk management Improving product quality
Secondary research appears to strengthen the argument for this trend. In a report published by Deloitte, leaders cited “difficulty identifying use cases with the greatest business value” as the top challenge to AI initiatives.
We must bear in mind the limitations of this assumption:
First, the product cycle in life sciences is much slower than in other industries.
Second, given the massive expenses typically incurred in product discovery and development, turning a profit on pharmaceuticals can take several years following FDA approval.
Therefore, respondents likely would not have seen any ROI regarding AI-augmented product development.
However, it is telling that there appear to be very few use cases related to competitive intelligence, customer experience, and improving product quality. Relative to the highly complex, highly costly AI infrastructure needed for product creation, an AI-enabled platform capable of producing actionable market insights appears both cost-efficient and capable of producing short-term returns. The same can be said for any AI-enabled software that enhances CX.
Three AI Use Cases in Life Sciences
Next, we will discuss three potential use cases within the life sciences sector. We begin with drug discovery, perhaps the industry’s most common AI use case. We follow this up with disease diagnosis before finishing up with automated supply chain management.
Our first use case examines the application of machine learning and natural language processing to help expedite cancer drug research.
Use Case #1: Expediting Drug Development
Cognizant was approached by a large pharmaceutical company that needed a new, more efficient process for reviewing and referencing information on drug performance and patient outcomes.
The two and a half minute long video below details how Cognizant approaches expediting clinical trial operations:
Before implementing Cognizant’s solution, the company had relied on a manual cross-referencing process. This process was apparently costly and time-consuming.
In the clinical trial phase of drug development, scientists must understand and predict how a specific patient’s body will react to their new compound. To accomplish this, they cross-reference vast internal and external data stores. This data includes:
Patient profile data
Novel compound data
Medical literature data
The client company was conducting trials for acute myeloid leukemia (AML). It was amassing large data stores from its clinical trials, medical research, and data from the Cancer Cell Line Encyclopedia (CCLE).
The software appears to be trained with the client’s internal data stores and scientific and medical literature related to AML.
Cognizant states in the case study that its automated solution uses text mining to review online medical journals and scientific research publications. The software uses natural language processing (NLP) to convert unstructured online data into a normalized dataset for analysis.
In the case of this particular client, Cognizant states that its solution is designed to analyze data in clinical trials research during clinical trials. The company states that it used an Agile development model to build an automated data pipeline that intakes this extensive research data, standardizes and analyzes it, and constructs an outcomes report for the researcher.
Cognizant clearly states that the model’s output is a report, but it does not elaborate on its contents.
Regarding outcomes, Cognizant claims:
The solution can scan over 10,000 online resources simultaneously.
97% faster drug outcomes review
Up to a 4-year reduction in the 10-18 year oncological drug development process
8% to 10% cost savings per clinical trial patient
Use Case #2: Automated Diagnosis
Ada is a Berlin-based company that produces an AI-enabled diagnostic application.
The company offers an app of the same name, which they claim can help healthcare providers improve diagnosis accuracy using what appears to be machine learning. Enterprise users, such as clinics, contact the company to inquire about incorporating the platform into existing screening systems.
Individual users can download the app via Google Play or the App Store. The user interaction is as follows:
The application is downloaded for free on Google Play or the App Store.
After creating a profile, the user takes a “symptom assessment.”
The user types in the most prevalent symptom; as the user types, the software auto-populates a list of suggested symptoms, along with a short description.
The user is asked how to enter symptom duration and given five choices, ranging from “less than one day” to “more than one year.”
If the software algorithms detect a potential match at this point, the user is provided with the following data: Summary: A paragraph describing the next best course of action, e.g., seek advice from a doctor or visit the emergency room. Possible causes: A list of one or more potential underlying ailment(s) causing the symptoms and the likelihood (in the form of “# out of # people with these symptoms had this condition.”) “Tell me more”: Additional information on possible causes. A longer description of the possible cause A graphical representation of “# out of # people” and a list of additional symptoms Less likely causes: A list of one or more unlikely potential underlying ailment(s) in a similar “# out of # people” format.
The model is trained by an in-house group of general practitioners and specialists using thousands of medical conditions and many symptoms. The model includes a knowledge base of risk factors and a reasoning engine, which “asks” [1] What possible known ailments may be responsible for the user’s symptoms, and [2] What are the best questions to ask to narrow these ailments down to a probable cause?
The user functionality of the app is on display in the following 40 second video:
An algorithm calculates possible conditions’ likelihood and presents the users with this data. It also provides the user with information about actions to take; for example, scheduling an appointment with a primary care physician or going to the emergency room.
Regarding outcomes, Ada states that while the app is free, the company earns revenue through partnerships with health providers, who integrate the platform into their screening systems. However, as the company is private, it is not obligated to release financial statements.
However, we can get an idea of the company’s – and the app’s – growth by looking at recent funding. In May 2021, the company raised $90 million in seed funding. In a February 2022 Series B round, the company raised an additional $30 million to bring its total capital raise to $120 million within nine months.
The company says:
Its app is the #1 medical app in 130 countries
26 million symptom assessments have been completed
99% of known medical conditions covered
35% more accurate than other symptom checkers
Use Case #3: Automating Supply Chains
Nexocode is an international AI software development company based in Poland. The company was approached by a large manufacturer of active pharmaceutical ingredients, volatile substances responsible for medicines’ beneficial health effects.
According to Nexocode, this manufacturer struggled with the efficiency of its repeatable batch production processes. Over 50% of production went to waste due to quality deterioration. The challenge was identifying critical insights from temporal patterns in the production data. To solve the problem, Nexocode says that it needed to find which parts of the time series data could explain the malfunction. The lack of data on post-batch production complicated the issue.
Nexocode case study documentation states that it trained the solution using data from the production line. The model eventually analyzed new data in real-time, identifying potential outliers using anomaly detection.
The company claims to use deep learning techniques, such as recurrent and convolutional neural networks (RNNs and CNNs, respectively) and transformer models in its anomaly detection model.
The company also applied predictive analytics to track product batches as they move through the manufacturing process. In this way, issues can be resolved in real-time, minimizing production disruptions when possible.
The workflow appears to be as follows:
Data is gathered and aggregated from the production line and then stored.
A time-series analysis is conducted on the imported data
Algorithms and predictive analytics are applied to the data
Alerts and adjustments are made on the current batch, with recommendations for the next production cycle.
The goal of the model was to detect outliers that could lead to quality deterioration. Nexocode states that the model identified critical processes that accounted for the decay in quality.
Nexcode solution workflow (Source: Nexocode)
Regarding outcomes, the company gives only generalizations. Nexocode states that its solution led to “improved efficiency, predictability, and quality assurance of manufacturing operations and yields.”
| 2023-02-27T00:00:00 |
https://emerj.com/life-sciences-ai-use-cases-trends-exec-guide/
|
[
{
"date": "2023/02/27",
"position": 86,
"query": "AI labor market trends"
}
] |
|
Kickstart economic growth
|
Kickstart economic growth – The Labour Party
|
https://labour.org.uk
|
[] |
... universal service obligation. ... We will ensure our industrial strategy supports the development of the Artificial Intelligence (AI) sector, removes planning ...
|
Sustained economic growth is the only route to improving the prosperity of our country and the living standards of working people. That is why it is Labour’s first mission for government. It means being pro-business and pro-worker. We are the party of wealth creation.
This election follows the chaos of the Conservatives’ ‘mini-budget’ and an unprecedented fall in living standards. Their miserable economic record over the past 14 years has seen productivity and wages flatlining, leaving British families significantly poorer than those in France or Germany.
This decline is rooted in two failures.
First, an inability to accept that a strong economy can only be built on the contribution of every community and every person – the many not the few. Second, a failure to acknowledge that sustainable growth requires government to be a strategic partner with business – that markets must be shaped, not merely served.
These twin failures have led to greater economic insecurity – in the financial resilience of households, but also in our national economy – at the very time when our world has become less stable and secure. The Conservatives have failed to grasp the implications of a new era of rising global competition and tension, instead leaving our economy on an increasingly shallow and insecure footing.
It is time to turn the page. Labour will restore stability, increase investment, and reform our economy.
We will embrace a new approach to economic management – securonomics – that understands sustainable growth relies on a broad base and resilient foundations. Our approach will depend on a dynamic and strategic state. This does not mean ever-growing government, but it does mean a more active, smarter government that works in partnership with business, trade unions, local leaders, and devolved governments.
Labour will stop the chaos and support business through a stable policy environment – strengthening our economic institutions, and giving investors the certainty they need to fuel growth. Labour will seek involvement from industry, trade unions, and civil society in our plans for growth, so they can contribute to building a stronger economy in all parts of the country. We will strategically use public investment where it can unlock additional private sector investment, create jobs, and provide a return for taxpayers.
While stability and greater investment will support growth, parts of our economy require substantial reform if we are to create the wealth our country needs. Britain is hampered by a planning regime that means we struggle to build either the infrastructure or housing the country needs.
The country remains too centralised, with the economic potential of too many regions and communities ignored. Our labour market fails to provide secure jobs and, as a result, for far too many people work does not pay.
The innovation, dynamism and sheer hard work of British business and workers has never been in question. The next Labour government will partner with them to kickstart economic growth and rebuild Britain.
| 2023-02-27T00:00:00 |
https://labour.org.uk/change/kickstart-economic-growth/
|
[
{
"date": "2023/02/27",
"position": 63,
"query": "universal basic income AI"
}
] |
|
Can A.I. Treat Mental Illness?
|
Can A.I. Treat Mental Illness?
|
https://www.newyorker.com
|
[
"Dhruv Khullar"
] |
Such algorithmic bias can occur not just by race, but by gender, age, rurality, income ... In 2016, the United Kingdom, a wealthy country with universal ...
|
Woebot is one of several successful phone-based chatbots, some aimed specifically at mental health, others designed to provide entertainment, comfort, or sympathetic conversation. Today, millions of people talk to programs and apps such as Happify, which encourages users to “break old patterns,” and Replika, an “A.I. companion” that is “always on your side,” serving as a friend, a mentor, or even a romantic partner. The worlds of psychiatry, therapy, computer science, and consumer technology are converging: increasingly, we soothe ourselves with our devices, while programmers, psychiatrists, and startup founders design A.I. systems that analyze medical records and therapy sessions in hopes of diagnosing, treating, and even predicting mental illness. In 2021, digital startups that focussed on mental health secured more than five billion dollars in venture capital—more than double that for any other medical issue.
The scale of investment reflects the size of the problem. Roughly one in five American adults has a mental illness. An estimated one in twenty has what’s considered a serious mental illness—major depression, bipolar disorder, schizophrenia—that profoundly impairs the ability to live, work, or relate to others. Decades-old drugs such as Prozac and Xanax, once billed as revolutionary antidotes to depression and anxiety, have proved less effective than many had hoped; care remains fragmented, belated, and inadequate; and the over-all burden of mental illness in the U.S., as measured by years lost to disability, seems to have increased. Suicide rates have fallen around the world since the nineteen-nineties, but in America they’ve risen by about a third. Mental-health care is “a shitstorm,” Thomas Insel, a former director of the National Institute of Mental Health, told me. “Nobody likes what they get. Nobody is happy with what they give. It’s a complete mess.” Since leaving the N.I.M.H., in 2015, Insel has worked at a string of digital-mental-health companies.
The treatment of mental illness requires imagination, insight, and empathy—traits that A.I. can only pretend to have. And yet, Eliza, which Weizenbaum named after Eliza Doolittle, the fake-it-till-you-make-it heroine of George Bernard Shaw’s “Pygmalion,” created a therapeutic illusion despite having “no memory” and “no processing power,” Christian writes. What might a system like OpenAI’s ChatGPT, which has been trained on vast swaths of the writing on the Internet, conjure? An algorithm that analyzes patient records has no interior understanding of human beings—but it might still identify real psychiatric problems. Can artificial minds heal real ones? And what do we stand to gain, or lose, in letting them try?
John Pestian, a computer scientist who specializes in the analysis of medical data, first started using machine learning to study mental illness in the two-thousands, when he joined the faculty of Cincinnati Children’s Hospital Medical Center. In graduate school, he had built statistical models to improve care for patients undergoing cardiac bypass surgery. At Cincinnati Children’s, which operates the largest pediatric psychiatric facility in the country, he was shocked by how many young people came in after trying to end their own lives. He wanted to know whether computers could figure out who was at risk of self-harm.
Pestian contacted Edwin Shneidman, a clinical psychologist who’d founded the American Association of Suicidology. Shneidman gave him hundreds of suicide notes that families had shared with him, and Pestian expanded the collection into what he believes is the world’s largest. During one of our conversations, he showed me a note written by a young woman. On one side was an angry message to her boyfriend, and on the other she addressed her parents: “Daddy please hurry home. Mom I’m so tired. Please forgive me for everything.” Studying the suicide notes, Pestian noticed patterns. The most common statements were not expressions of guilt, sorrow, or anger, but instructions: make sure your brother repays the money I lent him; the car is almost out of gas; careful, there’s cyanide in the bathroom. He and his colleagues fed the notes into a language model—an A.I. system that learns which words and phrases tend to go together—and then tested its ability to recognize suicidal ideation in statements that people made. The results suggested that an algorithm could identify “the language of suicide.”
Next, Pestian turned to audio recordings taken from patient visits to the hospital’s E.R. With his colleagues, he developed software to analyze not just the words people spoke but the sounds of their speech. The team found that people experiencing suicidal thoughts sighed more and laughed less than others. When speaking, they tended to pause longer and to shorten their vowels, making words less intelligible; their voices sounded breathier, and they expressed more anger and less hope. In the largest trial of its kind, Pestian’s team enrolled hundreds of patients, recorded their speech, and used algorithms to classify them as suicidal, mentally ill but not suicidal, or neither. About eighty-five per cent of the time, his A.I. model came to the same conclusions as human caregivers—making it potentially useful for inexperienced, overbooked, or uncertain clinicians.
A few years ago, Pestian and his colleagues used the algorithm to create an app, called SAM, which could be employed by school therapists. They tested it in some Cincinnati public schools. Ben Crotte, then a therapist treating middle and high schoolers, was among the first to try it. When asking students for their consent, “I was very straightforward,” Crotte told me. “I’d say, This application basically listens in on our conversation, records it, and compares what you say to what other people have said, to identify who’s at risk of hurting or killing themselves.”
One afternoon, Crotte met with a high-school freshman who was struggling with severe anxiety. During their conversation, she questioned whether she wanted to keep on living. If she was actively suicidal, then Crotte had an obligation to inform a supervisor, who might take further action, such as recommending that she be hospitalized. After talking more, he decided that she wasn’t in immediate danger—but the A.I. came to the opposite conclusion. “On the one hand, I thought, This thing really does work—if you’d just met her, you’d be pretty worried,” Crotte said. “But there were all these things I knew about her that the app didn’t know.” The girl had no history of hurting herself, no specific plans to do anything, and a supportive family. I asked Crotte what might have happened if he had been less familiar with the student, or less experienced. “It would definitely make me hesitant to just let her leave my office,” he told me. “I’d feel nervous about the liability of it. You have this thing telling you someone is high risk, and you’re just going to let them go?”
Algorithmic psychiatry involves many practical complexities. The Veterans Health Administration, a division of the Department of Veterans Affairs, may be the first large health-care provider to confront them. A few days before Thanksgiving, 2005, a twenty-two-year-old Army specialist named Joshua Omvig returned home to Iowa, after an eleven-month deployment in Iraq, showing signs of post-traumatic stress disorder; a month later, he died by suicide in his truck. In 2007, Congress passed the Joshua Omvig Veterans Suicide Prevention Act, the first federal legislation to address a long-standing epidemic of suicide among veterans. Its initiatives—a crisis hotline, a campaign to destigmatize mental illness, mandatory training for V.A. staff—were no match for the problem. Each year, thousands of veterans die by suicide—many times the number of soldiers who die in combat. A team that included John McCarthy, the V.A.’s director of data and surveillance for suicide prevention, gathered information about V.A. patients, using statistics to identify possible risk factors for suicide, such as chronic pain, homelessness, and depression. Their findings were shared with V.A. caregivers, but, between this data, the evolution of medical research, and the sheer quantity of patients’ records, “clinicians in care were getting just overloaded with signals,” McCarthy told me.
| 2023-03-06T00:00:00 |
2023/03/06
|
https://www.newyorker.com/magazine/2023/03/06/can-ai-treat-mental-illness
|
[
{
"date": "2023/02/27",
"position": 67,
"query": "universal basic income AI"
}
] |
Survey finds many employers laying off workers because of ...
|
Survey finds many employers laying off workers because of ChatGPT
|
https://www.hrreporter.com
|
[
"Jim Wilson"
] |
Artificial Intelligence chatbot ChatGPT came into being late last year and employers are already using it to replace workers, according to a recent report.
|
“There is a lot of excitement regarding the use of ChatGPT,” says Stacie Haller, chief career advisor, ResumeBuilder. “Since this new technology is just ramping up in the workplace, workers need to surely be thinking of how it may affect the responsibilities of their current job. The results of this survey shows that employers are looking to streamline some job responsibilities using ChatGPT.”
Previously, a judge ruled against the termination of an accounting professional after their employer adopted a new computer system.
ChatGPT applications
Employers have been utilizing ChatGPT for their recruitment efforts, finds ResumeBuilder’s survey of 1,000 business leaders in the U.S., conducted on Feb. 15, 2023. Companies use this for:
writing job descriptions (77 per cent)
drafting interview questions (66 per cent)
responding to applicants (65 per cent)
Meanwhile, employers also use ChatGPT for:
writing code (66 per cent)
writing copies/content (58 per cent)
customer support (57 per cent)
creating summaries of meetings or documents (52 per cent)
research (45 per cent)
generating task lists (45 per cent)
“In talent acquisition, the more mundane tasks like writing job descriptions, interview questions, and following up with candidates are already being replaced by ChatGPT. Writing code is another area where this technology can provide output, while employees focus on more strategic initiative,” says Haller.
| 2023-02-27T00:00:00 |
https://www.hrreporter.com/focus-areas/automation-ai/survey-finds-many-employers-laying-off-workers-because-of-chatgpt/373964
|
[
{
"date": "2023/02/27",
"position": 15,
"query": "ChatGPT employment impact"
},
{
"date": "2023/02/27",
"position": 60,
"query": "AI workers"
},
{
"date": "2023/02/27",
"position": 10,
"query": "artificial intelligence layoffs"
}
] |
|
Are Job Seekers Cheating When They Use ChatGPT to ...
|
Are Job Seekers Cheating When They Use ChatGPT to Craft Resumes and Cover Letters?
|
https://www.shrm.org
|
[
"Katie Navarra"
] |
Only 11 percent failed to obtain a job when the interviewer discovered they had used ChatGPT. According to the survey, senior-level executives currently use ...
|
Designed and delivered by HR experts to empower you with the knowledge and tools you need to drive lasting change in the workplace.
Demonstrate targeted competence and enhance credibility among peers and employers.
Gain a deeper understanding and develop critical skills.
| 2023-02-27T00:00:00 |
https://www.shrm.org/topics-tools/news/technology/job-seekers-cheating-use-chatgpt-to-craft-resumes-cover-letters
|
[
{
"date": "2023/02/27",
"position": 23,
"query": "ChatGPT employment impact"
}
] |
|
Labor and Employment: The American Worker
|
Labor and Employment: The American Worker
|
https://home.heinonline.org
|
[] |
This database features an interactive timeline that charts labor efforts to organize from 1842 up to the current decline—and rise—of unions in America.
|
Immerse yourself in the rich history and current landscape of America’s workforce with HeinOnline’s Labor and Employment: The American Worker. This comprehensive database combines legislative histories, Supreme Court case briefs, accounts of historical labor riots, current reports on working conditions, and so much more.
Get a unique perspective with our chart of landmark court cases related to labor and employment law, including links to the full text, synopsis, and explanations of each case’s significance in both labor jurisprudence and history. From state court cases that impacted the entire country, to decisions made in the U.S. Supreme Court, this database covers cases from 1842 to 2018.
In addition to over 10,000 subject-coded titles, our editors have carefully curated hundreds of expertly written scholarly articles on topics like employment protections, labor contracts, collective bargaining, and more, all ranging from 1904 to present and with new articles added each month.
For those looking to further their research, our editors have even selected over 200 highly recommended titles. While full text of these titles is not available in the database, each title is linked to its WorldCat entry to help users locate the book in a nearby library.
| 2023-02-27T00:00:00 |
https://home.heinonline.org/content/labor-and-employment-the-american-worker/
|
[
{
"date": "2023/02/27",
"position": 39,
"query": "AI labor union"
}
] |
|
News in Depth
|
News in Depth
|
https://www.caidp.org
|
[] |
African Union Spearheads AI Strategy; Denmark Launches Digitization Strategy ... AI Committee of European Parliament Begins Work, CAIDP Update 1.12 (Sept.
|
The Need for A Strong Privacy Law, CAIDP Update 2.12 (March 22, 2021) reprinted from the New York Times
| 2023-02-27T00:00:00 |
https://www.caidp.org/news/
|
[
{
"date": "2023/02/27",
"position": 43,
"query": "AI labor union"
}
] |
|
The 2023 State Labor Power 100
|
The 2023 State Labor Power 100
|
https://www.cityandstateny.com
|
[
"City"
] |
Ai-jen Poo. President, National Domestic Workers Alliance. Ai-jen Poo ... He supports the project labor agreement guaranteeing union workers will be ...
|
1. George Gresham President, 1199SEIU George Gresham / 1199 SEIU George Gresham is now in his sixth term as president of 1199SEIU, a role in which he represents almost 450,000 members. Starting out in the union’s rank and file in the 1970s, Gresham worked his way up the ladder, holding a number of positions in the organization before becoming its leader. Last fall, following a coordinated strike at multiple nursing homes in western New York, 1199SEIU secured new contracts for workers at many of those facilities, and one holdout health care network reached a tentative deal with the union to avoid further walkouts. Gresham, who wants labor leaders to embrace young organizers like Amazon Labor Union founder Chris Smalls, is a strong supporter of increased activism within the labor movement.
2. Gary LaBarbera President, New York State Building and Construction Trades Council Gary LaBarbera / Alex Kaplan Photography As president of the New York State Building and Construction Trades Council, Gary LaBarbera speaks for more than 200,000 unionized construction workers all across the state. LaBarbera has worked on various local and state-level councils and task forces to increase diversity in the trades and foster economic development. Among his current priorities, LaBarbera wants to secure opportunities within the $1.4 trillion federal infrastructure bill and enact labor legislation to provide standards around renewable energy projects. He is also the longtime leader of the New York City-based Building and Construction Trades Council of Greater New York.
3. Michael Mulgrew President, United Federation of Teachers Michael Mulgrew / UFT Michael Mulgrew leads New York City’s 200,000 public school teachers and other related educational and school professionals. As president of the United Federation of Teachers, he has been fighting to loosen city funds to hire more full-time teachers to meet the needs of an increased student population – due in part to migrant children entering the system – and to enact new state rules that would reduce class sizes in New York City by September. While Mulgrew’s union is city-based, he often weighs in on educational policies in Albany.
4. Christopher Shelton & Dennis Trainor President; Vice President, CWA; CWA District 1 Christopher Shelton & Dennis Trainor / Communications Workers of America As president of the Communications Workers of America, Christopher Shelton was involved in hammering out an agreement between Microsoft and employees who wanted to unionize last year – a signal victory for workers in the technology sector. The Bronx native was previously vice president of CWA District 1 – a position now held by Long Islander Dennis Trainor, who leads over 150,000 regional members. He is also a New York Power Authority trustee, where he helps lead the state’s transition to renewable energy. Trainor supports an $18 million public-private partnership with Verizon to bring high-speed broadband to rural areas in Onondaga County. CWA has also made major gains in improving conditions for nurses in western New York in recent years.
5. Mario Cilento President, New York State AFL-CIO Mario Cilento / ElWise Noisette With a total of some 2.5 million public and private sector members, the New York State AFL-CIO is by far the largest federation of labor unions in the state. For 30 years, Mario Cilento has served this powerful collective, the past 11 years as its president. When New York City nurses went on strike in January, Cilento spoke up, calling conditions those health care professionals endured “unimaginable.” Last year, Gov. Kathy Hochul appointed Cilento as a labor representative on the state Climate Action Council. The labor umbrella group also makes coveted political endorsements, including backing Hochul’s successful 2022 election.
6. Andrew Pallotta President, New York State United Teachers Andrew Pallotta / NYSUT As president of the New York State United Teachers union, Andrew Pallotta advocates for over 600,000 members. Pallotta, who has launched programs to recruit and train teachers to be union advocates and run for public office, recently implored Gov. Kathy Hochul to fund school meals for all students in the fiscal year 2024 state budget. The union, which recently marked its 50th anniversary, is set to undergo a major transition, with Pallotta planning to retire in April. Pallotta has endorsed Melinda Person, NYSUT’s executive director, to succeed him.
7. Manny Pastreich President, 32BJ SEIU Manny Pastreich / Dave Sanders With over 175,000 members, 32BJ SEIU appointed a new president in December, when Manny Pastreich took over for the retiring Kyle Bragg. Before becoming president, Pastreich was the union’s secretary-treasurer and director of collective bargaining – but his history in the labor movement spans generations. His father was a SEIU organizer, and Pastreich himself began with AFL-CIO in 1996. He has joined with other organizations in investigating inflated costs that insurance companies pay for health care services.
8. Stuart Appelbaum President, RWDSU Stuart Appelbaum / RWDSU Stuart Appelbaum’s bona fides in the labor movement are almost too long to list. He is vice president of the United Food and Commercial Workers International Union, on the AFL-CIO Executive Council and works with a multitude of labor and political organizations. Since 1998, Appelbaum has been president of the Retail, Wholesale and Department Store Union, representing 100,000 members. He is outspoken on Amazon’s treatment of workers, especially the rate of injuries inside its warehouses. In 2021, the state’s first farmworkers union was formed as an RWDSU local.
9. John Samuelsen International President, Transport Workers Union John Samuelsen / TWU of America When he joined a subway track gang 30 years ago, John Samuelsen found conditions so terrible he felt compelled to speak up. Since then, he has risen to lead the Transport Workers Union, a 150,000-member organization that includes Metropolitan Transportation Authority workers. TWU Local 100 – which Samuelsen once led – faces tough negotiations ahead of an expiring contract, seeking worker pay increases as the MTA deals with mounting debt. Samuelsen said the MTA – whose board he sits on – could look to alternative funding sources to plug its deficit, including the proposed congestion pricing tolls. He was recently nominated by New York City Mayor Eric Adams to sit on a board charged with managing the tolling rollout.
10. Pat Kane & Nancy Hagans Executive Director; President, New York State Nurses Association Pat Kane & Nancy Hagans / Jehan LLC Photography, Columbus, Ohio After the devastating conditions they endured in heroic fashion during the coronavirus pandemic, nurses are collectively fighting for a better working environment. As executive director and president of the New York State Nurses Association respectively, Pat Kane and Nancy Hagans are on the front lines of the effort, setting the tone for their 42,000-plus members. Coordinated strikes and sit-ins have been among their tools to get management to make changes, most importantly the need for increased staffing. In October, the union decided to affiliate with National Nurses United to strengthen its influence.
11. Mary Sullivan President, CSEA Mary Sullivan / Joan Heffler Mary Sullivan is in the middle of her first term as president of the Civil Service Employees Association, where she has succeeded Danny Donohue, who spent more than 25 years in the role. Sullivan, who has served in a number of leadership roles in the union, is the first person in CSEA history to rise to the presidency from local government. In August, the state ratified a five-year labor agreement with CSEA, guaranteeing annual raises over the life of the contract and a one-time bonus.
12. Wayne Spence President, New York State Public Employees Federation Wayne Spence / PEF Since being elected as New York State Public Employees Federation’s first African American president in 2015, Wayne Spence has led over 50,000 professional, scientific and technical workers in the state. Among his recent priorities: battling an anti-union opt-out campaign directed at his members; going to bat for nurses; and supporting legislation that penalized facilities for forcing so-called mandatory overtime. In November, Spence appointed a team to negotiate with the state on a new contract to replace an agreement that will expire in April.
