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
|
|---|---|---|---|---|---|---|---|---|---|
AI ethics staff layoffs across big tech bring safety concerns
|
AI ethics staff layoffs across big tech bring safety concerns
|
https://www.information-age.com
|
[
"Aaron Hurst",
"More Aaron Hurst"
] |
Layoffs at an array of big tech corporations affecting responsible AI personnel have raised concerns around long-term safety.
|
Companies including Amazon, Google, Meta, Microsoft and Twitter are resorting to including employees responsible for overseeing AI ethics in staff redundancies, to cut further costs, reported the Financial Times.
The amount of staff affected is said to be in the dozens, accounting for a small fraction of the tens of thousands of tech employees laid off by big tech firms in response to economic uncertainty and stakeholder dissatisfaction.
Microsoft demobilised its ethics and society lead team in January, with the company stating that the departments consisted of less than 10 members of staff, and that hundreds were still actively working in responsible AI, as well as growth of responsible AI operations being cited by chief responsible AI officer Natasha Crampton.
Meta disbanded its responsible innovation team back in September, which affected engineering and ethicist roles overseeing evaluation of civil rights and ethics on Facebook and Instagram. A Meta spokesperson declined to comment.
Meanwhile, the employees laid off at Twitter — amounting to over half of its workforce — included the ethical AI team responsible for fixing algorithm biases around race, on which the social media platform is yet to comment.
A source said to have inside knowledge of Alphabet’s operations said the redundancy of 12,000 Google employees included ethical AI oversight staff, but the search engine giant said it is unable to specify the proportion, though says that responsible AI remains a “top priority at the company”.
Ethics and safety concerns
With tools such as Microsoft-backed OpenAI‘s ChatGPT, Google’s Bard and Anthropic’s Claude bringing a new wave of generative AI innovation, the ethical nature and safety of the technology has been called into question in the wake of ethics staff layoffs.
Misinformation and bias are among the risks that the technology has been found to be susceptible to.
“It is shocking how many members of responsible AI are being let go at a time when arguably, you need more of those teams than ever,” Andrew Strait, associate director at the Ada Lovelace institute, and former ethics and policy researcher at Alphabet-owned DeepMind, told the FT.
Josh Simons, ex-Facebook AI ethics researcher and author of Algorithms for the People, commented: “Responsible AI teams are among the only internal bastions that big tech have to make sure that people and communities impacted by AI systems are in the minds of the engineers who build them,
“The speed with which they are being abolished leaves algorithms at the mercy of advertising imperatives, undermining the wellbeing of kids, vulnerable people and our democracy.”
There are also questions posed towards internal AI ethics teams regarding whether intervention into algorithms should also transparently involve public and regulatory stakeholders.
Related:
What is generative AI and its use cases? — Generative AI is the is a technological marvel destined to change the way we work, but what does it do and what are its use cases for CTOs?
ChatGPT vs GDPR – what AI chatbots mean for data privacy — While OpenAI’s ChatGPT is taking the large language model space by storm, there is much to consider when it comes to data privacy.
UK government announces AI white paper to guide innovation — The government announcement of a national white paper for AI innovation states an aim to “supercharge growth” across the UK.
| 2023-03-29T00:00:00 |
2023/03/29
|
https://www.information-age.com/ai-ethics-staff-layoffs-across-big-tech-bring-safety-concerns-123502579/
|
[
{
"date": "2023/03/29",
"position": 3,
"query": "artificial intelligence layoffs"
}
] |
Generative artificial intelligence (AI) in education
|
Generative artificial intelligence (AI) in education
|
https://www.gov.uk
|
[] |
This document sets out DfE 's position on the use of generative artificial intelligence ( AI ) – including educational technology tools powered by generative ...
|
We use some essential cookies to make this website work. We’d like to set additional cookies to understand how you use GOV.UK, remember your settings and improve government services. We also use cookies set by other sites to help us deliver content from their services.
You have accepted additional cookies. You can change your cookie settings at any time.
You have rejected additional cookies. You can change your cookie settings at any time.
| 2023-03-29T00:00:00 |
https://www.gov.uk/government/publications/generative-artificial-intelligence-in-education
|
[
{
"date": "2023/03/29",
"position": 10,
"query": "artificial intelligence education"
},
{
"date": "2023/03/29",
"position": 95,
"query": "artificial intelligence education"
},
{
"date": "2023/03/29",
"position": 96,
"query": "artificial intelligence education"
},
{
"date": "2023/03/29",
"position": 94,
"query": "artificial intelligence education"
}
] |
|
Introduction to Teaching with Artificial Intelligence (AI)
|
Introduction to Teaching with Artificial Intelligence (AI)
|
https://www.gse.upenn.edu
|
[] |
This program aims to engage professionals in exploring the benefits and challenges of using AI in education.
|
Overview
This program aims to engage professionals in exploring the benefits and challenges of using AI in education. Through the course, gain exposure to AI tools to support teaching and learning, as well as develop a greater capacity to perceive the nuances and dilemmas of this technology, pedagogy, and its effect on education.
You will engage in a series of live virtual workshops where you will design learning activities and experiences that you intend to implement in your own classroom.
| 2023-03-29T00:00:00 |
https://www.gse.upenn.edu/professional-development/introduction-teaching-artificial-intelligence-ai
|
[
{
"date": "2023/03/29",
"position": 14,
"query": "artificial intelligence education"
}
] |
|
Artificial Intelligence (AI) in Education - Instructional Tech Talk
|
Artificial Intelligence (AI) in Education: Revolutionizing the Learning Experience
|
https://instructionaltechtalk.com
|
[
"Jeff Herb"
] |
AI can analyze student work and provide feedback and grades more quickly and accurately than human teachers. This automation frees up time for teachers to focus ...
|
Artificial Intelligence (AI) is rapidly becoming an essential part of modern society. It is transforming the way we live, work, and communicate. In recent years, AI has also made its way into education, providing new ways to enhance learning and teaching.
AI is defined as the development of computer systems that can perform tasks that would typically require human intelligence. These systems can learn, reason, and adapt over time to provide better results. In education, AI is being used to enhance the learning experience, personalize education, and automate administrative tasks.
How is AI Implemented in the Classroom?
AI is implemented in the classroom in various ways. One of the most common ways is through the use of adaptive learning software. Adaptive learning software uses AI algorithms to analyze student performance data and provides personalized feedback and instruction to meet the needs of each student. This personalized approach can help improve student engagement, motivation, and achievement.
Another way AI is used in the classroom is through intelligent tutoring systems. These systems use AI to provide real-time feedback and guidance to students as they complete assignments or work on projects. They can identify common mistakes and provide explanations, tips, and resources to help students learn more effectively.
AI is also being used to automate administrative tasks, such as grading and assessment. AI can analyze student work and provide feedback and grades more quickly and accurately than human teachers. This automation frees up time for teachers to focus on more meaningful tasks, such as developing lesson plans and providing one-on-one support to students.
Research Supporting the Benefits of AI Implementation in Education
The use of AI in education has been the subject of numerous studies and research projects. The results of these studies have shown that AI can provide significant benefits to both students and teachers.
A study conducted by the Bill and Melinda Gates Foundation found that the use of adaptive learning software can improve student achievement by up to 30%. Another study by Carnegie Mellon University found that intelligent tutoring systems can improve student learning outcomes by up to 50%.
Research also suggests that AI can help reduce the achievement gap between students from different socio-economic backgrounds. A study by the University of Michigan found that students who used an adaptive learning system saw greater improvements in achievement than those who did not, regardless of their socio-economic status.
Examples of How AI Can be Used in Elementary, Middle, and High School
AI can be used in a variety of ways in elementary, middle, and high school. Here are some examples:
Elementary School:
AI-powered educational games that provide personalized feedback and instruction
Intelligent tutoring systems that help students learn basic math and reading skills
Adaptive learning software that adjusts instruction based on student performance data
Middle School:
AI-powered writing and grammar tools that provide feedback and suggestions for improvement
Intelligent tutoring systems that help students with complex math and science concepts
Adaptive learning software that helps students build study skills and time-management strategies
High School:
AI-powered college and career planning tools that provide personalized recommendations based on student interests and abilities
Intelligent tutoring systems that help students prepare for college entrance exams, such as the SAT and ACT
Adaptive learning software that helps students prepare for advanced placement (AP) exams and college-level coursework
Tips for Educators to Use AI in Education Effectively
Understand the capabilities and limitations of AI: Educators should have a clear understanding of what AI can and cannot do. This will help them choose the right AI tools and applications for their specific needs. Start small: Implementing AI in education can be overwhelming. Start small by using one or two AI-powered tools in the classroom and then gradually expand as needed. Involve students in the process: Encourage students to give feedback on the AI tools and applications being used in the classroom. This will help educators identify any issues and make improvements. Monitor and evaluate student progress: Regularly monitor student progress to ensure that the AI-powered tools and applications are effectively improving student learning outcomes. Provide training and support: Provide training and support to teachers on how to effectively use AI-powered tools and applications in the classroom. This will help them to integrate AI into their teaching practices more effectively. Ensure privacy and security: AI-powered tools and applications may collect and store sensitive student data. Ensure that appropriate privacy and security measures are in place to protect student data. Emphasize the importance of human interaction: AI should not replace human interaction in the classroom. Emphasize the importance of human interaction in the learning process and use AI to enhance rather than replace it. Keep up-to-date with new developments: AI technology is rapidly evolving. Educators should stay up-to-date with new developments and innovations to ensure that they are using the latest and most effective AI-powered tools and applications.
| 2023-03-29T00:00:00 |
2023/03/29
|
https://instructionaltechtalk.com/artificial-intelligence-ai-in-education-revolutionizing-the-learning-experience/
|
[
{
"date": "2023/03/29",
"position": 31,
"query": "artificial intelligence education"
}
] |
The Impact of AI Technology on High School Education
|
The Impact of AI Technology on High School Education
|
https://collegereadiness.uworld.com
|
[] |
AI as a valuable tool that can enhance learning in a number of ways, such as by providing differentiated instruction and efficient data analysis.
|
It's 2:00 am, and although you know you have to be at school in just a few hours, you're sitting up in bed, unable to sleep. Your stomach churns and your palms feel clammy as you open a new Google search on your phone. You wonder why you're doing this–it won't make you feel any better. Anxiously, you type:
Will AI in schools destroy education?
AI technology, or artificial intelligence, has been a hot topic in the education sector for the past several years but has become a central point of debate in recent months. If you read educational journals or peruse teacher groups on social media, you're guaranteed to see discussions about it.
The concept of using machines and algorithms to assist with teaching and learning has been met with mixed reactions.
Some high school educators are concerned about the negative impacts of AI on student learning and college readiness, such as the discouragement of critical thinking or the promotion of a one-size-fits-all approach to education.
Teachers also worry about students using AI in schools to cheat on tests or assignments with the increasing availability of AI-powered writing tools.
Many teachers fear that the integration of AI technology in education will replace the need for actual educators in the classroom.
Additionally, there is a gigantic elephant in the room that many educators worry about, but few are willing to openly discuss with their colleagues and see AI as a valuable tool that can enhance learning in a number of ways, such as by providing differentiated instruction and efficient data analysis. As AI technology continues to advance, it is important for educators to understand both the negative consequences and positive potential of using it. Doing so will help them make informed decisions about AI integration in the high school classroom.
How AI Technology is Used for High School Writing, Research, and Math
It’s common knowledge that artificial intelligence can do a lot of complex tasks–many people use it for writing, solving complicated math problems, and for quickly conducting research. Although AI tools do not always produce perfect results, they can be very useful for generating complete outlines, paragraphs, and full articles in a wide range of voices and lengths. These tools work because of AI’s machine learning algorithms and natural language processing. These scan the internet to “understand the text” and then form that information into output that best fits the writer’s request. Furthermore, AI-powered technology keeps evolving and developing in order to strengthen its ability to help users find relevant information on any given topic. The potential for AI to improve the efficiency and quality of written projects is endless.
Artificial intelligence doesn’t just help with written content, but also can create images and solve complex math problems. The capabilities of this technology go far beyond those of a basic calculator. The purpose of an optimization problem in calculus, for example, is to find the best solution among many possibilities. AI algorithms can do this in a matter of moments. Even difficult symbolic computations, such as differential equations and simplifying expressions, are no problem for AI technology. Additionally, AI can produce new mathematical models and recognize mathematical patterns simply by analyzing data. This opens the door to new mathematical insights and solutions.
For AP® Teachers, by AP® Teachers. How prepared are your AP students? We give them the skills and confidence to succeed.
Learn More
Concerns About AI Use in College Readiness
Many educators have raised concerns about the use of artificial intelligence when preparing students for college. This is by no means an exhaustive list, but it does include a few of the most common worries that are currently being discussed by educators.
Cheating on Tests and Assignments
As AI continues to improve, it’s understandable that high school educators would become increasingly concerned. After all, effectively teaching students greatly depends on accurate data from quizzes and assignments. If students use AI to cheat, that data will be inauthentic and unhelpful. ChatGPT and other AI-powered writing tools have made computer-generated essays appear to be written by humans, making it possible for students to pass off 100% AI-created papers as their own. Additionally, some students may use AI to answer test questions. This, of course, would further undermine the integrity of information the teacher could use to address learning misconceptions.
Loss of Creativity and Critical Thinking
Educators also worry that students who fully rely on AI tools may develop a lack of critical thinking skills and creativity. They believe that students who use AI too much will lose their ability to develop their own ideas and solutions. Rather than coming up with ready-made (computer-generated) answers to questions, teachers want their students to learn how to think critically and come up with their own ideas. Without these integral critical thinking skills, students may not develop the problem-solving skills necessary for success in their future careers.
Teachers Replaced by AI Technology
The thought of AI technology taking over the role of educators in the classroom has caused concern among many teachers. Although AI has made grading and providing feedback to students more efficient, it cannot replace the human element that teachers bring to education. Teachers offer emotional support, mentorship, and personalized learning experiences that artificial intelligence simply cannot replicate. Additionally, teachers are responsible for designing lessons, creating engaging activities, and promoting critical thinking skills. While AI technology may be able to assist in some aspects of education, it will never fully replace the role of a teacher. Take the example of offering students feedback on their assignments; teachers may use artificial intelligence to generate an initial critique of student work, but then they must look through that critique, add or remove anything that needs to be tweaked and track the student's progress. Without this step of human input, the teacher's feedback becomes as pointless as a fully AI-generated essay submission. Boost your AP® program effectiveness Attract, retain, and support AP® students with the right tools!
Learn More
Although some school districts have blocked access to ChatGPT on their internal networks, this has not prevented students from using the tool at home. With the rise of remote learning, high schoolers are increasingly turning to AI-powered platforms like ChatGPT to help with their studies and assignments. Despite being blocked by some school districts, AI continues to be a valuable resource for many teachers, too. Some liken the controversy behind AI technology to the fear many people once had about allowing students to use calculators in school. Artificial intelligence may have a greater potential for task completion than a typical calculator, but it is still just a tool (albeit one the public is currently learning how to use). Concerns over AI technology are certainly valid, but those concerns won't make it disappear. Rather, the concerns educators have over artificial intelligence highlight the importance of understanding how to balance the benefits of new technology with the need for responsible usage and monitoring.
Overcoming AI Technology Fears
People fear what they don't understand, so the best way to assuage any fear of AI in education is to familiarize educators with it. Administrators can prepare for AI integration in schools by learning about the technology, exploring its potential uses, and considering its ethical implications.
Teachers can
educate students on the proper use of AI technology by modeling ethical and responsible behavior, teaching digital citizenship, and demonstrating how AI can assist with their learning
encourage students to evaluate the accuracy of AI results, just as they are taught to evaluate the credibility of other informational resources
encourage critical thinking skills with AI by posing open-ended questions, asking students to analyze and evaluate information, and promoting diverse perspectives
facilitate group discussions on real-world problems, challenging their students to consider multiple solutions
In terms of cheating, educators can determine
if a student's submission is fully AI-generated by looking for patterns in writing style, content, and language usage
use plagiarism detection tools to check for originality or analyze the submission using AI models to verify if it was generated by a machine
ask students questions to gauge their understanding of the material and see if the answers match the content of the submission
By integrating AI technology as just one tool in a larger critical thinking process, educators can ensure students develop the skills necessary to make informed decisions in an increasingly technology-driven world.
Possibilities for AI in Education
For as many concerns as there are about artificial intelligence in education, there are just as many–if not more–potential benefits. The possibilities are greater than what can fit in just one blog post, but here are a few:
Personalized learning: AI can analyze student data and create individualized study plans.
AI can analyze student data and create individualized study plans. Automated grading and initial feedback: AI can grade assignments and provide initial feedback that teachers can build upon and track for student progress.
AI can grade assignments and provide initial feedback that teachers can build upon and track for student progress. Intelligent tutoring: AI can provide real-time, personalized tutoring. This can be especially helpful for closing learning gaps, or when a teacher is working with small groups of students while others work independently.
AI can provide real-time, personalized tutoring. This can be especially helpful for closing learning gaps, or when a teacher is working with small groups of students while others work independently. Interactive simulations: AI can provide engaging and educational learning experiences.