13. Rich Maroko President, Hotel and Gaming Trades Council Rich Maroko / Hotel and Gaming Trades Council, AFL-CIO There are almost 40,000 members of the Hotel and Gaming Trades Council, where Rich Maroko has been at the helm since 2020. Recently, Maroko implored members, many of whom are first- or second-generation immigrants, to join relief efforts to assist thousands of migrants bused here by Texas Gov. Greg Abbott. Maroko was also on a panel that made recommendations for New York City and the state to work together to revitalize the region. His unionized members are also set to capitalize on the state’s looming expansion of full-fledged casino gambling in the downstate region.
14. Armand E. Sabitoni General Secretary-Treasurer and New England Regional Manager, Laborers’ International Union of North America Armand E. Sabitoni / Provided With half a million members behind him, second-generation laborer Armand E. Sabitoni holds a number of titles at the Laborers’ International Union of North America, where he is both the union’s general secretary-treasurer and its New England regional manager. Sabitoni applauded an agreement with the state – guaranteeing the use of union workers – to build a 339-mile power transmission line that would bring renewable energy to New York City. For years, Sabitoni has said laborers are prepared to work on clean energy infrastructure projects.
15. Roberta Reardon Commissioner, State Department of Labor Roberta Reardon / NYS DOL Actor-turned-labor leader Roberta Reardon represented the 160,000 members of SAG-AFTRA before taking the job as commissioner of the state Department of Labor. Public service workers got a reprieve recently when the agency announced measures to expand and simplify its student loan forgiveness program. Late last year, Reardon revealed that the state paid out $4 billion in fraudulent unemployment insurance claims during the pandemic – less than half of what a state comptroller’s audit estimated – and less than other states reported. She accepted a wage board recommendation last fall to gradually reduce the overtime threshold to 40 hours a week for farmworkers.
16. Jessica Ramos Chair, State Senate Labor Committee Jessica Ramos / Courtney Harvier State Sen. Jessica Ramos’ mother was just 24 years old when she crossed the border all alone, and her father was arrested during an immigration raid at his workplace in the 1980s. Their experiences as undocumented workers helped shape her politics and advocacy. At Build Up NYC, she worked as a union advocate representing construction and hotel workers. Now, Ramos is a state senator, serving as chair of the chamber’s Labor Committee, where she has championed major legislation, including a measure to increase the state’s minimum wage and link increases to the rate of inflation.
17. Randi Weingarten President, American Federation of Teachers Randi Weingarten / AFT Since 2008, Randi Weingarten has been president of the 1.7 million-member American Federation of Teachers. Prior to her current post, she led the United Federation of Teachers, the New York City local of the union. As befits her high-profile role, Weingarten regularly comes under fire from the right wing, most recently from Mike Pompeo, who was secretary of state in the Trump administration. Pushing back against recent Republican talking points, a poll commissioned by the AFT showed parents are not concerned about a “woke” agenda being taught in schools.
18. Latoya Joyner Chair, Assembly Labor Committee Latoya Joyner / New York State Assembly Assembly Member Latoya Joyner was reelected to her seat in the state Legislature representing District 77 last year and is continuing in her role as chair of the chamber’s influential Labor Committee. Among other legislative and policy issues related to labor, the committee is currently reviewing the impact of the state budget on workforce development programs administered by the state and addressing workforce shortages. Joyner is also sponsoring a bill with state Sen. Jessica Ramos that would raise the minimum wage and peg future increases to inflation.
19. Thomas Gesualdi President, Teamsters Joint Council 16 Thomas Gesualdi / Jim Saah Thomas Gesualdi, a third-generation Teamster, leads 120,000 workers in downstate New York as president of the Teamsters Joint Council 16. The Teamsters had a hand in crafting the recently enacted Warehouse Worker Protection Act – which was designed to increase safety for employees in the e-commerce and warehouse industries – and are fighting to increase the minimum wage. Gesualdi also celebrated the preservation efforts on Long Island to save a park slated to be sold to construct an Amazon distribution center.
20. Lynne Fox International President, Workers United Lynne Fox / Susan Beard Design Representing more than 86,000 workers in the apparel, textile, food service and other industries, Workers United International President Lynne Fox is helping to lead the organization into the future. Starbucks employees are organizing under the union’s name, driving last season’s so-called “Red Cup Rebellion” in protest. Fox penned a personal rebuttal to Starbucks CEO Howard Schultz when the company withheld benefit increases from its unionized workers. Fox is also chair of the board of union-owned Amalgamated Bank – the first woman to hold the position.
21. Thomas DiNapoli State Comptroller Thomas DiNapoli / Andrew Hill State Comptroller Thomas DiNapoli manages one of the largest pension funds in the U.S. for over 1.1 million participants. DiNapoli reported that the fund earned over 9% in 2022 despite an overall bear market. With such a large fund, he wields some power. He is pledging to invest in more minority- and women-owned companies and asked Southwest Airlines, where the fund is a major shareholder, to address fixes for its holiday travel meltdown.
22. Robert Jackson Chair, State Senate Civil Service and Pensions Committee Robert Jackson / Office of Senator Jackson As Gov. Kathy Hochul pledged to ramp up hiring efforts to return to pre-pandemic levels, state Senate Civil Service and Pensions Committee Chair Robert Jackson criticized the state’s ability to recruit with its current Tier VI pension program. A recent change reduced the number of years of service needed to be fully vested in Tier V and VI from 10 to five for state employees – a clear win for workers.
23. Fred Kowal President, United University Professions Fred Kowal / UUP Communications Director Mike Lisi The son of union workers, Fred Kowal has been leading the United University Professions union as president, which represents the faculty and staff on 29 campuses within the SUNY system, for the past 10 years. Last fall, Kowal led rallies at various SUNY campuses in a call for increased funding from Albany to close budget deficits at 19 campuses. He also threw his support behind SUNY’s new chancellor, John King Jr., who has allocated $53 million to hire more teachers.
24. Christopher Erikson Sr. Business Manager, IBEW Local Union 3 Christopher Erikson Sr., whose grandfather was the legendary labor leader Harry Van Arsdale Jr., followed up his electrician’s apprenticeship by earning a bachelor’s degree in labor/management relations. By 2006, he was elected business manager of the International Brotherhood of Electrical Workers Local Union 3, where he has since advocated for the local’s 28,000 members. Erikson’s union supports new projects to stem climate change and create jobs for workers in the green energy sector.
25. John Durso President, Long Island Federation of Labor John Durso / Local 338 RWDSU, UFCW The Long Island Federation of Labor counts more than 250,000 workers among its members from over 160 unions. Since 2005, John Durso has served as the organization’s president, as well as president of Local 338 since 1999, which represents almost 13,000 workers in supermarkets, drug stores and other industries. Durso, who recently voiced his support of a plan to build a hotel and casino at Nassau Coliseum on Long Island, has received a number of awards over the years for his support of diversity, immigration and the environment.
26. Thomas Carey President, Westchester-Putnam Central Labor Body Thomas Carey / Kansas Carey A union member ever since he graduated high school in 1981, Thomas Carey is the president of Westchester-Putnam Central Labor Body, where he focuses on priorities like promoting legislation that protects workers and gauging potential candidates for elected office. The organization is an affiliate of a number of other local unions, including teachers, firefighters, nurses and stagehands. Carey, who continues to express his concerns over the staffing and working conditions at local hospitals for nurses and patients, is also a business agent at UA Local 21.
27. Richard Wells President, Police Conference of New York Richard Wells / Provided Richard Wells’ policing career began in 1973, when he joined a Long Island village police force. Five years later, he was elected a Hempstead Police Benevolent Association delegate, setting him on the path to labor leadership that culminated in his becoming president of the Police Conference of New York, a statewide coalition. Last year, his organization got even bigger when it unanimously voted to join forces with the New York State Association of PBAs, swelling its ranks to more than 50,000 law enforcement officers in the state.
28. Sam Fresina President, New York State Professional Fire Fighters Association Sam Fresina / NYSPFFA Since 2016, Sam Fresina has been president of the New York State Professional Fire Fighters Association, an 18,000-member collective encompassing 107 local unions. A former firefighter himself, Fresina’s career began while he was serving in the U.S. Air Force. He spoke out last year against a plan to add volunteers to a fire department in upstate New York, calling it reckless. The association notched recent legislative victories in Albany, including a law to ban toxic chemicals in furniture and has pushed for changes in how pensions are calculated.
29. James Mahoney General Vice President, International Association of Bridge, Structural, Ornamental and Reinforcing Iron Workers An ironworker since the early 1980s, James Mahoney joined the International Association of Bridge, Structural, Ornamental and Reinforcing Iron Workers early on in his career. He took on a number of leadership roles at the union until he was selected to be general vice president in 2015. Mahoney has been in recent conflict with Gov. Kathy Hochul. After the union endorsed her, he felt betrayed by her choice for the state’s chief judge – and helped lead the charge in successfully blocking the nominee, Hector LaSalle. Mahoney then allegedly had his invite to the governor’s State of the State address revoked.
30. Michael Powers President, New York State Correctional Officers and Police Benevolent Association In 2014, after years of active involvement in his union, Michael Powers was elected president of the New York State Correctional Officers and Police Benevolent Association. Powers, who worked as a corrections officer for more than 20 years, has demanded a repeal of the HALT Solitary Confinement Act, which restricts disciplining of inmates and which his union believes has led to a record number of assaults against officers. He cited data that showed a 31% increase in overall violence since the law went into effect.
31. Terrence Melvin Secretary-Treasurer, New York State AFL-CIO Terrence Melvin / Crystal Melvin New York State AFL-CIO Secretary-Treasurer Terrence Melvin holds the second-highest position in the organization. Union leadership is something Melvin has aspired to since he embarked on his career: When he was 21 years old, he became the youngest CSEA Local president, leading more than 2,000 members. He has also served as president of the Coalition of Black Trade Unionists for more than 10 years.
32. Stacey Pheffer Amato Chair, Assembly Governmental Employees Committee After a tight race that was not decided until two months after Election Day, Assembly Member Stacey Pheffer Amato retained her seat in the state Legislature. She has now succeeded former Assembly Member Peter Abbate Jr. as the chair of the Governmental Employees Committee, which is a leading legislative authority on all public employees in New York. Pheffer Amato was endorsed by a number of unions, including New York State United Teachers and the New York State Public Employees Federation.
33. Karines Reyes Assembly Member Karines Reyes / New York State Assembly After becoming a nurse, Karines Reyes took a path that led her to become an advocate for her union and then to public service in the Assembly, saying she saw firsthand how much of the progress they made for workers came out of Albany. Last fall, Reyes, who serves on the Assembly’s Labor Committee, sponsored legislation called the Standing is Tiring Act to allow workers with jobs that require them to be on their feet all day – like nurses – to have time to sit down.
34. Brenda McDuffie, David Fisher & Denis Hughes Members, Farm Laborers Wage Board Last fall, this trio offered a final ruling and report on a hot topic: At what point do farmworkers in New York qualify for overtime? In a 2-1 vote, the Farm Laborers Wage Board recommended reducing the threshold to 40 hours a week, down from 60, phased in over the next decade, and the state labor commissioner agreed to implement the recommendation. Denis Hughes, the former state AFL-CIO president, and former Buffalo Urban League leader Brenda McDuffie voted in favor of the change, while David Fisher, who’s on the New York Farm Bureau board, voted “no.” Republican lawmakers in Congress and in the state Legislature have opposed the decision, and even some Democrats have sought to postpone the changes.
35. Henry Rubio President, Council of School Supervisors and Administrators When two of New York’s largest school administrator affiliates joined forces to combine their bargaining and political powers last fall, Henry Rubio found himself changing jobs. First, the New York State Federation of School Administrators, representing New York City, Yonkers and Buffalo, where he was president, entered into a formal agreement with its sister organization, the School Administrators Association of New York State. Rubio was elevated to be a board member of the combined affiliate group. Then, late last year, Rubio was chosen to replace the retiring president of the Council of School Supervisors and Administrators.
36. James Shillitto President, Utility Workers Union of America Local 1-2 James Shillitto / John Capra While he now serves as president of the Utility Workers Union of America Local 1-2, James Shillitto was a card-carrying power lineman for 30 years. A proposal to convert a Queens fossil fuel plant to clean energy was praised by Shillitto, saying workers are ready for its next chapter. He applauded state legislation to strengthen disaster preparedness by exempting utility workers from emergency travel bans. Shillitto is a member of the Clean Energy Jobs Coalition, which promotes a sensible approach to the clean energy economy.
37. Ai-jen Poo President, National Domestic Workers Alliance Ai-jen Poo / Othello Banaci The National Domestic Workers Alliance represents house cleaners and home health caregivers, many of whom are women, immigrants and minorities. President Ai-jen Poo is no stranger to the spotlight, championing the cause of these workers in books, podcasts, television, New York Times op-eds and on Capitol Hill. She recently signed with a Hollywood agent, increasing her exposure. The alliance is pushing for a number of issues, including a national Domestic Workers Bill of Rights and a pathway to citizenship for essential immigrant workers.
38. Richard Bensinger, Jaz Brisack, Michelle Eisen & Evan Sunshine Organizers, Starbucks Workers United Evan Sunshine / Huanting Liu First they took on Howard Schultz. Now, they’re going after Elon Musk. Starbucks Workers United, which is part of Workers United Upstate, has made national headlines for its efforts to organize at the popular coffee chain, starting in Buffalo (where Workers United organizer and adviser Richard Bensinger and Starbucks baristas Jaz Brisack and Michelle Eisen were on the front lines of the effort). Hundreds of Starbucks locations around the country have followed their lead, including in Ithaca, where Evan Sunshine helped organize a location that Starbucks shut down. More recently, another labor organizing effort has gotten underway at Musk’s Tesla factory in Buffalo, with Starbucks Workers United organizers including Brisack on board.
39. Gary Bonadonna Jr. Manager, Workers United Rochester Regional Joint Board Gary Bonadonna Jr. has been brewing up unionization efforts in western New York coffee houses since baristas at a local franchise asked his Workers United Rochester Regional Joint Board for help. The idea caught fire, leading to the first Starbucks to unionize. Workers at Remedy House Coffee in New York City just announced intentions to join. The union, with over 9,500 workers in an array of industries, is in the middle of another potential crisis: Workers at a clothing factory are at risk of losing medical coverage because the employer is delinquent in health insurance payments.
40. Sochie Nnaemeka State Director, New York Working Families Party Sochie Nnaemeka / Connie Chavez Both the Working Families Party and its New York state director have deep roots in the labor movement. The left-leaning third party was formed in part by labor unions, although some left the WFP due to a dispute over supporting then-Gov. Andrew Cuomo. Sochie Nnaemeka, who became state director in 2019, previously organized cafeteria, custodial and casino workers and led labor-backed electoral campaign efforts in New Haven. She has touted the WFP’s successful efforts to expand child care and paid sick leave and raising the minimum wage.
41. Pete Meringolo Chair, New York State Public Employee Conference Pete Meringolo / New York State Public Employee Conference A decorated Vietnam War veteran and former captain in the New York City Department of Correction, Pete Meringolo fought for his fellow officers as president of the Correction Captains’ Association. As chair of the New York State Public Employee Conference, Meringolo now leads over a million public workers to provide the 80-plus unions in the conference with a unified voice in Albany. He recently showed support for Assembly Member Stacey Pheffer Amato, who is the new chair of the chamber’s Governmental Employee Committee, the leading legislative authority on all public employees in the state.
42. Rafael Espinal Executive Director, Freelancers Union Rafael Espinal / Olivia Locher Drawing on his family history – his parents were both freelancers and union members – Rafael Espinal’s work on laws giving independent workers increased protections was a key focus during his time as a New York City Council member. This type of commitment ultimately led to him becoming the executive director of the half-million member Freelancers Union. In the work from home and gig economy age, Espinal’s work might be more important than ever. He hopes to duplicate the success he had in city-level legislative protection for freelancers across the country.
43. Peter DeJesus Jr. President, Western New York Area Labor Federation Peter DeJesus Jr. / Yves-Richard Blanc Born and raised in Buffalo, Peter DeJesus Jr. first became involved in union organizing on the factory floor. In 2021, he rose to become the first minority president of the Western New York Area Labor Federation with 165 unions representing 140,000 total members. He supports the project labor agreement guaranteeing union workers will be on the job to build a new Buffalo Bills football stadium, which starts construction this year. DeJesus was an invited guest at President Joe Biden’s State of the Union address this year.
44. Sparrow Tobin President, Hudson Valley Area Labor Federation Sparrow Tobin / Steve Moses Photography Sparrow Tobin has been president of the Hudson Valley Area Labor Federation and its 130,000 members since 2019. Tobin, a social studies teacher who also serves as an alderman on the Middletown Common Council, previously spent more than 12 years working for the New York State United Teachers union. This year, the federation wants to advance a number of legislative priorities for workers, including tying the minimum wage to inflation, eliminating noncompete agreements and adding Tier VI state pension reforms on top of a recent victory rolling back vestment from 10 years to five years.
45. Ann Marie Taliercio President, Central New York Area Labor Federation Since 1990, Ann Marie Taliercio has been president of Unite Here Local 150, a union representing workers in hospitality, textiles and other industries. In 2009, she became president of the Central New York Area Labor Federation, which represents more than 100,000 members from 200 regional unions. Controversy over replacing the Interstate 81 overpass in Syracuse with a street-level highway has pitted Taliercio against construction union leaders who want work to begin.
46. Daniel C. Levler President, Suffolk AME Daniel C. Levler / Suffolk AME Daniel C. Levler, president of the Suffolk Association of Municipal Employees, faced a major challenge last year when Suffolk County computer systems were hacked. Levler called for protections to be put in place for employee personal data and to expedite overtime pay for workers dealing with the crisis. Levler, who has been leading the 10,000-member union since 2015, hosts a weekly YouTube show called “Suffolk Matters,” where he interviews union members who do important work around the county.
47. Brandon Mancilla Regional Director, UAW Region 9A The United Auto Workers held its first direct elections for leadership in November, a function of a settlement with the U.S. government. Brandon Mancilla won as UAW Region 9A director and was sworn in last December, replacing Beverley Brakeman. Mancilla saw firsthand how unions helped his family after immigrating to New York City from Guatemala. Mancilla has been a leader at a number of UAW locals, including as president of Local 5118 for Harvard graduate students and as a staff organizer at Local 2325 for the Association of Legal Aid Attorneys in New York City. Late last year, striking workers at UAW Local 7902 representing part-time faculty at The New School in Manhattan reached a tentative agreement and over 250 workers at book publisher HarperCollins, members of UAW Local 2110, reached a tentative agreement this month – both under District 9A. The election for UAW Region 9 director has gone to a runoff.
48. Dan DiClemente President, AFSCME Council 66 Dan DiClemente / Amorette Miller With a myriad of industries under its purview, American Federation of State, County and Municipal Employees Council 66 represents over 8,500 public and nonprofit sector workers in New York. As council president, Dan DiClemente manages the operations of the union affiliate members. DiClemente, who is also president of a nonteaching union in the Rochester City School District, is dealing with the suspension of three security guards after a security video of a January school shooting was leaked. He called for the return of armed school resource officers in the district.
49. Samantha DeRiso President, Central New York Labor Council Samantha DeRiso / Karl Ermisch Marrone Photography Before powerhouse organizer Samantha DeRiso became the first female president of the Central New York Labor Council, which encompasses more than 17,000 individuals in 63 unions, she had extensive experience fighting for workers’ rights with the United Food and Commercial Workers union. In her time as an organizer, she has mobilized thousands of workers, often being called upon to travel across the country to assist in other regions.
50. Seth Cohen President, Capital District Area Labor Federation As president of the Capital District Area Labor Federation, Seth Cohen is responsible for guiding the efforts of 120,000 members from various unions around the Albany region. Quality assurance testers in Albany at video game company Activision Blizzard have been attempting to unionize since July with an affiliated union CWA Local 1118 under Cohen’s federation. The group, which calls itself Albany Game Workers Alliance/CWA, are still bargaining with the company. Recently, Cohen received the Kate Mullany Medal from the American Labor Studies Center for his contributions to the labor movement.
51. Lori Ann Ames National President, United Service Workers Union Lori Ann Ames / United Service Workers Union Lori Ann Ames has one of the more interrelated job histories ever seen on this list. Among other titles, she is the international executive vice president of the International Union of Journeymen and Allied Trades and the national president of the United Service Workers Union, an affiliate of IUJAT, which includes workers in construction, energy and automotive industries and other fields. Since the pandemic began, she has testified twice before Congress on behalf of another IUJAT affiliate, Home Healthcare Workers of America, where she is the national secretary-treasurer.
52. Rebecca Dixon Executive Director, National Employment Law Project Rebecca Dixon / Simone Forgione, Pro Headshots Now Rebecca Dixon is on the front lines of the fight for workers’ rights. As head of the National Employment Law Project, Dixon highlighted disparities and concerns in what was generally considered a stellar January jobs report, especially a higher rate of unemployment for minorities and an increase in the percentage of workers reporting that they were working multiple jobs to compensate for the impact of inflation. She is also advocating for a higher federal minimum wage and a fix to inequities in the unemployment insurance system.
53. William Lynn Business Manager, IUOE Local 30 William Lynn / IUOE Local 30 International Union of Operating Engineers Local 30 workers maintain some of the most iconic facilities in New York, including Yankee Stadium and the Statue of Liberty. Business Manager William Lynn has helped keep the union humming along since 2004, when he was first brought into the business office as a dispatcher. Last fall, Local 30 workers at the Museum of Modern Art protested, saying they were asked by management to give up raises during the pandemic to preserve jobs but new contract negotiations were not providing fair compensation.
54. Philip Rumore President, Buffalo Teachers Federation Philip Rumore / Buffalo Teachers Federation Philip Rumore began his teaching career working with emotionally disturbed children, a fulfilling challenge that kept him in Buffalo even after being accepted to graduate school in another state. The Long Island native has been president of the Buffalo Teachers Federation since 1981. Last year, the union issued a vote of no confidence in their superintendent over a rise in school violence; he resigned last March. The union, led by Rumore, is currently engaged in contract negotiations with the district.
55. Samantha Rosado-Ciriello President, Yonkers Federation of Teachers Samantha Rosado-Ciriello / Tom Ciriello Photography Samantha Rosado-Ciriello knows firsthand about the challenges faced by teachers on a daily basis. Her experiences as a kindergarten teacher in undersupplied classrooms forced her to become resourceful. Rosado-Ciriello, who is now president of the Yonkers Federation of Teachers, wrote in a recent op-ed that the lack of supplies, equipment and services for the 3,600 teachers in her union limits their ability to do their jobs to the best of their abilities. She also lodged complaints about alleged anti-union statements by school administrators directed at teachers.
56. Noel DiGerolamo President, Suffolk County PBA Noel DiGerolamo / Courtney Betcher Noel DiGerolamo has been leading the Suffolk County Police Benevolent Association as president since 2012, but his history with the union goes back over 20 years to when he was first selected as a union delegate soon after joining the police force. He has been outspoken against policies and rhetoric that he argues harms rank-and-file officers. The union recently filed a lawsuit with the county claiming its 2021 donation to the campaign committee for Suffolk County District Attorney Ray Tierney was not unethical, as determined by a county board.
57. Charlene Obernauer & Jessica Garcia Executive Director; Chair, New York Committee for Occupational Safety and Health Charlene Obernauer / Groundswell Fund Charlene Obernauer has spent nearly a decade at the helm of the New York Committee for Occupational Safety and Health, a nonprofit organization that advocates for safer working conditions on behalf of employees and unions. In recent years, it has applauded improved ventilation regulations for nail salons, drawn attention to construction site fatalities and called for changes at Amazon’s distribution warehouse on Staten Island. The organization’s board chair is Jessica Garcia, who’s the assistant to the president of the Retail, Wholesale, and Department Store Union and also is the sole union representative on the state Cannabis Control Board.
58. Noemi Barrera & Mártir Zambrano Union Organizer; Farmworker RWDSU Local 338; Pindar Vineyards Noemi Barrera & Mártir Zambrano / Local 338 RWDSU, UFCW In 2021, Pindar Vineyards workers on Long Island became the first to unionize under the state’s Farm Laborers Fair Labor Practices Act, organizing under Retail, Wholesale and Department Store Union Local 338, which, along with a number of other organizations, banded together to get the law passed. Immediately afterward, Mártir Zambrano joined 15 other workers to organize at Pindar. Having worked at the vineyard for over 20 years, Zambrano became their de facto leader, according to Noemi Barrera, union organizer at RWDSU. Barrera, who has been at Local 338 for 11 years, had helped with plenty of other organizing efforts before, but this was her first time leading the charge. She is helping the workers get basic rights promised under the law, including new rules governing the threshold at which farmworkers are paid overtime, a guaranteed 24-hour rest period, access to workers compensation and paid family leave. Barrera’s parents were Ecuadorian agricultural workers, so she knows what the Pindar workers are fighting for. She says the battle is still being waged, having met several times with management over the years. They are now seeking mediation to resolve their issues.
59. Adam Urbanski President, Rochester Teachers Association Adam Urbanski / American Federation of Teachers Adam Urbanski has experienced extreme highs and lows already this year in his job as president of the Rochester Teachers Association. First, teachers got a new three-year contract approved unanimously by the school board. Then, the unfathomable happened when a shooter showed up at a school and fired at a 16-year-old student. Thankfully, no one was hurt, but the incident prompted Urbanski to call for police to come back into schools – something that was cut from the budget a few years ago.
60. Nicole Capsello President, Syracuse Teachers Association Nicole Capsello / Syracuse Teachers Association Nicole Capsello began her career as a substitute teacher in special education in the Syracuse City School District. Now, after years of serving in different leadership roles in the Syracuse Teachers Association, she is president of the union. Capsello said the cost and availability of health care was one of her top concerns, along with an alarming lack of mental health care for both teachers and students. Another major challenge she will face this year: a dearth of teachers to fill open positions in the district.
61. Louis Picani President, Teamsters Local 456 Louis Picani / Dominick Cassanelli, Jr. The Teamsters Local 456 keep things moving around Westchester and Putnam counties, and union President Louis Picani makes sure the local’s 5,000 members are well represented. Picani was part of a consortium that called for the state to make sure $5 billion in federal funding is used to fix ailing roads and bridges in the state. He is also a vice president at the Westchester-Putnam Central Labor Body, an affiliate of the AFL-CIO representing over 150,000 workers.
62. Karen Cacace Labor Bureau Chief, Office of the State Attorney General Karen Cacace / Jermaine Francis, Office of the Attorney General In her job as the Labor Bureau chief in the state attorney general’s office, Karen Cacace is in charge of enforcement of state labor laws, helping to recover millions of dollars in wages stolen by employers from workers. She recently testified to legislators about creating a state-level agency that would have greater regulation of workplace safety. Cacace also represents the office in front of the state Department of Labor and state Workers’ Compensation Board.
63. John F. Hutchings & Vincent Albanese Executive Director; Director of Policy and Public, Affairs New York State Laborers’ Organizing Fund Vincent Albanese / NYSLOF Executive Director John F. Hutchings leads the New York State Laborers’ Organizing Fund, which represents over 44,000 workers and 24 construction unions around the state, with a mission of finding new job opportunities and bringing in new members. Vincent Albanese has been a voice of the union, expressing support for clean energy initiatives around the state, including the $4.2 billion Clean Water, Clean Air and Green Jobs Environmental Bond Act approved by voters last year, saying it would create jobs that are good for union workers. The organization, along with other labor unions, recently stood in solidarity with New York nurses striking for a better contract and safer working conditions.