AI can provide engaging and educational learning experiences. Improved accessibility: AI can make education more accessible to students with disabilities by catering to learning accommodations.
Teachers can support students by personalizing interventions for different learning preferences with AI, and also by providing them with real-time feedback. Artificial intelligence can gamify lessons by incorporating interactive elements, such as adaptive learning and gamified exit tickets. Additionally, AI-powered virtual tutors can offer 24/7 support, allowing students to ask questions and receive immediate feedback at any time. To effectively use AI, educators should seek training on it and regularly assess its impact on student learning.
If You Can't Beat It, Join It: AI Technology and the Future of College Readiness
The concept of artificial intelligence can be a little scary for some people. It's hard not to worry as you sit beside your aunt over the holidays while she insists you're going to lose your career to computers. But AI technology is not going away, so there are only three ways to approach it: cross your fingers and hope it will faze out (it won't), lose sleep while worrying over it (a waste of time), or do what you do best, and when everyone else is fretting about how educators can possibly take on this new technology, look them in the eye and say, "Watch me."
Perhaps artificial intelligence in education will raise the baseline of expectations for student work and the passing level of assignments. Assignment submissions in a computer-generated content era will certainly need to demonstrate critical thinking skills and personal connections to learning. AI might be able to fake personal experience, but it will never be able to truly replicate it. In essence, AI's only job is to pick out pieces of other people's experiences and formulate them in a way it deems relevant. Just as most people can tell the difference between machine-made cookies from the snack aisle of the grocery store and a grandparent's homemade ones baked "with love," most people can tell the difference between a real human experience and an AI-generated one.
Still not sure? For this blog post, I asked ChatGPT a question that many educators have answered throughout their careers, then proceeded to answer it, myself. Both responses are included below:
In 100 words, write a first-hand experience about a time when, as an educator, you made a difference in a student's life:
"One of the most rewarding experiences as an educator is making a positive impact in a student's life. I recall a student who had struggled with self-confidence and motivation in the classroom. I took the time to build a rapport with this student and found ways to make the subject matter more engaging and relatable. Over time, I saw a noticeable improvement in the student's attitude and performance. The student's grades improved, and their confidence grew, leading to a newfound love for learning. Seeing the transformation in this student was a proud moment for me and reinforced the importance of the role educators play in shaping the lives of their students."
"During the 2019-2020 school year, I had a student who was convinced he couldn't write. After working with him for some time, it became clear to me he needed accommodations for dysgraphia. With the proper writing support and a ton of encouragement, this student began to gain confidence in his ability to write and created the most wonderful stories. Years later, his mom reached out to me, saying he'd just found out that a poem of his had been selected to be published in a book of poetry. She said he'd specifically wanted to thank me for believing in him because now he could believe in himself. That meant more to me than any test score could."
You tell me… Which response is real?
By the time students enter the workforce, understanding how to use artificial intelligence may very well be an expectation–and if we're being honest, part of helping students with college readiness is teaching them how to effectively and ethically use current technology, and that includes AI.
Key Takeaways
Artificial intelligence is an exciting tool with many wonderful possibilities for education. It’s unlikely that it will replace teachers or destroy the need for critical thinking skills, but it can certainly have a great impact on the educational sector as a whole.
| 2023-03-29T00:00:00 |
2023/03/29
|
https://collegereadiness.uworld.com/blog/impact-of-ai-technology-on-ap-education/
|
[
{
"date": "2023/03/29",
"position": 60,
"query": "artificial intelligence education"
}
] |
Goldman Sachs Report: ChatGPT Could Impact 300 Million Jobs
|
Goldman Sachs Report: ChatGPT Could Impact 300 Million Jobs
|
https://opendatascience.com
|
[
"Odsc Team"
] |
Goldman Sachs is claiming that up to 300 million full-time jobs can be affected by ChatGPT-like technology.
|
In the world of art, writing, and even the way we work, generative AI is taking the world by storm. But...
In the world of art, writing, and even the way we work, generative AI is taking the world by storm. But a report by investment giant, Goldman Sachs, is claiming that up to 300 million full-time jobs can be affected by ChatGPT-like technology. This “significant disruption” in an already uncertain labor market could have unexpected consequences and is likely one reason why researchers and technology experts have asked for a “pause” in AI development.
Written by Joseph Briggs and Devesh Kodnani, the report claims that around two-thirds of current jobs are currently exposed to AI automation in some form. This is taken from the data from their analysis of occupational tasks in both the United States and Europe which shows how automation could reduce labor needs. It says in part, “If generative AI delivers on its promised capabilities, the labor market could face significant disruption.”
What exactly that disruption means is still up in the air. According to the investment firm, up to 7% of jobs could be entirely replaced by AI with 63% being complemented by AI-powered tools. The remaining 30% would be unaffected. “Although the impact of AI on the labor market is likely to be significant, most jobs and industries are only partially exposed to automation and are thus more likely to be complemented rather than substituted by AI.”
There is a clear line between white-collar jobs, management positions, and blue-collar jobs. The latter of which is by far less likely to be affected by the advent and spread of artificial intelligence. Examples of positions that are most at risk by AI are legal workers, administrative staff, and elements of human resources. Another study, done by the University of Pennsylvania and New York University also estimated that the legal services industry could be the most likely impacted by AI such as ChatGPT.
Though some are holding out hope that AI won’t act as a great replacer, but instead will help humans work better. Microsoft CEO Satya Nadella said earlier this year that workers should see AI as a means of enhancing their abilities, not replacing them at the office. Already, AI-powered tools are being used and adapted in a variety of industries at a fast past. From software engineers, to artists, and even gaming, AI is already driving change in multiple industries. Though many positions could be affected, the report also sees the economic benefits of AI-powered tools.
Finally, the report states that “a major advancement with potentially large macroeconomic effects,” which would see an increase in the value of all worldwide goods and services by 7% in ten years. Whichever direction AI goes, it’s clear that there will be a significant impact in the labor market due to generative AI.
| 2023-03-29T00:00:00 |
2023/03/29
|
https://opendatascience.com/goldman-sachs-report-chatgpt-could-impact-300-million-jobs/
|
[
{
"date": "2023/03/29",
"position": 74,
"query": "ChatGPT employment impact"
},
{
"date": "2023/03/29",
"position": 73,
"query": "ChatGPT employment impact"
},
{
"date": "2023/03/29",
"position": 65,
"query": "ChatGPT employment impact"
},
{
"date": "2023/03/29",
"position": 65,
"query": "ChatGPT employment impact"
}
] |
Goldman Sachs: 300 million jobs could be affected by AI
|
Goldman Sachs: 300 million jobs could be affected by AI
|
https://www.cbsnews.com
|
[] |
According to Goldman Sachs, up to 300 million full-time jobs around the world could be affected by artificial intelligence.
|
Goldman Sachs: 300 million jobs could be affected by AI
Goldman Sachs: 300 million jobs could be affected by AI
Goldman Sachs: 300 million jobs could be affected by AI
According to Goldman Sachs, up to 300 million full-time jobs around the world could be affected by artificial intelligence.
The new wave of AI that has spawned platforms like ChatGPT could lead to jobs being automated in some way.
In a report Sunday, Goldman Sachs economists predicted 18% of work globally could be computerized. Economists at the investment bank believe the effects would be felt more deeply in advanced economies than emerging markets, with white-collar workers more at risk than manual laborers.
The report also showed that the most affected jobs would be administrative workers and lawyers. Less affected jobs are expected to be in physically demanding or outdoor occupations, such as construction and repair work.
However, the report noted that technological innovation that initially displaces workers has historically also created employment growth over the long haul.
| 2023-03-30T00:00:00 |
https://www.cbsnews.com/sacramento/news/goldman-sachs-300-million-jobs-could-be-affected-by-ai/
|
[
{
"date": "2023/03/30",
"position": 47,
"query": "artificial intelligence employment"
}
] |
|
AI Job Search Statistics: Key Insight
|
AI Job Search Statistics: Key Insight
|
https://careerimprovement.club
|
[
"Career Improvement"
] |
AI could help generate $14 trillion in additional revenue and 38 million new jobs by 2035 (Accenture). 59% of CEOs believe AI will lead to new job categories in ...
|
With the rise of artificial intelligence (AI), employers and job seekers are needing to navigate a new landscape of hiring tools and techniques. In this post, we'll explore key AI job Search Statistics and insights that can help job seekers make the most of the AI job search as well as understand the mindset of employees..
THE JOB LANDSCAPE IS EVOLVING
The world of work is changing, right in front of our very eyes the rule book is being re-written and re-defined. It seems that almost overnight whole swathes of established professionals are wondering what the future holds in store for them.
In a recent report published by OpenAI (the platform behind tools such as ChatGPT), they worringly highlighted over 70 professions which are 100% exposed to the advancement of AI.
That's right, 100% exposed and at risk, and these aren't low skilled jobs either, they include serious professions from Copywriters to Web Designers, Tax Auditors to Translators. It's a diverse and comprehensive list.
And consider this, we haven't even got out the starting blocks yet, what is the technology going to look like in 4, 5 or even 10 years time. It's no wonder that 1100 of the tech elite have called for a slow down on further development until we can understand the impact it's going to make. Included in the letter they ask the question:
Should we automate away all the jobs, including the fulfilling ones?
We are at the dawn of a crazy new era, and as we approach it let's read into the mindset of both the job seekers and employers.
AI JOB SEARCH STATISTICS & INSIGHT
By 2025, 50% of the job seekers will use AI-powered job search assistants (Gartner)
Job postings for AI-related positions have increased by 119% in the last three years (Glassdoor)
40% of job seekers believe AI will help them find a job more quickly (Kelly Services)
72% of job seekers believe AI could help them find a better matched job for their skills (Monster)
RECRUITMENT AI STATISTICS & INSIGHT
| 2023-03-30T00:00:00 |
https://careerimprovement.club/blog/ai-job-search-statistics
|
[
{
"date": "2023/03/30",
"position": 62,
"query": "artificial intelligence employment"
},
{
"date": "2023/03/30",
"position": 35,
"query": "artificial intelligence hiring"
}
] |
|
Harnessing AI in Public Employment Services to connect ...
|
Harnessing AI in Public Employment Services to connect people with jobs
|
https://www.oecd-events.org
|
[] |
This session will present several innovative cutting edge use cases of AI in public employment services, highlighting the opportunities AI represents.
|
Description
Digitalisation is a major opportunity for public - and private - employment services (PES) to reach out to large numbers of jobseekers, workers and employers with diverse needs, and provide effective and efficient services. This session will present several innovative cutting edge use cases of AI in public employment services, highlighting the opportunities AI represents and discussing some of its challenges.
| 2023-03-30T00:00:00 |
https://www.oecd-events.org/ai-wips-2023/session/8d837eb4-cbbc-ed11-9f73-6045bd8890e4/harnessing-ai-in-public-employment-services-to-connect-people-with-jobs
|
[
{
"date": "2023/03/30",
"position": 81,
"query": "artificial intelligence employment"
}
] |
|
The impact of emerging technologies on the job market in ...
|
The impact of emerging technologies on the job market in 2023
|
https://www.kyotutechnology.com
|
[] |
In recent years, automation and robotics have replaced human labor in many tasks and industries, leading to job displacement and unemployment. For example ...
|
The world we live in today is vastly different from what it was just a few years ago, thanks to the rapid advancement of technology. From artificial intelligence to blockchain, emerging technologies are transforming the way we live, work, and interact with one another. While these innovations offer exciting possibilities for our future, they also pose significant challenges to the job market. As we move forward into 2023 and beyond, it’s crucial to examine the impact of emerging technologies on the workforce. How will these new technologies change the types of jobs available? What skills will be in demand? And what challenges will workers face in adapting to these changes? In the following sections, we will explore these questions and more, providing insight into the impact of emerging technologies on the job market and what it means for all of us.
Overview of Emerging Technologies
Emerging technologies are defined as new or advanced technologies that have the potential to significantly impact industries and societies. In 2023 and beyond, some of the most impactful emerging technologies include artificial intelligence, automation, robotics, blockchain, and virtual reality.
Artificial intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence, such as visual perception, speech recognition, and decision-making. Companies such as Amazon, Google, and IBM are using AI to enhance customer experience, improve supply chain management, and develop new products and services. Automation involves the use of technology to automate repetitive and routine tasks, such as data entry and assembly line work. For example, Tesla uses automation in its manufacturing process to increase efficiency and reduce costs, while UPS employs automated drones for delivery. Robotics refers to the development of machines that can perform tasks that are typically done by humans, such as manufacturing and transportation. Companies such as Boston Dynamics and Intuitive Surgical are leading the way in robotics innovation. Blockchain is a decentralized digital ledger that enables secure and transparent transactions without the need for intermediaries. For example, JP Morgan, Walmart, and Maersk are leveraging blockchain to streamline their operations and improve trust. Virtual reality (VR) is an immersive computer-generated environment that simulates a physical presence. Companies such as Oculus, HTC, and Samsung are driving the development of VR technology and its applications.
These emerging technologies are changing the way work is done across industries. For example, AI and automation are being used to improve customer service and streamline supply chain operations. Robotics is being used in manufacturing and healthcare to increase efficiency and precision. Blockchain is being used in finance and logistics to improve transparency and security. VR is being used in education and entertainment to create immersive experiences. As these technologies continue to advance and become more widely adopted, they are expected to have a profound impact on the job market.
Positive Impact of Emerging Technologies on the Job Market
Emerging technologies are not only transforming the job market but also creating new opportunities in various fields. For instance, cybersecurity is a rapidly growing industry that is benefiting from emerging technologies like AI and machine learning. Companies such as IBM and McAfee are using AI to help identify cyber threats and develop security solutions.
In the field of data science, emerging technologies like big data analytics and machine learning are providing new ways to extract insights and drive business decisions. This has led to the creation of new job roles such as data scientists and data analysts. Companies such as Amazon, Google, and Microsoft are investing heavily in data science to improve their products and services.
In digital marketing, emerging technologies like augmented reality and virtual reality are helping businesses to create more immersive and engaging experiences for their customers. This has led to the creation of new job roles such as VR/AR developers and content creators. Companies like Coca-Cola and IKEA are already using AR and VR in their marketing campaigns to enhance customer engagement.
Moreover, emerging technologies are also helping businesses to streamline work processes and increase efficiency, leading to higher productivity and profitability. For example, Amazon’s use of robotics in their fulfillment centers has led to faster and more efficient order processing. This has resulted in a decrease in delivery times and an increase in customer satisfaction. In addition to creating new job opportunities in existing industries, emerging technologies are also creating entirely new industries and fields that did not exist even a few years ago. For example, the rise of virtual and augmented reality has given birth to a new industry focused on creating immersive experiences for consumers, ranging from gaming to virtual tourism. The development of blockchain technology has given rise to the field of cryptocurrency, which has grown into a multi-billion dollar industry with its own unique job opportunities in areas such as blockchain development, cryptocurrency trading, and cybersecurity. The emergence of the gig economy, fueled in part by mobile apps and online platforms, has also created new job opportunities for freelancers and independent contractors in fields such as ride-sharing, food delivery, and home-sharing. As emerging technologies continue to evolve, new industries and job opportunities are likely to emerge, creating a constantly changing job market that requires ongoing adaptation and reskilling. This however can lead to unemployment and job displacement.
Negative Impact of Emerging Technologies on the Job Market
The negative impact of emerging technologies on the job market cannot be ignored. In recent years, automation and robotics have replaced human labor in many tasks and industries, leading to job displacement and unemployment. For example, Amazon has implemented automated warehouses that utilize robots to move products and packages, which has led to a significant reduction in the number of human workers needed. Similarly, the adoption of self-driving trucks and cars is likely to have a profound impact on the job market for truck drivers and taxi drivers. Likewise in manufacturing, robotics are being used to replace workers on the assembly line. This has led to a decrease in manufacturing jobs and a shift towards more high-tech and specialized jobs.
Moreover, offshoring and outsourcing, while not necessarily new technologies, have been made much easier and more widespread due to the rise of digital communication technologies. Many companies have chosen to move their operations to other countries with cheaper labor, resulting in the loss of jobs in the home country. For example, the outsourcing of call center jobs to countries like India has been a significant cause of job displacement in the United States and other Western countries.
The skills needed to succeed in the job market are also changing rapidly, and many workers may struggle to adapt. As more jobs become automated, the demand for workers with technical and digital skills is increasing, leaving those without these skills at risk of job displacement. The rise of the gig economy and platform-based work also presents challenges for workers, as many are classified as independent contractors and are not entitled to the same benefits and protections as traditional employees.
To further disfranchise such workers, machine learning algorithms may result in algorithmic bias and discrimination against certain groups of workers, while the adoption of new technologies may also increase the risk of cyber attacks, requiring additional cybersecurity personnel but potentially resulting in job loss for workers in other areas. Lastly, there is a risk that increased automation and robotics may lead to social isolation and decreased job satisfaction.
As we can see, emerging technologies are creating both winners and losers. These examples illustrate the real and significant negative impacts of emerging technologies on the job market. As the pace of technological change continues to accelerate, it is important for individuals, businesses, and governments to invest in education and training programs that can help workers acquire the skills they need to succeed in a rapidly changing job market.