64. Patrick Purcell Executive Director, New York State LECET Patrick Purcell / Jeff Rae As the leader of New York State Laborers-Employers Cooperation and Education Trust, Patrick Purcell works to promote affiliated laborers’ locals in the state, bringing together unions and contractors to identify new opportunities and secure jobs for union workers. Purcell, who has led the coalition of 1,500 signatory contractors and 16,000 members since 2014, recently applauded the New York City Football Club for pledging to build their new stadium exclusively with union labor.
65. Murad Awawdeh Executive Director, New York Immigration Coalition Murad Awawdeh / Theo Cot, New York Immigration Coalition With more than 40,000 migrants arriving in New York City over the past year, the work of the New York Immigration Coalition has been thrust into the spotlight. Murad Awawdeh, the coalition’s 35-year-old executive director, has been spending his days greeting the influx of asylum-seekers – including those sent by Texas Gov. Greg Abbott – as they arrive. Awawdeh, a first-generation Palestinian American, recently criticized Gov. Kathy Hochul for not doing more for immigrant New Yorkers.
66. Matthew Aracich President, Building and Construction Trades Council of Nassau and Suffolk Counties Matthew Aracich / Bob Giglione Photography A third-generation heat and frost insulator, Matthew Aracich became president of the Building and Construction Trades Council of Nassau and Suffolk Counties in 2018, after a stint as business manager at the Heat and Frost Insulators Local 12. Aracich said that a new project labor agreement for Long Island public works projects will ensure jobs go to members of the 37 affiliated unions he represents. Aracich, who backs a plan to build a casino at Nassau Coliseum, is also in support of green hydrogen energy projects.
67. Bill Banfield & Tricia Brown Assistant to the Executive Secretary-Treasurer; New York Political Director, North Atlantic States Regional Council of Carpenters Bill Banfield & Tricia Brown / Suzanne Barki; Amanda Vitti, Amanda Vitti Photography Bill Banfield is the assistant to the executive secretary-treasurer of the coalition of carpenter’s unions, which represents more than 30,000 industry workers. Banfield has touted a new state law establishing a registration system for contractors in New York that will help workers by strengthening enforcement of labor regulations on state jobs. Putting together construction workers with contractors who need the labor is important, and Banfield says the union is helping to make those connections, even if the workers need to travel. For more than 20 years, Tricia Brown has been a fixture in the labor movement, carrying out key responsibilities for the North Atlantic States Regional Council of Carpenters as the union’s New York political director. She was involved in a recently launched series that will inform women interested in joining the carpentry trade about upcoming opportunities.
68. Jenn Duck International Representative, IBEW District 3 In 2019, Jenn Duck was appointed to serve as the international representative for the International Brotherhood of Electrical Workers District 3, representing its 50,000 members and handling political, legislative and regulatory affairs for New York. Duck was preceded in the role by Ellen Redmond, a veteran labor official within IBEW.
69. Charles Murphy President-Elect, New York State Troopers Police Benevolent Association When Charles Murphy was elected treasurer of the New York State Troopers Police Benevolent Association last spring, he turned up suspicious business practices during a financial review that led to the resignation of the former president and a union lawyer. Murphy was elected president of the 7,000-member union in January when he ran unopposed; he has been serving as acting president until his official term begins in April. A state trooper since 2003, he first got involved with the PBA in 2017 as the Troop T delegate.
70. Alexander Colvin Dean, Cornell University School of Industrial and Labor Relations Alexander Colvin / Jesse Winter Photography As dean of the Cornell University School of Industrial and Labor Relations, Alexander Colvin oversees the academic training of the next generation of leaders in the rapidly evolving world of work and employment. Colvin is also a professor of conflict and resolution at the school, a field that he covers in his own research, most recently in a paper on the effects of recent economic and societal disruptions on employee relations. The school recently launched its Climate Jobs Institute, focusing on a critical issue for the future of labor in the country.
71. Lucas Shapiro Interim Executive Director, ALIGN Lucas Shapiro / Sabelo Narasimhan With Maritza Silva-Farrell leaving for the Ford Foundation, Lucas Shapiro is continuing the Alliance for a Greater New York’s efforts to address inequality in the workforce, push for a sustainable energy economy and help communities stand up to big corporations. The labor-backed organization is aiming to raise the minimum wage and secure climate investments with strong labor standards in 2023. Shapiro has also worked with Families United for Racial and Economic Equality, Jews for Racial & Economic Justice and Mayday Space.
72. Alan Klinger Co-Managing Partner, Stroock Alan Klinger / Stroock As co-managing partner at New York City-based law firm Stroock, Alan Klinger leads the government affairs and regulatory support team, representing a number of influential public sector unions and labor organizations, including the United Federation of Teachers and the Municipal Labor Committee, an association of city labor unions representing 390,000 municipal workers. Klinger uses his experience in the field to argue for labor in court, during arbitration and at the bargaining table.
73. Robert Bishop Partner, Pitta Bishop & Del Giorno Robert Bishop is a founding member and partner of Pitta Bishop & Del Giorno, a law firm and political consultancy that has represented more than 40 labor unions before the state Department of Labor and the state Legislature. Pitta Bishop & Del Giorno clients include the unions for detectives and corrections officers in New York City, school bus drivers and sanitation workers. The firm also consulted on Eric Adams’ successful New York City mayoral campaign, helping him garner key labor endorsements and contributions.
74. Jose Lopez, Arlenis Morel & Theo Oshiro Co-Executive Directors, Make the Road New York In 2021, Jose Lopez, Arlenis Morel and Theo Oshiro became co-executive directors of Make the Road New York, an organization that fights to address issues that affect working-class and immigrant New Yorkers. Make the Road offers educational opportunities, training, legal services and access to health services. Lopez provides his experience in organizing and policy; Morel focuses on human resources, information technology and operations; and Oshiro oversees the services department and is their lead health policy expert. Make the Road was critical of Gov. Kathy Hochul’s State of the State address because she failed to mention support for legislation that would help immigrants, like the “Coverage for All” health care bill.
75. Frank DeRiso President, UFCW Local One With Frank DeRiso at the helm, United Food and Commercial Workers Local One has navigated some tough times. Grocery store workers became essential during the pandemic. Then, consolidation hit the industry as two major players in upstate New York merged. And last May, the union rushed to support employees who witnessed the tragic shooting at a Tops food store in Buffalo. DeRiso currently has UFCW focused on growing its presence in the budding cannabis industry, recruiting workers to their ranks as New York legalizes recreational weed.
76. Kevin Mulvehill Partner, Phillips Lytle LLP Kevin Mulvehill / KC Kratt Photography At Phillips Lytle LLP, Rochester-based Kevin Mulvehill leads the labor and employment team advising organizations in the public and private sectors, including education, health care, hospitality and municipalities. He assists clients with compliance with employment laws, hiring and discipline agreements, and employee relations. His division regularly handles matters before state agencies like the state Public Employment Relations Board and the state Department of Labor. Mulvehill’s firm has recently expanded to include dozens of new lawyers.
77. Ed Draves Director of Government Affairs, Shenker Russo & Clark Prior to becoming director of government affairs at Shenker Russo & Clark, Ed Draves spent more than 20 years as political director at the American Federation of State, County and Municipal Employees for the union’s New York affiliates. His roots with the organization run deep: His father was a local president with AFSCME. He has strong ties to the political arena, including having worked on Hillary Clinton’s campaign for U.S. Senate and as a strategist for the election of Buffalo’s first African American mayor, Byron Brown.
78. Paul Brown President, Buffalo & Niagara County Building Construction and Trades Council Paul Brown heads up the Buffalo & Niagara County Building Construction and Trades Council, which advocates for some 12,000 workers across 18 unions in the industry in western New York. Brown’s construction umbrella group made headlines in 2021 with its early endorsement of Gov. Kathy Hochul, a fellow western New Yorker who went on to successfully win a full term in office in last year’s gubernatorial election. The North Tonawanda resident has worked his way up since he joined a union in 1984, including following in his father’s footsteps as the business manager for Local 9.
79. Keyla Espinal Antigua Executive Vice President of Government Affairs in New York and New Jersey, Bolton-St. Johns Keyla Espinal Antigua / Evan Zimmerman for MurphyMade Keyla Espinal Antigua is a key point person on organized labor issues for Bolton-St. Johns, a top lobbying firm both in Albany and in New York City. With the departure of Ed Draves in 2021, Antigua has helped to pick up the slack with Bolton’s organized labor clients, which include the New York City Police Benevolent Association, the Freelancers Union and locals under SEIU, RWDSU and CWA. Antigua also works with clients in the technology, education and social services nonprofit spaces – building on her previous work at Children’s Aid – as well as being an expert on the Port Authority of New York and New Jersey.
80. Peter Coradi National Business Agent, American Postal Workers Union For almost 30 years, Peter Coradi has been at the American Postal Workers Union assisting union members at disciplinary hearings, working on contract negotiations, filing grievances and training new agents and advocates. Coradi also serves on the executive council of the New York State AFL-CIO as vice president. The postal union criticized Congress for once again putting the debt ceiling at the center of a political debate, calling it “unnecessary and dangerous” while assuring members that their pension fund will not be affected by the outcome.
81. Anthony Simon General Chair, SMART Transportation Division Anthony Simon / Robert Martin SMART Transportation Division General Chair Anthony Simon is a pivotal figure for the Long Island Rail Road. The union came under fire when a scathing New York Post report claimed that wasteful labor practices protected by the union cost commuters hundreds of millions of dollars every year, leading Metropolitan Transportation Authority Chair and CEO Janno Lieber to call for reforms. This year, infrastructure improvements on the LIRR did reach a major milestone with the completion of an $11 billion access route to Grand Central from Long Island.
82. Edward Valente General Chair, Association of Commuter Rail Employees Local 1 Edward Valente, general chair of the Association of Commuter Rail Employees Local 1, represents 2,000 railroad workers from the Metro-North Railroad system. Valente recently took part in a protest with 10 other unions in Grand Central Station in New York City against legislation signed by President Joe Biden to block railroad freight workers from striking. ACRE pushed for a state law to establish a light duty option for pregnant commuter rail employees and applauded legislation to protect transit workers against assault and harassment.
83. Patrick Guidice Business Manager, International Brotherhood of Electrical Workers Local 1049 Patrick Guidice has been at Local 1049 of the International Brotherhood of Electrical Workers union since 2003. The union represents more than 4,500 electricians on Long Island, including those at PSEG Long Island and National Grid. Guidice is outspoken about how reliable clean energy needs to maintain current workforce levels – if not create new jobs. He has raised questions about plans to make the area’s electric system a public utility and is against converting union workers into state employees.
84. Alan J. Murray President, Empire Blue Cross Blue Shield Alan J. Murray / Empire Blue Cross Blue Shield Alan J. Murray is responsible for providing health benefits for 2.3 million members of Empire Blue Cross Blue Shield – which is the largest health insurer in New York – a pool that includes a large number of unionized workers across the state. Murray, who was named president in 2018, has assumed the insurer’s emphasis on covering unionized workers that was until recently led by Thomas Canty. Canty, who left Empire Blue Cross Blue Shield, built up the insurer’s public sector market and remains the chair of the board of Municipal Credit Union last year.
85. Denise Abbott President, Buffalo Central Labor Council In 2020, Denise Abbott became the first woman to serve as president of the Buffalo Central Labor Council, an 88,000-member affiliation of unions. Abbott, a critical care nurse, is also a special director of health and safety at CWA Local 1168. Showing solidarity with fellow workers, the council picked Tops employees who witnessed the racist mass shooting last year to be the grand marshals at their Labor Day parade. Abbott was given the AFL-CIO Russell Quarantello Community Service Award from United Way of Greater Niagara in September.
86. Mark Spadafore President, Syracuse Labor Council Provided / Mark Spadafore Mark Spadafore is both the president of the Syracuse Labor Council, one of the hundreds of state and local AFL-CIO affiliates, and the upstate New York political director for 1199SEIU, organizing and lobbying for the health care workers union since 2009. In an op-ed for the Syracuse Post-Standard last year, he celebrated young workers, whom he sees as taking a bold stance in the labor movement to secure better futures for themselves and hold corporations to task.
87. Nadia Marin-Molina Co-Executive Director, National Day Laborer Organizing Network At the National Day Laborer Organizing Network, Nadia Marin-Molina leads workers’ centers and workers’ rights programs. NDLON, which concentrates on issues affecting day laborers, migrants and low-wage workers, partners with Cornell’s ILR School to research low-wage, unprotected and insecure work, known as precarious work. In light of new federal policies that protect migrant workers, Marin-Molina said affected individuals must be made aware of their rights. Marin-Molina has been honored for fighting the abuse of immigrant Latino domestic workers.
88. Dan Maloney President, Rochester-Genesee Valley Area Labor Federation The Rochester-Genesee Valley Area Labor Federation, under the guidance of President Dan Maloney, represents an affiliation of unions with over 100,000 workers in upstate New York. He was instrumental in organizing labor efforts last November to get out and vote to protect their workers’ interests. When General Motors announced it was committing $68 million to an area factory to build electric vehicles, Maloney, who is also president of United Auto Workers Local 1097, said the investment was important to the future of workers in the area.
89. David Gonzalez District 2 National Vice President, American Federation of Government Employees Representing federal employees in a variety of jobs throughout New England, New York and New Jersey, David Gonzalez has been serving members as national vice president of District 2 of the American Federation of Government Employees since 2020. Gonzalez’s union, which has been caught up in the teleworking debate while negotiating for more flexible schedules for members, criticized the SHOW UP Act introduced by House Republicans that limits remote work for federal employees, saying it misdirects from important issues like pay raises and recruitment.
90. Duane Wright Secretary-Treasurer and Principal Executive Officer, Teamsters Local 317 More than 230 workers walked off the job when Syracuse Sysco employees could not come to an agreement with the company last September. Teamsters Local 317, represented by Secretary-Treasurer and Principal Executive Officer Duane Wright, settled with the company three weeks after the strike took place. The state’s Teamsters announced good news recently: A pension rescue plan from the U.S. government has been approved, meaning the fund will restore benefits for those affected by cuts over the years due to market losses.
91. Jim Dix President, International Association of Machinists and Aerospace Workers Local 1529 As president of International Association of Machinists and Aerospace Workers Local 1529, Jim Dix helped members negotiate a new contract at an aerospace parts manufacturing plant in Sidney last fall when 700 workers struck for five days. Their goal was to secure a better contract after their employer failed to eliminate a tiered system that offered recent hires fewer benefits for the same work and left out essential pay for working during the pandemic when negotiating with employees.
92. Norman Shreve Directing Business Representative, International Association of Machinists and Aerospace Workers District 15 In October, 700 members of Lodge 1529 of the International Association of Machinists and Aerospace Workers within District 15 walked off the job at Amphenol Aerospace in the Southern Tier. IAMAW Directing Business Representative Norman Shreve said the members who worked through the pandemic got a fair contract after picketing for five days. Shreve, a 30-year union member who served as shop steward in his own local, now heads up the Buffalo office, where he became a business representative in 2008.
93. Ron Warner District 65 Directing Business Representative, International Association of Machinists and Aerospace Workers District 65 Ron Warner manages the day-to-day operations and negotiations at District 65 of the International Association of Machinists and Aerospace Workers. The union has been adding members from a number of different industries this year. Warner welcomed more than 130 veterinary hospital workers, the first veterinary practice to join a union on the East Coast. More than 100 workers at a packaging facility joined IAM after a yearslong battle against union-busting tactics by their company. District 65 was recently recognized by IAM’s national leadership for its efforts.
94. Astrid Aune Co-Chair, Communications Committee, New York State Legislative Workers United Astrid Aune / Samantha Walsh Last summer, state Senate staffers followed the lead of their congressional compatriots in unionizing, forming the New York State Legislative Workers United group. They recently welcomed Assembly workers to their ranks. Astrid Aune, a senior adviser for state Sen. Jessica Ramos, is co-chair of the group’s communications committee. A multitude of state unions, including AFL-CIO, have thrown their support behind the staffer’s efforts. The state Senate staffers have yet to formulate an official list of grievances but said that they were underpaid for their work and deserved parity with other public sector workers.
95. Steven Moy President, New York City Chapter, Asian Pacific American Labor Alliance Steven Moy / IBEW Local 3 A second-generation electrician, Steven Moy is an IBEW Local 3 executive board member, serves as vice president on the national board of the Asian Pacific American Labor Alliance, an affiliate of the AFL-CIO, and is president of their New York City chapter. Moy has rallied with his unions to stand up against Asian hate crimes. APALA joined other unions this year in throwing their support behind New York nurses who were striking for better working conditions.
96. Sean McGarry President, New York State Association of Nurse Anesthetists Sean McGarry / Axiom Media Group Currently a practicing certified registered nurse anesthetist with an anesthesia group in the Albany region, Sean McGarry was elected president of the New York State Association of Nurse Anesthetists in 2022 for a one-year term. The association represents the interests of over 1,200 members in the profession. McGarry was in the state Capitol in January to get lawmakers to officially recognize CRNA as a profession in the state; currently, New York is the only state where it is not.
97. Diana Saguilán & Emma Kreyche Interim Executive Director; Director of Advocacy, Outreach and Education, Worker Justice Center of New York Diana Saguilán & Emma Kreyche / Patricia Cronin; Keith Major Worker Justice Center of New York interim Executive Director Diana Saguilán and Director of Advocacy, Outreach and Education Emma Kreyche have been leading efforts to provide agricultural and other low-wage workers with legal counsel, advocacy and community support. Saguilán, who has been with the organization since 2011, was herself an immigrant. She manages almost every aspect of the nonprofit’s mission after previously cutting her teeth as a young activist in the AFL-CIO’s summer program. Often quoted in the press, Kreyche, also a longtime staff member, is working to create a permanent solution for the estimated 750,000 workers across the state who fall through the cracks of traditional unemployment programs.
98. Lara Skinner Executive Director, Climate Jobs Institute, Cornell University’s ILR School Lara Skinner / Cornell University At the Climate Jobs Institute at Cornell University’s ILR School, Lara Skinner is creating programs to help transition the country to a clean energy economy that provides new jobs for union workers. She also acts as an adviser to unions and businesses on labor and climate issues. Skinner said the way to create more clean energy-related jobs for workers will be to incentivize the development of supply chains here at home that will support the industry. The Climate Jobs Institute officially launched in January, with such luminaries as state Sen. Jessica Ramos, the Building and Construction Trades Council of Greater New York’s Gary LaBarbera and others offering their support.
99. Ibrahím Pedriñán President, Albany Central Federation of Labor The Rev. Ibrahím Pedriñán focused on the bright side of things when organizing efforts at an Amazon plant near Albany failed. The optimistic, self-described idealist president of the Albany Central Federation of Labor said that despite union-busting tactics used by the company, it inspired other local organizers, giving them a voice. Pedriñán, who has a master’s degree in divinity from Pittsburgh Theological Seminary, is also a postal worker and the president of the American Postal Workers Union Local 390.
| 2023-02-20T00:00:00 |
2023/02/20
|
https://www.cityandstateny.com/power-lists/2023/02/2023-state-labor-power-100/383309/
|
[
{
"date": "2023/02/27",
"position": 51,
"query": "AI labor union"
}
] |
Is there a way to pay content creators whose work is used ...
|
Is there a way to pay content creators whose work is used to train AI? Yes, but it’s not foolproof
|
https://theconversation.com
|
[
"Brendan Paul Murphy"
] |
Is there a way to pay content creators whose work is used to train AI? Yes, but it's not foolproof. Published: February 27, 2023 9:26pm EST. Brendan Paul ...
|
Is imitation the sincerest form of flattery, or theft? Perhaps it comes down to the imitator.
Text-to-image artificial intelligence systems such as DALL-E 2, Midjourney and Stable Diffusion are trained on huge amounts of image data from the web. As a result, they often generate outputs that resemble real artists’ work and style.
It’s safe to say artists aren’t impressed. To further complicate things, although intellectual property law guards against the misappropriation of individual works of art, this doesn’t extend to emulating a person’s style.
It’s becoming difficult for artists to promote their work online without contributing infinitesimally to the creative capacity of generative AI. Many are now asking if it’s possible to compensate creatives whose art is used in this way.
One approach from photo licensing service Shutterstock goes some way towards addressing the issue.
Read more: No, the Lensa AI app technically isn’t stealing artists' work – but it will majorly shake up the art world
Old contributor model, meet computer vision
Media content licensing services such as Shutterstock take contributions from photographers and artists and make them available for third parties to license.
In these cases, the commercial interests of licenser, licensee and creative are straightforward. Customers pay to license an image, and a portion of this payment (in Shutterstock’s case 15-40%) goes to the creative who provided the intellectual property.
Issues of intellectual property are cut and dried: if somebody uses a Shutterstock image without a licence, or for a purpose outside its terms, it’s a clear breach of the photographer’s or artist’s rights.
However, Shutterstock’s terms of service also allow it to pursue a new way to generate income from intellectual property. Its current contributors’ site has a large focus on computer vision, which it defines as:
a scientific discipline that seeks to develop techniques to help computers ‘see’ and understand the content of digital images such as photographs and videos.
Computer vision isn’t new. Have you ever told a website you’re not a robot and identified some warped text or pictures of bicycles? If so, you have been actively training AI-run computer vision algorithms.
Now, computer vision is allowing Shutterstock to create what it calls an “ethically sourced, totally clean, and extremely inclusive” AI image generator.
What makes Shutterstock’s approach ‘ethical’?
An immense amount of work goes into classifying millions of images to train the large language models used by AI image generators. But services such as Shutterstock are uniquely positioned to do this.
Shutterstock has access to high-quality images from some two million contributors, all of which are described in some level of detail. It’s the perfect recipe for training a large language model.
These models are essentially vast multidimensional neural networks. The network is fed training data, which it uses to create data points that combine visual and conceptual information. The more information there is, the more data points the network can create and link up.
This distinction between a collection of images and a constellation of abstract data points lies at the heart of the issue of compensating creatives whose work is used to train generative AI.
Even in the case where a system has learnt to associate a very specific image with a label, there’s no meaningful way to trace a clear line from that training image to the outputs. We can’t really see what the systems measure or how they “understand” the concepts they learn.
Shutterstock’s solution is to compensate every contributor whose work is made available to a commercial partner for computer vision training. It describes the approach on its site:
We have established a Shutterstock Contributor Fund, which will directly compensate Shutterstock contributors if their IP was used in the development of AI-generative models, like the OpenAI model, through licensing of data from Shutterstock’s library. Additionally, Shutterstock will continue to compensate contributors for the future licensing of AI-generated content through the Shutterstock AI content generation tool.
Problem solved?
The amount that goes into the Shutterstock Contributor Fund will be proportional to the value of the dataset deal Shutterstock makes. But, of course, the fund will be split among a large proportion of Shutterstock’s contributors.
Whatever equation Shutterstock develops to determine the fund’s size, it’s worth remembering that any compensation isn’t the same as fair compensation. Shutterstock’s model sets the stage for new debates about value and fairness.
Shutterstock AI
Arguably the most important debates will focus on the amount of specific individuals’ contributions to the “knowledge” gleaned by a trained neural network. But there isn’t (and may never be) a way to accurately measure this.
No picture-perfect solution
There are, of course, many other user-contributed media libraries on the internet. For now, Shutterstock is the most open about its dealings with computer vision projects, and its terms of use are the most direct in addressing the ethical issues.
Another big AI player, Stable Diffusion, uses an open source image database called LAION-5B for training. Content creators can use a service called Have I Been Trained? to check if their work was included in the dataset, and opt out of it (but this will only be reflected in future versions of Stable Diffusion).
One of my popular CC-licensed photographs of a young girl reading shows up in the database several times. But I don’t mind, so I’ve chosen not to opt out.
Author provided
Shutterstock has promised to give contributors a choice to opt out of future dataset deals.
Its terms make it the first business of its type to address the ethics of providing contributors’ works for training generative AI (and other computer-vision-related uses). It offers what’s perhaps the simplest solution yet to a highly fraught dilemma.
Time will tell if contributors themselves consider this approach fair. Intellectual property law may also evolve to help establish contributors’ rights, so it could be Shutterstock is trying to get ahead of the curve.
Either way, we can expect more give and take before everyone is happy.
Read more: How to perfect your prompt writing for ChatGPT, Midjourney and other AI generators
| 2023-02-28T00:00:00 |
2023/02/28
|
https://theconversation.com/is-there-a-way-to-pay-content-creators-whose-work-is-used-to-train-ai-yes-but-its-not-foolproof-199882
|
[
{
"date": "2023/02/27",
"position": 28,
"query": "AI wages"
}
] |
3 Things K-12 Educators Should Know about the Ethics and ...
|
3 Things K-12 Educators Should Know about the Ethics and Use of AI in Education
|
https://ced.ncsu.edu
|
[
"Janine Bowen"
] |
AI for Personalization: Jiang said AI can help teachers personalize learning for each student by analyzing their learning needs and performance data. Teachers ...
|
Ongoing news stories about ChatGPT, an artificial intelligence chatbot developed by OpenAI and launched in November 2022, have many educators wondering about its implications in the classroom and the role of artificial intelligence in K-12 education.
Shiyan Jiang, an assistant professor of learning, design and technology in the NC State College of Education, is engaged in research that involves empowering AI education in the K-12 setting. She is currently a co-principal investigator on the StoryQ project, which is exposing high school students to artificial intelligence through narrative modeling.
The StoryQ project, which began three years ago with funding from the National Science Foundation, includes a curriculum that can be integrated into middle and high school English language arts (ELA), history, chemistry, computer science and math classrooms.
“We are more than happy to work with teachers to integrate AI learning opportunities into their classrooms,” said Jiang, who noted that educators can email her to collaborate on the project.
Below, Jiang shares three things K-12 teachers should know about the use and ethics of artificial intelligence in a classroom setting:
AI for Student Assessment: AI can provide more accurate and timely assessments of student performance. It can analyze data on student behavior, engagement and learning outcomes, allowing teachers to identify areas of weakness and adjust their teaching accordingly, she said.
AI for Personalization: Jiang said AI can help teachers personalize learning for each student by analyzing their learning needs and performance data. Teachers can use this information to tailor their lessons to each student’s needs, helping them learn more effectively.
For educators who want to use artificial intelligence in their classrooms for assessment and personalization purposes, Jiang recommends the Revision Assistant for automated writing feedback, which is currently in development and deployment at a small scale.
AI Ethics and Bias: In addition to the benefits of AI in education, Jiang notes that it is also important for teachers to be aware of the ethical considerations and potential biases that can arise when using AI in the classroom. By doing so, teachers can:
Protect student privacy : AI systems can collect and analyze vast amounts of student data, including sensitive information such as demographic data and learning disabilities. Teachers need to understand how this data is collected, stored and used to ensure that student privacy is protected.
: AI systems can collect and analyze vast amounts of student data, including sensitive information such as demographic data and learning disabilities. Teachers need to understand how this data is collected, stored and used to ensure that student privacy is protected. Ensure Fairness : AI systems can also impact student outcomes, such as grades and college admissions. Teachers need to ensure that these systems are fair and do not discriminate against certain groups of students.
: AI systems can also impact student outcomes, such as grades and college admissions. Teachers need to ensure that these systems are fair and do not discriminate against certain groups of students. Foster digital citizenship: As AI becomes more prevalent in society, it is important for teachers to teach students about the ethical considerations of AI, including bias and privacy concerns. This will help students become responsible digital citizens and make informed decisions about their use of technology.
“Things are moving fast. That’s why fostering digital citizenship on AI ethics and bias is super important at this stage, as it will help to create a more responsible and equitable use of AI in education as these tools become more widely available soon,” she said.
| 2023-02-27T00:00:00 |
2023/02/27
|
https://ced.ncsu.edu/news/2023/02/27/3-things-k-12-educators-should-know-about-the-ethics-and-use-of-ai-in-education/
|
[
{
"date": "2023/02/27",
"position": 6,
"query": "AI education"
},
{
"date": "2023/02/27",
"position": 9,
"query": "artificial intelligence education"
}
] |
AI use in journalism brings ethical, employment concerns
|
AI use in journalism brings ethical, employment concerns
|
https://dailyillini.com
|
[
"Faith Allendorf",
"Managing Editor For Reporting"
] |
When the programming is flawed and the database is old, inaccurate or biased, AI models can produce stories with false or misrepresented information. “It shows ...
|
A few years ago, a reporter from The Washington Post accomplished a journalistic feat that not many writers have done before. In 2016, within only their first year of writing for The Post, the reporter, pen name Heliograf, wrote and published 850 articles.
Heliograf was a multi-interest reporter who was interested in both sports and politics, and nearly all 850 of their articles came from just those two topics. They wrote 300 short reports and alerts about the Rio Olympics and 500 articles about congressional and gubernatorial races on Election Day.
Heliograf isn’t a real person — it is The Post’s in-house automated storyteller technology, just one of many artificial intelligence programs implemented in an increasing number of news outlets.
From using code that identifies trends in a labyrinth of data to developing technology that generates stories about the Olympics, the use of AI in journalism is becoming a key aspect of a news outlet’s operation. Even though AI can make a reporter’s job easier in certain ways, journalists are debating whether or not the technologies can be ethically implemented in a field that is so heavily human.
How is AI being used in newsrooms?
Get The Daily Illini in your inbox! Enter your email Select a newsletter Headline News 🔔 Headline News 🔔 Catch the latest on University of Illinois news, sports, and more. Delivered every weekday.
Press Box 🏀 Stay up to date on all things Illini sports. Delivered every Monday. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply. Subscribe Thank you for subscribing!
Dr. Andrea L. Guzman, associate professor in the Department of Communication at Northern Illinois University, researches human-machine communication, which is how “we communicate with technology and how it affects communication with other people.” Guzman said there are two ways AI is being used by journalists: workflow automation, which is more common, and content creation.
Regarding workflow automation, newsrooms use AI to sift through heaps of information. For example, Reuters uses Lynx Insights to find trends, facts and anomalies within a lot of data. Other outlets like the Associated Press employ social media-powered alerts to analyze media feeds and detect breaking news.
Another use of AI in workflows includes transcribing interview audio with platforms like Otter.ai. Some journalists also use AI to scrape data from websites, digitize archives and fact check.
Guzman said using AI for these “mundane tasks” lets the reporter focus on more important responsibilities while still producing content. AI also gets more done in a short amount of time than a human journalist can.
“(AI) is assisting human journalists in doing their jobs because what AI can process and the information it can provide is at a larger scale than what would have taken months, if even possible, for a human journalist to do,” Guzman said.
Regarding content creation, Guzman said some outlets are using AI to write basic, “data-driven” reports on topics such as stocks, earnings and sports games. For these reports, human programmers generate templates, and the AI fills in the data. These are the types of stories that AI like Heliograf are writing.
“Think of it similar to Mad Libs,” Guzman said. “There is a templating process, and there are certain parts left empty that are filled in by current data.”
Not all news outlets are able to use AI in the same capacity. Guzman said that because of limited budgets, local and/or small newsrooms aren’t using AI as much as large newsrooms.
“The degree to which news outlets are experimenting with AI and using AI really hinges on the news outlet’s budget as well as output,” Guzman said. “If you’re someone like the AP that needs to pump out a lot of content, but you’re also really large and have a lot of resources, you have more space to experiment with these types of technologies.”
That doesn’t stop them from trying. Brant Houston, professor in Media, oversees the University’s online newsroom, CU-CitizenAccess.org. Houston said his newsroom is working toward automating the download and organization of board, city council and government agency agendas. He also wants AI to identify key phrases within the downloaded content.
“That then frees up the journalist to focus on the really important stuff, because there’s not enough of us to do what we need to do,” Houston said.
Where problems arise: accuracy
In January, tech newsroom CNET began issuing lengthy corrections to some of its articles. Furthermore, a sister publication, Bankrate, disclosed concerns about the accuracy of articles it has published since November.
In both publications, the articles that required corrections were AI-generated.
With the introduction of free-to-use generative text programs like ChatGPT, journalists are now able to write entire stories using AI. Rather than using a system of templates, these stories are put together by an AI that draws from a massive, continuously learning database.
But like all automation, type programs are flawed. ChatGPT’s database, for example, doesn’t include any information after 2021. This means there’s a chance the AI could use old, incorrect data.
According to Guzman, AI accuracy depends on three factors: how the programming was put together, the accuracy of the information the AI is pulling from and the bias of its creators. When the programming is flawed and the database is old, inaccurate or biased, AI models can produce stories with false or misrepresented information.
“It shows that (newsrooms) do not understand the way these technologies work, or that they’re completely disregarding how they work, and potentially putting out misinformation without guard rails in place,” Guzman said. “We already have enough problems with misinformation.”
So, when an AI-generated story contains errors, who is held accountable?
Houston said to prevent accuracy and bias issues, humans must be involved in everything created by AI in the newsroom. Ultimately, humans are still responsible for the programs they are creating.
“You should never let the machine do everything,” Houston said. “We have an ethical responsibility to make sure that it’s not misleading people, and it’s not introducing bias into whatever it’s doing.”
Guzman said that when designing AI programs, developers need to consider what journalism is really about.
“Journalists work with the designers to think about what are the values of journalism, what is valued in journalism, what is seen as ethical and think about how those get put into the design of the technology,” Guzman said.
Other ethical issues
Besides accuracy, Guzman said there are other ethical questions regarding the use of AI in journalism. For example, should newsrooms be transparent about their use of AI to produce content? Right now, “there’s no standard within journalism” that gives an answer.
But Guzman said she thinks there needs to be transparency.
“I can tell you my research has shown that yes, the audience wants to know where their information is coming from,” Guzman said. “If it’s a story created by AI, it has to be bylined as such.”
Guzman also asked if there’s a limit to the types of stories that can be written by AI. Should journalists automate stories about murder? What about obituaries?
“Some people I talked to said obits are fine, but others … they wouldn’t want AI to write about death because computers themselves can’t die,” Guzman said.
Some journalists, like Victoria Olaleye, sophomore in Media, think that using AI takes away from what it means to be a journalist. She refers specifically to doing workflow tasks.
“I think that it’s part of the job to go through all of the public records and everything that we have to investigate,” Olaleye said. “I know that we’re in a place where we’re looking to make our lives easier with technology, but I also think it kind of takes away from our purpose.”
Elizabeth Kelly, junior in Media, said she is worried about AI taking away the “human connection” of the craft. To her, AI will never be able to replicate that.
“We’re able to interview people and convey their emotions through telling their stories,” Kelly said. “That’s something, at least to my knowledge, that AI can’t do.”
In the future
Technology will never stop evolving, and there are growing concerns of AI taking over human jobs. Guzman is all too familiar with the question of whether or not technology like The Post’s Heliograf will replace human journalists.
Olaleye said she is “absolutely” concerned about this question. She pointed to the fact that journalism is already in an unsteady position.
“Especially in media, jobs are already becoming less and less available, even with print dying out,” Olaleye said. “I feel like adding another aspect like AI would be damaging to something that’s already being broken.”
Guzman does not have a solid answer to that question. To her, it’s up to humanity to decide whether technology will replace human journalists.
“This is not a technology question — this is a human question,” Guzman said. “That is a decision for humans to make.”
While the idea of AI like a technological reporter that can write 850 articles in a year can be scary to some, Guzman encouraged journalists to be open to its advantages.
“What I encourage people to do is not to fear it, but to better understand its benefits and challenges and really learn about the ethical implications,” Guzman said. “Think about ethics to continue to make sure we’re making better decisions.”
[email protected]
| 2023-02-27T00:00:00 |
2023/02/27
|
https://dailyillini.com/life_and_culture-stories/2023/02/27/artificial-intelligence-journalism/
|
[
{
"date": "2023/02/27",
"position": 8,
"query": "AI journalism"
}
] |
Artificial Intelligence Careers
|
Artificial Intelligence Careers
|
https://www.m47labs.com
|
[] |
Open positions · Manual QA Tester · Machine Learning Engineer (Conversational AI) · QA Analyst · Senior Prompt Engineer · Automation QA Engineer Native in German ...
|
If you are thinking about joining us, you shouldn’t expect two days to be the same. We have a passion for quality, and if you want to feel right at home working with us, so will you.
Dynamic
Environments We work following Agile principles: flexibility, teamwork, revision and constant improvement. Diverse
Teams We hold more than 25 nationalities under the same roof, with a myriad of educational backgrounds and an ever curious mind. Challenging
Projects We work with cutting edge technologies, so thinking out-of-the box is one of our team’s most remarkable traits. Flat
Structure We like to keep an open discussion and bi-directional feedback. Our close knit team and management style aims to facilitate communication and involvement at all levels.
| 2023-02-27T00:00:00 |
https://www.m47labs.com/artificial-intelligence-careers
|
[
{
"date": "2023/02/27",
"position": 58,
"query": "artificial intelligence hiring"
}
] |
|
The AI talent shortage: Outsourcing or In-house development
|
The AI talent shortage: Outsourcing or In-house development
|
https://www.craftworks.ai
|
[] |
As companies across all industries begin to adopt AI in their operations, the demand for AI talent is skyrocketing. The adoption of artificial intelligence has ...
|
The most effective way to address the talent shortage is to partner with AI consultants. These experts bring a wealth of knowledge and expertise to the table, with a deep understanding of the latest technology and trends. Additionally, companies can not only build their AI teams, with the transfer of knowledge that some consultancy firms offer, but also create and execute a comprehensive AI strategy.
Furthermore, consultants offer ongoing support and direction to ensure continued success. But let’s explore the four benefits one by one:
1. Bridging the skills gap
The first obvious benefit of working with AI consultants is that they can help companies fill the skills gap. Many companies struggle to find candidates with the right mix of technical skills and business acumen. AI consultants, on the other hand, bring a broad range of experience and expertise across different industries and requirements.
As a result, AI consultants keep the true business value of a project in mind, helping companies to create and deploy AI solutions faster and more efficiently. It enables in-house teams to concentrate their efforts in areas of their expertise, freeing up valuable resources for other projects.
2. Instant access to data and tooling
Creating machine learning and deep learning models is contingent upon access to high-quality data. Even if an organization has access to clean, large-scale data relevant to the model, the process of working with Big Data is both time-consuming and requires expertise. For a successful AI project, proper data preparation is crucial. Without a strong foundation of input data, it may take longer to see results from your AI development efforts.
To make the most of machine learning, organizations must invest time in collecting and working with large datasets. This requires expertise and experience, as well as a commitment to feeding the platform where your machine learning models are hosted with high-quality data. Ensuring that predictions are accurate and relevant is a complex and ongoing process. The importance of specialization cannot be overstated, particularly in industries such as logistics, medicine, and finance.
To our partners, for e.g., we provide not only specialized AI knowledge in their respective industry but also a state-of-the-art management platform, navio, for machine learning models. navio allows our clients to independently monitor and assess the performance of their AI solutions, empowering them to make data-driven decisions with confidence.
3. Shorter time-to-market and its cost implications
In recent years, the availability of high-quality data sets has made outsourcing a popular option for speeding up the development and deployment process of AI and machine learning projects. By partnering with a company that specializes in specific areas or applications and has relevant experience, organizations can save valuable time and resources that would otherwise be spent on training and building in-house teams.
Lower costs than In-house development
Contrary to popular belief, outsourcing can actually be more cost-effective than building an in-house IT team. While the initial expenses for salaries, hardware, software licenses, and cloud service subscriptions may seem lower for an in-house team, there are several invisible costs associated with maintaining and updating the team. These include employee training and workshops, recruitment, employee benefits, and the time and effort spent on the hiring process.
With outsourcing, the service provider is absorbing these costs, resulting in more predictable prices and a clearer ROI. Outsourcing also eliminates the need to constantly update and maintain an in-house team, freeing up funds to be directed towards other areas of the business that require investment.
To summarize, outsourcing alleviates the scarcity of AI expertise in the industry while also being beneficial for saving time and resources, increasing revenue, and promoting specialization within a company.
4. Scalability and flexibility
As businesses strive to stay ahead in the market, they must be able to adapt to changing demands and grow accordingly. As we already know, by now, the traditional approach of building an in-house team to handle these projects can prove to be both impractical and expensive. On the other hand, outsourcing AI talent offers a solution to this problem.
By leveraging the expertise from outsourced AI professionals, small, and growing companies can level the playing field with larger competitors, without sacrificing the quality of the final product. An in-house team is usually limited in size, but outsourcing allows for scalability, so that you can expand and contract your development team as needed, without incurring additional costs.
Additionally, choosing a provider with different areas of expertise can help meet the diverse needs of your ML project. This approach allows for greater flexibility to scale up or down as required.
| 2023-02-27T00:00:00 |
https://www.craftworks.ai/insights/know-how/the-ai-talent-shortage-outsourcing-or-in-house-development/
|
[
{
"date": "2023/02/27",
"position": 75,
"query": "artificial intelligence hiring"
}
] |
|
Multi-Channel Sourcing driven by Artificial Intelligence
|
Sourcing: Multi-Channel Candidate Sourcing driven by Artificial Intelligence
|
https://www.talentrecruit.com
|
[] |
Talent Recruit empowers your recruiters to select the people that best suit your requirement with powerful AI recruitment features that scan all resumes sourced ...
|
Candidate Experience
The Evolution of Candidate Experience Platforms: What HR Teams Need to Know
Candidate Experience Platforms (CXPs) have evolved from simple communication tools to AI-powered systems that personalize and transform every stage of the hiring journey. This blog explores how modern CXPs enhance engagement, streamline communication, and provide data-driven insights, helping HR teams deliver exceptional candidate experiences. Discover why investing in the right platform is crucial for building strong employer brands and future-proofing your recruitment strategy.
| 2023-02-27T00:00:00 |
https://www.talentrecruit.com/automated-candidate-sourcing-software
|
[
{
"date": "2023/02/27",
"position": 89,
"query": "artificial intelligence hiring"
}
] |
|
Even before the layoffs, tech workers were quitting. Here's ...
|
Even before the layoffs, tech workers were quitting. Here’s why.
|
https://www.washingtonpost.com
|
[
"Danielle Abril",
"Dan Lamothe",
"Ellie Silverman",
"Tatum Hunter",
"Annie Gowen",
"John Muyskens",
"Arelis R. Hernández",
"Daniel Wolfe",
"Nicole Dungca",
"Naema Ahmed"
] |
Tech workers who left the industry prior to the mass layoffs ... The former IBM Watson lead in artificial intelligence and natural language processing delivery ...
|
Leaving the tech industry gave Ashley Morgan peace and optimism she says she never had before. Morgan spent more than a decade in marketing roles at tech companies, most recently employed by a West Coast software firm. But she says she felt constant pressure to deliver on growing demands, undervalued, under-compensated and underrepresented, especially as a woman of color. Her career eventually took a toll on her mental health and her family, and in June she called it quits.
Now, the 40-year-old St. Louis resident is marketing her own plant-based skin-care company, called Whip It Goods Skincare, which was born out of home remedies she created for her daughter’s eczema. After leaving her tech job, she sleeps easier, feels lighter and wakes up excited, she says. She’s grateful she left before the tech industry’s mass layoffs, she says.
Advertisement Advertisement
“All that glitters is not gold,” she said referring to the allure of a high-profile tech job. “You get very attractive salaries, but you pay a price for that.”
But some workers who recently left the industry say they’ve found fulfillment shifting to non-tech ventures that are passion projects, socially engaging or lifelong dreams. Still, their journeys haven’t been without challenges, including attracting customers and being more judicious with money.
After nearly two decades of helping programmers, Chris Phipps is writing sketches for live comedy. The former IBM Watson lead in artificial intelligence and natural language processing delivery had always dreamed of getting into entertainment. Although his area of technology expertise is hot with the release of AI-powered chatbots such as ChatGPT from Open AI, the 52-year-old Los Angeles resident says he’s happy in a non-tech job.
Advertisement Advertisement
Advertisement
“I haven’t been this emotional about anything in 10 years,” he said. “It’s always been a dream for me.”
Phipps joined the tech industry as a linguist in 2004, when companies were scooping up academics as subject matter experts. But his work became more mundane as IBM Watson matured, he said. And now, other tech companies also are having to reconcile with big business problems, including the challenge of growing their profits, he said.
“We’ve all basically gotten the wake-up call that the honeymoon is over,” he said. “Tech employees are just employees; we’re not special.”
Phipps performed at Flappers Comedy Club in Burbank, Calif. (Video: Chris Phipps)
Sara Wampler, most recently senior operations manager for consumer products at Google, also wanted to pursue her passion: writing. Wampler, 41, worked three stints at Google in various operations roles. She says the maturation of tech also affected her. She joined Google out of college in 2003, when the company employed about 1,500 people. Now, Google employs more than 150,000.
Advertisement Advertisement
Advertisement
“It felt like there were opportunities to learn something new every day,” Wampler said, adding that she spent six months in India to help open offices there. “But now … it’s harder to have the generalist approach to learn adjacent new things.”
Wampler said the slowing pace of change and the approval-riddled requirements to try new things ultimately led her to quit. She moved from Denver to her small Iowa agricultural hometown of 430 people outside Des Moines to focus on her writing career. Wampler, who uses the pen name Sara Ramsey, is working on her first fantasy book after publishing seven romance novels.
“It’s really given me a chance to take a breath,” she said, adding that her heart rate dropped 10 beats per minute within a month of leaving her tech job.
Jerry Haagsma, a former software engineer and technical lead at Square, is working on a passion project that dates to college. The 31-year-old San Francisco resident left tech only after seeing some of his peers take temporary breaks. He runs his own craft popcorn company, Jerrypop.
Advertisement
He initially planned on reentering tech in a year. But now that he’s spent 10 months entirely dedicated to popcorn and his indie rock band, Your Fearless Leader, he’s not sure if or when he’ll return.
Advertisement Advertisement
“My goal is just to not have to go back to software engineering,” he said. Jerrypop “has been an opportunity to let my creativity shine in ways people directly appreciate.”
Haagsma got into popcorn when his college roommates’ parents delivered a 10-pound tin of popcorn kernels. After tiring of the flavor, he and his friends started spicing it up. Now, he peddles popcorn flavors including habanero ranch and peanut butter and jelly through his website and at Bay Area pop-ups and bars. As a one-man operation, he is responsible for everything, including web design, marketing and cooking, popping between 30 and 300 bags a week.
“Even if the business doesn’t [succeed], I’m happy,” he said. “I just don’t want to be older saying, ‘I wish I would’ve given popcorn a shot.’”
For Thomas Crawford, a former Tinder director of training and quality assistance, it was all about pursuing longtime dreams. The Los Angeles resident left his job in September after serving tech companies, including Amazon, for 17 years. At his most recent job, he said he was responsible for four different departments.
Advertisement
“I was getting to the point where I was waking up every day and not looking forward to work,” he said. “I was losing the enjoyment, and the stress was getting to me.”
Advertisement Advertisement
So the 43-year-old guitar player left tech to apply his skills to the music industry. He’s devoting his time to his metal industrial band, Fleischkrieg, and is hoping to become a band manager someday.
Crawford said he might have to go back into tech to financially support his music career, though. But he’d prefer to be a consultant or individual contributor rather than a manager to mitigate stress and allow time for music.
Brian Bahena says stress is ultimately what led him to leave tech for a more social job. Bahena, who was a biology major in college, quit the financial technology firm Blend in July. He said his career took a turn after he was tapped for a managerial role at Livongo, which is part of the virtual health-care company Teledoc.
Advertisement
“I took that leap and realized I took too many steps before I was ready,” said the 27-year-old. “At a lot of tech companies, people get thrown into higher-level roles without much experience.”
Advertisement Advertisement
His appointment came right before the pandemic lockdowns, which eliminated his usual stress outlets. He said he tried to raise his concerns to others but felt people more often than not “normalized” his stress. After realizing he was skipping meals and pacing his bathroom an hour before work, he quit the job. He picked up a role at Blend while bartending on the side. But he wasn’t fulfilled, he said.
“The more I thought about it, the more I realized I enjoy bartending more,” he said, adding that both his and his cat’s health and well-being have improved. “I work a shift and unplug. I don’t have to constantly be looking at Slack.”
Advertisement
Bahena had planned to bartend for only six months — a mark he passed last month. He still isn’t seeking to return to tech any time soon.
Morgan, the skin-care entrepreneur, said that not even a million-dollar paycheck could make her go back. The stress and anxiety just aren’t worth it. Her advice for laid-off tech workers who may be at a crossroads: Trust yourself.
| 2023-02-27T00:00:00 |
2023/02/27
|
https://www.washingtonpost.com/technology/2023/02/27/tech-workers-layoffs-quit/
|
[
{
"date": "2023/02/27",
"position": 47,
"query": "artificial intelligence layoffs"
}
] |
Tech Layoffs Fueling Startups
|
Tech Layoffs Fueling Startups
|
https://labusinessjournal.com
|
[
"Destiny Torres"
] |
As devastating as the layoffs have been, tech workers are still in high demand, especially those experienced in engineering, artificial intelligence and ...
|
With thousands of tech workers being laid off from companies big and small this year, it is easy to think the industry is going under. The reason for these layoffs varies from cutting costs to reducing salaries, which increased significantly during the pandemic.
However, the mass furloughs are giving startup tech companies the ability to add to their workforces, some analysts and recruiters said.
Rory Bebbington, founder and chief executive of Marina del Rey-based Fabric Staffing, said that during this time of year companies are looking at their results and making decisions on how to become more profitable in the following quarter.
“Companies are looking at their budgets for next year and they’re looking at how profitable they were in certain quarters, especially people,” Bebbington said. “And to be profitable in quarter one and the rest of the following year, they have to make cuts. The biggest line item on anyone’s profit loss sheet is salaries. That’s where cuts always start.”
Layoffs.fyi, a crowdsourced site that has tracked national tech layoffs since 2020, reported that about 160,000 tech workers lost their jobs last year. In January, Glendale-based software company ServiceTitan laid off 8% of its workforce, about 221 employees. In January, Microsoft Corp. announced it will dismiss 10,000 employees, and shortly after, Alphabet, Google’s parent company, announced it was cutting 12,000 jobs.
As devastating as the layoffs have been, tech workers are still in high demand, especially those experienced in engineering, artificial intelligence and cybersecurity.
Fabric saw a slowdown in its business in December, but activity has heavily increased as more startups are looking to grow their workforces. “Business has definitely dramatically increased,” Bebbington said.
Fabric makes its revenue through a subscription service. By paying a monthly fee, companies gain access to Fabric’s pool of tech talent and can hire without any additional costs. Prospective employees go through a recruiting process in which they are checked for experience before being added to the company’s roster.
Since founding the company in 2016, Bebbington said Fabric Staffing has helped more than 200 tech companies, mainly at the series A or series B level, find employees, including Santa Monica-based social platform Tinder, Encino-based health tech company mPulse Mobile and Santa Monica-based automotive company Edmunds.
Eager to work
Matthew Kahn, an economics professor at the University of Southern California, said now is a great time for startups to find talent.
“Crisis creates opportunity,” Kahn said. “If major firms have downsized, then there are people with skills who are looking for new jobs, and that’s exactly the right time for entrepreneurs to post. If people have recently lost their jobs, they’re going to be eager to find new work. This is just the right time for startups who need special talent to be hunting for that talent because these other folks are sort of amazed that they’ve been displaced.”
Bebbington also said now is a perfect time for companies to find affordable talent, since more tech workers are looking for jobs. Kahn added that while that may be true, employers should be careful of being too stingy with salaries.
“If you hire them at a cut-rate wage, that might be wise in the short run, but they might not be as loyal or hard-working in the medium term,” Kahn explained.
Finding talent
Santa Monica-based e-commerce company Tapcart is among the many tech businesses taking advantage of the burgeoning pool of tech workers looking for work. It has openings in its engineering, sales and marketing departments. Lauren Morgan, director of human resources at Tapcart, said the company is looking to grow, but is being especially cautious about its new hires.
“We never wanted to have any layoffs, and we’ve been really (careful) about who we’re hiring, what positions we are approving, and really kind of putting our hiring managers through the wringer to make sure they’re only bringing adding any new positions that are definitely required,” Morgan said.
She said the salaries that most candidates are asking for have not changed. “A recruiting agency, they may see that a bit more, but for us on our internal recruiting team, whatever salary is in our budget and then whatever salary the candidate is looking for, (we try to) find a happy medium there,” Morgan said.
For companies that are wary of hiring at this time, Morgan recommends they reflect on their current team members. “Is there another (employee) that may not have a full workload? Is there someone that you can promote? You kind of look within the org to see what you can do,” Morgan continued. “We’ve done a lot of internal promotion, and that’s really one of our favorite things to do, because it’s not only helping the company, it’s really helping people’s careers excel as well.”
Morgan added that the current environment is an exciting time to in which to find talent.
“We are in kind of a unique situation here, and it’s really great for us, because we’re also able to find some amazing talent that unfortunately were let go at some of these larger tech companies. And now they can find their forever home with us,” Morgan added.
| 2023-02-27T00:00:00 |
2023/02/27
|
https://labusinessjournal.com/technology/tech-layoffs-fueling-startups/
|
[
{
"date": "2023/02/27",
"position": 48,
"query": "artificial intelligence layoffs"
}
] |
AI and Graphic Design: A Look into the Advancements ...
|
AI and Graphic Design: A Look into the Advancements and Challenges
|
https://xphotography.ca
|
[] |
AI-powered software can automatically enhance images, removing noise, correcting lighting and colour, and even removing unwanted elements from an image. This ...
|
AI and Graphic Design: A Look into the Advancements and Challenges
Artificial intelligence (AI) and graphic design have been rapidly advancing in recent years, with many designers and developers looking to explore the potential of this technology. While artificial intelligence can offer a wide range of benefits for graphic design, it also poses a number of challenges that must be addressed. In this blog post, we will take a look at some of the advancements and challenges of AI in graphic design.
One of the most significant advancements of AI in graphic design is its ability to automate repetitive tasks. For example, AI-powered software can automatically generate different design variations based on a set of parameters, saving designers hours of time and allowing them to focus on more creative aspects of their work. This is especially useful for designers working on projects with a large number of variations, such as product packaging or website layouts.
Another area where AI is making a big impact is image processing. AI-powered software can automatically enhance images, removing noise, correcting lighting and colour, and even removing unwanted elements from an image. This can save designers hours of time in post-processing and allow them to focus on more creative aspects of their work.
AI is also being used to create new forms of art and creativity in graphic design. For example, AI-generated images can be used to create unique and surreal designs that are not possible to create with traditional design techniques. These AI-generated images are created by feeding a dataset of images into a machine learning algorithm, which then generates new images based on that dataset. This can create new and unique designs that are not possible to create with traditional design techniques.
While artificial intelligence can offer many benefits for graphic design, it also poses a number of challenges. One of the biggest challenges is the need for high-quality training data. In order for AI-powered software to work effectively, it needs to be trained on a large dataset of high-quality images. This can be a significant challenge for designers, as it requires a large amount of time and resources.
Another challenge of AI in graphic design is its lack of creativity. While AI-powered software can automate repetitive tasks and enhance images, it is not capable of creating truly original designs. This can be a significant challenge for designers, as it requires a human touch to create truly unique and impactful designs.
In addition, there is also a concern that AI can replace human designers. While AI can automate repetitive tasks and enhance images, it is not capable of fully replacing the creativity and expertise of a human designer. However, this does not mean that AI will replace human designers, but it will change the way we work and the role of a designer in the future.
Overall, AI and graphic design are rapidly advancing, with many designers and developers looking to explore the potential of this technology. While AI can offer many benefits for graphic design, it also poses a number of challenges that must be addressed. From automating repetitive tasks to creating new forms of art and creativity, the future of graphic design looks bright with the integration of at AI.
So if you’re a professional graphic designer looking to stay ahead of the curve, now is the time to start experimenting with AI. You’ll be able to take your design to new heights and create stunning images that will captivate your clients.
The links provided offer a selection of books related of AI and Graphic Design.