Potential Solutions to Mitigate Negative Impacts
While emerging technologies are transforming the job market and leading to job displacement in certain industries, there are also potential solutions to mitigate their negative impacts. Companies and governments are starting to take action to support workers who are most affected by these changes.
For instance, IBM has launched a program called P-TECH that offers free education and training in fields such as cybersecurity, cloud computing, and data science. Similarly, Amazon has launched a $700 million initiative to retrain 100,000 workers for more in-demand jobs within the company. Microsoft has announced a $20 million initiative to provide AI training to workers who have lost their jobs due to automation.
On a larger scale, the European Union has launched a fund to support the retraining of workers who have lost their jobs due to automation. They have also established a European Globalisation Adjustment Fund to help workers who have lost their jobs due to globalization or emerging technologies.
In addition, some governments are exploring the idea of Universal Basic Income (UBI) as a way to support workers who have lost their jobs. For example, the Finnish government has launched a pilot program to test UBI in certain regions.
Companies like Microsoft have also partnered with LinkedIn to offer free online courses to help workers develop new skills and transition to new careers.
These initiatives are just the beginning of what can be done to mitigate the negative impacts of emerging technologies on the job market. Continued investment in reskilling and upskilling programs, worker retraining, and UBI could help ensure that workers are not left behind in the rapidly changing job market.
ESTIMATE MY PROJECT
Conclusion
The impact of emerging technologies on the job market in 2023 and beyond is a complex issue that requires careful consideration and planning. While these technologies have the potential to create new job opportunities and increase efficiency and productivity, they can also lead to job displacement and other negative impacts, such as algorithmic bias and social isolation.
However, there is hope for the future. By embracing emerging technologies and investing in reskilling and upskilling programs, individuals, businesses, and governments can prepare for the changes that are coming and ensure that workers are equipped with the skills they need to succeed in the job market. Companies can also adopt responsible automation practices that prioritize worker well-being and balance the benefits of technology with the needs of employees.
Furthermore, emerging technologies are creating entirely new industries and fields that did not exist even a few years ago. As these fields continue to develop, there will be new opportunities for workers to apply their skills and knowledge in exciting and innovative ways.
| 2023-03-29T00:00:00 |
2023/03/29
|
https://www.kyotutechnology.com/the-impact-of-emerging-technologies-on-the-job-market-in-2023/
|
[
{
"date": "2023/03/30",
"position": 19,
"query": "automation job displacement"
}
] |
The AI Workforce Revolution: The Augmented Future
|
The AI Workforce Revolution: The Augmented Future
|
https://www.thedigitalspeaker.com
|
[
"Mar"
] |
As AI and automation advance, many jobs may become obsolete or undergo significant transformations. This can be a source of anxiety for workers and can lead to ...
|
👋 Hi, I am Mark. I am a strategic futurist and innovation keynote speaker. I advise governments and enterprises on emerging technologies such as AI or the metaverse. My subscribers receive a free weekly newsletter on cutting-edge technology.
The world of work is constantly evolving, and as technology advances at an unprecedented pace, it is becoming increasingly clear that the workforce of tomorrow will look vastly different from the one we know today. A new term has emerged in this brave new world— the augmented workforce. This term refers to integrating advanced technologies into the traditional workplace to enhance the capabilities of human workers.
But what exactly does this mean for the future of work? How will it impact how we work, and what are the potential benefits and challenges of this emerging trend? This is a topic close to my heart as a futurist, so let's take a closer look at the exciting possibilities and potential challenges of this emerging trend, and discover how your organisation can leverage the augmented workforce of tomorrow to achieve greater efficiency, productivity, and success.
Analysis of the Augmented Workforce
As businesses increasingly turn to advanced technologies such as generative AI and automation to drive productivity and efficiency, the concept of an augmented workforce is gaining momentum. As opposed to traditional work approaches that rely solely on human labour, an augmented workforce integrates advanced technologies into the workplace to enhance the capabilities of human workers. This emerging trend has the potential to transform the way we work. It is essential to understand how this trend will affect your business by examining its key characteristics and potential implications.
In this analysis of the augmented workforce, we will explore its definition, key features, and the challenges and opportunities associated with this new approach to work. Get ready to discover how the augmented workforce could revolutionise the way we work and propel organisations to greater success.
Defining the Augmented Workforce
The term "augmented workforce" refers to a new approach to work that leverages advanced technologies such as artificial intelligence (AI), machine learning, and automation to enhance the capabilities of human workers. This integration of technology and human labour—also known as "bionic organisation"—transforms how businesses operate and creates new opportunities for organisations to streamline processes, reduce costs, and drive growth.
The augmented workforce is all about integrating humans and machines to work together. Human workers can perform their jobs more efficiently and effectively by leveraging advanced technologies, while machines can automate routine tasks and provide valuable data to support decision-making. This integration allows workers to focus on tasks that require human ingenuity, such as complex problem-solving and creativity, while the machines handle the more routine and repetitive tasks.
The augmented workforce differs from traditional approaches to work in several key ways. First and foremost, it represents a shift from a labour-centric model to a more technology-focused approach that leverages advanced technologies to enhance the capabilities of human workers. Organisations can streamline processes, reduce costs, and boost productivity by integrating machines and automation into their workplace.
This new paradigm emphasises continuous learning and development, while traditional approaches to work focus on specific job skills. With the rapid pace of technological change, it is essential for workers to continually develop new skills and knowledge to remain relevant in the workforce.
According to a report by the World Economic Forum, upskilling and reskilling workers will be critical to the success of the augmented workforce.
While there are concerns about the potential displacement of human workers by automation, the augmented workforce seeks to augment human labour with advanced technologies to create a more efficient and effective workforce. Automating routine tasks allows humans to focus on tasks requiring unique skills and expertise.
Moreover, the augmented workforce is not limited to any specific industry or sector. From manufacturing and logistics to healthcare and finance, organisations across a wide range of industries are leveraging advanced technologies to enhance the capabilities of their workforce and drive innovation.
The concept of an augmented workforce has gained significant attention among business leaders and industry experts, and many have shared their insights and opinions on this emerging trend. Some experts— including David De Cremer, professor at NUS Business School, founder of the Centre on AI Technology for Humankind, and author of several books on leadership and management, and Garry Kasparov, former world chess champion, is now a human rights activist, speaker, and author focused on artificial intelligence and human-machine collaboration— believe that the augmented workforce has the potential to revolutionise the way we work, creating new opportunities for businesses to streamline operations, increase productivity, and drive innovation. According to a 2022 report by Deloitte, integrating advanced technologies into the workplace can help businesses achieve more productivity than what they currently gain from traditional automation approaches.
However, other experts from the U.S. Government Accountability Office have raised concerns about the potential impact of the augmented workforce on human workers. There are worries that automation could lead to the displacement of workers in certain industries while also creating new skill requirements for workers in other areas. In a 2022 report by the World Economic Forum, it was predicted that the adoption of automation and artificial intelligence could result in the displacement of up to 85 million jobs by 2025.
Although there are concerns about how to manage, what many experts consider a workforce of the future, most agree that businesses can gain significant advantages from integrating technology into their work processes. By leveraging advanced technologies to enhance the capabilities of human workers, businesses can create a more flexible, efficient, and effective workforce that is better equipped to tackle the challenges affecting us around the world.
While the augmented workforce is still in its early stages of development, it is clear that it has the potential to transform the way we work and create new opportunities for businesses and workers alike. As technology continues to evolve, it will be essential for organisations to embrace this emerging trend and take advantage of the opportunities it presents.
Employee Perspectives on AI and the Augmented Workforce
Integrating artificial intelligence and automation into the workforce has become increasingly prevalent, and employees have varying perspectives on the augmented workforce. While some workers view adopting advanced technologies as a potential threat to their job security, others see it as an opportunity to enhance their skills and job satisfaction.
According to a 2021 survey conducted by ABBYY Survey, 52% of workers feel that AI and automation will positively impact their work. This indicates a growing acceptance and optimism among employees regarding the augmented workforce.
New research from 2022 by the Massachusetts Institute of Technology (MIT) also reveals that workers who can collaborate effectively with AI and automation tools are more likely to report high levels of job satisfaction and engagement. This suggests that the integration of advanced technologies into the workforce has the potential to improve employee well-being and job performance, as well as overall business outcomes.
A new concept that has been proposed in the discussion of augmented workforces is "human-in-the-loop" AI. This refers to AI systems that require human input and oversight to function effectively. Rather than replacing human workers, these systems are designed to work in collaboration with them, augmenting their abilities and decision-making processes. This approach has gained popularity as a way to address concerns about job displacement and maximise the benefits of AI and automation while minimising potential risks.
In the long run, however, I believe that the human-in-the-loop is only temporary, as more organisations will transition to fully automated organisations, which will minimise the number of employees required to do the work.
In recent discussions about the augmented workforce, building trust between workers and AI systems has been highlighted as an important area of focus. As AI and automation become more integrated into the workforce, workers must trust that these systems are reliable and that their decisions are transparent and explainable. This requires a focus on ethical AI development and a commitment to transparency and accountability in deploying AI systems. Above all, it requires employees to understand AI and other emerging technologies well.
In addition, discussions around the augmented workforce are increasingly centring on the role of governments and policymakers in shaping the future of work. As AI and automation transform the workforce, policymakers grapple with issues such as job displacement, income inequality, and the need for upskilling and reskilling programs. There is a growing recognition of the need for collaborative efforts between governments, businesses, and workers to ensure that the benefits of the augmented workforce are shared equitably and that workers are prepared for the changing nature of work.
How Generative AI will Shape the Augmented Workforce of the Future
Recent developments in Generative AI have the potential to significantly influence the augmented workforce. Using advanced AI models such as GPT-4, companies can generate automated content that saves time and increases productivity. This could lead to new possibilities for content creation, copywriting, customer service and even healthcare, to name a few industries. With the right approach, Generative AI has the potential to augment human skills and create a more efficient and productive workforce. This technology can transform how we approach work and unlock new possibilities for businesses to innovate and grow.
Here are a few examples of how generative AI is already being used to augment the workforce:
Content generation: Large Language Models such as GPT-4 or Bard can be used to automate content creation for articles and social media posts. This can save content creators significant time and resources, allowing them to focus on other tasks. Chatbots and customer service: Generative AI is used to create intelligent chatbots and virtual assistants that can interact with customers and answer common questions. This can reduce the time it takes customers to receive answers and make them feel more satisfied with their transactions. Design and creativity: Generative AI is being used to generate designs for logos, websites, and other creative projects. Designers use brainstorming sessions to generate new ideas and explore different possibilities. Data analysis and decision-making: Generative AI is used to analyse large datasets and generate insights to help businesses make more informed decisions. Analysing data in a way that allows for faster decision-making can reduce both the time and resources needed.
These are just a few examples, and we can expect to see many more applications of generative AI in the future as the technology continues to evolve.
The Impact of AI on the Most Relevant Jobs and Industries
The impact of AI on jobs and industries is a topic that has received significant attention in recent years, and the conversation continues to evolve as new research and data become available. While there is no doubt that AI and automation will have a profound impact on the workforce, the specific nature and extent of this impact remain a topic of debate and discussion.
The benefits of artificial intelligence are expected to be particularly apparent in situations involving many routines and repetitive tasks. According to a 2017 report from McKinsey—the most recent report on this matter—approximately 50% of all work activities could be automated using existing technology. This is likely to significantly impact jobs that involve predictable, routine tasks, such as data entry, customer service, and assembly line work. However, the report also notes that the impact of automation is likely to be uneven across industries and job types and that there will be significant variation in the pace and scale of automation across different regions. In 2019, the Brookings Institution researched this issue, concluding that implementing AI should consider geographical factors to avoid exacerbating existing imbalances.
The potential for AI to transform industries and local labour markets is both exciting and daunting, and a coordinated effort is needed to mitigate potential negative impacts. However, there are huge differences across the world and between developed and developing countries in how AI is applied and used. The report also suggests that by learning from past experiences and committing to helping communities and workers adjust to change, we can create a future where AI benefits all communities.
Another point of discussion about the impact of AI on jobs and industries is the potential for new job creation. While it is true that some jobs are likely to be displaced by automation, experts also suggest that AI will create new job opportunities in areas such as data analysis, machine learning, and robotics. In fact, a recent report released in 2023 from the World Economic Forum predicts that AI will create 97 million new jobs globally by 2025.
There is also recognition that the impact of AI on the workforce is likely to be uneven across different regions and industries. For example, while automation may significantly impact manufacturing jobs in developed countries, it may have a more limited impact in developing countries where labour costs are lower. Similarly, while AI will likely transform some industries, it may have a more limited impact on others.
However, the impact of AI on jobs is not the only factor to consider. AI is also expected to significantly impact industries and business models. For example, AI is already transforming the healthcare industry, potentially improving patient outcomes, increasing efficiency, and reducing costs. Similarly, AI is expected to play an increasingly important role in the transportation industry, improving safety and reducing traffic congestion.
It is also important to consider that the impact of AI on the workforce is not just a matter of jobs being replaced or created but also of how work is organised and structured. For example, AI may lead to changes in how work is done, with a greater emphasis on remote work, flexible hours, and project-based work. This may require new skills and working methods, and businesses and workers must adapt accordingly.
The impact of AI on jobs and industries is a complex and multifaceted topic that requires careful consideration and planning. AI will likely bring significant benefits and opportunities, but it will also likely have significant implications for the workforce and the broader economy. As such, businesses, policymakers, and workers need to collaborate and plan for the future to ensure that the benefits of AI are shared equitably and that the transition to a more automated workforce is as smooth as possible.
Benefits of AI Technology on the Augmented Workforce
AI has the potential to transform the way we work, providing new opportunities for efficiency, productivity, and innovation. AI can help businesses and workers achieve more with less effort, time, and resources. In this section, we will explore the various benefits that AI technology can bring to the augmented workforce, including increased accuracy, speed, and consistency, improved decision-making, and enhanced creativity and collaboration.
Increased Productivity, Efficiency, and Creativity
The benefits of AI technology on the augmented workforce are numerous and significant. One of the most prominent benefits is the potential for increased productivity and efficiency. AI can automate routine tasks and processes, freeing up time for workers to focus on more complex and creative work. According to a report by McKinsey presented by the European Parliament, AI has the potential to increase global GDP by up to $13 trillion by 2030 through increased productivity and efficiency.
Generative AI could free human workers to focus on higher-value tasks such as strategy, decision-making, and customer service, while generative AI handles the more routine and repetitive tasks. In addition, generative AI could help address skill shortages and enable businesses to expand into new areas by creating customised solutions for specific industries or applications. With the help of generative AI tools like ChatGPT, or Midjourney, organisations can generate high-quality content in a fraction of the time it would take a human to do so, enabling them to be more productive and efficient.
The use of chatbots powered by AI has become increasingly popular in various industries. These chatbots are designed to mimic human conversations and provide assistance to customers or employees in a timely and efficient manner. In the context of the augmented workforce, chatbots can play a crucial role in improving productivity and efficiency. For instance, companies can use chatbots to automate routine tasks such as answering customer queries, processing orders, and scheduling appointments. This frees up time for human workers to focus on more complex and creative tasks.
Also, chatbots can help employees collaborate more effectively. For example, a chatbot could mediate between team members, facilitating real-time communication and information sharing. This can help reduce communication gaps and enhance collaboration within teams. These chatbots can also be used to generate high-quality content quickly and efficiently. This is especially useful in industries such as marketing, where content creation is a time-consuming process. With the help of any of the thousands of AI tools now available, organisations can create engaging and personalised content at scale without the need for human intervention.
Streamlining Processes using Generative AI
ChatGPT is a powerful AI tool that can play a significant role in implementing an augmented workforce, as it is currently happening. With its ability to generate natural language responses and insights, ChatGPT can streamline various HR processes, including recruitment, onboarding, and training. For example, ChatGPT can assist in candidate screening and selection, providing real-time feedback to hiring managers.
ChatGPT can also provide employees personalised training and development opportunities, helping them acquire new skills and stay up-to-date with the latest trends in their respective fields. This can improve employee satisfaction and retention rates, ultimately leading to a more efficient and effective workforce.
Research has shown that ChatGPT can improve communication and collaboration among team members, resulting in better decision-making and problem-solving. For example, by analysing chat logs and other communication data, ChatGPT can identify potential communication breakdowns or areas where team members struggle to collaborate effectively. This can enable managers to provide targeted training or coaching to improve team dynamics and productivity.
Plus, ChatGPT can help businesses improve their customer service and satisfaction levels. ChatGPT can enhance the overall customer experience by providing real-time support and personalised recommendations, leading to increased loyalty and retention rates. This can ultimately contribute to the bottom line of the organisation.
As AI technology continues to evolve, the role of ChatGPT and other AI tools in the workforce is expected to grow significantly. These tools will likely become increasingly integrated into organisational processes, leading to more efficient and effective operations.
Improved Decision-Making and Problem-Solving
Artificial intelligence technology transforms work by enabling employees to make better decisions faster. AI-powered tools can process vast amounts of data and provide valuable insights that humans may not have been able to uncover on their own. This can lead to more informed and data-driven decisions.