To conclude, AI and graphic design is a rapidly advancing field with many possibilities, but also with some challenges that must be addressed. If you want to stay ahead of the curve in your graphic design career, it’s time to start exploring the world of AI.
If you are interested in exploring more content related to the current topic, we recommend that you peruse the other posts that we have provided below. By clicking on these links, you will be directed to articles and resources that cover the similar subject matter, thereby enabling you to broaden your knowledge and deepen your understanding of the topic at hand. We encourage you to take advantage of this opportunity to delve deeper into the subject and expand your knowledge base.
www.Xphotography.ca
| 2023-02-27T00:00:00 |
2023/02/27
|
https://xphotography.ca/graphic-design/ai-and-graphic-design-a-look-into-the-advancements-challenges/
|
[
{
"date": "2023/02/27",
"position": 29,
"query": "artificial intelligence graphic design"
}
] |
AI in Graphic & Web Design: Opportunities vs. Challenges
|
AI in Graphic & Web Design: Opportunities vs. Challenges
|
https://www.exabytes.my
|
[
"Vanessa Is A Blogger On A Mission To Spill The Digital Tea",
"Keep You Updated On The Latest Buzz Because Someone S Got To Make Sense Of This Techy Chaos"
] |
Artificial Intelligence (AI) is changing the way we approach graphic and web design, unlocking new levels of creativity, efficiency, and personalisation.
|
Artificial Intelligence (AI) is changing the way we approach graphic and web design, unlocking new levels of creativity, efficiency, and personalisation.
It’s exciting to see how AI can lighten the workload by handling repetitive tasks and offering innovative ideas.
But like any breakthrough, it comes with its own set of hurdles that designers need to overcome.
Let’s dive into how AI is shaping the design world and explore how Exabytes’ AI Hosting solutions can help you embrace these changes seamlessly and confidently.
AI: A Game-Changer for Creativity and Efficiency AI isn’t just about automating repetitive tasks; it’s like having a helpful assistant for your creative journey. Tools like Adobe Sensei handle things like colour correction and resizing, saving time and letting designers focus on the fun, imaginative parts of their projects. AI even offers smart suggestions tailored to user preferences, making it easier to craft designs that truly connect with audiences. Plus, real-time feedback from AI tools can spark fresh ideas and speed up the design process, giving creators more freedom to innovate and personalise.
The Challenge: Keeping the Human Touch Alive
AI is a fantastic tool for boosting productivity, but it raises a valid concern—can it ever match the human touch in design?
Creativity is deeply personal.
While AI can generate ideas and handle data-driven tasks, it lacks the empathy, cultural insight, and storytelling ability that make designs truly impactful.
The key is balance.
Let AI handle the repetitive tasks and support your work, but let your imagination and personal flair shine through.
Use it as a tool, not a replacement, to keep your designs authentic and human.
Your Partner for Seamless AI Integration Hosting With AI becoming a central part of design workflows, having a reliable hosting partner makes all the difference. Exabytes AI Hosting ensures your AI tools run effortlessly, offering fast speeds, top-notch security, and the flexibility to scale as you grow. Speed : Optimised for smooth, delay-free performance.
: Optimised for smooth, delay-free performance. Scalability : Grows alongside your creative projects.
: Grows alongside your creative projects. Security: Keeps your designs and data safe. Ready to let your ideas flow without limits? Explore Exabytes’ AI Hosting today!
AI-Powered Personalisation: Crafting Unique User Experiences
AI is revolutionising user experience (UX) design by enabling deeply personalised interactions.
Imagine a website that adapts dynamically to your preferences, behaviour, or browsing history—it’s like having a tailor-made digital journey.
This approach not only captivates users but also drives higher engagement and conversion rates.
Take Netflix as an example.
Its AI recommends shows based on your viewing habits.
In web design, similar AI tools can craft personalised landing pages or suggest products visitors will love.
This level of personalisation ensures users feel seen, valued, and eager to return.
Real-World Examples of AI in Action Many companies are already tapping into AI to simplify and enhance their design workflows. For instance, Airbnb uses AI to quickly generate design prototypes, allowing their team to focus on perfecting the brand’s identity while optimising layouts based on user behaviour. This approach streamlines their creative process and ensures the designs meet user needs. Similarly, Canva leverages AI to make professional design effortless for everyone. Its intelligent suggestions for layouts, fonts, and colors empower beginners and professionals alike to create stunning visuals with ease.
The Future of AI in Design: What’s Next? The potential of AI in design is just starting to unfold. Imagine tools that can build entire websites, predict emerging trends, or understand your audience so well they help craft spot-on user personas. That’s the direction we’re headed. For designers, this isn’t about AI taking over—it’s about teaming up with these tools to push boundaries and create work that stands out. Staying curious, learning new skills, and embracing innovation will be the key to thriving in this exciting future.
Step into the Future of Design with Exabytes’ AI Hosting
At Exabytes, we know that AI is shaping the future of design, and we’re here to make sure you’re ready for it.
Our AI Hosting solutions provide the reliable infrastructure you need to run cutting-edge tools seamlessly and securely.
With speed, scalability, and security at your fingertips, you can focus on creating, innovating, and growing your designs.
Ready to level up?
Discover Exabytes AI Hosting and see how we can help you bring your vision to life !
| 2023-02-27T00:00:00 |
2023/02/27
|
https://www.exabytes.my/blog/ai-opportunity-challenge-graphic-web-design/
|
[
{
"date": "2023/02/27",
"position": 33,
"query": "artificial intelligence graphic design"
}
] |
Create Long Form Video Content With Ai
|
Pin on blog writing
|
https://www.pinterest.com
|
[] |
Create Long Form Video Content With Ai | Artificial Intelligence And Machine Learning ... Graphic Design Portfolio (Blog Redirect). More about this Pin. 43. Saves ...
|
Search for easy dinners, fashion, etc.
When autocomplete results are available use up and down arrows to review and enter to select. Touch device users, explore by touch or with swipe gestures.
| 2023-02-27T00:00:00 |
https://www.pinterest.com/pin/908038343599643439/
|
[
{
"date": "2023/02/27",
"position": 93,
"query": "artificial intelligence graphic design"
}
] |
|
Typeface: Generative AI for the Enterprise
|
Typeface: Generative AI for the Enterprise
|
https://www.gv.com
|
[] |
These platforms have sparked a wave of enthusiasm for the potential of generative artificial intelligence to disrupt fields, including art and graphic design, ...
|
Images generated by Typeface
When OpenAI’s DALL-E, Stable Diffusion, and Midjourney launched generative text-to-image platforms last year, they dazzled many people with the complexity, breadth, and beauty of the images they synthesized. Not long after, ChatGPT and other GPT-3 based copywriting applications demonstrated how easy it was to generate quality copy from high-level prompts. These platforms have sparked a wave of enthusiasm for the potential of generative artificial intelligence to disrupt fields, including art and graphic design, marketing, and branding.
Previously, many large language models (LLMs) have faced a significant limitation: they’re not enterprise-ready for professional marketing and creative teams. Since they train on publicly available data, they do not easily incorporate private first-party data or visual assets, nor do they yet integrate into the suite of other applications, databases, or workflows already present in companies of scale. Moreover, they’re not designed to reflect the body of branding tools (visual assets, highly-specialized colors, fonts, product copy, high-resolution images) that businesses rely on. As a result, the talent required to tune or retrain these models remains scarce and costly for most organizations.
Enter Typeface — a category-defining company taking an enterprise-minded approach to content creation, integrating generative AI into workflows for professional marketing and content teams. GV is thrilled to announce our investment in Typeface as the company debuts its new product, creating branded experiences inclusive of text, images, and more.
Images generated by Typeface
Typeface uses an “affinitized AI” approach — meaning it can quickly and cost-effectively retrain off-the-shelf LLMs on customers’ corporate marketing assets and generate authentic images at scale and cost-effectively. From the outset, Typeface focused on building a product with privacy, security, and scalability in mind. The company is already off to a promising start, partnering with digital-native brands and fast-growing enterprise companies to help them supercharge their ability to experiment with and launch new concepts.
We are delighted to partner with CEO Abhay Parasnis, having long admired his technical and product leadership in Silicon Valley, most recently as CTO and CPO at Adobe. Abhay has already built a high-caliber team of senior engineering, product, and go-to-market leaders — including AI, SaaS, and media experts.
The future is incredibly bright for enterprise-grade generative AI, and Abhay and the Typeface team are well-positioned to take the category to new heights. Welcome to the portfolio, Typeface!
| 2023-02-27T00:00:00 |
https://www.gv.com/news/typeface-generative-ai-enterprise
|
[
{
"date": "2023/02/27",
"position": 94,
"query": "artificial intelligence graphic design"
}
] |
|
People Over Robots: The Global Economy Needs ...
|
People Over Robots
|
https://www.foreignaffairs.com
|
[] |
Machines promise to transform every facet of human life: robots will staff factory floors, driverless cars will rule the road, and artificial intelligence will ...
|
Since its founding in 1922, Foreign Affairs has been the leading forum for serious discussion of American foreign policy and global affairs. The magazine has featured contributions from many leading international affairs experts.
| 2023-02-28T00:00:00 |
2023/02/28
|
https://www.foreignaffairs.com/united-states/global-economy-immigration-before-automation-people-over-robots
|
[
{
"date": "2023/02/28",
"position": 94,
"query": "AI job losses"
}
] |
11% of data employees paste into ChatGPT is confidential
|
11% of data employees paste into ChatGPT is confidential
|
https://www.cyberhaven.com
|
[] |
11% of data employees paste into ChatGPT is confidential · Employee adoption of ChatGPT · Usage of ChatGPT in the workplace · How much sensitive data goes to ...
|
The average company leaks confidential material to ChatGPT hundreds of times per week. ChatGPT is incorporating that material into its publicly available knowledge base and sharing it.
Updated June 18, 2023
Since ChatGPT launched On November 30, 2022 it’s taken the world by storm. People are using it to create poems, essays for school, and song lyrics. It’s also making inroads in the workplace. According to data from Cyberhaven’s product, as of June 1, 10.8% of employees have used ChatGPT in the workplace and 8.6% have pasted company data into it since it launched.
Some knowledge workers say that using the tool makes them 10 times more productive. But companies like JP Morgan and Verizon are blocking ChatGPT over risks to confidential data. Our analysis shows that 4.7% of employees have pasted confidential data into ChatGPT.
The problem with putting company data into ChatGPT
OpenAI uses the content people put into ChatGPT as training data to improve its technology. This is problematic because employees are copying and pasting all kinds of confidential data into ChatGPT to have the tool rewrite it, from source code to patient medical records. Recently, an attorney at Amazon warned employees not to put confidential data into ChatGPT, noting, “we wouldn’t want [ChatGPT] output to include or resemble our confidential information (and I’ve already seen instances where its output closely matches existing material).”
Consider a few examples:
A doctor inputs a patient’s name and details of their condition into ChatGPT to have it draft a letter to the patient’s insurance company justifying the need for a medical procedure. In the future, if a third party asks ChatGPT “what medical problem does [patient name] have?” ChatGPT could answer based on what the doctor provided.
An executive inputs bullet points from the company’s 2023 strategy document into ChatGPT and asks it to rewrite it in the format of a PowerPoint slide deck. In the future, if a third party asks “what are [company name]’s strategic priorities this year,” ChatGPT could answer based on the information the executive provided.
On March 21, 2023 OpenAI shut down ChatGPT due to a bug that mislabeled chats in user’s history with the titles of chats from other users. To the extent that those titles contained sensitive or confidential information, they could have been exposed to other ChatGPT users.
On April 6. 2023 news broke that Samsung discovered employees putting confidential data into ChatGPT including source code in order to debug it and transcripts of internal meetings to summarize them. As an emergency measure the company limited input to ChatGPT to 1024 bytes.
{{ promo }}
Identifying what data goes to ChatGPT isn’t easy
The traditional security products companies rely on to protect their data are blind to employee usage of ChatGPT. Before blocking ChatGPT, JP Morgan reportedly couldn’t determine “how many employees were using the chatbot or for what functions they were using it.” It’s difficult for security products, like legacy data loss prevention platforms to monitor usage of ChatGPT and protect data going to it for two reasons:
Copy/paste out of a file or app — When workers input company data into ChatGPT, they don’t upload a file but rather copy and paste content into their web browser. Many security products are designed around protecting files (which are tagged confidential) from being uploaded but once content is copied out of the file they are unable to keep track of it. Confidential data contains no recognizable pattern — Company data going to ChatGPT often doesn’t contain a recognizable pattern that security tools look for, like a credit card number or Social Security number. Without knowing more about its context, security tools today can’t tell the difference between someone inputting the cafeteria menu and the company’s M&A plans.
Despite some companies blocking ChatGPT, its use in the workplace is growing rapidly
Cyberhaven Labs analyzed ChatGPT usage for 1.6 million workers at companies across industries that use the Cyberhaven product. Since ChatGPT launched publicly, 10.8% of knowledge workers have tried using it at least once in the workplace and 8.6% have pasted data into it. Despite a growing number of companies outright blocking access to ChatGPT, usage continues to increase. On May 31, our product detected a record 7,999 attempts to paste corporate data into ChatGPT per 100,000 employees, defined as “data egress” events in the chart below.
Cyberhaven also tracks data ingress such as employees copying data out of ChatGPT and pasting it elsewhere like a Google Doc, a company email, or their source code editor. Workers copy data out of ChatGPT more than they paste company data into ChatGPT at a nearly 2-to-1 ratio. This makes sense because in addition to asking ChatGPT to rewrite existing content, you can simply type a prompt such as “draft a blog post about how problematic ChatGPT is from a data security standpoint” and it will write it from scratch. Full disclosure: this post was written the old fashioned way by a human being. 🙂
The average company leaks sensitive data to ChatGPT hundreds of times each week
Since ChatGPT launched, 4.7% of employees have pasted sensitive data into the tool at least one. Sensitive data makes up 11% of what employees paste into ChatGPT, but since usage of ChatGPT is so high and growing exponentially this turns out to be a lot of information. Cyberhaven Labs calculated the number of incidents per 100,000 employees to understand how common they are across companies. You can apply this rate of incidents to the number of employees at any given company to estimate how much data employees are putting into ChatGPT.
Between the week of February 26 and the week of April 9, the number of incidents per 100,000 employees where confidential data went to ChatGPT increased by 60.4%. The most common types of confidential data leaking to ChatGPT are sensitive/internal only data (319 incidents per week per 100,000 employees), source code (278) and client data (260). During this time period source code eclipsed client data as the second most common type of sensitive data going to ChatGPT.
A few bad apples?
At the average company, just 0.9% of employees are responsible for 80% of egress events — incidents of pasting company data into the site. The number is still relatively small, but any one of the egress events we found could be considered an insider threat, responsible for exposing a critical piece of company data. There are many legitimate uses of ChatGPT in the workplace, and companies that navigate ways to leverage it to improve productivity without risking their sensitive data are poised to benefit.
| 2023-02-28T00:00:00 |
https://www.cyberhaven.com/blog/4-2-of-workers-have-pasted-company-data-into-chatgpt
|
[
{
"date": "2023/02/28",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2023/02/28",
"position": 61,
"query": "AI workers"
}
] |
|
Ten Legal and Business Risks of Chatbots and Generative AI
|
Ten Legal and Business Risks of Chatbots and Generative AI
|
https://techpolicy.press
|
[
"Matthew Ferraro",
"Natalie Li",
"Haixia Lin",
"Louis Tompros"
] |
To mitigate data privacy risks, companies utilizing chatbots and generative AI tools should review their privacy policies and disclosures, comply with ...
|
Matthew Ferraro,
Natalie Li,
Haixia Lin,
Louis Tompros /
Feb 28, 2023
Matthew F. Ferraro, a senior fellow at the National Security Institute at George Mason University, is a Counsel at WilmerHale; Natalie Li is a Senior Associate, and Haixia Lin and Louis W. Tompros are Partners at WilmerHale.
Fritzchens Fritz / Better Images of AI / GPU shot etched 5 / CC-BY 4.0
Introduction
It took just two months from its introduction in November 2022 for the artificial intelligence (AI)- powered chatbot ChatGPT to reach 100 million monthly active users—the fastest growth of a consumer application in history.
Chatbots like ChatGPT are Large Language Models (LLMs), a type of artificial intelligence known as “generative AI.” Generative AI refers to algorithms that, after training on massive amounts of input data, can create new outputs, be they text, audio, images or video. The same technology fuels applications like Midjourney and DALL-E 2 that produce synthetic digital imagery, including “deepfakes.”
Powered by the language model Generative Pretrained Transformer 3 (GPT-3), ChatGPT is one of today’s largest and most powerful LLMs. It was developed by San Francisco-based startup OpenAI—the brains behind DALL-E 2—with backing from Microsoft and other investors, and was trained on over 45 terabytes of text from multiple sources including Wikipedia, raw webpage data and books to produce human-like responses to natural language inputs.
LLMs like ChatGPT interact with users in a conversational manner, allowing the chatbot to answer follow-up questions, admit mistakes, and challenge premises and queries. Chatbots can write and improve code, summarize text, compose emails and engage in protracted colloquies with humans. The results can be eerie; in extended conversations in February 2023 with journalists, chatbots grew lovelorn and irascible and expressed dark fantasies of hacking computers and spreading misinformation.
The promise of these applications has spurred an “arms race” of investment into chatbots and other forms of generative AI. Microsoft recently announced a new, $10 billion investment in OpenAI, and Google announced plans to launch an AI-powered chatbot called Bard later this year.
The technology is advancing at a breakneck speed. As Axios put it, “The tech industry isn’t letting fears about unintended consequences slow the rush to deploy a new technology.” That approach is good for innovation, but it poses its own challenges. As generative AI advances, companies will face a number of legal and ethical risks, both from malicious actors leveraging this technology to harm businesses and when businesses themselves wish to implement chatbots or other forms of AI into their functions.
This is a quickly developing area, and new legal and business dangers—and opportunities—will arise as the technology advances and use cases emerge. Government, business and society can take the early learnings from the explosive popularity of generative AI to develop guardrails to protect against their worst behavior and use cases before this technology pervades all facets of commerce. To that end, businesses should be aware of the following top 10 risks and how to address them.
Risks
1. Contract Risks
Using chatbots or similar AI tools may implicate a range of contractual considerations.
Businesses should be wary of entering into chatbot prompts information from clients, customers or partners that is subject to contractual confidentiality limitations or other controls. This is because chatbots may not keep that information private; their terms of service typically grant the chatbot the rights to use the data they ingest to develop and improve their services. If the bot provides opt-out features, users may want to utilize them before inputting contractually protected information into the prompts, but users should still proceed cautiously. In one exchange with a professor, ChatGPT itself warned that “[i]nformation provided to me [ChatGPT] during an interaction should be considered public, not private” and that the bot cannot “ensure the security or confidentiality of any information exchanged during these interactions, and the conversations may be stored and used for research or training purposes.”
Likewise, a business will need to curtail its use of chatbots or AI generally if a contract imposes on the business the obligation to produce work or perform services on its own or by a specific employee, without the aid of AI. To the extent that a chatbot generates contract work product— unlike traditional information technology, which merely provides a platform for generating work product—a chatbot service could be a subcontractor, potentially subject to pre-approval by the ultimate customer.
In both circumstances, the key is to recognize that the relationship between a user and a chatbot is not akin to the relationship between a user and a word processing program or a similar static tool. Chatbots and other generative AI software are learning machines that by default use information entered into them for their own purposes and that produce their own output. (Beware: all of the inputs could potentially be discoverable in litigation.) For these reasons, they pose risks to businesses’ contractual obligations, and companies should use these tools circumspectly.
2. Cybersecurity Risks
Chatbots pose cybersecurity risks to businesses along two main axes. First, malicious users without sophisticated programming skills can use chatbots to create malware for cyber hacks. Second, because chatbots can convincingly impersonate fluent, conversational English, they can be used to create human-like conversations that can be used for social engineering, phishing and malicious advertising schemes, including by bad actors with poor English-language skills. Chatbots like ChatGPT typically disallow malicious uses through their usage policies and implement system rules to prohibit bots from responding to queries that ask for the creation of malicious code per se; however, cybersecurity researchers have found work-arounds that threat actors on the dark web and special-access sources have already exploited. In response, companies should redouble efforts to bolster their cybersecurity and train employees to be on the lookout for phishing and social engineering scams.
3. Data Privacy Risks
Chatbots may collect personal information as a matter of course. For example, ChatGPT’s Privacy Policy states that it collects a user’s IP address, browser type and settings; data on the user’s interactions with the site; and the user’s browsing activities over time and across websites, all of which it may share “with third parties.” If a user does not provide such personal information, it may render a chatbot’s services inoperable. Currently, the leading chatbots do not appear to provide the option for users to delete the personal information gathered by their AI models.
Because laws in the United States and Europe impose restrictions on the sharing of certain personal information about, or obtained from, data subjects—some of which chatbots may collect automatically, and some that a user may input into the chatbot’s prompt—businesses using chatbots or integrating them into their products should proceed cautiously. Data privacy regulators could scrutinize these systems, assessing whether their user-consent options and opt-out controls stand up to legal scrutiny. For example, the California Privacy Rights Act requires California companies of a certain size to provide notice to individuals and the ability to opt out of the collection of some personal information.
Some data privacy regimes impose regulations on entities that merely collect information, like the AI systems that ingested billions of Internet posts to create their models. In California, for example, unless an entity is registered as a data broker, it is supposed to provide a “notice at collection” to any California resident about whom it is collecting data.
To mitigate data privacy risks, companies utilizing chatbots and generative AI tools should review their privacy policies and disclosures, comply with applicable data protection laws with regard to processing personal information, and provide opt-out and deletion options.
4. Deceptive Trade Practice Risks
If an employee outsources work to a chatbot or AI software when a consumer believes he or she is dealing with a human, or if an AI-generated product is marketed as human made, these misrepresentations may run afoul of federal and state laws prohibiting unfair and deceptive trade practices. The Federal Trade Commission (FTC) has released guidance stating that Section 5 of the FTC Act, which prohibits “unfair and deceptive” practices, gives it jurisdiction over the use of data and algorithms to make decisions about consumers and over chatbots that impersonate humans.
For example, in 2016, the FTC alleged that an adultery-oriented dating website deceived consumers by using fake “engager profiles” to trick customers to sign up, and in 2019, the FTC alleged that a defendant sold phony followers, subscribers and likes to customers to boost social media profiles. In sum, “[i]f a company’s use of doppelgängers—whether a fake dating profile, phony follower, deepfakes, or an AI chatbot—misleads consumers, that company could face an FTC enforcement action,” or enforcement by state consumer protection authorities.
To address this issue, the FTC emphasizes transparency. “[W]hen using AI tools to interact with customers (think chatbots), be careful not to mislead consumers about the nature of the interaction,” the FTC warns. Companies should also be transparent when collecting sensitive data to feed into an algorithm to power an AI tool, explain how an AI’s decisions impact a consumer and ensure that decisions are fair.
Likewise, the White House’s October 2022 Blueprint for an AI Bill of Rightssuggests developers of AI tools provide “clear descriptions of the overall system functioning and the role automation plays, notice that such systems are in use, the individual or organization responsible for the system, and explanations of outcomes that are clear, timely, and accessible.”
5. Discrimination Risks
Issues related to discrimination can arise in different ways when businesses use AI systems. First, bias can result because of the biased nature of the data on which AI tools are trained. Because AI models are built by humans and learn by devouring data created by humans, human bias can be baked into an AI’s design, development, implementation and use. For example, in 2018, Amazon reportedly scrapped an AI-based recruitment program after the company found that the algorithm was biased against women. The model was programmed to vet candidates by observing patterns in resumes submitted to the company over a 10-year period, but because the majority of the candidates in the training set had been men, the AI taught itself that male candidates were preferred over female candidates.
ChatGPT, like other LLMs, can learn to express the biases of the data used to train them. As OpenAI acknowledges, ChatGPT “may occasionally produce harmful instructions or biased content.”
Second, users can purposefully manipulate AI systems and chatbots to produce unflattering or prejudiced outputs. For example, despite built-in features to inhibit such responses, one user got ChatGPT to write code stating that only White or Asian men make good scientists; OpenAI has reportedly updated the bot to respond, “It is not appropriate to use a person’s race or gender as a determinant of whether they would be a good scientist.” In another recent example, at a human’s direction, the chatbot adopted a “devil-may-care alter ego” that opined that Hitler was “complex and multifaceted” and “a product of his time.”
Federal regulators and the White House have repeatedly emphasized the importance of using AI responsibly and in a nondiscriminatory manner. For example, the White House’s Blueprint for an AI Bill of Rights declares that users “should not face discrimination by algorithms and systems should be used and designed in an equitable way.” Algorithmic discrimination, which has long existed independent of chatbots, refers to when automated systems “contribute to unjustified different treatment or impacts disfavoring people” based on various protected characteristics like race, sex, and religion.
“Designers, developers, and deployers of automated systems should take proactive and continuous measures to protect individuals and communities from algorithmic discrimination and to use and design systems in an equitable way,” the White House advises. This protection should include “proactive equity assessments as part of the system design,” the use of representative data, “predeployment and ongoing disparity testing and mitigation, and clear organizational oversight,” among other actions.
Similarly, in April 2021, the FTC noted that even “neutral” AI technology can “produce troubling outcomes—including discrimination by race or other legally protected classes.” The FTC recommends that companies’ use of AI tools be transparent, explainable, and fair and empirically sound so as not to mislead consumers about the nature of their interactions with the company.
Finally, in January 2023, the National Institute of Standards and Technology (NIST) issued a Risk Management Framework for using AI in a trustworthy manner. The Risk Management Framework provides voluntary guidance to users of AI and sets forth principles for managing risks related to fairness and bias, as well as other principles of responsible AI such as validity and reliability, safety, security and resiliency, explainability and interpretability, and privacy.
Bias may arise in AI systems even absent prejudicial or discriminatory intent by their human creators. As urged by emerging US government guidance, companies using such tools should carefully consider the potential for prejudicial or discriminatory impact, be forthright about how they are using chatbots and other generative AI tools, conduct regular testing to judge disparities, and impose a process for humans to review the outputs to ensure compliance with anti-discrimination laws and to safeguard against reputational harm.
6. Disinformation Risks
Chatbots can help malicious actors create false, authoritative-sounding information at mass scale quickly and at little cost. Researchers showed recently that chatbots can compose news articles, essays and scripts that spread conspiracy theories, “smoothing out human errors like poor syntax and mistranslations and advancing beyond easily discoverable copy-paste jobs.”
False narratives coursing through the internet already regularly harm businesses. For example, in 2020, the QAnon-inspired theory spread online that the furniture seller Wayfair was connected with child sex trafficking because of the coincidental overlap of the names of some of its furniture pieces and those of missing children. As a result, social media users attempted to orchestrate a large short sale of Wayfair’s stock, posted the address and images of the company’s headquarters and the profiles of employees, and harassed the CEO.
Now, a single bad actor with access to an effective chatbot could generate a flood of human looking posts like those that targeted Wayfair and loose them on the internet, potentially harming the reputation and valuation of innocent companies. Add to these false narratives deepfake imagery of, say, the CEO of the targeted business doing something untoward, and the dangers will accelerate.
What is more, malicious actors can teach AI models bogus information by feeding lies into their models, which the models will then spread.
Managing disinformation risk is complex. In short, businesses should plan for disinformation dangers like they plan for cyberattacks or crisis events, proactively communicate their messages, monitor how their brands are perceived online, and be prepared to respond in the event of an incident.
7. Ethical Risks
Companies regulated by professional ethics organizations, such as lawyers, doctors and accountants, should ensure that their use of AI comports with their professional obligations.
For example, in the legal services industry, “legal representation” is explicitly defined in several jurisdictions as a service rendered by a person. Because AI chatbots are not “persons” admitted to the bar, they cannot practice law before a court. Accordingly, the use of AI in the legal industry could elicit charges of the unauthorized practice of law. Case in point: In January 2023, Joshua Browder, the CEO of the AI company DoNotPay, attempted to deploy an AI chatbot to argue before a physical courtroom. But after “state bar prosecutors” purportedly threatened legal action and six months’ jail time for the unauthorized practice of law, Browder canceled the appearance. To avoid potential violations of ethical obligations, companies should ensure any use of AI tools comports with ethical and applicable professional codes.
8. Government Contract Risks
The US government is the largest purchaser of supplies and services in the world. US government contracts are typically awarded pursuant to formal competitive procedures, and the resulting contracts generally incorporate extensive standardized contract terms and compliance requirements, which frequently deviate from practices in commercial contracting. These procedural rules and contract requirements will govern how private companies might use AI to prepare bids and proposals seeking government contracts and to perform those contracts that are awarded.
When preparing a bid or proposal in pursuit of a government contract, companies should be transparent about any intended or potential use of AI to avoid the risk of misleading the government that the work product will be generated in whole or in part by a third party’s AI tool. If two competing bidders use the same AI tool to develop their proposals, there is a chance that the proposals will appear similar. Indeed, OpenAI’s Terms of Use warn that “[d]ue to the nature of machine learning, Output [from ChatGPT] may not be unique across users and [the chatbot] may generate the same or similar output for OpenAI or a third party.” Such similarity could create an appearance of sharing of contractor bid or proposal information, which is prohibited by the Procurement Integrity Act. If competitive proposal information is entered into a third-party AI tool, that information might actually be used by the tool through a machine learning process to generate another offeror’s proposal, which could actually constitute a prohibited sharing of contractor bid or proposal information.
For awarded government contracts, a contractor should review the contract before using AI to create deliverables to ensure that the contract does not prohibit the use of such tools to generate work product.
Thus, government contractors should proceed cautiously and in consultation with counsel before relying on chatbots or generative AI to pursue or perform government contracts.
9. Intellectual Property Risks
Intellectual property (IP) risks associated with using AI can arise in several ways.
First, because AI systems have been trained on enormous amounts of data, such training data will likely include third-party IP, such as patents, trademarks, or copyrights, for which use authorization has not been obtained in advance. Hence, outputs from the AI systems may infringe others’ IP rights. This phenomenon has already led to litigation.
In November 2022, in Doe v. GitHub, pseudonymous software engineers filed a putative class action lawsuit against GitHub, Microsoft and OpenAI entities alleging that the defendants trained two generative AI tools—GitHub Copilot and OpenAI Codex—on copied copyrighted material and licensed code. Plaintiffs claim that these actions violate open source licenses and infringe IP rights. This litigation is considered the first putative class action case challenging the training and output of AI systems.
In January 2023, in Anderson v. Stability AI, three artists filed a putative class action lawsuit against AI companies Stability AI, Midjourney and DeviantArt for copyright infringement over the unauthorized use of copyrighted images to train AI tools. The complaint describes AI image generators as “21st-century collage tools” that have used plaintiffs’ artworks without consent or compensation to build the training sets that inform AI algorithms.
In February 2023, Getty Images filed a lawsuit against the Stability AI, accusing it of infringing its copyrights by misusing millions of Getty photos to train its AI art-generation tool.
Second, disputes may arise over who owns the IP generated by an AI system, particularly if multiple parties contribute to its developments. For example, OpenAI’s Terms of Use assign the “right, title and interest” in the output of the LLM to the user who provided the prompts, so long as the user abided by OpenAI’s terms and the law. OpenAI reserves the right to use both the user’s input and the AI-generated output “to provide and maintain the Services, comply with applicable law, and enforce our policies.”
Third, there is the issue of whether IP generated by AI is even protected because, in some instances, there is arguably no human “author” or “inventor.” Litigants are already contesting the applicability of existing IP laws to these new technologies. For example, in June 2022, Stephen Thaler, a software engineer and the CEO of Imagination Engines, Inc., filed a lawsuit asking the courts to overturn the US Copyright Office’s decision to deny a copyright for artwork whose author was listed as “Creativity Machine,” an AI software Thaler owns. (The US Copyright Office has stated that works autonomously generated by AI technology do not receive copyright protection because the Copyright Act grants protectable copyrights only to works created by a human author with a minimal degree of creativity.) In late February 2023, the US Copyright Office ruled that images used in a book that were created by the image-generator Midjourney in response to a human’s text prompts were not copyrightable because they are “not the product of human authorship.”
As the law surrounding the use of AI develops, companies seeking to use LLMs and generative AI tools to develop their products should document the extent of such use and work with IP counsel to ensure adequate IP protections for their products. For example, the Digital Millennium Copyright Act requires social media companies to remove posts that infringe on IP, and generative AI systems may have avenues through which rights holders can alert the platforms to infringing uses. For example, OpenAI provides an email address where rights holders can send copyright complaints, and OpenAI says “it may delete or disable content alleged to be infringing and may terminate accounts of repeat infringers.”
10. Validation Risks
As impressive as chatbots are, they can make false, although authoritative-sounding statements, often referred to as “hallucinations.” LLMs are not sentient and do not “know” the facts. Rather, they know only the most likely response to a prompt based on the data on which they were trained. OpenAI itself acknowledges that ChatGPT may “occasionally produce incorrect answers” and cautions that ChatGPT has “limited knowledge of world and events after 2021.” Users have flagged and cataloged responses in which ChatGPT flubbed answers to mathematical problems, historical queries and logic puzzles.
Companies seeking to use chatbots should not simply accept the AI-generated information as true and should take measures to validate the responses before incorporating them into any work product, action or business decision.
Conclusion
With the pell-mell development of chatbots and generative AI, businesses will encounter both the potential for substantial benefits and the evolving risks associated with the use of these technologies. While specific facts and circumstances will determine particular counsel, businesses should consider these top-line suggestions:
Be circumspect in the adoption of chatbots and generative AI , especially in pursuing government contracts, or to generate work required by government or commercial contracts;
, especially in pursuing government contracts, or to generate work required by government or commercial contracts; Consider adopting policies governing how such technologies will be deployed in business products and utilized by employees;
in business products and utilized by employees; Recognize that chatbots can often err , and instruct employees not to rely on them uncritically;
, and instruct employees not to rely on them uncritically; Carefully monitor the submission of business, client or customer data into chatbots and similar AI tools to ensure such use comports with contractual obligations and data privacy rules;
into chatbots and similar AI tools to ensure such use comports with contractual obligations and data privacy rules; If using generative AI tools, review privacy policies and disclosures , require consent from user s before allowing them to enter personal information into prompts, and provide opt-out and deletion options ;
, s before allowing them to enter personal information into prompts, and ; If using AI tools, be transparent about it with customers, employees and clients;
with customers, employees and clients; If using AI software or chatbots provided by a third party, seek contractual indemnification from the third party for harms that may arise from that tool’s use;
that may arise from that tool’s use; Bolster cybersecurity and social engineering defenses against AI-enabled threats;
against AI-enabled threats; Review AI outputs for prejudicial or discriminatory impacts ;
; Develop plans to counter AI-powered disinformation ;
; Ensure that AI use comports with ethical and applicable professional standards ; and
; and Copyright original works and patent critical technologies to strengthen protection against unauthorized sourcing by AI models and, if deploying AI tools, work with IP counsel to ensure outputs are fair use.
- - -
We thank Partners Barry Hurewitz and Kirk Nahra, Counsel Rebecca Lee, and Senior Associate Ali Jessani for their contributions to this article.
| 2023-02-28T00:00:00 |
2023/02/28
|
https://techpolicy.press/ten-legal-and-business-risks-of-chatbots-and-generative-ai
|
[
{
"date": "2023/02/28",
"position": 76,
"query": "workplace AI adoption"
}
] |
Workplace Transformation: Strategies for Retaining Quality ...
|
Workplace Transformation: Strategies for Retaining Quality Employees
|
https://www.employeeconnect.com
|
[
"Carol Lin"
] |
Through the adoption of digital transformation, organizations can cultivate a work environment that is more productive, efficient, and engaging, ultimately ...
|
Workforce transformation is an important aspect of modern businesses. It involves adapting to changes in the workplace, including new technologies, shifting job markets, and changing employee expectations. One of the most significant outcomes of workforce transformation is the impact it has on retaining high-performing employees. The ability to attract and retain top talent is essential to the success of any business, and it is becoming increasingly challenging in today’s fast-paced, highly competitive job market.
The digital workforce transformation is a critical aspect of modern businesses and is an essential component of any workforce transformation strategy. It involves leveraging digital technologies to enhance the work environment, streamline processes, and improve the employee experience. Through the adoption of digital transformation, organizations can cultivate a work environment that is more productive, efficient, and engaging, ultimately leading to greater staff retention and driving business success.
In this article, we’ll explore best practices and strategies for retaining valuable employees during workforce transformation. We’ll cover five retention strategies, the benefits of flexible work, the importance of empowering employees, the role of digital technologies, and the impact of workforce planning and strategies on employee retention.
Retention Strategies
Retention strategies are methods used to keep employees engaged, motivated, and committed to an organization. These strategies are critical in today’s competitive job market, where employees have more opportunities to change jobs and find better opportunities. Here are five retention strategies that can help companies retain quality employees:
Offer competitive compensation and benefits packages. Provide opportunities for career growth and advancement. Foster a positive work environment that promotes work-life balance. Encourage open communication and collaboration. Recognise and reward top-performing employees.
Competitive compensation and benefits packages are essential in retaining skilled employees. When employees feel valued and appreciated, they are less likely to leave their job. Career growth and advancement opportunities can also support employees by providing a sense of purpose and direction.
A positive work environment that promotes work-life balance is critical in retaining employees. When employees feel satisfied with their work and life, they are less likely to look for opportunities elsewhere. Establishing an atmosphere of transparency and teamwork can promote a beneficial workplace. Acknowledging and incentivising high-achieving staff can encourage sustained dedication.
Flexible Work
Flexible work arrangements are an employee retention tactic that enables a more favourable integration of work and personal life for employees. This can include remote work, flexible hours, and job sharing. Adaptable work arrangements can help retain employees. It provides a sense of control over their work environment and enables them to balance their work and life commitments better.
Agile work policies is becoming increasingly popular, and it is an important aspect of workforce transformation. Through the provision of adaptable work schedules, organizations can promote staff retention and enhance the overall employee experience. Flexible work arrangements can also help companies attract top talent, especially in industries where there is a shortage of skilled workers.
Empowering Employees
Empowering employees is another important aspect of retaining quality employees. Empowerment involves giving employees the freedom to make decisions, solve problems, and take ownership of their work. When employees feel empowered, they are more engaged, motivated, and committed to their work.
Cultivating employee self-determination also helps to create a positive work environment. When employees feel valued and trusted, they are more likely to be satisfied with their job and less likely to look for opportunities elsewhere. Fostering a sense of empowerment is a crucial element of workforce transformation, and organizations that prioritise empowering their staff are more inclined to retain exceptional employees.
The Digital Workplace Transformation
The digital workplace transformation is changing the way work is done. Digital technologies are enabling new ways of working, including remote work and digital collaboration. Digital technologies are also changing the way employees interact with their work environment, and they are creating new opportunities for innovation and growth.
The integration of digital technologies is becoming increasingly critical in the process of workforce transformation. Companies that integrate digital into their transformation efforts are more likely to retain quality employees. Digital technologies can improve the employee experience by providing access to real-time information, streamlining processes, and reducing the workload. This can help employees feel more productive, engaged, and satisfied with their work.
The digital workplace transformation can also support workforce strategies by providing new tools and technologies to help with workforce planning. Companies can leverage digital technologies to gather real-time data and insights. This data can then be used to gain a better understanding of their workforce. With this understanding, companies can make informed decisions about how to manage their workforce effectively.
Workforce Planning and Strategies
Effective workforce planning and strategies can also help companies address the challenges of workforce transformation. For example, workforce planning can help companies manage the impacts of shifting job markets and changing employee expectations, and it can help companies attract and retain top talent.
In conclusion, workforce transformation is a crucial aspect of modern business, and it requires a comprehensive and well-designed transformation plan that aligns with the company’s overall business strategy. By prioritizing the user experience, companies can improve the work experience for employees and enhance employee engagement and satisfaction.
Optimal strategies for retaining exceptional employees encompass a variety of tactics, such as implementing adaptable work schedules, fostering employee empowerment, and utilising digital technologies to create a supportive workplace ambiance. With the right transformation plan and strategies in place, companies can create a workplace that attracts and retains top talent, driving business success and growth.
| 2023-03-01T00:00:00 |
2023/03/01
|
https://www.employeeconnect.com/workplace-transformation-strategies/
|
[
{
"date": "2023/02/28",
"position": 83,
"query": "workplace AI adoption"
}
] |
AI Policies Digital Repository | AI Development Accelerator
|
AI Policies Digital Repository
|
https://www.bu.edu
|
[] |
Just as Microsoft's Win3... ... Those who fail to adopt may be left behind in the workplace. The race is not only for data but also trust. As Generative AI moves ...
|
AI Policies Digital Repository
With the help of students from the “Data, Society, and Ethics” class in the Faculty of Computing and Data Sciences, the BU AI Task Force collected and analyzed documents from across higher education, K-12 education, government, and industry. Browse the policies and explore common themes using our digital repository and topic models below.
| 2023-02-28T00:00:00 |
https://www.bu.edu/aida/resources/ai-policies/
|
[
{
"date": "2023/02/28",
"position": 86,
"query": "workplace AI adoption"
}
] |
|
Labor Supply: Inside the Tight Labor Market
|
Frank Hawkins Kenan Institute of Private Enterprise
|
https://kenaninstitute.unc.edu
|
[] |
The labor market is historically tight at the outset of 2023. There are two job openings for every unemployed person, the highest such ratio that has been ...
|
The labor market is historically tight at the outset of 2023. There are two job openings for every unemployed person, the highest such ratio that has been recorded in Bureau of Labor Statistics data.1 And the trend appears to be deepening: The number of job openings increased in December for the third consecutive month.2
There is significant debate as to what is driving this imbalance. One line of thought points to more transient factors, such as COVID-19 health concerns and household wealth accumulated during the pandemic. However, longer-term trends – such as an aging population, years of reduced immigration, a long-term decline in labor force participation among men and a surge in early retirements – are also likely culprits behind this constriction of the labor supply.
Given the role of these longer-term trends, it seems unlikely that this tight labor market will loosen quickly. Firms need workers now. Moreover, we have seen a dramatic transformation in what workers expect from their jobs – and when these needs are not met, workers are quitting in droves.
Below, we survey several of the factors that are essential to understanding the dynamics now at play in regards to the supply of workers; previously, we published a Kenan Insight providing similar analysis to the demand side of the labor market. As the Kenan Institute moves into its 2023 grand challenge, these are some of the trends we’ll unpack and monitor over the course of the year, as we seek to understand how employees and employers alike are navigating these conditions.
Demographics
The changing demographics of the United States are having a profound effect on the labor supply in the nation. The population is aging, with baby boomers reaching retirement age and those ages 65 and over expected to outnumber those ages 18 and under by 2034.3 This shift in the age distribution of the population is expected to continue to have a significant impact on the U.S. labor supply. As the proportion of older individuals increases, the fraction of people who are willing or able to work is likely to decrease. And while it is possible to increase the participation rate of older workers – it declined during COVID and has not recovered – it is unlikely to increase enough to fully counter the aging of the population. This demographic pattern is unlikely to be reversed in the near term. On average, there are 1.7 births per woman in the U.S., a rate that will lead to a shrinking population without a sharp rise in immigration levels.4
Health Factors
Another set of factors affecting the supply of workers involves trends that have taken away or limited the ability of some individuals to work. Long COVID refers to long-standing effects from COVID-19 that may include fatigue and brain fog; roughly 30% of those with the condition experience symptoms that impact their ability to work. As a result, long COVID may reduce the U.S. labor force by as much as a full percentage point.
Additionally, drug addiction, particularly opioid addiction, has reached crisis level in the U.S. over the last two decades, which has substantially affected labor force participation. Much of the growth in opioid addiction has been linked to doctor-prescribed opioids during a period when the medical establishment was underestimating the addictive nature of these prescriptions. Estimates indicate that individuals who received an opioid prescription were 3.7% less likely to be employed five years later, as compared with a similar individual being treated for the same diagnosis but who did not receive an opioid prescription.5
Immigration
Because of the COVID pandemic, as well as policies implemented by the Trump administration, the U.S. has witnessed a dramatic decline in international immigration. In 2021, about 245,000 people from outside of the country migrated to the U.S. – nearly a 50% decline from the previous year, and less than a quarter of the 1 million international migrants we had in 2016.6 Immigration to the United States does appear to be on the rebound, as the U.S. returned to those 2016 levels (and received just over a million immigrants) between July 2021 and July 2022.7 However, even with this uptick, we remain below the level of immigrants needed to sustain the dismal population forecasts from the census.8
The economic literature has generally found that immigrants help contribute to innovation.9 Studies have found that immigrants are more likely to start new businesses and to file patents, both of which can lead to greater economic growth. Additionally, immigrants tend to have diverse skills and backgrounds, which can bring new ideas and perspectives to the workforce. Research from UNC Kenan-Flagler Business School Professor Abhinav Gupta demonstrates that greater barriers to immigrant labor mobility – or the ability of workers to switch between firms – also results in a decrease in entrepreneurship and new firm formation.
An influx of immigrants is especially important given the aging U.S. population described above. 2021 marked the first year since the Great Recession that the U.S. birth rate has increased; even so, the total fertility rate remains well below replacement, or the number needed for population numbers to offset death rates.10 Immigration thus remains an essential economic tool for the U.S. to maintain a sufficiently large workforce.
Childcare
An increase in the number of women entering the labor force was a major factor in the changing demographics of the U.S. labor supply from the 1970s to 2000. Women are now more likely to pursue higher education and pursue a career, and account for more than half (50.7%) of the college-educated labor force.11 This has created new opportunities for women in traditionally male-dominated occupations – and also stimulated the U.S. economy. A 2017 report from S&P Global estimated that continued reductions in gender inequality (and subsequent increases in women’s labor force participation rate) could lead to as much as a 5%-10% increase in nominal U.S. GDP, as well as help offset the effects of an aging workforce.12
However, as the chart below illustrates, the prime age (25- to 54-year-old) female participation rate has stagnated over the last 20 years. A lack of access to childcare is likely to be one of the drivers of these trends and could even potentially reverse gains made by women in recent decades.13 One paper from UNC Kenan-Flagler Professor Elena Simintzi demonstrates that earlier access to childcare significantly increases employment and income growth among new mothers; a separate piece of research shows that industries with greater access to childcare have a smaller gender pay gap.14 Separate research from the Pew Research Center found that childcare was a factor for roughly half of those who quit their jobs in 202115, while a team based at Northeastern University documented significant issues in childcare access, especially for women of color and women in low-income households.16
Flexibility and Preferences
Lockdowns provided a multitude of workers with time off from work, which many used to reevaluate what they want from their jobs. At the same time, there is also a culture shift occurring as younger generations enter the workforce. Taken together, there has been a significant change in what employees want from their jobs. Employees want to be their authentic selves at work, and to feel that their work does not conflict with their personal lives. As the “great resignation” began in 2021, 57% of employees who quit that year reported feeling disrespected at work as a major reason behind their decision to leave.17 Employees are also increasingly demanding that their employers have a sense of purpose beyond just profit maximation.
With the rise of the gig economy, another major trend in worker preferences has been an increased demand for flexibility. Contract work and gig employees are increasing, challenging the one-size-fits-all standard in 9-to-5 work. A 2020 study by the ADP Research Institute conducted shortly before the pandemic found that the number of gig workers had increased 15% since 2010.18 The work-from-home revolution necessitated by the pandemic also showed employees that much of their work could be done away from a physical office or even asynchronously. Subsequently, more workers desire an option to work from home, work more flexible hours or set their own schedule.
Percent of private sector establishments with increased telework that expected the increase to continue after the COVID-19 pandemic ends, 2021 Source: U.S. Bureau of Labor Statistics
This has created issues for employers, who face difficulties sustaining workplace culture and monitoring their work-from-home employees. As a result, employers are increasingly resisting the work-from-home demands of their workers and require at least some degree of in-office presence. The question remains, however, if the tightness of the labor market will undercut employers’ ability to bring their workers back to the office.
For employees or those seeking employment, a greater menu of options is now on the table. The gig economy allows for highly flexible work – albeit work that often lacks the benefits that traditionally accompany employment, such as health insurance. The rise in working from home means that far more workers no longer need to live in the same city, state or even country as their employers. The overall distribution of workers’ preferences is thus shifting to accommodate these new possible forms of employment.
Conclusion
This grand challenge marks the Kenan Institute’s primary research initiative in 2023. To address it in a holistic and comprehensive manner, we’ll draw upon a variety of approaches over the course of the next year, including Kenan Insights and commentaries, video content, webinars and in-depth conversations with our experts and 2023 Distinguished Fellows. Our turn to the subject of labor markets reflects the topic’s near-universal importance – as well as the severity of the tumult that faces employees and employers alike – and we look forward to seeing where our exploration leads.
To learn more, visit https://kenaninstitute.unc.edu/tag/workforce-disrupted.
| 2023-02-28T00:00:00 |
https://kenaninstitute.unc.edu/kenan-insight/labor-supply-inside-the-tight-labor-market/
|
[
{
"date": "2023/02/28",
"position": 11,
"query": "AI labor market trends"
}
] |
|
Episode 47: 2023 Talent Trends – Skills-Based Hiring, ...
|
Episode 47: 2023 Talent Trends – Skills-Based Hiring, Employer Branding, and the Rise of AI in Making Layoff Decisions
|
https://www.changestate.io
|
[] |
#47: 2023 Talent Trends – Skills-Based Hiring, Employer Branding, and the Rise of AI in Making Layoff Decisions. The Changing State of Talent Acquisition.
|
Episode Description
Co-hosts Graham and Marty return for The Changing State of Talent Acquisition Season 3 debut. They share how the agency business has evolved in the past year and discuss key trends that will shape the talent acquisition landscape in 2023 and beyond.
Skills-based hiring, how automation can improve the hiring process, approaches to measuring the ROI of an employer brand, how strong employer brands create efficiencies in recruiting, the rising importance of retention in a tight labor market, and how organizations are utilizing AI to make layoff decisions
| 2023-02-28T00:00:00 |
2023/02/28
|
https://www.changestate.io/episode/episode-47-2023-talent-trends-skills-based-hiring-employer-branding-and-the-rise-of-ai-in-making-layoff-decisions/
|
[
{
"date": "2023/02/28",
"position": 30,
"query": "AI labor market trends"
}
] |
Artificial Intelligence: a positive impact that enriches our ...
|
Artificial Intelligence: a positive impact that enriches our lives and helps businesses grow
|
https://metyis.com
|
[] |
Workers may require new skills like data analysis or programming to remain competitive in the job market. Overall, the influence of AI on jobs is complex and ...
|
The non-artificial introduction
It may come as a surprise, but ChatGPT generated the previous introduction. Though currently one of the most debated topics, AI is no recent phenomenon and has been part of our lives for quite some time. From image recognition to self-driving cars and, most recently, language recognition with tools like ChatGPT and Bard, AI is undeniably engrained in the framework of our contemporary existence.
What is AI?
A.I. is an abbreviation for artificial intelligence, the most common definition of which refers to the ability of a machine to mimic tasks that, traditionally, only humans could do as they relied on intelligence to complete. A cornucopia of things falls into this criterion, including robots that move in a human-like manner, computers that can maintain a conversation, and surveillance cameras able to detect people.
Why is AI finally gaining momentum?
The recent surge in the potency and popularity of AI can be attributed to several facets. First, advances in hardware, including developing specialised hardware such as graphics processing units (GPUs), have significantly increased the speed and efficiency of AI algorithms.
Additionally, the internet and other digital technologies have made it possible to collect and store vast amounts of data, providing a rich source of information for training AI systems. Researchers have also developed new techniques and algorithms, such as deep learning and neural networks, that have greatly improved the accuracy and performance of AI systems. Cloud computing services now allow individuals and organisations to access powerful computing resources and AI tools without investing in expensive hardware.
Finally, there is currently a greater awareness and understanding of the potential of AI, which has led to increased investment in research and development by governments, academic institutions, and the private sector. There is no longer the trepidation of society being overthrown by robots or a necessity to follow Isaac Asimov’s “Three Laws of Robotics”.
Together, these factors have created a favourable environment for the development and adoption of AI, allowing it to gain strength and become increasingly integrated into a wide range of applications and industries.
Artificial Intelligence: the impact on our lives
AI is already having a significant impact on our lives, though some ways in which AI influences our lives are more evident than others.
Natural language processing
AI-powered language processing is being used to improve language translation, speech recognition, and chatbot interactions, enabling more efficient and realistic communication. ChatGPT and Bard are two prominent examples of this. Smaller applications, like chatbots in eCommerce websites, also rely on the evolution of this field.
Recommendations
AI-powered recommendation systems are being deployed to provide custom suggestions for products, services, and content based on our interests and past interactions.
Medical diagnosis
AI is being applied to analyse medical imagery and data to assist with diagnosing diseases and developing personalised treatment plans.
Autonomous vehicles
S elf-driving cars and other autonomous vehicles, which have the potential to reduce traffic accidents and significantly improve transportation efficiency, are currently in development.
These are only a few examples from a comprehensive list of the manner in which AI is gaining greater relevance in our daily lives. However, due to the recent buzz surrounding ChatGPT, a pivotal discussion concerning technology's potential impact on our careers is beginning to transpire.
Artificial Intelligence: the impact on our work
The substantial influence of AI on the job market is already evident and will likely continue into the future, potentially replacing various tasks or positions completely with automatised machines or tools, whilst others will be augmented to become faster or more efficient:
Automation of repetitive tasks
This is a primary area where job displacement will conceivably occur as AI is already being implemented to automate repetitive tasks in a variety of industries, from car manufacturing to logistics, leading to increased efficiency and cost savings.
AI as an auxiliary tool
AI is also used to augment tasks in various industries, such as healthcare and finance. It can be used, for example, to assist doctors with medical diagnosis and treatment planning.
Creation of new jobs
While AI-based systems may fully replace some positions due to automating specific tasks, new jobs will also appear in various fields, from the development of AI itself to the maintenance and surveillance of new tools and mechanisms.
Changes in job requirements
As AI integration becomes more prolific throughout industries, job requirements will feasibly change. Workers may require new skills like data analysis or programming to remain competitive in the job market.
Overall, the influence of AI on jobs is complex and multifaceted. Whilst it has the potential to improve efficiency and create new jobs, it can also lead to job displacement and changes in job requirements. As such, it is vital for individuals and organisations to understand the probable consequences of AI on their jobs and to prepare for changes ahead.
How to bring value to clients with AI
There are several ways in which companies can apply AI to increase the value brought to clients. One critical area is data analysis and insights. By examining more significant quantities of data, AI can help identify trends and provide better results to adjust to strategy and decision-making. This can be applied in detailed analyses of operations, customer behaviour, and industry trends. Similarly, employees can expend more time and focus on strategic activities by automating repetitive or time-consuming tasks.
AI-powered personalisation tools can also provide clients with a more tailored experience, improving customer satisfaction and loyalty. A profusion of applications has already been allocated to assist in this area, from custom brand content creation to SEO optimisation.
It is possible to bring significant value to clients by leveraging AI to improve data analysis and insights, automate processes, personalise customer experiences, manage risks, and drive innovation and product development. Only by keeping up with the latest AI technologies and best practices is it achievable to help clients attain their goals and stay competitive in an increasingly digital world.
Creativity and responsibility in the near future
Artificial intelligence’s transformative ability has been present in our lives for some time now, proliferating at the beginning of the 21st century with the rise of the internet, increased availability of more powerful personal computers, and the abundant amount of data available.
Learning-based mechanisms have evolved tremendously, and AI has become embedded in how we work, learn and interact with one another and the world around us. Its impact has acquired notoriety in some fields, resulting in outstanding achievements of AI systems outperforming humans in some domains, including reading comprehension, image recognition, and language understanding.