Moreover, AI-powered tools can also help identify patterns and trends that may not be immediately visible to human workers. For example, in the healthcare industry, AI tools can analyse patient data to identify potential health risks and help doctors make more accurate diagnoses. Likewise, AI can analyse financial data to identify patterns and trends that may indicate potential risks or opportunities.
AI-powered tools can also help streamline decision-making processes. For example, in supply chain management, AI can analyse data to optimise inventory levels and delivery routes, leading to more efficient operations and cost savings. A survey released in 2017 by PwC found that 72% of business leaders believe AI will be a significant business advantage in the future, thanks to improved decision-making and productivity. Later, in 2022, a new report by PwC stated that the percentage of companies that take a comprehensive approach to AI implementation would be approximately 36.6% at the time of research.
Challenges of Building an Augmented Workforce
As businesses seek to stay ahead in the ever-evolving landscape of the global economy, many are turning to emerging technologies such as AI and machine learning to streamline operations and improve performance. However, implementing an augmented workforce also poses several challenges, from technological limitations to cultural shifts. In this section, we will explore some key challenges organisations face when integrating AI and other technologies into their workforce and discuss potential strategies for overcoming these obstacles.
Job Displacement and Worker Privacy Concerns
One of the most pressing concerns surrounding the implementation of an augmented workforce is the potential displacement of human workers. As AI and automation advance, many jobs may become obsolete or undergo significant transformations. This can be a source of anxiety for workers and can lead to resistance to technological change. However, it is important to note that while some jobs may be automated, new jobs will also be created in fields such as data analysis, software engineering, and AI management.
According to a 2020 report by the World Economic Forum, while technological advances may lead to job displacement in the short term, they will also create new jobs and opportunities in the long term. The report suggests that by 2025, emerging technologies such as AI will create millions of jobs in machine learning, education and data science.
Concerns about worker privacy are growing as AI systems become more pervasive in the workplace. With increased data collection and analysis, employees may feel that their privacy is being violated, especially in areas such as performance monitoring and biometric identification. Organisations must address these concerns by implementing transparent data policies and ensuring employee privacy rights are respected.
To address concerns about job displacement, organisations must take proactive steps to reskill and upskill their workforce to adapt to the new technological landscape. This can include investing in training programs and creating new roles that utilise human skills such as creativity and critical thinking, which are less easily automated.
In terms of worker privacy, organisations can implement policies that prioritise transparency and employee consent when collecting and analysing data. They can work with employees to establish clear boundaries around what data will be collected and how it will be used and ensure that data is stored securely and complies with relevant regulations.
It is key to approach the challenges of implementing an augmented workforce with a balanced perspective, understanding the potential benefits and the concerns. Organisations can use a thoughtful and proactive approach to successfully integrate AI technologies into their workforce while prioritising the well-being of employees.
Ethical Implications of AI-Powered Decision-Making
The rise of AI-powered decision-making has brought a host of ethical concerns that cannot be ignored. While AI algorithms can process vast amounts of data and make decisions faster and more accurately than humans, there are significant risks associated with relying solely on technology to make important decisions.
Recently, the Future of Life institute started an initiative in the form of an open letter called Pause Giant AI Experiments: An Open Letter. The open letter calls for a pause on the development and training of artificial intelligence systems more powerful than GPT-4 for at least six months, to develop and implement a set of shared safety protocols for advanced AI design and development rigorously audited and overseen by independent outside experts.
The letter highlights the risks posed by AI systems with human-competitive intelligence, the need for responsible management and planning, and the development of AI governance systems based on an ethical framework to mitigate potential harm. The authors emphasise the importance of making current AI systems more accurate, safe, interpretable, transparent, robust, aligned, trustworthy, and loyal, rather than continuing to engage in a dangerous race to create ever-larger and unpredictable black-box models. I agree with the call for a pause to stop and think, but only if it applies to all industries, including car makers such as Tesla, who also work on advanced AI for their car and robot.
One major concern is the potential for algorithmic bias, where the data used to train AI systems is biased and leads to discriminatory outcomes. AI systems are only as unbiased as the data and algorithms they are trained on, which means that if there are inherent biases in the data or algorithms, the AI system will learn and replicate those biases. This is particularly troubling in areas such as hiring and lending decisions, where biases can perpetuate and amplify existing inequalities. There are concerns about accountability and transparency in decision-making and the potential for AI systems to be hacked or manipulated.
For example, facial recognition technology has been shown to have higher error rates for people with darker skin tones and women, which could have serious implications in areas such as law enforcement and hiring practices. This has raised concerns about the fairness and accuracy of AI decision-making and the need to ensure that biases are identified and addressed throughout the development and implementation process.
Experts are increasingly emphasising the need for ethical considerations to be integrated into developing and deploying AI systems. This includes ensuring that the data used to train AI is diverse and representative and implementing systems for ongoing monitoring and auditing of AI decision-making. It is also crucial for organisations to prioritise transparency and accountability, providing clear explanations of how AI decisions are made and allowing for human oversight when necessary.
Another significant problem is that the inner workings of AI-powered programs are often inscrutable, making it hard to tell how they reach their conclusions. Many AI systems use complex algorithms and machine learning models that are difficult for humans to interpret or understand. This lack of transparency makes it challenging to hold AI systems accountable for their decisions and raises questions about who is responsible if something goes wrong.
As AI becomes increasingly integrated into our daily lives, it is essential that we carefully consider the ethical implications of this technology and work to ensure that its benefits are shared equitably across all members of society. Only by taking proactive steps to address these challenges can we fully realise the potential of AI to improve decision-making and enhance our lives.
Technological Limitations and Integration Challenges
Organisations that look to implement augmented workforce solutions, face several technological limitations and integration challenges. Among these limitations, we find the inability of current AI technologies to fully replicate human decision-making and cognitive abilities. While AI can improve productivity and efficiency, it cannot fully replace human intuition and creativity.
Another challenge is the integration of AI with existing systems and processes. This requires significant investment in IT infrastructure, as well as the need for specialised skills and expertise. According to analysts and technologists, the cost of training a big language model like GPT-4 is estimated to exceed $4 million, which represents a significant challenge for companies today. Also, there may be resistance from employees who fear AI and advanced chatbots like ChatGPT will replace their jobs, highlighting the importance of communication and collaboration between management and employees during the implementation process.
It is highly advisable that organisations carefully consider the costs and benefits of implementing augmented workforce solutions, as well as the potential risks and challenges. Organisations should also work closely with AI vendors and invest in employee training and upskilling programs to ensure the successful integration and adoption of AI technologies.
Harvard research shows that integrating AI with existing systems is a significant challenge, as companies struggle to implement the necessary changes to support AI-powered workflows. Moreover, experts point out that the lack of standardisation and interoperability between AI platforms can further complicate the integration process. To address these challenges, organisations need to prioritise investments in IT infrastructure and collaboration and communication between IT and business teams. It is also important to focus on the development of AI-powered systems that are user-friendly and accessible to employees of all levels of technical expertise.
Organisations will likely continue to grapple with the challenges of implementing an augmented workforce, but it is clear that the benefits of AI-powered technologies are significant, we just need to apply careful consideration and planning necessary to ensure successful integration and adoption.
HR Strategy for an Augmented Workforce
As we explore the potential of an augmented workforce, it becomes increasingly evident that HR strategy needs to adapt to this new era. It is no longer enough to hire talented individuals and assign tasks, as integrating AI technology requires a more strategic and holistic approach. A successful human resource strategy for a workforce augmented by technology is based on providing employees with the necessary training and education. Allowing them to work with AI requires teaching technical skills and instilling a mindset that embraces change and innovation.
Creating a culture of innovation and collaboration is another crucial aspect of an HR strategy for an augmented workforce. According to a 2021 report by McKinsey, companies that successfully integrate AI into their businesses do not just use it to automate processes; they reimagine how work gets done to create new value. This requires a collaborative culture where employees feel empowered to share their ideas and work together towards a common goal. Also, a culture of innovation allows for continuous improvement and adaptation as AI technology evolves.
Proper training and education, combined with a culture of innovation and collaboration, can help organisations maximise the benefits of an augmented workforce while mitigating the challenges. As AI continues to shape the future of work, HR leaders must adapt their strategies accordingly and prioritise the development of their employees.
It is also vital for companies to create a culture of innovation and collaboration, where employees are encouraged to experiment with new ideas and work collaboratively across departments. This not only fosters a more creative and dynamic work environment but also helps to break down silos and facilitate better communication.
There is also growing recognition among industry experts of the need for a more strategic approach to HR management that aligns with the overall business strategy and incorporates AI technologies into talent management processes. This includes using AI-powered tools for recruitment, talent assessment, and performance management.
Lastly, companies must prioritise ethical considerations when designing their HR strategies for an augmented workforce. This includes ensuring transparency in decision-making processes, establishing clear guidelines for using AI systems, and protecting employee privacy rights.
The Future of Work and the Augmented Workforce
As we move into a world where the augmented workforce plays an increasingly significant role, organisations have begun to reflect this shift by shaping structures and management practices accordingly. Many experts predict that AI and automation technologies will continue to accelerate, leading to a more dynamic and agile workforce. This will undoubtedly have significant implications for the roles and responsibilities of workers, as well as the skills and knowledge required for success in the modern workplace.
Perhaps the most important outcome of the augmented workforce is the creation of new types of jobs and the restructuring of traditional roles. As AI becomes more prevalent in customer service, human employees may shift to high-level tasks requiring empathy, critical thinking, and problem-solving. This will require focusing on upskilling and reskilling employees to ensure they have the necessary expertise to thrive in this new environment.
Another area of focus will be the integration of AI and automation technologies into organisational structures and management practices. This will require a significant shift in how companies approach work and talent management, as well as how they measure performance and success. For example, using chatbots and other AI-powered tools for customer service may require a new approach to performance management that considers the ability of these tools to handle routine tasks and free up human employees to focus on higher-value work.
In short, the future of work and the augmented workforce is a complex topic with multiple ramifications, with many potential implications for organisational structure and management practices. As we continue to explore these possibilities, it will be important for companies to stay attuned to the latest trends and best practices, as well as to the needs and desires of their employees. By doing so, they can ensure that they are well-positioned to thrive in the rapidly evolving world of work.
Final Thoughts
The augmented workforce of tomorrow represents a promising future where humans and technology work hand in hand to achieve unparalleled productivity and efficiency. With the rise of AI, robotics, and other advanced technologies, the workforce is evolving at an unprecedented pace, and companies that fail to embrace this change risk being left behind. However, the benefits of a well-designed augmented workforce are significant, including increased productivity, better decision-making, and improved employee satisfaction.
We now look forward to an exciting future, where it is essential to recognise that the augmented workforce is not a replacement for human workers but rather a complement to them. It is time to leverage technology to augment human capabilities to create a more agile, innovative, and successful workforce that can tackle the complex challenges of the 21st century.
Images: Midjourney
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.thedigitalspeaker.com/ai-workforce-revolution-augmented-future/
|
[
{
"date": "2023/03/30",
"position": 44,
"query": "automation job displacement"
},
{
"date": "2023/03/30",
"position": 10,
"query": "government AI workforce policy"
},
{
"date": "2023/03/30",
"position": 12,
"query": "machine learning workforce"
},
{
"date": "2023/03/30",
"position": 47,
"query": "artificial intelligence workers"
}
] |
Artificial Intelligence
|
Artificial Intelligence
|
https://encord.com
|
[] |
Job displacement: AI could lead to the automation of many jobs, potentially resulting in job losses for human workers. Bias: AI algorithms can be biased if ...
|
Encord Computer Vision Glossary
Artificial intelligence (AI) is a rapidly growing field that has the potential to transform the way we live and work. AI is already making significant contributions to various industries, from self-driving cars to personalized medicine. However, as with any new technology, AI has many questions and concerns. Here, we will explore some of the most frequently asked questions about artificial intelligence.
What is Artificial Intelligence?
Artificial intelligence refers to the ability of machines to perform tasks that typically require human intelligence, such as recognizing speech, making decisions, and understanding natural language. AI algorithms can be trained using large amounts of data and can improve their performance over time.
From scaling to enhancing your model development with data-driven insights Learn more
What are the different types of AI?
There are three main types of AI:
Narrow or Weak AI: Weak AI is designed to perform a specific task, such as facial recognition or speech recognition. It is the most common type of AI currently in use.
Weak AI is designed to perform a specific task, such as facial recognition or speech recognition. It is the most common type of AI currently in use. General or Strong AI: This type of AI is designed to perform any intellectual task that a human can do. Strong AI is currently still in the realm of science fiction.
This type of AI is designed to perform any intellectual task that a human can do. Strong AI is currently still in the realm of science fiction. Superintelligence: Superintelligence is the type of AI refers to AI that surpasses human intelligence and is capable of solving complex problems far beyond human capabilities.
How is AI Being Used Today?
AI is being used in a wide range of applications, including:
Self-driving cars: AI recognizes and responds to different driving situations.
AI recognizes and responds to different driving situations. Healthcare: AI is being used to diagnose diseases and develop personalized treatment plans for patients.
AI is being used to diagnose diseases and develop personalized treatment plans for patients. Customer service: AI-powered chatbots can provide customers with instant responses to their queries.
AI-powered chatbots can provide customers with instant responses to their queries. Finance: AI is used for fraud detection and to analyze stock market trends.
AI is used for fraud detection and to analyze stock market trends. Manufacturing: AI is used to optimize production processes and improve quality control.
AI is used to optimize production processes and improve quality control. Education: AI-powered systems can personalize learning experiences for students.
AI-powered systems can personalize learning experiences for students. Entertainment: AI is used to recommend personalized content to users on streaming platforms and social media.
How does AI Learn?
AI algorithms learn by analyzing vast amounts of data and identifying patterns. The data used to train AI algorithms can come from a variety of sources, including text, images, and audio. Once the algorithm has been trained, it can be used to perform the task for which it was designed.
What are the Potential Risks Associated with AI?
While AI has the potential to bring about many benefits, there are also concerns about the potential risks associated with this technology. These risks include:
Job displacement: AI could lead to the automation of many jobs, potentially resulting in job losses for human workers.
AI could lead to the automation of many jobs, potentially resulting in job losses for human workers. Bias: AI algorithms can be biased if they are trained on data that is itself biased. This can lead to unfair outcomes for certain groups of people.
AI algorithms can be biased if they are trained on data that is itself biased. This can lead to unfair outcomes for certain groups of people. Security: As AI becomes more prevalent, there are concerns about the potential for cyber attacks on AI systems.
As AI becomes more prevalent, there are concerns about the potential for cyber attacks on AI systems. Privacy: AI systems can collect large amounts of personal data, raising concerns about privacy and data protection.
What are Some of the Ethical Considerations Surrounding AI?
As AI becomes more advanced, several ethical considerations must be taken into account. These include:
Transparency: There is a need for transparency in the development and deployment of AI systems, particularly when it comes to how data is collected and used.
There is a need for transparency in the development and deployment of AI systems, particularly when it comes to how data is collected and used. Accountability: There needs to be accountability for the decisions made by AI systems, particularly when these decisions have significant impacts on people's lives.
There needs to be accountability for the decisions made by AI systems, particularly when these decisions have significant impacts on people's lives. Fairness: AI systems need to be designed to ensure that they are fair and do not discriminate against certain groups of people.
AI systems need to be designed to ensure that they are fair and do not discriminate against certain groups of people. Human oversight: There is a need for human oversight of AI systems to ensure that they are being used ethically and responsibly.
Is AI Going to Replace Human Workers?
While it is true that AI has the potential to automate many jobs, it is unlikely that AI will completely replace human workers. Instead, AI is more likely to augment human work, taking on tasks that are repetitive or dangerous, while leaving more complex tasks to humans.
What is the Future of AI?
The future of AI is both exciting and uncertain. AI has the potential to transform many industries and bring about significant improvements in people's lives. However, there are also concerns about the potential risks associated with this technology. We must continue to monitor the development of AI and ensure that it is being used ethically and responsibly.
Overall, artificial intelligence is a rapidly evolving field that has the potential to transform the way we live and work. While there are many benefits associated with AI, risks and ethical considerations must be taken into account. As AI continues to develop, we must ensure that it is being used ethically and responsibly and continue monitoring its impact on society.
| 2023-03-30T00:00:00 |
https://encord.com/glossary/artificial-intelligence-definition/
|
[
{
"date": "2023/03/30",
"position": 80,
"query": "automation job displacement"
},
{
"date": "2023/03/30",
"position": 95,
"query": "artificial intelligence workers"
}
] |
|
Advancing Equity Through Tech (AETT) - TechPoint
|
Advancing Equity Through Tech (AETT)
|
https://techpoint.org
|
[] |
The Advancing Equity Through Tech (AETT) program connects Central Indiana's residents to high-wage, low unemployment-rate tech careers. ... Indiana AI Innovation ...
|
The Advancing Equity Through Tech (AETT) program connects Central Indiana’s residents to high-wage, low unemployment-rate tech careers. A partnership of InnoPower, Sagamore Institute, and TechPoint, AETT is designed to reduce barriers to increasing skills and developing career track opportunities.
With the support of a $300,000 grant from the Indianapolis Urban League, the program will create and market a tech-focused, Adult Apprenticeship program for low-income, central Indiana residents.
| 2023-03-30T00:00:00 |
https://techpoint.org/aett/
|
[
{
"date": "2023/03/30",
"position": 90,
"query": "AI unemployment rate"
}
] |
|
From Automation to Reinvention: How AI Is Shifting the ...
|
From Automation to Reinvention: How AI Is Shifting the Nature of Work
|
https://www.aei.org
|
[
"Jake Easter",
"John Bailey",
"Michael M. Rosen"
] |
OpenAI and the University of Pennsylvania released a working paper estimating that 80 percent of the workforce could see at least 10 percent of their tasks ...
|
The latest breakthroughs in artificial intelligence (AI) will bring numerous productivity improvements to businesses but are likely to change the nature of work itself, which could disrupt millions of workers.
Three factors are driving the rapid adoption of AI technologies. First, the pandemic compelled companies to undergo digital transformations. A McKinsey survey found that over 67 percent of CEOs accelerated AI and automation adoption during this time.
Second, persistent labor shortages are causing companies to adopt automation instead of hiring more workers. For example, a shortage of truck drivers is driving the development of autonomous vehicles for use in construction, farming, and heavy industry. North Dakota’s Gov. Doug Burgum has even proposed a $5 million expansion of the state’s automation tax credit to help businesses adopt new technologies.
Finally, the emergence of large language models (LLMs) such as OpenAI’s ChatGPT, Microsoft’s Bing Chat, Google Bard, Anthropic‘s Claude, and MidJourney has not only raised awareness of AI capabilities but also led to a growing number of new productivity tools.
It’s been four months since ChatGPT first captured the country’s imagination and we’re beginning to see the first set of economic impact estimates. Goldman Sachs predicts a 7 percent global GDP boost from generative AI over a decade but warns of significant labor market disruption, with 63 percent of US jobs potentially affected by AI automation.
OpenAI and the University of Pennsylvania released a working paper estimating that 80 percent of the workforce could see at least 10 percent of their tasks affected by large language models. And for 19 percent of jobs, nearly 50 percent of their functions could be “exposed” to these AI tools.
One shared observation in both reports is that in a departure from prior automation waves, higher-skilled and higher-income professions stand to be most affected. AI technologies possess the capacity to undertake at least half of the tasks currently performed by professionals such as auditors, interpreters, and writers.
It is also important to distinguish between jobs “exposed” to AI and those displaced by it. Workers will increasingly interact with AI technologies, which will alleviate the burden of mundane, tedious tasks, enabling them instead to focus on more advanced and valuable work. Box CEO Aaron Levie aptly expressed this notion, stating, “The impact of AI for the vast majority of work will be as an accelerant to getting to the next most important task that only a human can do.”
These tools are also likely to lower the barriers for workers to enter new jobs or perform higher-skilled work. Two graduate students from the Massachusetts Institute of Technology’s economics department conducted a study with professionals in fields such as marketing and human resources. Half of the participants incorporated ChatGPT into their daily tasks while the other half did not. As expected, ChatGPT increased overall productivity. However, the most intriguing finding was that ChatGPT significantly benefited the least skilled and accomplished workers, narrowing the performance gap among employees. In essence, weaker writers got much better while good writers simply became more efficient.
What does this all mean? It’s still too early in this wave of AI technologies to fully know, but it seems reasonable to assume that several productivity tools will be quickly deployed across a wide range of occupations. That means that every new job will become slightly higher-skilled as workers need to learn to use these new AI systems for their specific tasks.
Source: US Bureau of Labor Statistics and Wall Street Journal
While these technologies will displace some jobs, it seems more likely that the biggest disruption will be the new jobs these technologies create. History offers important lessons from when other technologies were introduced to the economy. For example, the adoption of spreadsheets led to fewer bookkeepers but fueled a surge in financial managers and accountants. AI is likely to create similar trends, including the introduction of new occupations, such as prompt engineers, or create new hybrid jobs that combine domain expertise with new AI technical skills.
Policymakers can take proactive steps to smooth out these transitions’ volatility. As the US Chamber of Commerce’s Commission on AI Competitiveness, Inclusion, and Innovation recommended, the United States must increase education around AI in K–12 and higher education systems. Efforts such as aiEDU and Code.org will be important in the years ahead. And public and private sectors need to focus on training and reskilling the workforce through targeted investments in programs that facilitate worker transitions and provide incentives for businesses to invest in retraining.
The rapid adoption of AI technologies promises significant productivity gains and economic growth, but it also necessitates a workforce reevaluation as new AI systems reshape the landscape of higher-skilled professions, potentially altering the nature of work and driving the need for adaptation and reskilling in the face of unprecedented change.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.aei.org/technology-and-innovation/from-automation-to-reinvention-how-ai-is-shifting-the-nature-of-work/
|
[
{
"date": "2023/03/30",
"position": 14,
"query": "job automation statistics"
},
{
"date": "2023/03/30",
"position": 3,
"query": "reskilling AI automation"
},
{
"date": "2023/03/30",
"position": 94,
"query": "AI skills gap"
},
{
"date": "2023/03/30",
"position": 7,
"query": "AI labor market trends"
},
{
"date": "2023/03/30",
"position": 6,
"query": "AI economic disruption"
},
{
"date": "2023/03/30",
"position": 18,
"query": "artificial intelligence workers"
}
] |
Attract and Retain Your Best Employees by Automating ...
|
Attract and Retain Your Best Employees by Automating Menial Tasks
|
https://www.emburse.com
|
[] |
Only 53.5 percent of employees' weekly planned tasks are completed, and 10.8 percent of their workweek is spent recovering and catching up after reprioritizing ...
|
Despite the mass layoffs that have taken place this year, unemployment is still near historically low levels, and demand for talented finance professionals remains high. In fact, according to a December 2022 report by the Bureau of Labor and Statistics, layoffs and discharges decreased in finance and insurance (-43,000) while they increased in other sectors like the federal government (+4,000).
In other words, the talent crunch hasn’t eased, which means you need a proactive plan.
One of the biggest hurdles for finance leaders identified in our report, Finance Trends: How Finance Leaders Can Thrive during a Recession in 2023, was navigating market, talent, and process challenges. The report found that leaders are turning to automation to help relieve talent pressures due to the direct impact on employee recruitment, retention, and satisfaction.
One popular way to use automation is to identify and eliminate menial tasks like spreadsheet data entry or receipt capture. By finding ways to minimize the amounts of manual tasks employees are responsible for, organizations provide more meaningful work to employees — which translates to higher retention rates, employee engagement, and productivity.
A recent study cited by Inc. demonstrated that burnout, a leading cause of turnover, can happen when people feel overworked or burdened by menial tasks. In general, this sense of burnout has worsened – 23.4 percent of respondents in the study think workload has increased directly due to the Great Resignation.
The analysis showed that workers who have to play “catch-up” because of the lack of automated tasks are more stressed than their counterparts who have automation baked into their processes. Only 53.5 percent of employees' weekly planned tasks are completed, and 10.8 percent of their workweek is spent recovering and catching up after reprioritizing work. Finance teams who automate tools improve their output by eliminating manual work and lowering burnout rates.
The Emburse report found that finance leaders are strongly leaning on automation to remove menial tasks, retain their top talent and attract new employees :
Jobseekers want more responsibility. After basics like hours, compensation, and benefits, “step up in responsibility” was ranked the most valued attribute in a new job.
37% of leaders plan to redistribute workloads this year to combat talent challenges and reduced budgets.
Retention is a crucial driver of automation — improving employee experience (35%) ranked just below overall business performance (38%) as a reason for automating.
Download the full report now to learn more about how automation can help your recruitment and retention strategy succeed.
| 2023-03-30T00:00:00 |
https://www.emburse.com/blog/attract-and-retain-your-best-employees-by-automating-menial-tasks
|
[
{
"date": "2023/03/30",
"position": 25,
"query": "job automation statistics"
}
] |
|
Start A Career With Massman Companies
|
Employment Opportunies
|
https://massmanautomation.com
|
[] |
Looking for a career opportunity in the fast-growing automated packaging industry? Massman offers competitive pay, great benefits, and a friendly ...
|
Interested in Working With Massman?
Massman Automation has several job openings we want to fill with dedicated people like you. Join the Massman mission by applying online today!
Contact us online or call 320.554.3611 for more information about automated packaging job openings at Massman.
| 2020-04-06T00:00:00 |
2020/04/06
|
https://massmanautomation.com/employment-opportunities/
|
[
{
"date": "2023/03/30",
"position": 69,
"query": "job automation statistics"
}
] |
Human Resource statistics to know in 2023
|
Human Resource statistics to know in 2023
|
https://sonary.com
|
[
"Sonary Team"
] |
HR automation statistics · Hiring algorithms outperform humans by 25%. · Using an algorithm to screen applicants for character traits can drop workers' ...
|
Introduction
For many employees, the COVID-19 pandemic flipped the world on its head. Needing to stay home was an awakening for most, resulting in many leaving their jobs, and becoming what is known as The Great Resignation. Because of this, knowing more about human resources (HR) has become incredibly important.
Many of these changes have shown a need in improving the overall HR process. Businesses have grown increasingly reliant on HR software.
But regardless of technology’s power to provide a consistent HR process, the need to develop effective strategies is still there. But for HR strategies to work, you need data.
To help you with this data pursuit, we’ve gathered the most important HR and HR software statistics for 2023. Below, you’ll find information you can use to help with your human resource decisions.
Employee productivity statistics
Ultimately, many HR specialists need to focus on hiring productive employees. To do this, employers need to be just as engaged as their employees, as 63% of employees say culture drives success. The data also points toward that resulting in improved productivity (by 14%), higher customer satisfaction (10%), and more sales (18%).
Freelancers represent a new potential, having more productive hours than standard employees. Sometimes, getting a fresh perspective can be helpful, as the average worker doesn’t get much done beyond the first two and a half hours. This lack of productivity relates to stress (41% of employees share this) and lack of control regarding big decisions.
Top performers are 400% more productive than average ones. This gap rises to 800% when the job is more complex. (McKinsey & Company)
63% of employees say business culture affects organizational success. This includes doing their best work, productivity, and their ability to serve customers. (Eagle Hill Consulting)
68% of hiring managers say remote work is going more smoothly now than when their company first made the shift at the start of the pandemic. (Upwork)
Engaged employees are 14% more productive. (Gallup)
Highly engaged businesses get 10% higher customer ratings and 18% more sales (Gallup)
The average worker is only productive for 2 hours and 53 minutes each day (Vouchercloud)
Freelancers are productive for 36 hours each week (Friday)
50% of employees consider meetings wasted time (Atlassian)
Big decision participation is an important booster of employee satisfaction and productivity (ResearchGate)
47% of workers say that stress causes them to be less productive. (breeze)
Only 7% of workers feel productive during regular work hours (FlexJobs)
Employee morale and engagement statistics
Morale and engagement rates reveal a lot about how HR professionals can assist employees and companies. There’s clearly a lot of work to be done, as only 20% of global employees are engaged. Much of this comes from not finding work meaningful, a lack of transparency, and having a poor work leader or manager, which can result in overall employee burnout and poor job satisfaction.
More personal recognition of an employee’s hard work can be incredibly helpful. Meanwhile, also providing employees with hybrid work schedules has been shown to improve employee wellbeing. Much of this has been shown to work in any company’s favor, resulting in increased profitability by 23%.
Only 36% of US employees are engaged with their workplace. Meanwhile, only 20% of global employees are engaged. (Gallup)
Two out of five white-collar workers prefer to work from home. (Gallup)
At least 70% of employees state the quality of the manager or team leader creates more engaged employees (Gallup)
85% of employees say that they have more motivation when receiving regular updates on company news (Trade Press Services)
Three in four employees want more transparency from their company (Paychex)
Companies with high engagement are 23% more profitable (Gallup)
Highly engaged businesses have 18% fewer turnovers in high turnover organizations and 43% less turnover in low turnover organizations. (Gallup)
When employees thrive, there are 53% fewer missed days because of health issues (Gallup)
Disengaged workers cost organizations up to $550 billion per year (Gallup)
37% of employees say that personal recognition would encourage them to produce better work (Fortune)
Only 33% of employees are thriving in overall wellbeing while the remaining don’t find their work meaningful or don’t feel hopeful about the future (Gallup)
About 50% of the world’s workers felt a lot of daily stress, with most of this stress affecting working women in the US and Canada (Gallup)
Development and training statistics
(LinkedIn)
Continued development of training links heavily in with job advancement and development. This much is true, especially for new employees and retention. After all, without senior support, 68% of workers will consider leaving a job.
The push for smaller teams and the need for flexible employees is clear. Internal mobility and cross-functional training will more likely keep employees, so providing employees with skills is important.
In addition, it’s important to check your preference for remote vs on-site employees. There is evidence pointing towards an implicit bias towards development (through promotion) of on-site employees.
On-site employees are 76% more likely for promotion when compared to remote workers (Gartner)
68% of employees consider leaving their jobs without support from senior employees (Staples)
72% of companies say that learning and development is a strategic function of their organization (LinkedIn)
Companies that excel at internal mobility (cross-functional training) are two times more likely to keep employees (LinkedIn)
61% of new hires do not receive training on company culture (TalentLMS)
People are four times more likely to think about your company for future opportunities when offering constructive feedback (LinkedIn)
HR profession statistics
With The Great Resignation and the Coronavirus pandemic, the HR profession is now more challenging than ever. Employee expectations within their work environment has changed immensely, resulting in HR professionals needing to adjust their approach. Below, you’ll find some statistics related to the HR profession.
Employee retention statistics
Employee retention is one of the biggest challenges for the HR profession. Namely, because one in three hires (33%) will quit within the first year. Even among later employees, 3% of them will still quit. HR professionals will need to work with employee needs, which have been shown to be related to achievement in their career, health or family-related issues, or desire for a better work-life balance.
The average rate of turnover in all industries was 47.2% in 2021. (Bureau of Labor Statistics)
Southern states experienced the highest rate of turnover with rates averaging at 52.2%. (Bureau of Labor Statistics)
Companies that focus on their culture see a 72% lower attrition rate (Gallup)
First-year employees have the highest turnover rate, sitting at 33% (Work Institute)
Nearly 18% of people who leave say its related to the lack of growth, achievement, and security in their career (Work Institute)
About 12% leave because of family or health issues while 10% want a better work-life balance (Work Institute)
Onboarding statistics
Over 90% of employees decide whether they want to stick with a company based on onboarding. However, few companies (one in four) and employees (12%) rate those onboarding processes as successful. Much of it comes down to having a formalized onboarding process, as 77% of employees who follow a clear and formal onboarding process are more likely to stay. HR professionals need to pay close attention to onboarding to increase employee retention.
It takes new employees up to eight months to be as efficient as new employees (AlliedHR IQ)
Only one in four companies rate their onboarding programs as “highly successful.” (AlliedHR IQ)
86% of HR professionals said recruiting is more like marketing (Glassdoor)
Nearly 50% of companies do not know how to define success or failure in their current onboarding process (SHRM)
52% of companies see improved retention rates with good onboarding practices. 60% of those same companies see better productivity while 53% of those companies see improved customer satisfaction. (SHRM)
77% of employees who go through formalized onboarding processes meet their first performance reviews (eLearning Industry)
56% of new hires would like a “buddy” to help them through the onboarding process (ClickBoarding)
93% of employers think a good onboarding process is critical when an employee decides whether to stay with your company (CareerBuilder)
Less than half of companies think their onboarding process is effective at retaining new hires (HCI)
Only 12% of employees think that their company is good at onboarding. (Gallup)
80% of job seekers are discouraged from pursuing additional job opportunities at an organization if they aren’t notified of their job application status. (G2)
Employees are 3.5 times more likely to re-apply if notified of their job application status. (G2)
General HR market size statistics
Despite technology being a major driving force behind HR, the industry is more than tech. Overall, this is proven with expected growth rates above 12%. With a current overall market size of $87 billion, this means that there is significant growth potential for newcomers to the HR industry. Leading companies, like Randstad, are likely to try to take advantage of this growth rate.
The global human resources market size is expected to grow at a 12.8% CAGR from 2022 to 2030. (Grand View Research)
The total human resources & benefits administration market size in the US is $87.3 billion as of 2022. (IBISWorld)
The US has over 380 thousand businesses with nearly one million employees in the HR industry as of 2022. (IBISWorld)
The growth rate for the overall human resources and benefits administration sector in 2022 was 5.1%. (IBISWorld)
The leading companies in the human resource services industry were Randstad, Adecco, and Manpower. (Statista)
HR software market size statistics
When looking at the HR market size, there are two areas to look at: the overall field and how technology has affected it. To start, we will focus more on the technology aspect.
HR technology market size statistics
Below, you’ll see a breakdown of various market sizes and spending statistics related to HR technology. From these statistics, there is consistent data across the board that the value of HR software is expected to nearly double. A good portion of this will be driven by a combination of artificial intelligence (AI) and cloud-based solutions. Most of this growth will take place in North America, with both the European and Asia Pacific markets just behind.