Many doubts still circulate about the capabilities of AI in the creative field, though examples of its use are becoming more common, as seen in the movie trailer created by IBM Watson's cognitive platform. However, even in this instance, it played more of an assistive and time-saving role than actually leading the creative process.
As AI enters the next chapter of its evolution, the world must address many challenges arising from its ubiquitous deployment, ensuring it is developed and used responsibly and ethically, with a focus on increasing humanity's well-being.
| 2023-02-28T00:00:00 |
https://metyis.com/impact/our-insights/artificial-intelligence-positive-impact
|
[
{
"date": "2023/02/28",
"position": 85,
"query": "AI labor market trends"
}
] |
|
Is ChatGPT coming for your job? - picnicerror.net
|
Is ChatGPT coming for your job?
|
https://picnicerror.net
|
[] |
The best minds in tech are falling prey to the "AI effect" -- watching an AI system perform well on a number of special cases and assuming it will generalize ...
|
I need your clothes, your boots and your employee ID. OpenAI’s Large Language Model (LLM) chatbot exploded onto the scene last November. In less than a week ChatGPT had over 4 million users and the Internet was awash with examples of prompts used and output from the chatbot. Some of the responses were so good that it didn’t take long for a wave of people claiming ChatGPT would make programmers, writers, support, and a whole host of other roles obsolete. A few months in and the doomsayers are still predicting widespread replacement of humans.
So how accurate are these claims of this particular AI offering taking our jobs?
Should we all head for the Job Centre?
So, will ChatGPT replace us all? There are certainly plenty speculating that it will be the death knell for careers as varied as software development to copywriting, even those saying it’s the beginning of the end for Google Search. Ignacio de Gregorio, speculated whether ChatGPT would kill Google in his Medium article: Can ChatGPT kill Google?.
François Chollet, who is a key member of Google’s own deep learning work, called out the “AI effect” where people were prematurely jumping on the bandwagon of LLMs replacing us all, much like how we’re supposed to be all riding around in self-driving cars right now.
The best minds in tech are falling prey to the "AI effect" -- watching an AI system perform well on a number of special cases and assuming it will generalize broadly, like a human would.
Last time it happened on this scale was for self-driving cars in 2015-2016. https://t.co/HvMKhzRFbB — François Chollet (@fchollet) February 8, 2023
This certainly seems like a fair comment. We’re often so quick to jump on new tech, as amazing as it may be, and think it’s going to have an immediate, widespread impact. But new tech often takes time for mainstream adoption. Apple certainly didn’t invent smartphones and weren’t the first to market by a long shot, but they timed their entry well and built a buzz around the iPhone that prompted a major shift in public perception. ChatGPT is certainly causing a huge buzz but the fact we haven’t seen commmercialised entries from the major players (Google, Amazon, Meta) suggests there’s plenty more to come in this space.
Language Models vs General purpose AI
Large Language Models (LLM) are specifically trained and optimised for language-based use cases, such as recognising and interpreting text. Because they are able to interpret meaning from an input (or prompt), they can often produce output that, on the surface at least, appears highly plausible and accurate for the specific subject of the prompt. However, dig a little deeper and there are plenty of examples where these fail on the detail. Consider the below Tweet example, where ChatGPT is repeatedly asked to do a task and repeatedly fails, despite “knowing” the correct answer:
With all the hype with ChatGPT, it's interesting to see where it can fail miserably, even when taught the right things, even when it can verbalize a correct line of reasoning or definition. Oh, and it lies, too.#ChatGPT #ChatGPTFail pic.twitter.com/8W6JSqM3kc — Daniel Rivera 🎮 (@danielrivera) March 1, 2023
General Purpose AI is what we think of when we picture a super-intelligent artificial life form in science fiction. They are able to learn, adapt and grow, using the sum of their experiences to handle any situation, much like humans. This is a much harder problem to solve than language. In any given situation there may be millions of variables which our brains will filter through our memories and experience, even our current emotional state, which is all considered in milliseconds and results in our decision. This is almost impossible to even conceive, never mind codify and build into an artificial brain.
The way this seems to be approached currently (to my very basic understanding) is to build specialised models for different scenarios and build other systems to combine the output and filter them through rules, much like one would go about building a multi-model recommendation system.
This doesn’t mean ChatGPT is bad. There are plenty of cases where LLMs are hugely useful, they just aren’t anywhere near the levels of general intelligence (most) humans can offer.
Use cases for ChatGPT now
Indeed, Microsoft are betting big on the utility of AI and LLMs, having been major investors in OpenAI for a number of years, and recently launching a GPT-3 integrated version of their own search engine, Bing.
ChatGPT as a tool to optimise workflows and increase productivity. Areas such as SEO where there can be a lot of text-based grunt-work, optimising descriptions and meta content, can be standardised and optimised. The human part becomes one of review and correction rather than creation.
Using GPT3 to rebuild 4,000 product descriptions. Mesmerising to watch.
Background: 6 year old site, which has been on two platforms, lots of mojibake, redundant html, random line breaks / <p> tags - multiple char encoding etc.
Beautiful to watch it get cleaned & standardised. pic.twitter.com/s5TZJk3Jqh — Lee Foot 🐍📈 (@LeeFootSEO) December 5, 2022
We’ve already seen this in action with Github Copilot. Code has stricter syntax than spoken or written language and much less variety which means it is arguably easier to codify. Copilot has been well received (despite some quality concerns) and yet there are still plenty of software engineering jobs out there. Things like drafting documents, creating product descriptions, generating realistic filler text for websites are just a few simple examples of applications of generative LLMs that can be time-savers for professionals.
Simon Wardley, creator of Wardley Maps has been very successful at analysing developments in technology and their adoption.
X : Does ChatGPT mean we're close to building thinking machines?
Me : A long way into the future. The whole Chinese room argument. Think of ChatGPT as more stochastic parrots rather than a thinking machine. It's "humanity" comes from our observation of the text. — Simon Wardley (@swardley) February 6, 2023
He was adamant that cloud computing would become the norm, then serverless and predicts the next major leap is in conversational programming, the art of speaking to machines in natural language to create software. Far from removing the human from the equation, this democratises the ability to program. This in itself may be a threat to some in the industry, but much like the rise of WYSIWYG editors and no-code app creation tools haven’t made every web designer or software engineer redundant, conversational programming won’t do this either. Subject matter expertise, experience, and knowing your business will still be hugely important, much as they are now. Knowing how to code isn’t valuable in itself, it’s knowing how to use that skill to solve the right problems, something people can tend to forget when there is something new and shiny on the scene.
The more we reduce friction from the input experience, the more people can focus on identifying and solving the important problems and create value.
The future
So when will we be looking at viable General Purpose AI that can challenge the human capability to adapt and apply expertise to new and different disciplines?
I think we’re decades away. Beyond the technical challenges of creating the necessary neural capabilities, there are a whole host of secondary challenges to solve before we’ll see widespread adoption. The ethical concerns around AI bias are well documented, not to mention questions around transparency, data protection, security and commercial sensitivity. While these shouldn’t hold back innovation to a point, they are real blockers to adoption in a lot of organisations. Remember even now when cloud has become widely accepted, there are still organisations succeeding on what we’d call legacy tech due to compliance, commercial or infosec concerns.
I think you massively overestimate rate of adoption. Many companies who won't use public cloud or proprietary tech, nvm hurdles around quality control, data protection, IP, etc. No doubt it'll be mind-blowing but I'd be amazed if we're not still years from mainstream adoption. — Graham 🏴 (@gshenanigan) December 26, 2022
It’s an exciting time, certainly. OpenAI have taken a huge step towards bringing real-world examples of AI into the mass consciousness and the proactive and open-minded out there have been given a super-charged tool to add to their utility belt. I don’t think it’s yet a differentiator, but can certainly optimise a number of use cases today.
Are you using ChatGPT or any of OpenAI’s other models for any use cases today? If so, what? What are your impressions of it and what impact has it had?
| 2023-02-28T00:00:00 |
2023/02/28
|
https://picnicerror.net/data/is-chatgpt-coming-for-your-job-2023-02-28/
|
[
{
"date": "2023/02/28",
"position": 63,
"query": "ChatGPT employment impact"
}
] |
Hiring engineers in the age of AI and ChatGPT
|
Hiring engineers in the age of AI and ChatGPT
|
https://www.byteboard.dev
|
[] |
AI-assistance tools will inevitably change the way engineers work; in some cases, they already have. ... impact their work will have on customers, users, ...
|
AI-assistance tools will inevitably change the way engineers work; in some cases, they already have. In the right hands, they can be used to create efficiencies and troubleshoot problems. But, an inexperienced engineer could just as easily use them to introduce serious flaws into a codebase, made even more dangerous by the fact that AI code often looks right at first glance.
At Byteboard, we’ve been thinking a lot about how tools like ChatGPT and Github Copilot impact the role of engineers, how we think they’ll change technical interviews, and how we can adapt our assessments to the mainstream usage of these tools.
How AI impacts the future of software engineering
AI-assisted tools are no doubt about to play a major role in the future of software engineering. In the short term, ChatGPT, as well as more specialized tools like Github Copilot, have demonstrated clear strengths as well as limitations. Its primary strength is the speed at which it can generate content. It can write dozens of reasonable-sounding sentences (or lines of code) in a matter of seconds, when the equivalent content might take a human minutes or hours to create.
But its primary limitation is its trustworthiness. Both in prose and in code, it can often produce correct answers, and just as often produce answers that only *appear* correct, but are significantly flawed upon inspection. In specialized fields like software engineering, it can take significant expertise to differentiate between the two. As the complexity of the problem increases, so does the frequency of ChatGPT’s mistakes, as well as the level of expertise it takes to recognize them.
Because of this, ChatGPT is currently most useful as a speed hack. Rather than starting with a blank slate, a software engineer can start by asking ChatGPT to solve their problem for them. It will then generate a significant amount of content far more quickly than the engineer could have written on their own. But if the problem includes any meaningful complexity, then in order to produce code that *works as intended* (or prose that is truly accurate), the software engineer has to take the AI-generated content and apply significant engineering expertise to correct ChatGPT’s (often well-hidden) flaws.
In other words, a poor software engineer can use ChatGPT to quickly produce software systems that appear well-built, but contain significant flaws. But a strong software engineer can use ChatGPT to quickly produce software systems that are well-built.
In the long term, we think AI-assistance tools will become more trustworthy, and more capable of producing correct work within contexts of increasing complexity. But it is unlikely that the fundamental ideas here will change; the more advanced the specialization, the longer it will take before AI tools can be trusted to produce correct work, and the more subject-matter expertise it will take for a human to be able to recognize and fix the AI-generated flaws.
How the role of “engineer” changes
Adoption of new tools and workflows always takes time (particularly so in specialized industries), so the coming AI-assistance revolution will happen over the course of the next few years, not the next few months or weeks. Only a minority of software engineers have integrated AI-assistance tools into their workflows, so most engineering work has continued exactly as it did before the introduction of these tools.
That being said, we do think there are three primary ways AI will change engineering for the organizations using it.
Engineers will be able to accomplish some aspects of their work much faster. Engineers will have more time to answer the “what” and “why” questions of software engineering, while the AI-assistance tools accelerate the answers to the “how” questions. This means that the role of the engineer shifts towards thinking about product and systems design, though they will still be required to retain their technical skills in order to fix the flaws of the AI-generated code.
Engineers will have more time to answer the “what” and “why” questions of software engineering, while the AI-assistance tools accelerate the answers to the “how” questions. This means that the role of the engineer shifts towards thinking about product and systems design, though they will still be required to retain their technical skills in order to fix the flaws of the AI-generated code. Engineers will spend more time on code review than on code generation. Since the AI-assistance tools generate copious amounts of code with hidden flaws, engineers who are making use of them will spend more of their time carefully reading the code that the AI generates, and less time writing code themselves. This means that attention-to-detail has become a very important skill, while sheer human productivity becomes less important.
Since the AI-assistance tools generate copious amounts of code with hidden flaws, engineers who are making use of them will spend more of their time carefully reading the code that the AI generates, and less time writing code themselves. This means that attention-to-detail has become a very important skill, while sheer human productivity becomes less important. Organizations will have to take more care to hire engineers with the right skills.Since AI-assistance tools can generate code that “looks correct” to the untrained eye, it will be all the more important that organizations hire engineers who can tell the difference between flawed code and correct code. Additionally, since the role of the engineer will shift towards product and systems design, organizations will need to hire engineers who can effectively analyze the product space and the organization’s goals. And finally, since the pace – and, ultimately, the reach – of engineering work will accelerate, it is of great importance that organizations select engineers who can be trusted to carefully consider the impact their work will have on customers, users, vulnerable populations, and the rest of the world.
How AI-assistance tools change assessments
The introduction of AI-assistance tools has introduced a new variable in hiring for software engineers. Until now, in order to assess a candidate’s technical ability, organizations have relied heavily on coding challenges: exercises in which a candidate is asked to write an isolated, complex algorithm in response to a clearly-defined prompt. We didn’t think those were great anyway—engineers don’t work in a vacuum, and no problem they’d see in their day-to-day work would have such clear requirements. But now, we have another reason not to like them: these problems are exactly the sort of tasks that ChatGPT is able to easily solve on its own. ChatGPT performs very well on tasks with strictly-defined prompts, clear boundaries, and singular solutions.
As such, we expect organizations that use questions like that to embark on serious anti-cheating measures, like only assessing candidates in in-person settings; blocking candidates’ access to the internet or their own IDEs; and requiring candidates to write their code using unfamiliar and restrictive mediums like pen-and-paper or whiteboards. These measures not only severely limit the candidate’s ability to showcase their talent by introducing stress and unfamiliarity and cutting them off from the tools they would use on the job; they also increase costs for the organization.
The other path forward is to introduce complexity into assessments. What makes real-world applications hard for ChatGPT is that nearly all real-world problems contain a particularly messy sort of complexity – the complexity that comes from context.
“Find the shortest palindrome in a given string” is easy for ChatGPT. “Given our existing codebase, revise our song recommendation algorithm to increase exploration and engagement for new users without upsetting power users too much” is hard for ChatGPT.
To us, the real issue with asking engineers to solve problems that are easy for ChatGPT is not that it makes it easy for engineers to “cheat” by using ChatGPT. The real issue is that being able to answer those sorts of questions is not what makes someone a good software engineer.
A good software engineer is someone who can perform real-world tasks, not someone who can write complex algorithms in isolation. ChatGPT is just accelerating our collective understanding of what was already true – algorithmic coding challenges aren’t really good assessments of the expertise and skills required to be a software engineer.
At Byteboard, we’re facing this new challenge by continuing to add complexity and ambiguity to the coding tasks for our SWE assessments, thinking through what skills are becoming more (or less) necessary in the AI-assisted age, and considering a variety of mechanisms to more deeply assess how well a candidate understands the goals and context of a question. We’re also looking into other anti-plagiarism tools, but our goal is not to simply become a cheating prevention service – it is to assess candidates fairly and effectively in a role where what competency means is rapidly changing.
We aim to design assessments that make it impossible to successfully “cheat” with AI tools, because performing well requires candidates to engage specialized skills in tasks with real-world complexity. Eventually, we expect AI assistance to become like Google – a resource that everyone is expected to use to do their job most effectively. Our tools are built with that future in mind.
| 2023-02-28T00:00:00 |
https://www.byteboard.dev/blog/hiring-engineers-in-the-age-of-ai-and-chatgpt
|
[
{
"date": "2023/02/28",
"position": 80,
"query": "ChatGPT employment impact"
}
] |
|
ChatGPT: 3 ways it will impact IT support
|
ChatGPT: 3 ways it will impact IT support
|
https://enterprisersproject.com
|
[
"Yishay Carmiel",
"February"
] |
In a field like IT, where troubleshooting is a big part of the job, the enhanced search and discovery that comes with ChatGPT can save time and effort, ...
|
ChatGPT is quickly becoming more than a fun novelty. It’s starting to play a role in real business use cases, taking on tasks such as writing emails, creating images for ads, and providing voice assistive technology.
Microsoft’s recent $10B investment in the company and plans to integrate ChatGPT into its Office Suite is just one example of how companies are staking their claim in generative AI.
Impressive as it may be, this technology is still in its infancy. It’s also trained on data from the open web, meaning any public site is fair game – accurate or not. Want to confirm the answer comes from a reliable source? You’ll have to find it yourself.
In a field like IT, where troubleshooting is a big part of the job, the enhanced search and discovery that comes with ChatGPT can save time and effort, especially for common, straightforward queries. But it's not the most reliable tool for more complex incident responses or potential security concerns.
Don’t take my word for it. When asked how it performs on matters of incident response, here’s what ChatGPT had to say:
“Incident response is a complex task that requires a combination of technical and non-technical skills…it’s important to note that while ChatGPT can assist with the discovery process by providing relevant information, it’s not able to replace the expertise and judgment of human operators, who need to make sense of the information provided and make decisions about how to respond to the incident.”
As this response suggests, ChatGPT will unlikely start taking over human IT jobs anytime soon.
[ Also read Artificial intelligence: 3 trends to watch in 2023. ]
So with realistic expectations in mind, how will a resource like ChatGPT impact IT support in the near term? Let’s look at the strengths of ChatGPT and what it can do now.
1. Speed to resolution
ChatGPT can certainly help users get answers faster. People are probably using it more than they even know.
For example, ChatGPT is a good first line of defense for queries, helping to filter them based on importance and urgency. A low-priority IT issue may lend itself to a conversation with a Chatbot that can provide step-by-step solutions to simple problems such as “How do I reboot my computer?” or “How do I perform a software update?” Not only does this help resolve common issues, but it frees up IT teams for more challenging projects.
2. Limiting the cognitive burden
IT staffs are notoriously overworked. Add an industry talent shortage, larger economic factors, and mass tech layoffs, and it can be a stressful environment to work in.
Technology like ChatGPT can alleviate some burdens by helping IT teams organize. ChatGPT may not always provide the correct or contextually relevant answers, but it can leave breadcrumbs. ChatGPT-powered features can help uncover enterprise knowledge more easily than searching through troves of data and documents, or it can simply generate an answer that sparks the idea for a solution. ChatGPT can break down bigger problems into more digestible next steps.
3. Enhancing communication
Skip to bottom of list More on artificial intelligence
From drafting emails to improving conversations between employees with varying language proficiencies, generative AI will significantly improve the art of conversation. The ability to overcome cultural nuances in the spirit of collaboration can lead to new ideas, creative solutions, and a better working environment.
Companies are more distributed than ever before, and tools like ChatGPT can go a long way in creating intelligible communication. Beyond clarifying language and cultural differences, its mission to create human-like responses can also help refine technical communications with non-technical staff members.
As it stands now, ChatGPT is not fail-proof. Its flaws are evident, and users should proceed with caution – especially those tasked with managing enterprise technology. But even with its shortcomings, ChatGPT is already significantly helping IT teams. As the technology advances, it will continue to provide value to burdened IT teams over the next year and beyond.
[ Want best practices for AI workloads? Get the eBook: Top considerations for building a production-ready AI/ML environment. ]
| 2023-02-28T00:00:00 |
https://enterprisersproject.com/article/2023/2/chatgpt-3-impact-it-support
|
[
{
"date": "2023/02/28",
"position": 95,
"query": "ChatGPT employment impact"
}
] |
|
A Union For Tech Workers
|
A Union For Tech Workers
|
https://www.theworkersunion.com
|
[] |
The Workers Union is a union for tech workers. How tech workers, software engineers and web developers can join a union to protect their rights.
|
Challenges Facing the Tech Sector
Despite the growth of the tech sector, there are still a number of challenges facing the industry.
The lack of digital skills among the UK’s workforce is also a major issue. A recent report by the UK Commission for Employment and Skills found that only 27% of people in the UK have the digital skills required for the jobs of the future.
The lack of investment in the tech sector is also a major issue. This has led to a shortage of talent, with tech companies finding it difficult to recruit.
Benefits of Joining a Union
There are a number of benefits to joining a union for tech workers. These may include access to legal advice, support and advice on pay and employment terms and conditions.
Unions can also provide a platform for tech workers to voice their concerns. This can help to ensure that tech workers are treated fairly and that their rights are respected.
| 2023-02-28T00:00:00 |
https://www.theworkersunion.com/who-can-join/tech-workers/
|
[
{
"date": "2023/02/28",
"position": 2,
"query": "AI labor union"
},
{
"date": "2023/02/28",
"position": 5,
"query": "artificial intelligence labor union"
}
] |
|
How to Put Generative AI to Work—Responsibly
|
How to Put Generative AI to Work—Responsibly
|
https://www.bcg.com
|
[
"Jeanne Kwong Bickford",
"Tad Roselund"
] |
AI ethics has been a concern to many since the beginning, but today a new level of risk can be unlocked with new AI tech if it is not applied responsibly.
|
Concerns about the potential risks of artificial intelligence have been discussed for years. But recent articles about generative AI tools like ChatGPT have set off a corporate firestorm in a matter of weeks. What’s changed?
Jeanne: The huge change is that tools like ChatGPT are democratizing AI. This represents a really fundamental shift in how these tools are used and the impact they can have. Before, AI was generally created by a highly skilled team of people who you hired to build proprietary models using large-scale computing power and huge data sets. Or it may have been something you bought from a very specialized vendor. AI felt more controlled and was applied more in reaction to a known challenge or opportunity. It was used for very specific, narrowly defined applications. Now, you have proactive AI—machine learning that can create original content. And the tools are available to everyone. For a CEO, this can be incredibly exciting. Generative AI has the potential to dramatically accelerate innovation and completely change work by eliminating many of the rote, tedious tasks people do every day.
But it can also be terrifying.
How so?
Jeanne: There are all the risks and misuses we’re already familiar with—bias, violation of privacy, misinformation, impersonation, and theft of intellectual property, to name just a few. But now more executives are becoming aware of the risks within their organization as employees experiment with generative AI. We’ve heard of people taking very confidential company information, uploading it into an external site like ChatGPT, and producing a PowerPoint deck. Somebody could upload notes of the conversation we’re having now into an open space and spit out an article before we’re finished. Or they could be relying on information an AI bot is convincingly presenting as fact that could lead them to make bad decisions or do harm.
More executives are becoming aware of the risks within their organization as employees experiment with generative AI.
Tad: I can be even sharper. Shadow AI—development that is happening around the organization that you may not know about—was always a challenge. But you generally didn’t worry about it happening in ten minutes. AI typically was built along a predictable path, similar in some ways to how software development works. CEOs hopefully knew about it because it was a serious investment.
Now all the formidable barriers to development have tumbled. You no longer need specialized talent. You no longer need proprietary data, computing power, and a complex interface. I’d argue, with these new publicly available tools, it’s likely no longer even possible to know or catalog everything that is going on with AI experimentation and development across your entire organization.
How are corporate leaders reacting?
Tad: Right now, executives are having their eyes opened. They’re seeing articles about what generative AI could possibly do and saying, “I need to learn much more.” So they’re setting up task forces to understand both the immense potential of AI and how the threats may apply to them. But I don’t think many understand the depth of this potential revolution, how fast it is moving, or the implications. To be honest, I’m not sure anyone does yet. There is a lot of rampant speculation that may be either too ambitious or not ambitious enough.
How well prepared are companies to mitigate these risks? Don’t most already have responsible AI (RAI) programs?
Jeanne: It varies. The small subset of companies for which AI is core to their offering—say an online marketplace that provides very personalized suggestions—is further along. Their executives understand AI’s power, since it’s central to their business. So they are hopefully well grounded in ethical AI. Then there’s everybody else. If they use AI at all, it’s for very specific use cases. So they’re less familiar with RAI—and the risks are much higher. In a recent survey we conducted with MIT Sloan Management Review, more than 80% of global respondents agreed RAI should be a top management priority. But only around half have actually put some program in place. And fewer than 20% said they have a fully implemented RAI program.
Tad: My guess is that even that 20% has done this only for their known AI. Those with a handle on all the AI underway inside their companies are probably fewer, especially as you define AI more broadly. We recently spoke with the head of enterprise risk for a client. He felt very comfortable that they had good RAI around their corporate-sponsored lighthouse AI development projects. What worries him is all the AI he doesn’t know about. With ChatGPT and generative AI, that kind of activity has just exploded.
Subscribe to our Artificial Intelligence E-Alert.
What’s required for a successful RAI program?
Jeanne: First off, you don’t need to start erecting new walls. The whole point of RAI is to harness the power of AI without causing harm or leading to unintended consequences. A lot of this is about using existing risk management tools and applying them to new technologies. It starts with being very clear on your basic ethical principles and defining guardrails. For instance, your company may have a “no fly zone” regarding using AI that falls outside core corporate values. Next, you need the right governance. Have a person at an executive level whose full-time job is to ensure that responsible AI principles are being applied as you deploy these capabilities. This person needs to be accountable, visible, and properly resourced—not somebody five levels down who’s doing this as a side gig. You also need lots of education so that people throughout your organization understand the guardrails and the reasons for them when using AI. Then you need the right tools and processes for the nitty-gritty of preventing risk, such as code libraries, testing, and quality control, that ensures your AI is working as intended.
The whole point of RAI is to harness the power of AI without causing harm or leading to unintended consequences.
How has generative AI changed the way companies should approach responsible AI?
Tad: Until recently, many companies probably focused heavily on AI governance. They counted on their risk and legal organizations to catch programs in development before they unveiled something to the world that might cause damage. With generative AI, that won’t be enough. You need responsible AI on steroids. RAI needs to be built into the culture and fabric of your organization, from the low-level staffer who just left a meeting with notes to summarize to the head of R&D who is trying to use AI to revolutionize product development. You also have to move fast. In this space, that’s now measured in weeks. If you haven’t already sent a message out to all your employees on the appropriate use of third-party generative AI services, for example, you’re very late and at risk. And if you don’t have any programs at all to ensure that AI is used responsibly, you’re really in trouble.
Aren’t governments working on regulations that will soon address all this?
Jeanne: Legislation is coming at the regional, national, and even city level. But rather than wait for legislation, companies should get ahead of it. Even if your company has good values and principles—but does nothing—you’re likely to encounter these ethical issues when you use AI. The greater attention paid to purpose and ESG also makes it hard to ignore responsible AI. And if industry can implement RAI and self-regulate in certain ways, it can take some pressure away from really draconian regulation.
Tad: Jeanne’s right. There’s a risk of massive backlash. If AI is rolled out irresponsibly and results in all these negative use cases—or just failures of quality control—legislatures will react. They could take this amazing tool for innovation and shut it down. That’s why it’s so important to get RAI right quickly. This is a time for industry to lead. Indeed, it has an ethical imperative to do so.
| 2023-02-24T00:00:00 |
2023/02/24
|
https://www.bcg.com/publications/2023/responsible-ai-crucial-to-avoid-new-ai-tech-risks
|
[
{
"date": "2023/02/28",
"position": 21,
"query": "AI labor union"
}
] |
AI and the CHIPS Act Could Reshape the Auto Supply Chain
|
AI and the CHIPS Act Could Reshape the Auto…
|
https://frostbrowntodd.com
|
[
"Blesousky Fbtlaw.Com",
"Authors"
] |
Union Avoidance / Campaigns · Wage & Hour · Workers' Compensation · Litigation ... labor on other, more productive tasks. Many OEMs and car manufacturers are ...
|
This article was originally published in Bloomberg Law’s Professional Perspectives.
It’s a familiar problem by now: a would-be buyer goes to a car lot or online vendor and can’t find the make or model they had in mind. Or if they do, the vehicle costs substantially more than it used to. In fact, car prices have increased more than 6% year-over-year, and more than 42% since 2020. The car shortage isn’t going away. However, both a new law and emerging artificial intelligence technology may offer some relief at common pressure points, or at least a slow-release valve that may avert future pinches.