The HR software market is projected to grow at a nearly 10% CAGR, or compound annual growth rate. (Verified Market Research)
The HR software market is expected to reach 33.57 billion by 2028, this is from 15.59 billion found in 2020. That’s a growth rate of 10%. (Verified Market Research)
North America accounts for the largest market share at 35.81%. Europe has the second largest market share, followed by the Asia Pacific region. (Verified Market Research)
The IT and Telecommunications industry will hold a 23.3% share of the human resources market. (Fortune Business Insights
HR salary statistics
For those who need to hire a new HR manager, most managers expect to be paid a minimum of $65 per hour. This is not considering the need for entry-level positions. The highest paying state for HR professionals is New York while the highest number of HR employees work in California.
The average wage of HR professionals is $65.67. Meanwhile, the annual wages average at about $136 thousand according to 2021 figures. (Bureau of Labor Statistics)
The top paying industry for human resources managers is in information services. Annual wages for HR professionals in this industry is about $192 thousand per year (Bureau of Labor Statistics)
Most HR professionals work in California, with their annual wages sitting at about $154 thousand per year (Bureau of Labor Statistics)
The top paying state for HR is New York, which has an annual wage of $186,930.(Bureau of Labor Statistics)
HR technology statistics
From our earlier section, the growth of HR technology is going to nearly double within the next decade. Because of this, the need to invest in HR software is real. In the below statistics, you’ll see the problems HR software seeks to solve and how they assist through automation.
HR technology function statistics
Technology can help solve many of the biggest challenges faced by HR professionals. Business owners and HR specialists benefit from its potential for increased flexibility and talent acquisition features.
Remote work, which has been heavily in demand since the COVID-19 pandemic, benefits heavily from the use of HR tech. Most hiring managers agree that remote working is better, as we’ve taken the past few years to develop those technologies. Thanks to the impact of modern video conferencing technology (which you can read more about in our blog about video conferencing statistics), it is easier than ever to establish genuine connections, regardless of where employees work.
Technology has also been shown to benefit those in talent management. Talent acquisition is an incredible challenge for recruiters, and most recruiters (69%) admit that usage of AI technology has improved with finding candidates, screening them, and supporting them. The statistics below will show you the benefits of using HR software.
Only 16% of employers use technologies to monitor employee engagement. (Gartner)
Technology-based performance management software is 12% more likely to engage with employees. (Aberdeen Group)
In 2019, 22% of companies used AI to help with talent challenges. (Aptitude)
44% of CEOs believe AI can help with acquisition and retention. (Aptitude)
63% of talent acquisition specialists state that usage of AI has changed the recruiting process. 69% of recruiters shared that AI helped with finding better job candidates. (Korn Ferry)
Over half (50% or more) of recruiters say AI is helpful with sourcing, screening, and nurturing candidates. (LinkedIn)
HR automation statistics
Automation has proven effective across a variety of functions and industries. In its current form, its most potent use has been to screen applicants, outperforming human hiring managers by 25%. With the right hiring algorithms, you can spot the character traits that meet your business needs, getting better job seekers with a reduced chance of worker’s compensation abuse.
IBM, in particular, has used their HR management system to reduce their HR team by 30%. Overall, this has saved them money that they can spend towards talented individuals.
AI and automation can cause increased profits, improved employee morale, and prediction of when a person is likely to leave their job. For many businesses, the issue is finding the talent who can leverage this technology, meaning that most businesses are still in the early stages of using this technology.
Hiring algorithms outperform humans by 25%. (University of Minnesota)
Using an algorithm to screen applicants for character traits can drop workers’ compensation abuse by 68%. (Richfield Management)
Mundane and repetitive tasks often cause reduced morale and employee retention. (IDC)
Artificial technology can predict which workers will leave their jobs. IBM has one with 95% accuracy. (CNBC)
Predictions show that 83% of early adopters of AI will see an increase in ROI, or return on investment. (Deloitte)
45% of companies are still in the beginning stages of process automation. (Forbes)
Lacking resources and skills is the biggest limitation to using AI technology across multiple business industries and sectors. (IBM)
Statistics from leading HR software companies
Below, you’ll see the top four human resource service providers worldwide. These rankings are from HRoot, a global ranker of HR service provider:
Randstad – $26.5 billion
The Adecco Group – $26.2 billion
Recruit Holdings – 22 billion
ManpowerGroup – $20.8 billion
While these are the top four companies worldwide, they have not earned the most profit. Below, these companies are the top five for profitability. This data also comes from HRoot:
Paychex – 36.3% operational profit margin.
Paycom Software – 30.7%
ADP – 21.3%
Paylocity – 12.0%
Most of these companies have a strong segment for HR management software. According to HRoot, operating profit growth among HR software companies sat at 103.1% on average, the highest compared to other types of HR businesses. For example, many of them are payroll service companies.
Should you use HR software?
The need for streamlined HR processes is essential. HR software allows you to create a consistent HR experience. So, you should use HR software to improve the employee experience.
HR software allows small to medium-sized businesses to save money and time. Companies like Paychex and ADP allow you to outsource your payment processing system. These payment systems remind us why detailed bookkeeping is important and how technology makes it easier.
Many of these HR software systems also allow for consistent file tracking systems. Sage, for example, works to streamline your onboarding process. It also assists you throughout employee training, an important aspect of HR management.
Many HR software systems also work with employee offboarding. Zenefits, for example, is another company that handles the full process. They can even help store your documents for compliance, which is important if you need to offboard an employee.
Check out our HR product reviews to compare your options.
How many companies are using HR software?
According to an International Services Group (ISG) survey taken in 2021, it’s estimated that 46% of companies are using HR platforms. This is up by 20% from the prior year, namely because of the push of COVID-19.
Additional data from IBISWorld tells us that there are over 500 HR & payroll businesses in the United States. This is concerning growth rates of 11%, which are expected to remain consistent. There is a good likelihood of more HR platforms and companies using these platforms.
Why is HR software necessary?
HR software is necessary because our world is creating more small businesses and teams. These teams need to work independently, requiring more effective HR solutions, many of them AI-driven and cloud-based.
The massive growth of these services, especially during COVID-19, allows for greater flexibility. This allows a business that runs out of a basement to compete with larger companies. These micro-specialized businesses need HR solutions as well, creating a demand for better software.
Even larger businesses are seeing the demands of their widespread workforces. Office and sales employees are demanding hybrid work schedules and remote work opportunities. Greater flexibility and freedom is something companies cannot avoid, increasing the demand for a more robust technology sector on all fronts, including human resources.
Conclusion
From the collection of statistics above, you should be able to make better strategic decisions. By considering the global and local effects of how HR has changed, you can better meet stakeholder needs.
Over the next ten years, the push for further automation and technology-driven features will probably change our perspectives again. As always, knowledge and information will be your best weapon in attracting top talent, retaining talent, and nurturing talent to push them to the next level.
| 2023-03-30T00:00:00 |
https://sonary.com/content/hr-statistics-every-business-owner-should-know-in-2022/?srsltid=AfmBOorlashnK1nNwMmY2OXDG7XghrsELyToU-hPSrMOe9eZlJQtpvll
|
[
{
"date": "2023/03/30",
"position": 79,
"query": "job automation statistics"
}
] |
|
Why Are Young Workers Leaving Their Jobs?
|
Why Are Young Workers Leaving Their Jobs?
|
https://shift.hks.harvard.edu
|
[
"Tyler Woods",
"Dylan Nguyen",
"Daniel Schneider",
"Kristen Harknett",
".Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow",
"Class",
"Wp-Block-Co-Authors-Plus",
"Display Inline",
".Wp-Block-Co-Authors-Plus-Avatar",
"Where Img"
] |
Using detailed longitudinal data that tracks younger workers from the Spring of 2021 to the Spring of 2022, we find that workers who began in the most ...
|
The American labor market has experienced dramatic changes since the start of the global COVID-19 pandemic in the early spring of 2020, with historic job losses followed by a sharp employment recovery. Since 2021, the pandemic labor market has entered a third phase, with a dramatic reshuffling of workers in the labor market. Commonly referred to as the “Great Resignation,” workers have left their jobs at extraordinary rates, particularly younger workers. While some argue that young workers left their jobs to rely on the federal stimulus money or other forms of public assistance, others believe that young workers left their current jobs for ones with better pay, benefits, or other working conditions.
Are workers quitting because they do not want to work, or because they want to find better work? Using data from the Shift Project collected between Spring 2020 and Spring 2022, we test these competing narratives of the Great Resignation by directly examining workers’ jobs and job leaving during this period.
Younger workers (ages 18 to 24) often faced challenging job conditions in the form of low pay, unpredictable schedules, and limited benefits, but these circumstances varied substantially between jobs and employers. This variation in job quality made a significant difference in job satisfaction and retention intentions. Across most measures, poorer baseline job quality is significantly associated with greater job dissatisfaction and higher likelihood to seek a new job for young workers.
Beyond workers’ stated intentions, we can also examine which workers did, in fact, leave their jobs, and how their job exits were associated with the quality of their baseline jobs. Using detailed longitudinal data that tracks younger workers from the Spring of 2021 to the Spring of 2022, we find that workers who began in the most precarious jobs were much more likely to exit their jobs than workers with higher baseline job quality (e.g., better wages, more stable schedules).
By using the Shift panel data which tracks workers over time, in addition to knowing which workers left their job, we also observe the employment trajectories of workers who left their jobs. This allows us to test whether workers are using job leaving as a way to “upgrade” their jobs or are simply leaving employment. In total, 49% of young workers stayed at their job, while 39% of workers left for a new job and only 12% transitioned to unemployment, most of whom were actively looking for work, were in school, or were providing care. Less than 1% of younger workers were sitting out of the labor market because they didn’t need to work.
Rather than large shares of workers leaving the ranks of the employed, the far more common outcome was to either stay put in their job or to move from one job to a new position. And, focusing exclusively on those who moved to a new job (i.e., excluding those who transitioned to unemployment), we find strong evidence that young workers who moved jobs were able to upgrade to higher wages and more stable schedules.
Our results suggest that young workers in the service sector seized the opportunities provided by a pandemic and an extremely tight labor market to improve their working conditions. Rather than being trapped in jobs with low pay or unstable schedules, these workers sought out roles that were a better fit for their own personal and professional goals.
If you want to learn more, read the Annie E. Casey Foundation’s blog on this report.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://shift.hks.harvard.edu/why-are-young-workers-leaving-their-jobs/
|
[
{
"date": "2023/03/30",
"position": 82,
"query": "job automation statistics"
}
] |
Generative AI Will Enhance — Not Erase
|
Generative AI Will Enhance — Not Erase — Customer Service Jobs
|
https://hbr.org
|
[
"Paul R. Daugherty",
"H. James Wilson",
"Karthik Narain",
"Is The Former Chief Technology Officer Of Accenture",
"Currently A Senior Technology Adviser At The Firm. He Is The Coauthor",
"With H. James Wilson",
"Is The Global Managing Director Of Technology Research",
"Thought Leadership At Accenture Research. He Is The Coauthor",
"With Paul R. Daugherty",
"Is Group Chief Executive Of Technology At Accenture. He Oversees Cloud"
] |
... jobs and creating the most effective mix of human, automated, augmented, and ... Data & Visuals · Case Selections · HBR Executive. Search hbr.org. CLEAR.
|
The potential for generative AI like ChatGPT to disrupt how humans interact with computers, change how information is retrieved, and transform jobs across industries has left a lot of company leaders scratching their heads. As with other breakthroughs in AI, ChatGPT and similar large language models (LLMs) raise big questions about their impact on jobs and how companies can apply them productively and responsibly.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://hbr.org/2023/03/generative-ai-will-enhance-not-erase-customer-service-jobs
|
[
{
"date": "2023/03/30",
"position": 90,
"query": "job automation statistics"
},
{
"date": "2023/03/30",
"position": 33,
"query": "AI job creation vs elimination"
},
{
"date": "2023/03/30",
"position": 4,
"query": "generative AI jobs"
}
] |
AI vs the job market: Experts say tech roles thought ...
|
AI vs the job market: Experts say tech roles thought 'immune' to automation could face disruption
|
https://www.foxbusiness.com
|
[
"Nikolas Lanum"
] |
Elaborating on his 2019 Ted Talk, Siraman said AI will change job descriptions more than eliminate jobs outright. "Engineers won't write as much code. Instead, ...
|
Artificial intelligence (AI) and technology industry experts claim that ChatGPT and generative AI will cause significant disruptions in the job market, but the impact will vary depending on the field and the decisions made by business leaders.
Goldman Sachs warned in a report Sunday that around the world, as many as 300 million jobs could be impacted by artificial intelligence automation, CNBC reported.
While CEOs and c-suite level employees have long predicted AI would significantly impact jobs requiring manual labor and customer service, the rapid evolution of generative AI like ChatGPT and its ability to debug and create code has illuminated the potential for disturbances in the tech field. This industry has already experienced over 118,000 layoffs in 2023, according to Crunchbase.
INDIAN JUDGE ASKS CHATGPT TO HELP DECIDE BAIL FOR MURDER SUSPECT
Tom Taulli, the author of "Artificial Intelligence Basics: A Non-Technical Introduction," suggested that some of these layoffs were due to automation technology being able to take over functions and "repetitive processes" in various fields.
"Over the next few years, several professions that we thought may have been immune to this we will find are not," he said.
He said that things like ChatGPT can configure and write the code for programmers, debug problems and even find the most optimal way to lay out the algorithm.
"If you're more of a cut and paste early level programmer you better up your skills. Those are skills that are going to be automated," Taulli added.
Taulli also warned that safeguards need to be implemented for "life and death industries," those involving large cash flows, essentially any heavily regulated industry.
"If you're an airline pilot, and you're using generative AI for the manual, it better be correct, or else maybe the jet crashes," he said.
Founder Prequel CEO Timur Khabirov said that AI is already proving to be "incredibly disruptive" and has made many workers fearful they will become redundant.
MUSK LOOKS TO BUILD CHATGPT ALTERNATIVE TO COMBAT ‘WOKE AI’: REPORT
"However, if you look back at technological advancements of the past, while the reduction of labor required to accomplish tasks ushers in change, the demand never goes away," he said. "The move from transportation via horseback to the combustion engine is a good example. People always needed to get from A to B, but one method was simply faster and more efficient."
Greg Kogan, VP of Marketing at Pinecone, a vector database company providing long-term memory for AI, said the impact of AI on the jobs of programmers and software engineers will largely be determined by those in the field. Some companies have already outright banned AI like ChatGPT.
"The way software is programmed is already starting to look drastically different. It's up to each individual programmer if they're going to adapt to this new AI-assisted way of programming or not. The same has been true for every monumental shift in computing for the past century," he told Fox News Digital.
Speaking specifically on engineers, Kogan said those who learn to collaborate with AI to design and build software will survive in the industry and thrive in the coming years.
Though Kogan does not think "any job is safe" from AI, he does not mean every job will be eliminated, merely affected by the evolving technology.
POPE FRANCIS DECLARES A.I. LEARNING ‘POSITIVE’ TO ‘FUTURE OF HUMANITY’ IF USED ‘ETHICALLY & RESPONSIBLY’
"Some people talk about hands-on work like construction or farming as being safe, but those people might not realize how much those jobs are already affected by technology, even before AI," he added.
Silicon Valley creative consultant and product designer Viputheshwar Siraraman told Fox News Digital that mathematicians, tax preparers, quantitative financial analysts, writers and web and digital interface designers are likely most vulnerable to AI.
However, he noted that "hallucinations," or falsehoods presented as fact by ChatGPT and other generative AI, indicate these tools are not mature enough to stand independently and create "production-ready assets" without human correction.
Elaborating on his 2019 Ted Talk, Siraman said AI will change job descriptions more than eliminate jobs outright.
"Engineers won't write as much code. Instead, they will manage, debug, and deploy AI-written code, Siraman said. "Doctors won't come up with diagnoses themselves. Instead, they will use AI to correlate symptoms to diagnosis and lawyers won't write legal docs from scratch. Instead, they will guide and revise AI-written contracts."
EVERYTHING YOU NEED TO KNOW ABOUT ARTIFICIAL INTELLIGENCE: WHAT IS IT USED FOR?
Yaniv Makover, the CEO and co-founder of generative AI copywriting platform Anyword, said the technology would change the way we work by eliminating or collapsing certain job functions.
"Mathematicians don't fear calculators - and gen-AI is analogous in this case. Initially, when the calculator was first invented, yes it might have replaced some people who solely did complex calculations, and suddenly it was solved by a calculator," Makover said. "But quickly, mathematicians universally recognized it as a useful tool. Mathematicians today are defining the equations, not solving them."
Speaking on writing-centric jobs like journalism and marketing, Makover said these workers still need to define the message and guide their writing themes. To that point, generative AI is a tool that will make it easier to convey that purpose, but according to Makover, there is still a lot of room for creativity.