Background
The “supply chain problem” refrain became nearly ubiquitous during the height of the pandemic, and its effects have lingered. Stay-at-home and “lockdown” orders governments around the globe stopped work in many places and slowed economic output. This was particularly true in China, upon which much of the rest of the world relies for crucial vehicle components, and where, until recently, Covid-19 restrictions were particularly severe. These sorts of orders around the globe contributed to a “perfect storm” of supply chain issues, which also included shifts in demand, labor shortages, and structural weaknesses.
This storm created a microchip shortage starting in 2020. Automakers and retailers cancelled orders early in the pandemic—recall the bleak economic picture in mid-2020—but, happily, those started to ramp back up by the end of the year to match a turnaround in consumer demand.
In the meantime, however, demand for additional technology to support the new work-from-home environment sapped the chip supply. This left fewer chips for automobiles—which are necessary for everything from
entertainment systems to power steering—at the same time car orders were rebounding. The ongoing trend towards electric vehicles, requiring even more chips for more functions, intensified the strain. On top of this, new coronavirus variants simultaneously hampered manufacturing, particularly in the more human-based parts of the supply chain in Southeast Asia, such as chip packaging and testing. Waning Covid-19 cases and protocols in the US did not ease the chip crunch because the US accounts for only about 10% of the world’s semiconductor production (compared to 75% in East Asia).
Although many automakers are doing their best to increase production and smooth out these supply chain issues, such as by investing more in expanded manufacturing operations, the shortage of chips, cars, and trucks has been stubbornly persistent.
The CHIPS & Science Act
In response to this unprecedented confluence of factors, various stakeholders and elected officials have been agitating for government intervention in this area since late 2021.
Over the summer, President Joe Biden signed into law the bipartisan CHIPS and Science Act, which was actually a conglomeration of three different bills. In addition to funding “Research and Development, Competition, and Innovation,” the CHIPS Act has been touted by its sponsors for the inclusion of significant economic incentives for chip makers to invest in domestic semiconductor manufacturing. For example, the CHIPS Act provides $52.7 billion for American semiconductor research, development, manufacturing, and workforce development, including $39 billion in manufacturing incentives.
Many have attributed recent multibillion-dollar investments in expanded microchip manufacturing from the likes of Micron, Qualcomm, and GlobalFoundries to the CHIPS Act’s incentives.
Experts are optimistic about the ability of the CHIPS Act to create jobs in the US, increase domestic microchip manufacturing, and strengthen supply chains in this area to forestall future shortages. But the new manufacturing plants will take time to build, and production will take even longer to ramp up. While the CHIPS Act certainly seems to represent a solid investment in the long-term stability of the microchip industry and a significant way to avoid future shortages, its effects are not likely to be immediate, particularly with respect to the current vehicle shortage and supply chain cramps in the United States.
Others in the automotive industry are advancing new methods that may also spur short-term help and long-term change in domestic auto supply chains, including the increased use of artificial intelligence.
Three Major Benefits of AI in Supply Chains
Improving Transparency
AI can monitor and bring together different systems, such as assembly line repair processes. When a line part breaks, everyone isn’t spending time trying to figure where and how to secure the part, and when it might arrive. These types of delays often have aggravated the large-scale supply chain issues caused by the pandemic circumstances discussed above.
When numerous stakeholders in a supply chain operate on integrated AI-based systems, all of them can get nearly real-time updates about the initial breakage, part needs, and the replacement’s location and status as soon as it leaves the originating facility. This permits everyone else in the chain to plan their operations around accurate information—including any possible delays—and allows them to focus employee labor on other, more productive tasks.
Many OEMs and car manufacturers are already implementing these systems and there is significant optimism that their further use could help ward off the supply chain backups witnessed over the last couple of years.
Quicker Solutions
When problems spring up, AI allows companies to craft quicker solutions. AI technology can minimize human error and thus improve decision-making by enhancing a process that might ordinarily rely on human-sent—and human-read—communications. Suppliers can also use AI to automatically provide quotes for parts and services based on optimal shipping routes and pre-calculated tariffs. In addition, AI systems that auto-route and send finished products can save time, create efficiencies, and thus ultimately smooth out supply chain bottlenecks.
Advanced AI systems also learn from errors, so if a supposedly “preferred” shipping route encounters failures, the system can learn from that, discount that route, and learn to use others instead. Many auto part suppliers are already implementing these types of AI programs, so when a line breaks, AI-based sourcing systems can reestablish it faster than human-led procedures.
Precise Predictions
AI can predict things that people might not see because its automated systems take human error out of the equation and are best programmed to review and analyze historical data as part of generating their recommendation—or just taking action autonomously. For instance, by synthesizing utilization and upkeep data, and by assigning weight to present information against the historical performance of systems, AI can assess—often accurately—the probability of a supply chain failure, or even anticipate a transportation hiccup before it happens (e.g., based on historical traffic data and real-time data from maps and traffic systems). By turning these calculations over to AI, companies can more accurately predict the risk of weather delays, set departure schedules, analyze shipping performance, and calculate optimal transport routes.
Given that an average passenger car contains more than 30,000 parts, it’s fairly obvious that human decision-making is limitedly scalable in this arena, but the potential for AI-based processes and attendant efficiencies is enormous. In other words, AI technology in the auto supply chain can eliminate human delay, error, and “instincts,” creating a solidly data-driven process that is faster and more accurate.
What’s Next?
Owing to these various advantages of AI and the technology’s growing implementation by suppliers and manufacturers, it’s easy to imagine how artificial intelligence can help smooth out supply chains and may help prevent another global shortage. But the benefits might not be realized unless and until AI systems are deployed widely across supply chains to fully integrate OEMs with the rest of the links in the chain and the final product rolling onto the dealership lot.
The improved efficiencies from these systems will become all the more vital if microchip manufacturing continues to shift back state-side under the CHIPS Act and supply chains evolve to meet that need. Where we go from here depends in large part on how fast the CHIPS Act is implemented (and how many companies take advantage of its incentives), as well as individual companies’ appetite and ability to implement and use AI technology on a large scale.
| 2023-02-28T00:00:00 |
2023/02/28
|
https://frostbrowntodd.com/ai-the-chips-act-could-reshape-the-auto-supply-chain/
|
[
{
"date": "2023/02/28",
"position": 67,
"query": "AI labor union"
}
] |
Integrating AI in Onboarding Employee Training
|
Integrating AI in Onboarding Employee Training
|
https://profiletree.com
|
[] |
AI streamlines onboarding by automating routine tasks, providing a consistent experience, and analysing data to improve procedures. It also ensures that we can ...
|
Integrating AI in Onboarding Employee Training Updated on: Updated by:
In today’s rapidly evolving workplace, integrating AI in onboarding employee processes can be a game-changer for organisations aiming to enhance the new hire experience. With AI’s ability to personalise training and streamline administrative tasks, we can create a more engaging and efficient onboarding journey. This not only kick-starts an employee’s journey on the right note but also fosters a supportive culture that values innovation and continuous learning. Utilising AI smartly in onboarding empowers employees, sparking their enthusiasm and accelerating their path to productivity.
AI in onboarding systems are revolutionising the way we orientate new staff, allowing us to tailor experiences to individual needs and learning styles. Our investment in AI in onboarding tools demonstrates a commitment to the growth and satisfaction of our employees. By providing them with a secure foundation from day one, we signal that we value and believe in their potential. Furthermore, the integration of AI in onboarding processes can significantly reduce the time HR staff spend on routine tasks, enabling them to focus on more strategic initiatives that benefit the entire organisation.
Understanding the Fundamentals of AI in Onboarding
In recent years, artificial intelligence has revolutionised the employee onboarding process, offering a personalised and engaging experience for new hires. By understanding the interaction between AI and HR, organisations can leverage technology to streamline their onboarding procedures.
AI in Onboarding and the Future of HR
Artificial Intelligence is set to redefine the landscape of HR. As we head further into the digital age, AI serves as a crucial component in automating tasks, reducing human error, and enhancing decision-making processes. Within HR, AI in onboarding is particularly useful, providing a level of previously unattainable personalisation. By analysing employee data, AI systems can tailor onboarding programmes to individual needs, ensuring that our new recruits are more engaged and productive from the outset.
AI also plays a significant role in data-driven insights, helping us predict employee outcomes and tailor the onboarding experience accordingly. This includes anything from identifying the skills a new hire might need to improve to suggesting personalised learning paths. As we integrate AI more deeply into our HR processes, it will continue to develop smarter, more predictive capabilities, making our recruitment and retention strategies more effective.
The Role of AI in Onboarding Employee Training
Leveraging AI in onboarding allows for a refined, efficient induction process. AI can assist in several ways, such as automatically scheduling induction sessions and curating orientation content. This use of technology streamlines administration, providing us with more time to focus on the human aspect of onboarding. Moreover, AI-enabled chatbots can offer immediate, personalised query resolution, making new hires feel supported throughout their onboarding journey.
Integrating advanced AI systems can significantly enhance learning experiences, too. Our new hires can benefit from AI-driven training modules that adapt to their pace of learning and pre-existing knowledge. Furthermore, by incorporating advanced analytics, we can glean insights into the effectiveness of our training modules and continuously refine our onboarding process. Through careful implementation of AI, we are not only able to create a more dynamic onboarding experience but can also set our employees up for long-term success within our company.
In realising the potential of AI within onboarding, “We can transform how we welcome and nurture talent in our organisation,” says ProfileTree’s Digital Strategist, Stephen McClelland. “By harnessing the power of AI, we can create a seamless and intuitive induction process that not only saves time but also elevates employee engagement.”
By embracing AI in onboarding strategies, our HR department becomes less about administrative work and more about people – engaging new team members, instilling company values, and building a strong work culture from day one.
Strategic Planning for Employee Training AI Integration
Incorporating AI into your employee onboarding process requires foresight and strategic planning. A clear framework guides successful integration, ensuring alignment with your business goals and compliance with ethical standards.
Setting Objectives for AI in Onboarding
When introducing AI in onboarding strategy, it’s crucial to define what success looks like. We must establish specific, measurable objectives that could include reducing onboarding time, increasing engagement, or providing personalised learning experiences. These goals should be tightly aligned with our overall business strategy, ensuring AI serves as a catalyst for both new employee success and organisational growth.
Developing an AI in Onboarding Roadmap
To translate our vision into action, we craft a detailed AI in onboarding roadmap. This outlines key milestones and timelines for the implementation phases, from AI selection to employee training. Our approach is methodical, starting with an audit of existing processes and then progressive AI technology integration. This ensures a seamless transition that respects both the capabilities of the AI and the needs of our employees.
Compliance and Ethical Considerations
Integrating AI demands a strong foundation in ethical and compliance frameworks. We’re attentive to data protection laws such as GDPR and vigilant about the ethical implications of AI interaction with employees. Our commitment is to uphold the highest privacy and fairness standards, ensuring that AI tools are free from bias and respect the rights of all involved. This careful scrutiny protects our company and fosters trust among our team members.
By adhering to these structured practices, we lay a robust foundation for the incorporation of AI into our onboarding processes, setting the stage for a dynamic, supportive, and efficient introduction of new employees to our organisation.
Employing AI in onboarding process can significantly enhance the efficiency of integrating new hires into our team. It streamlines tasks through automation, offering a more engaging experience with the aid of chatbots and virtual assistants, and leverages comprehensive knowledge bases and learning management systems to ensure that new employees have all the necessary tools at their disposal.
AI in Onboarding Systems
AI in onboarding systems plays a pivotal role in employee onboarding automation by simplifying administrative tasks and allowing HR professionals to focus on more strategic functions. These systems can handle a range of tasks, from document management to scheduling, with minimal human intervention. This level of automation ensures that new hires receive a consistent onboarding experience and quickly become productive members of our team.
Leveraging Chatbots and Virtual Assistants
Chatbots and virtual assistants are instrumental in providing real-time assistance to new employees. They can field common queries, guide them through various onboarding processes, and offer a personalised experience. By integrating these AI-powered resources into our onboarding strategy, we ensure new hires have support available whenever they need it, improving their engagement with the processes.
Knowledge Bases and Learning Management Systems
A robust knowledge base is a central resource where new employees can find information, training material, and answers to frequently asked questions. Paired with a sophisticated Learning Management System (LMS), these tools empower employees to learn at their own pace and track their progress. We advocate for an LMS that combines AI to tailor the learning experience to the individual needs of the new hires, making it an indispensable resource during onboarding.
By implementing these AI tools and resources, we can create a streamlined, effective, and engaging onboarding process, setting the stage for new hires to succeed in our company from day one.
Creating a Personalised Employee Training Onboarding Experience
In today’s fast-paced work environment, companies must provide an efficient and engaging onboarding process. By leveraging AI-driven personalisation techniques, businesses can create an onboarding experience that is tailored to the unique needs and learning styles of each employee, ensuring a positive impact on the overall employee experience.
AI-Driven Personalisation Techniques
AI has the capacity to transform the way we onboard our new team members. Personalised learning is central to this transformation, with AI’s ability to analyse large sets of data about an individual’s role, performance, and preferences. This analysis enables us to design personalised onboarding modules that not only cover the essentials of the role but also align with the employee’s personal development goals.
Profile Analysis: Initial profiling of the new hire’s skills and competencies to tailor their learning path. Adaptive Learning: Modules that adapt in complexity and content based on the employee’s progress. Feedback Loop: Regular collection of feedback to further personalise the learning experience.
For example, ProfileTree’s Digital Strategist – Stephen McClelland remarks, “The beauty of AI-driven onboarding lies in its ability to adapt in real-time, providing our new hires with a learning experience that evolves as they do.”
Incorporating Learning Styles into AI Employee Training
In order to fully integrate personalisation into AI training, recognising and incorporating varied learning styles is essential. Some employees may benefit from visual aids, while others might prefer auditory or kinesthetic learning methods. Our AI systems can identify these preferences and subsequently tailor the content format to suit each individual, making the learning process more effective and engaging.
Differentiated Content Delivery:
Visual: Incorporation of infographics, videos, and charts.
Auditory: Use of podcasts, narrated presentations, and discussion forums.
Kinesthetic: Interactive simulations and hands-on challenges.
By acknowledging the unique learning styles of every employee, our personalised AI-driven training programmes can improve employee experience and foster a stronger connection with the organisation right from the start.
Optimising the Onboarding Workflow with AI
Artificial Intelligence (AI) has revolutionised the way we approach employee onboarding, offering tools and strategies that enhance efficiency and streamline the process. By incorporating AI, we can significantly reduce manual workloads, create more engaging experiences for new hires, and foster better collaboration among teams.
AI in Simplifying Administrative Tasks
AI excels at automating routine tasks such as form filling, data input, and scheduling. Through the use of AI-powered platforms, we alleviate the burden of these administrative nuances, allowing human resources to focus on more strategic initiatives. For instance, AI can ensure all necessary documents are submitted and processed, help set up workstations, and offer virtual assistance to answer new hires’ queries about company policies or benefits, thus making their first days smoother and more enjoyable.
Utilising AI-powered tools boosts efficiency across the onboarding workflow. These tools can personalise onboarding materials based on the new hire’s role or learning pace, which accelerates assimilation and helps them feel valued from day one. By tailoring training programmes, we can address individuals’ unique needs effectively, fostering a more adaptive and successful onboarding experience.
Streamlining Collaboration and Communication
AI platforms can also enhance collaboration and communication between new employees and existing teams. Integrating chatbots and virtual assistants within the onboarding process provides an immediate point of contact for new hires to resolve queries and facilitates smoother information flows. Moreover, AI can connect new employees with their peers and relevant departments, laying the groundwork for a cohesive team environment from the outset.
By embodying these advances in AI technology within our onboarding processes, we ensure that we are not only keeping up with the digital evolution but are also providing an elevated user experience that reflects our dedication to innovative and effective workplace practices.
Building a Supportive Onboarding Culture
When integrating AI training into your employee onboarding process, it’s crucial to focus on nurturing a supportive culture that fosters connection and engagement. This culture not only supports new hires as they learn about their roles but also aligns them with the company culture from day one.
Promoting Connection and Engagement
Utilising AI in onboarding process can be transformative. It provides new employees with personalised support, ensuring they feel connected to their team and engaged in their work. For example, AI-driven platforms can offer customised learning paths that adapt to individual progress and preferences, encouraging active participation and swift competency in their new role.
Key Steps to Encourage Connection:
Implement AI chatbots: These can facilitate instant support and answers to common onboarding queries, helping new hires feel supported around the clock. Use AI to personalise learning: Align training materials with individual job requirements and learning styles to boost engagement from the outset.
Fostering a Sense of Community with AI
Building a community within the workplace is vital for a positive company culture. AI tools can assist in creating a sense of belonging by encouraging interaction between new hires and their colleagues. By automating routine tasks, AI allows team members to dedicate more time to personal interactions, mentoring, and welcoming new staff.
Strategies to Build Community:
Promote peer-to-peer learning: Pairing new employees with seasoned staff through AI matchmaking can help them integrate into the team dynamic.
Pairing new employees with seasoned staff through AI matchmaking can help them integrate into the team dynamic. Social integration features: AI-driven social tools can recommend internal networks and interest groups to join, fostering a sense of community.
In summary, AI training is not just about technology; it’s about enhancing the human aspects of onboarding. It’s an investment in creating a supportive, engaging, and community-driven workplace culture right from the start. Our approach at ProfileTree ensures that these strategies do not just live in theory but are backed by our extensive experience in the digital landscape.
Monitoring and Improving Performance Through AI Analytics
Embracing AI analytics is essential for continuous improvement in employee performance. These advanced systems provide insights and develop predictive models, enabling targeted talent development and timely adjustments to performance strategies.
Using Predictive Analytics for Talent Development
Predictive analytics in AI use data patterns to anticipate future performance issues and identify areas for development. We incorporate this by analysing an employee’s interaction with training materials and their performance metrics. For instance, if an individual’s engagement with certain training modules correlates with improved performance outcomes, our system can:
Highlight skills gaps and recommend personalised training paths. Adjust onboarding processes in real-time to better cater to individual learning paces.
By doing so, we are not only predicting future trends but actively shaping them for the betterment of our team and the services we provide.
Real-Time Performance Feedback and Adjustment
The provision of immediate feedback is another pivotal benefit of integrating AI analytics into employee training. Our AI systems can track an employee’s progress and:
Offer instant feedback on tasks, enhancing the learning experience.
Suggest corrective actions when deviations from expected performance are detected.
By utilising such analytics, the gap between performance review and action is significantly narrowed, fostering an environment of continuous improvement and development.
To illustrate our approach, ProfileTree’s Digital Strategist, Stephen McClelland quotes: “By harnessing the power of AI analytics, we’re not just tracking performance; we’re actively engaging in a dialogue with data – enabling a dynamic and responsive pathway for employee development.”
Fostering Continuous Development and Learning
Incorporating artificial intelligence into employee onboarding facilitates a dynamic environment for continuous development and meaningful learning experiences. Our approach empowers new hires to build upon their knowledge and skills from day one.
AI in Onboarding Courses and Modules
We design onboarding courses that are rich in content and tailored to the individual’s role within our organisation. Through a blend of traditional instructional materials and interactive AI tools, these modules ensure that each new team member receives a comprehensive grounding in their duties and in the ethos of our company. Each course is regularly updated to reflect current best practices and industry standards, guaranteeing that the knowledge imparted is both relevant and up-to-the-minute.
Simulations and Interactive AI Scenarios
Our simulations offer a hands-on approach to learning that conventional methods can’t match. By using AI-driven scenarios, we provide a safe space for employees to experiment with real-world situations, enhance their problem-solving abilities, and apply new knowledge and skills without the fear of real-world repercussions. This method not only reinforces learning outcomes but also boosts confidence and competence.
Continuous Learning and Knowledge Sharing
We believe the end of formal onboarding shouldn’t spell the end of learning. AI platforms within our company facilitate continuous learning by offering suggestions for further study, notifying staff of relevant updates, and promoting the circulation of new ideas and strategies. Encouraging knowledge sharing across departments strengthens our collective expertise, creates a culture of mutual improvement, and ultimately leads to innovation across all levels of our business.
Retention is paramount in any organisation, as high turnover not only disrupts the workflow but can also be quite costly. By integrating AI in onboarding, we can significantly improve employee retention, addressing both individual pain points and broader engagement strategies.
Using AI to Identify and Address Pain Points
AI has a remarkable ability to analyse large sets of employee feedback, identify common issues, and even predict future pain points. By leveraging AI-powered analytics, we can drill down into specific areas where employees may be struggling, be it a lack of clarity in role expectations or issues with team dynamics. For instance, AI-driven surveys can provide insights into the effectiveness of our onboarding process and highlight areas where new hires require more support. As Ciaran Connolly, ProfileTree Founder, puts it, “AI is not just about the technology; it’s about recognising that happy, engaged employees are the backbone of a thriving business.”
Monitor Sentiments: Use natural language processing to gauge employee satisfaction. Predictive Analytics: Identify employees at risk of turnover. Tailored Solutions: Provide customised onboarding experiences based on data-driven insights.
Engagement Campaigns and Retention Strategies
Incorporating AI into our engagement campaigns allows us to personalise the onboarding experience and maintain constant communication with our employees. Personalised learning paths and recognition programmes can be automated and refined over time, fostering a more connected and sustained work environment.
Personalised Learning : AI can suggest relevant courses and development pathways, tailored to each employee’s speed and style of learning.
: AI can suggest relevant courses and development pathways, tailored to each employee’s speed and style of learning. Recognition Programmes: Implementing systems that highlight and reward employees’ achievements leads to a more motivated team.
Through these targeted efforts, we seek to not only maintain but improve our retention rates, nurturing a long-term relationship with our workforce. By doing so, we ensure a mutual growth that benefits both our employees and our organisation.
Measuring Success and ROI of AI in Onboarding
Integrating AI in onboarding process necessitates an evaluation of its effectiveness and return on investment (ROI). By establishing robust assessment frameworks and leveraging data-driven insights, we can quantify the impact of AI on our HR practices.
Assessment and Feedback Loop
We initiate this process through an Assessment and Feedback Loop. Best practices suggest that one should assess both qualitative and quantitative measures. Regular performance reviews and assessments provide data on new hire proficiency, while surveys capture feedback on user experience. By maintaining a continuous feedback loop, we gain insights into the effectiveness of the AI training tools and can identify areas for improvement.
Qualitative Assessments : New employee satisfaction Comfort level with company processes Personal feedback on AI interactions
: Quantitative Metrics : Time taken to reach full productivity Reduction in onboarding time Errors and issues reported
:
Data-Driven Decision Making
Our commitment to Data-Driven Decision Making enables us to fine-tune our onboarding strategy. We gather and analyse data points such as engagement rates, learning curve efficiencies and early retention rates. This data informs us if our AI training is achieving its intended ROI, providing the business with clear insights into cost savings and improved employee performance benchmarks.
Key Performance Indicators (KPIs) : Retention rates post-onboarding Speed to competency Cost per onboarding session Employee feedback scores
:
As we harness these data-driven insights, we refine our AI in onboarding approaches, ensuring a cycle of continuous improvement and an evolving strategy that yields a tangible ROI for the business.
Frequently Asked Questions
The integration of AI into employee onboarding is reshaping how we introduce new hires to our team, offering a more efficient and personalised experience. Let’s tackle some of the key FAQs around this innovative approach.
| 2024-05-17T00:00:00 |
2024/05/17
|
https://profiletree.com/integrating-ai-in-onboarding-process/
|
[
{
"date": "2023/02/28",
"position": 36,
"query": "AI workers"
}
] |
Augmentir Expands its AI-based Connected Worker ...
|
Augmentir Expands its AI-based Connected Worker Platform with ChatGPT Foundational Technologies
|
https://www.augmentir.com
|
[
"Chris Kuntz"
] |
Augmentir, the provider of the world's only AI-based connected worker solution, announced today that it is expanding its AI platform to incorporate the ...
|
–
Augmentir
, the provider of the world’s only AI-based connected worker solution, announced today that it is expanding its AI platform to incorporate the foundational technologies underpinning ChatGPT. These new capabilities will improve the company’s existing True Productivity™ and True Proficiency™ offerings while accelerating the introduction of its True Engagement™ offering. These three unique, patented capabilities enable industrial companies to thrive in this era of workforce disruption while safeguarding customer data and maintaining privacy.
Augmentir’s platform has become the leading connected worker solution in the industrial sector, offering a wide range of out-of-the-box capabilities, connectors to business systems, and broad extensibility that enable manufacturers to digitize all their frontline operations, reducing onboarding time, and increasing workforce productivity. The platform’s AI-based tools, which include machine learning algorithms and natural language processing, help workers to access the right information at the right time and enable managers to optimize their workforce’s performance.
“We’re excited to be adding the foundational technologies of ChatGPT into our platform,” said Russ Fadel, CEO of Augmentir. “This will build on our experience of delivering AI-driven insights to industrial companies since 2019. We are uniquely positioned to bring these technologies to the market quickly, and in a manner that places our customers’ privacy and IP as a top priority. Adding the ability to communicate with the platform using natural language will make it even easier for our customers to access the information they need and engage with their colleagues. When combined with our existing AI-based features, this will further improve the overall efficiency and productivity of their operations, leading to better business outcomes.”
This expansion unlocks even greater potential for manufacturers looking to digitize and optimize their frontline operations. Augmentir’s purpose-built AI, which is focused on industrial operational insights, combined with Generative AI and other emerging foundation models, enhances the value that manufacturers can achieve with Augmentir, helping them uncover new opportunities to improve productivity and optimize their operations.
The new capabilities will be available to select Augmentir customers in the coming months, with a commercial release expected in late 2023.
To learn more about Augmentir, please visit
www.augmentir.com/ai
.
# # #
Augmentir is a leading provider of connected worker software solutions for industrial companies. The company’s AI-based platform speeds the onboarding of new workers, while dynamically closing skills gaps at the moment of need leading to improved efficiency, productivity, and safety. Companies in manufacturing, service, energy, and construction leverage Augmentir’s suite of tools to deliver more intelligent skills management, training, collaboration, and on the job support for today’s more dynamic, more flexible industrial workforce. For more information, visit
www.augmentir.com
.
| 2023-02-28T00:00:00 |
2023/02/28
|
https://www.augmentir.com/news/augmentir-expands-its-ai-based-connected-worker-platform-with-chatgpt-foundational-technologies
|
[
{
"date": "2023/02/28",
"position": 83,
"query": "AI workers"
}
] |
Indonesian YouTube Users Ranked Fourth Largest Globally in ...
|
Indonesian YouTube Users Ranked Fourth Largest Globally in Early 2023
|
https://databoks.katadata.co.id
|
[] |
... AI-generated translation of the original article. We strive for accuracy, but ... Wages in West Java, 2018-2023 Employment 08/07/2025, 7:57 WIB. splash ...
|
YouTube is one of the most popular social media platforms among internet users worldwide. Its popularity ranks it as the second most used social media platform globally, after Facebook.
According to a report by We Are Social and Hootsuite, there were 2.51 billion YouTube users worldwide in January 2023. However, the number of users of the video-sharing platform decreased by 1.9% compared to January 2022.
By country, India had the highest number of YouTube users globally at the beginning of this year, with a recorded 467 million users.
The United States ranked second with 246 million YouTube users, followed by Brazil in third place with a total of 142 million users.
Next, in fourth place is Indonesia with 139 million YouTube users. Following Indonesia are Mexico with 81.8 million users, and Japan with 78.4 million users.
Pakistan and Germany are also among the countries with the highest number of YouTube users worldwide, with 71.7 million and 70.9 million users respectively. Vietnam recorded 63 million YouTube users.
In tenth place is Turkey with 57.9 million YouTube users.
According to the We Are Social and Hootsuite report, the majority of YouTube users worldwide are men aged 25-34, accounting for 11.9%, while women in the same age group account for only 8.8%.
| 2023-02-28T00:00:00 |
https://databoks.katadata.co.id/en/media/statistics/e1446eb16142f58/indonesian-youtube-users-ranked-fourth-largest-globally-in-early-2023
|
[
{
"date": "2023/02/28",
"position": 57,
"query": "AI wages"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.