"The jobs in the most danger are those that include repetitive information tasks, like customer support, copywriting, processing and organizing data, simple graphic design," Makover said. "Though, in all cases, someone will need to curate and guide whatever the AI spits out. In no case would all jobs in a sector be eliminated. Roles may simply shift to managing, strategizing, and improving how work happens. Tasks may change, but people will still have jobs."
GET FOX BUSINESS ON THE GO BY CLICKING HERE
That might include jobs like social workers, medical professionals, therapists, caretakers, personnel directors and marketing or business strategists.
Makover noted that jobs requiring an understanding of empathy, emotional intelligence, problem-solving, critical decision-making and the capacity to adjust to unforeseen circumstances are "very difficult" for an AI to replicate at this point in time. Jobs with these qualifications include social workers, medical professionals, therapists, caretakers, personnel directors and marketing or business strategists.
| 2023-03-30T00:00:00 |
https://www.foxbusiness.com/technology/ai-vs-job-market-experts-tech-roles-immune-automation-could-face-disruption
|
[
{
"date": "2023/03/30",
"position": 14,
"query": "AI job creation vs elimination"
}
] |
|
Two-Thirds of Jobs Are at Risk: Goldman Sachs A.I. Study
|
Two-Thirds of Jobs Are at Risk: Goldman Sachs A.I. Study
|
https://observer.com
|
[
"Sissi Cao",
"Sissi Cao Is A Business News Editor For Observer. She Was Previously A Staff Reporter For Observer Covering Technology",
"Entrepreneurship",
"Economy. She Is A Graduate The University Of Maryland",
"Is Originally Shanghai",
"China. Follow Her On Twitter",
"Sissicao",
"Send Tips To Scao Observer.Com"
] |
Goldman Sachs estimates that 46% of administrative positions, 44% of legal positions, and 37% of engineering jobs could be replaced by artificial ...
|
As many as 300 million full-time jobs in the world, including two-thirds of jobs in the U.S. and Europe, are at risk of being replaced in some way by generative artificial intelligence, the technology behind tools like ChatGPT, according to a Goldman Sachs study this week.
Sign Up For Our Daily Newsletter Sign Up Thank you for signing up! By clicking submit, you agree to our <a href="http://observermedia.com/terms">terms of service</a> and acknowledge we may use your information to send you emails, product samples, and promotions on this website and other properties. You can opt out anytime. See all of our newsletters
“If generative AI delivers on its promised capabilities, the labor market could face significant disruption,” the investment bank’s economists wrote in a report.
What jobs are at the most at-risk and where?
The impact of A.I. disruption will be felt most deeply in developed countries, like the U.S. and European Union nations, the study noted, because those economies support a large number of white-collar jobs that are more prone to automation than manual labor-intensive work does.
In the U.S., 46 percent of office and administrative support positions could potentially be replaced by A.I., Goldman Sachs estimates. About 44 percent of legal positions could be automated, and 37 percent of engineering jobs are at risk.
Overall, approximately two-thirds of current jobs in the U.S. and Europe are exposed to some degree of A.I. automation, and up to a quarter of all work could be replaced by machines completely, the bank said, adding that, of affected positions where humans are still needed, as much as half of their workload could be computerized.
Tech elites raise alarm on A.I.’s threat to human jobs
Bill Gates painted a similarly alarming picture recently. In a lengthy blog post last week, the Microsoft cofounder predicted using tools like ChatGPT will increasingly feel like “having a white-collar worker available to help you with various tasks.”
Gates said A.I. has the potential of outperforming human workers in job functions like sales, service and document handling, where there are a plethora of good and bad examples for an algorithm to learn from.
Earlier this week, Elon Musk and hundreds of tech entrepreneurs and academics signed a letter urging A.I. labs to pause training systems that are more powerful than OpenAI’s GPT-4 until the industry develops a shared set of safety protocols.
“We must ask ourselves: Should we automate away all the jobs, including the fulfilling ones?” said the letter, authored by nonprofit Future of Life Institute. “Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us?”
It’s not all doom-and-gloom
Goldman Sachs economists appear more optimistic. They noted technological advancement that initially displaces human workers has historically also created employment and economic growth over the long term.
“Although the impact of A.I. on the labor market is likely to be significant, most jobs and industries are only partially exposed to automation and are thus more likely to be complemented rather than substituted by A.I.,” the report said.
Widespread adoption of A.I. will greatly increase productivity and boost global economic output by 7 percent annually over a 10-year period, which is more than double the typical economic growth rate of industrialized nations, Goldman Sachs predicted.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://observer.com/2023/03/generative-a-i-may-replace-300-million-jobs-goldman-sachs-study/
|
[
{
"date": "2023/03/30",
"position": 22,
"query": "AI job creation vs elimination"
}
] |
What is AI marketing? Everything digital marketers need to ...
|
What is AI marketing? Everything digital marketers need to know
|
https://unbounce.com
|
[
"Banafshe Salehi",
"Lindsay Sands"
] |
... AI to improve their bottom line. Graph showing the expected impact of AI marketing on marketing job creation and elimination. With so many everyday ...
|
Hey, remember the Big Bang? Y’know, creation of the known universe and all that. Game changer.
There have been smaller versions of that, too, ever since that big Big Bang. Events that changed the course of life as we know it. The invention of the internet was a pretty big one. The invention of wheels. The invention of yogurt-covered pretzels.
And of course, the invention of artificial intelligence. AI is totally reshaping how we work, how we create, how we communicate—and it’s getting more and more accessible each day. ChatGPT, anyone?
That’s true for marketers, too. Businesses are adopting AI marketing tools to help them get better results from their campaigns—often with less effort and lower costs. We even did a little research of our own and it turns out, more than 80% of businesses believe AI tools will positively impact their business in three years or less. Businesses—and not just the ones running tech startups out of Silicon Valley—are hungry for a piece of that AI pie.
Some marketers are already using AI to create more customized campaigns. Some are still skeptical that AI can deliver results as good (or better than) a real, live person. But one thing’s certain: AI marketing is happening, and even if you’re not gonna adopt AI tools, you need to know what it’s all about.
So, what does AI marketing really even mean? Let’s take a deep dive.
Here’s what you need to know about AI marketing:
What is AI marketing?
Before we can talk about AI marketing, we need to start by goin’ back to basics. What is artificial intelligence?
Artificial intelligence is just a way of talking about computers that can think—or appear to think—like humans. A brilliant ol’ fella named Alan Turing first proposed the question, “Can machines think?” The answer depends on who you ask (and what we agree “thinking” even means), but it’s generally accepted that machines today can successfully replicate human intelligence in some circumstances.
AI is all about programming computers to perform tasks that normally require a person, like recognizing speech, making decisions, and even learning from experience. If that thought freaks you out, instead imagine having a cute lil robot brain inside your computer, ready to help you out with whatever task you throw its way. Adorable.
AI marketing is just the application of AI for marketing purposes. Marketers in this day and age are using the power of AI to speed up (or even automate) content creation, analyze customer data for insights, respond to support requests—all sorts of things that would normally take time and expertise. Frickin’ cool, right?
Examples of AI in marketing
Maybe this all sounds a little abstract—but marketers are using AI and getting real, concrete results. Here are some examples of what that looks like:
Peter Letts is the founder of Abyss Scuba Diving. Peter is churning out PPC campaigns and landing pages that see an average conversion rate of 35% . He did it all using an AI landing page builder that takes makes data-backed recommendations gets folks converting like mad.
Jeff Taylor is the founder of his own digital marketing agency, Taylor Made Marketing. Jeff regularly gets his clients conversion rates 10 times the industry standard. He’s using an AI tool to analyze visitor attributes and automatically route ‘em to the page where they’re (statistically) most likely to convert. Since he started using AI, business has been boomin’.
AI offers tons of benefits to marketers. It doesn’t just get you better results—it also speeds up mundane tasks, reduces the need for additional headcount, and lets you focus on the big picture. Many marketers are adopting AI tools—like copy generators, design assistants, and marketing automation and optimization software—because they help ‘em save money, fill expertise gaps, and free up more time. Show us a marketer who doesn’t want literally all of those things?
Popular types of AI marketing
AI is everywhere. It’s like the sand you find all over your house after that one day playing volleyball at the beach. (Top Gun just made it look so darn fun.)
Many industries have adopted AI or are in the process, and it’s no different for marketing. So, what types of AI are available for marketers, and how are they used?
AI data analysis
To succeed in marketing, you gotta know what makes your customers tick. AI can crunch the numbers for you and analyze all your juicy data to understand consumer habits. From there, it can predict what products and services they’re likely to buy based on their online history and past purchases. With this intel, marketers can forecast sales, manage inventory, and push the right products to the right people.
It’s like having an octopus that can predict the future, but without that… fishy smell.
AI content generation
AI can help marketers create all sorts of content for social media, email marketing (hello, subject lines), and other communication channels. Marketers can set parameters around the generated content and ultimately have the final say in what gets sent or published.
For example, we’ve got an AI copywriting tool to help users write engaging content for landing pages, emails, and ads. Spin up some content, keep what you like, and bin the rest. (Also, check out our guide to AI writing and how it can improve your content.)
Though AI can’t replicate human creativity, it can save your team time—and maybe even fuel a bit of inspiration.
Dynamic pricing AI
The retail world’s version of “now you see it, now you don’t!” Dynamic pricing is when prices change based on things like traffic volume or product availability. You know the drill: You search for something, leave it for a bit, and when you come back, the price has gone through the roof. (Not nice, ecommerce website.) Of course, the theory is that prices then drop once demand ebbs.
For marketers, AI-powered dynamic pricing is gold. They can create campaigns that have a sense of urgency and maximize their ROI, without needing to adjust prices themselves manually. It’s a win-win situation. (Except when you have to pay through the nose for that flight to your cousin’s wedding.)
AI chatbots
Chatbots have become a common feature of the customer service experience. Think about the little chat bubble embedded on many websites, or the responses you get from brands on social media, by email, or by text. AI chatbots can be used to assist customers with various tasks, like placing orders or even working through technical hiccups. (Thanks again, “Brad,” for wishing me a happy birthday while fixing my phone service issue.)
Chatbots also have the potential to generate new sales opportunities. AI chatbots can make more personalized recommendations by collecting data about a customer’s interests and preferences. For marketers, that means more conversions. Good stuff.
AI conversion rate optimization
Forget about manual A/B testing. Marketers can use AI to automatically select the best version of your content—or better yet, eliminate the need to choose a “champion” entirely. Imagine using AI to quickly spin up dozens of ad or email variants, then letting the machine analyze demographic data to figure out which is likely to perform best for each individual.
For example, Unbounce has an AI conversion optimization tool for landing pages. Rather than split-testing a couple of variants at a time, marketers can create as many landing pages as they want, then let AI automatically send visitors to the top-converting page for people like them. On average, it gets marketers get 30% more conversions. Just sayin’.
Problems with AI in marketing
Of course, it’s not all sunshine and algorithmically-generated daisies. AI is changing the marketing landscape stupidly fast, and it’s important to also recognize some of the risks that come with this dramatic shift in the way we work.
For example, AI isn’t so great at replicating the emotional intelligence of marketers. Customers still value a human touch, and if their entire experience with your brand is jumpin’ from one artificial experience to the next, it could be a turn off. It’s crucial that marketers don’t let AI replace genuine interaction and connection with their customers.
Likewise, AI lacks human creativity. Generative AI models are incredible for their ability to churn out an absolutely bonkers amount of… well, pretty decent written and visual content. (After all, they were trained on the whole gosh-dang Internet.) But AI doesn’t yet come up with truly original ideas. It just combines other ideas it’s seen before into something that looks kinda new. Marketers can use these tools to accelerate their creative processes, but it you wanna make something great, you’re better off putting in the time to do in the ol’ fashioned way: Thinking of it yourself.
There are other problems with AI, like privacy and data collection. When you share data with an AI tool, you need to be aware of how that data is gonna be used. Imagine you turn over your customer list (with names, emails, phone numbers) for AI analysis. Can you say confidently that the data isn’t gonna be used to train the model, or even show up as generated content for other users?
And we can take that concern a step further. What says an AI tool is even correct?
AI is only as good as the human-created content it’s trained on, and as a species, we’re, uh… we’re not super reliable. If AI is using inaccurate data and biased information to determine its own outputs, then those outputs are inevitably gonna be inaccurate and biased, too.
It’s impossible for a marketer to fact-check the oceans of data informing the AI tools they use. The solution, then, is to always filter what you’re getting from AI through your own skepticism and expertise.
Will marketers be replaced by AI?
It’s true that AI marketing comes with a bunch of great perks. But we’re sure most marketers have woken in a cold sweat with an intrusive thought: Are robots gonna replace me? If AI is just so good at this whole marketing thing, what are we gonna need marketers for?
There’s no denying that digital marketing as we know it is in for some big changes. But marketers—being their usual, nimble selves— are already adapting. Our research shows that marketers are fully aware of how AI can help them juggle everyday challenges, supporting and enhancing their marketing efforts. And as of 2022, 31% of marketers were already using AI to improve their bottom line.
With so many everyday marketing tools integrating AI into the mix (think Notion or Canva), the days of marketers using AI without even knowing it are pretty close. So don’t worry so much about AI replacing you. Instead, worry about the other marketers using AI to level up their skills and increasing their impact. (Now that’s nightmare fuel.)
How to adopt AI in your marketing strategy
At this point, you’re probably thinking about adding some AI to your marketing strategy. Go, you!
While it’s not a magical solution that can solve all your problems, AI can give your marketing efforts that boost you’re lookin’ for. It won’t replace your entire marketing team, but it can automate tasks, improve conversion rates, and help you identify new opportunities to engage with your audience.
But before jumping in headfirst, here are some things to consider:
Evaluate your existing processes
If you’re considering adopting an AI tool, first think about how it’ll fit into your current workflows. That means deep divin’ into your audience, understanding their journey and potential pain points, and identifying areas where AI can help you create a better experience.
Let’s say you run an online clothing store. You could start by (manually) analyzing some of your existing customer data to identify patterns and trends. What are the most popular clothing items that are flyin’ off your shelves? What are the most common reasons you get for returns? What are the most asked questions by your customers?
This will help you identify how AI can best be used to improve customer experience, such as personalized clothing recommendations (you can match this top with this skirt), automated returns processing, and chatbots to answer customer inquiries.
Think about your gaps or inefficiencies
What are some of the frustrations you have with the processes of your team? Think about this in terms of actual manual labor. Think about what things could be slowing you and your team down, and decide where and when to get AI to do some heavy liftin’. It’s all about streamlining your marketing processes.
Let’s say you work for a marketing agency that specializes in social media management for small businesses. You and your team spend a heck of a lot of time manually scheduling social media posts, creating content calendars, and analyzing engagement metrics. Blegh.
You can use AI to tackle some of that manual work. Scheduling posts in advance, optimizing times for maximum engagement, and even creating content based on audience preferences. With all this work outta the way, your team could focus on other tasks that require human creativity. You’d be increasing efficiency and productivity, benefiting your clients and their social media presence—and gettin’ more business as a result.
Plan how you’ll implement new tech
Implementing any new technology into a team’s marketing processes can take lotsa time and effort. To get the most out of AI-powered tools, you’ve gotta know how to use ‘em efficiently so your team (and your customers) can get the best experience.
Imagine you’re the marketing director for an ecommerce company that sells consumer electronics. You’ve decided to implement an AI-powered chatbot on your website to handle customer inquiries and provide personalized product recommendations. Smart.
But implementing this technology into your team’s workflow means real time and effort. To get the most out of the chatbot, you’ll need to train it with accurate data, program it with relevant scripts, and integrate it seamlessly into your website. Not to mention training your team on how to use the chatbot—how to monitor conversations, escalate issues to human support, and analyze chat logs for insights.
Be sure you’ve got a plan for how you’ll implement AI tools before you pay for ’em.
Trends and the future of AI marketing
Artificial intelligence ain’t sci-fi anymore. The past few years have seen huge advances in AI tech. Crystal ball in hand, here are some trends we’re expectin’ to see in the future.
Concerns about privacy and security will increase. Despite all these great things happenin’ with AI, the trust issues are still there. Consumers are legit scared of their data being collected and used against them. That means marketers gotta start addressing privacy concerns by providing more transparency around the data they’re collecting, and using it only to the benefit of the customer. It’s also time for organizations to beef up their cybersecurity game—because hackers are starting to use AI, too . Businesses will need to take additional steps to protect their customers’ data from algorithmically-augmented outlaws.
Despite all these great things happenin’ with AI, the trust issues are still there. Consumers are legit scared of their data being collected and used against them. That means marketers gotta start addressing privacy concerns by providing more transparency around the data they’re collecting, and using it only to the benefit of the customer. It’s also time for organizations to beef up their cybersecurity game—because . Businesses will need to take additional steps to protect their customers’ data from algorithmically-augmented outlaws. Voice-enabled AI is (still) gonna change marketing. Voice-enabled AI has been the talk ‘o the town for years now. At this point, some of us talk to assistants like Siri and Google Home more than actual people. Still, this conversational AI remains under-utilized in marketing. That’s gonna change. In the not-so-distant future, marketers will need to consider speech recognition technologies in their marketing strategies. In fact, voice-recognition tech was already projected to become a key business channel in 2022. Who needs fingers when you’ve got a voice assistant?
Voice-enabled AI has been the talk ‘o the town for years now. At this point, some of us talk to assistants like Siri and Google Home more than actual people. Still, this conversational AI remains under-utilized in marketing. That’s gonna change. In the not-so-distant future, marketers will need to consider speech recognition technologies in their marketing strategies. In fact, voice-recognition tech was already projected to become a key business channel in 2022. Who needs fingers when you’ve got a voice assistant? AI will keep getting better at generating creative work. AI in marketing is getting smarter by the minute. With more marketers jumping on the AI marketing bandwagon, AI itself is learning all sorts of algorithms and refining its content like a pro. The best part? The more data it collects, the more impressive its outputs become. That means we can expect to see some seriously impressive content generated by AI—we’re talkin’ copy, images, videos, and basically any other medium you can think of.
Marketers: It’s time to join forces with AI
AI is the new hotness, and it’s shakin’ things up in the world of marketing. But don’t worry—it’s not here to steal your job. In fact, by combining your marketing expertise with the power of artificial intelligence, you can become more impactful than ever before. Marketers who adopt AI are more effective than those who don’t—because it saves ’em time, helps them with complex tasks, and boosts the results they get from their campaigns.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://unbounce.com/marketing-ai/what-is-ai-marketing/
|
[
{
"date": "2023/03/30",
"position": 86,
"query": "AI job creation vs elimination"
},
{
"date": "2023/03/30",
"position": 90,
"query": "AI labor market trends"
}
] |
The importance of AI-based skill taxonomies
|
The importance of AI-based skill taxonomies
|
https://learningpool.com
|
[
"Shannon Layton"
] |
Among other things, a skill taxonomy makes it possible to describe the skills required per job.
|
Among other things, a skill taxonomy makes it possible to describe the skills required per job.
O*Net or ESCO are well-known skill taxonomies that represent a standard and are available free of charge. However, they are based on outdated technology. On the other hand, modern AI-based approaches enable an efficient, more updated and simpler way of determining the skills per job.
AI-based competence taxonomies
Providers of AI-based skill taxonomies collect information about jobs from sources such as LinkedIn, job portals or other relevant sources. Next, so-called NLP models (linguistic data processing models) help to identify which skills can be found in which jobs. These analyses are not entirely simple, because the primary goal is to identify the skills that are of great importance for the job. Recognising the relevance of a skill (importance) and its level (professionalism) is crucial. If these analyses are carried out on a daily basis, the job-skill relations is checked daily and dynamically adjusted to market changes.
If you want to ensure the relevant skills within a company for the future, you have to rely on this market view. Thanks to the job-skill relation, potential candidates can be matched with job offers, internal candidates can be found for projects, the skill gap between a person and a targeted job can be identified and career paths between jobs with similar skills can be found.
At Learning Pool, we have developed a multilingual and unique skills taxonomy that includes job titles, industries, sectors, company names and other important attributes in addition to skills and their professionalism levels.
Click here to read the full article “The Rise of Skills Taxonomies” by David Creelman.
| 2023-03-30T00:00:00 |
https://learningpool.com/blog/the-importance-of-ai-based-skill-taxonomies
|
[
{
"date": "2023/03/30",
"position": 16,
"query": "AI skills gap"
}
] |
|
Why And How To Bridge The Skills Gap?
|
Why And How To Bridge The Skills Gap?
|
https://elearningindustry.com
|
[
"Suresh Kumar Dn",
"Satyabrata Das",
"Aranya Mukerjee",
"Seanan Heaney",
"Nikos Andriotis"
] |
Skills gap = skills required minus available skillset. Let's look at the ... Leveraging The Power Of AI To Pinpoint Skill Gaps And Address Them Head-On.
|
Importance Of Bridging The Skills Gap
Recently, a food delivery company had to close its new grocery delivery initiative due to a shortage of delivery partners. In another example, a city-based pick-and-drop service company has expanded its services to pan India. Expansion and contraction across industries are levered to the availability of human resources. Skills gaps can be a significant spoke in the wheel of business success. In this article, we will see how to address the skills gap.
What Is A Skills Gap?
The variance between the required skillset and the available capability within the organization is referred to as a skills gap.
Skills gap = skills required minus available skillset
Let’s look at the recruitment scenario, which is landscaped in duality. On the one hand, there are layoffs, and on the other hand, companies find it challenging to source qualified candidates. Some skills are becoming obsolete, while others are gaining traction. Most HR and L&D professionals feel the need for skilling, but many employees express concern over the lack of support for skill development.
These oxymorons deepen the skills chasm. What is the result of this?
The Consequence Of Skills Gaps
Life is all about growth and movement. The continuous evolution of technology has created new opportunities and rendered some skillsets redundant. Digitalization has changed the way people connect with things around them.
The fluid nature of living has had an impact on the job market. The rapidly changing skill requirements and the aforesaid dualism has created skill shortages and deviation from expectation. This skills gap has a negative impact on the country’s economy and the company’s revenue. The increasing unemployment rate is a cause of concern for everyone.
Failing to upskill the population has tremendous implications which are not so positive. These include:
Rise in the percentage of youths who are unemployed or trained
Increase of demotivated job-seeking population
Wastage of funds due to wrong or inadequate training
The surge in unemployment insurance
Loss of revenues, GDP, and tax
As per the Korn Ferry study, there will be a shortage of more than 85 million people globally by 2030. This could lead to about $8.5 trillion in unrealized annual revenues. The USA alone is expected to burn its pockets by $162 billion. Korn Ferry is a global organizational consulting firm.
One might wonder if the skills abyss affects them. They need to find out.
Skills Gap Analysis
Organizations that identify the skills gap are better positioned to address it. Skills analysis helps strategize workforce planning, boost individual learning of the employees, and provide a competitive edge to the organization.
Here are the main steps to conducting a skills gap analysis.
Company Goals
Etch out the company’s goals. In addition to the vision and the mission, the research on the market, competition, consumer, and industry would serve as a great pointer to design the business strategy.
Identify The Roles
Once the business plan is in place, companies must identify the defined goal’s roles. For example, if a food delivery business intends to venture into courier and grocery delivery, some of the roles required would be the management of the warehouse, delivery partners, logistics support, etc., to name a few.
Skill Inventory
Create a skill inventory for the roles defined.
Skillset Available
Identify the skillsets available in the organization. This can be done through continuous reviews, observations, tests, and data collected from curricular vitae about their certificates and competencies. Assess the potential of each employee beyond the current role and skillsets.
Skillset Required
Derive the skillsets required after matching the required and the available skill inventory.
Addressing The Skills Gap
Once the analysis is done, the company must close or narrow the skill chasm. There must be more job openings and qualified candidates, whether in manufacturing, media, finance, technology, etc. Organizations need to look beyond career fairs, hiring events, and other traditional hiring processes to survive the skill shortage.
Talent Hunt
The question arises whether the company has dug deep enough to identify the talent. Here are some avenues that may have skipped attention.
Employees with long careers may have varied skillsets, which equip them to take up additional tasks. Employees might be pursuing education to upgrade their skillsets. Veterans and former service members can be hired, onboarded, and retained.
In addition, organizations should be open to incorporating people with diversity. Diversity refers to differences based on race, socio-economic factors, gender, experience, disability, geographic location, and more. Diverse populations help to fill the skills gulf.
Non-Traditional Source Of Candidates
Several government learning centers and nonprofit organizations are training people in industry-based skills such as driving, coding, website creation, etc. Build synergies with these organizations.
Stay Connected With Educational Institutions
Communicate to the educational institutes what skill and proficiency they need to teach as a part of their curriculum so that it is relevant to the industry requirement. Collaborate with academic institutions, technical centers, and certificate programs to allow for a steady influx of talent.
Adopt Policy Changes
Create policies to support learning opportunities. It could be learning camps, academies, in-house training, digital learning, or incentivizing of education of the employees.
Train The Recruitment Team
Train the hiring teams to make them adept at identifying the knowledge, skills, and abilities (KSAs) of applicants so that every qualified skillset is noticed. It is also essential that the management and the recruitment teams shed their biases so that they can reach out to a broader population. This amplifies the chances of finding the required qualification.
“Governments and organizations must make talent strategy a key priority and take steps now to educate, train, and upskill their existing workforces.” – Yannick Binvel, president of Korn Ferry’s Global Industrial Markets Practice
Upskill And Reskill
Prioritize an effective and robust training program to empower the employees. The learning path could be a combination of face-to-face classes, self-guided eLearning courses, webinars, and resources comprising textbooks, PDFs, videos, and more.
The digital learning component may differ based on the skillset. Customized eLearning solutions and online Learning Management Systems help to punctuate the learning in the flow of work without disturbing the work schedule.
Addressing the skills gap will help to:
Make effective training programs
Improve employee productivity
Retain talent pool and reduce turnover
Build strong and diverse teams
Make the company future-ready
Conclusion
Investment in training your employees is an investment in the company’s future. Make your training program engaging and efficient by incorporating digital learning. We help you to analyze the skills required to make your organization competitive. This is in line with the ADDIE design model.
Leverage the services of the SmartChoice Preferred Solution Provider by Brandon Hall Group. Give an edge to your corporate training and achieve your L&D goals and objectives. Contact me or leave a comment below to learn more about our services and how we can help you.
Tesseract Learning Pvt Ltd Tesseract Learning works with global organizations improve employee performance through spectrum of digital learning solutions. Solutions include eLearning, mobile learning, Microlearning, game based learning, AR/VR, Adaptive learning amongst others. Read More
| 2023-03-30T00:00:00 |
2023/03/30
|
https://elearningindustry.com/why-and-how-to-bridge-the-skills-gap
|
[
{
"date": "2023/03/30",
"position": 26,
"query": "AI skills gap"
}
] |
Skills Gap Analysis: Definition, Importance + 5 Benefits
|
Skills Gap Analysis: Definition, Importance + 5 Benefits
|
https://www.chrmp.com
|
[] |
Analyzing skill gaps first helps identify the specific skills and knowledge required for each job. This helps identify whether the existing employees possess ...
|
In today’s rapidly evolving job market, companies face a significant challenge in sourcing skilled candidates to fill in the gaps in their workforce.
Rapid technological advancement has transformed the nature of work. Many companies now need help to keep up with the latest trends and find it challenging to source candidates with the proper set of skills that the company requires.
Here’s where a skills gap analysis comes in. Skills gap analysis can help companies identify gaps in the workforce and take proactive steps to bridge these gaps, whether through targeted training programs, recruitment strategies, or other means.
This blog will look at the definition, importance, benefits and steps to conduct a skills gap analysis.
Let’s dive right in!
What is a Skills Gap Analysis?
A skills gap analysis is a process companies use to identify skill gaps in the workforce. It aims to find out the gaps between the skills and knowledge possessed by existing employees and the skills and knowledge required to help the company achieve business goals.
The analysis attempts to identify specific skills, abilities and knowledge required for certain job roles, and areas where there might be a shortage of them and help develop strategies to bridge these gaps.
Analyzing skill gaps can prove invaluable for organizations that need to hire the right talent for their positions that help drive business success.
By identifying and addressing gaps in the workforce, the organization can improve in several key areas like job satisfaction, employee productivity and engagement while maintaining a solid foothold in the competitive job market.
What’s the Importance of a Skills Gap Analysis?
Skills gap analysis is crucial as it helps organizations identify gaps in the workforce, stay competitive in a rapidly changing job market, and enhance key areas like employee engagement, productivity, job satisfaction and reduce employee turnover rate.
Let’s discuss this in more detail.
Analyzing skill gaps first helps identify the specific skills and knowledge required for each job. This helps identify whether the existing employees possess the skills and competencies necessary for the position. Gaps can be addressed through training or coaching to allow employees acquire the required skills, hiring new employees with the skills necessary, or outsourcing tasks to external contractors or vendors.
Analyzing skill gaps also helps organizations stay ahead of the competition by keeping updated with the latest trends in the job market and ensuring employees have the necessary skills and knowledge to succeed in their roles. This also helps the company adapt to changes in the market.
In addition, companies can also improve employee engagement and reduce attrition rates. By providing employees with learning opportunities and helping them acquire new skills and knowledge, companies demonstrate a sense of commitment to their employees and support career progression and development. This, in turn, increases employee satisfaction and reduces the employee turnover rate.
To conclude, a skills gap analysis is an essential tool for organizations to identify and address gaps in their workforce and ensure business success.
6 Steps To Conduct a Skills Gap Analysis in Your Organization
Conducting a skills gap analysis can be lengthy, but you can manage it better by understanding the process clearly.
The steps to conduct a Skills Gap Analysis are:
1. Define the goals and objectives:
A clear definition of the goals and objectives of the Skills Gap Analysis is an important step to start the process.
Identifying the job roles or departments that need to be analyzed and the specific skills and knowledge required for each role is an important part of this step.
The goals and objectives of the analysis must align with the organisation’s overall strategic objectives.
Questions such as “What skills and knowledge do we need to achieve our organizational goals?” and “Which job roles are most critical to achieving these goals?” must be asked because therein lies the solution.
2. Identify the required skills and knowledge:
The next step is identifying the specific skills, knowledge, qualification, the technical, interpersonal, and cognitive skills required for each job role. This can be done by reviewing job descriptions, examining industry standards, and consulting with subject matter experts.
It must be ensured that the required skills and knowledge are up-to-date and reflect the changing needs of the organization and the industry.
3. Assess current employee skills and knowledge:
The next step is to assess employees’ current skills and knowledge in the identified job roles. This can be done through performance reviews, skills assessments, and self-assessments.
This step involves collecting data on the skills and knowledge of employees and comparing it to the required skills and knowledge identified in step two.
This step involves creating benchmarks for skills and knowledge, identifying high-performing employees and using them as a benchmark for skills and knowledge for the organization as a whole or even the
industry where the company operates.
4. Identify skills gaps:
After assessing the current skills and knowledge of employees, the next step is to identify any skills gaps that exist between the required skills for various positions and the skills possessed by employees.
This can be done by comparing the results of the skills assessment with the required skills for each job role. It is important to identify both individual and group skills gaps, as well as any trends or patterns in the data available for the analysis.
Questions such as “What are the specific skills gaps that need to be addressed?” and “Which job roles or departments have the largest skill gaps?” must be asked because they provide the answer.
5. Develop a plan to address skills gaps:
Once the skills gaps have been identified, a plan has to be developed to address them.
Training or coaching has to be provided to help employees acquire new skills, hire new employees with the required skills, or tasks have to be outsourced to external contractors or vendors.
However, the plan has to align with the overall goals and objectives of the organization and check if it is feasible within the budget and timeframe of the organization.
Next, questions such as “What specific actions do we need to take to address the skills gaps?” and “What resources do we need to implement the plan?” must be asked to find feasible solutions.
6. Implement the plan:
The final step is implementation of the plan and monitoring progress.
Providing training and development opportunities to employees, monitoring the effectiveness of the plan, and making adjustments as needed to ensure that the skills gaps are effectively addressed, and the organization is able to procure the skills ,knowledge and qualification required for the roles which were lacking in the same.
Communication of the plan to all stakeholders, including employees, managers, and executives, and to provide regular updates on the progress of the implementation of the program.
The next questions asked would be “How can we ensure that the plan is effectively implemented?” and “How can we measure the impact of the plan on employee performance and organizational goals?”
Following these steps, organizations can conduct a thorough Skills Gap Analysis and take proactive steps to address any skills gaps, thereby improving employee performance, increasing productivity, and staying competitive in a rapidly changing job scenario.
Top 5 Benefits of Conducting a Skills Gap Analysis
Below are listed the top 5 benefits of conducting a Skills Gap Analysis:
1. Helps to identify skill gaps:
Conducting a Skills Gap Analysis helps to identify the specific skill gaps that exist within an organisation.
By comparing the benchmark of required skills for each job role with the current skills possessed by employees, organizations can identify areas where training and development are needed.
This helps to ensure that employees have the skills and knowledge needed to perform their jobs effectively and meet the changing needs of the organization.
2. Improves employee performance:
After identification of skill gaps and providing targeted training and development, organizations can improve the performance and productivity of their employees which in turn is bound to affect the organizational performance as a whole.
It is obvious that employees who have the skills and knowledge needed to perform their jobs effectively are more productive and better mengaged, leading to better business outcomes.
Additionally, by providing employees with opportunities to develop new skills, organizations can help to retain top talent and attract new talent to the organization.
3. Aligns workforce with organizational goals:
Conducting a Skills Gap Analysis helps to ensure that the goals and objectives of the workforce are aligned with the goals and objectives of the organization.
By identifying the specific skills and knowledge needed to achieve organizational goals, organizations can ensure that employees are equipped with the tools they need to contribute to the success of the organization.
This ensures that the organization is well-positioned to respond to changing market conditions and stay competitive.
4. Increases efficiency and effectiveness:
By addressing skill gaps, organizations can improve the efficiency and effectiveness of their operations. Employees who have the skills and knowledge needed to perform their jobs effectively are better able to work efficiently and make sound decisions.
This can lead to cost savings and improved quality, as well as increased customer satisfaction.
5. Supports strategic decision-making:
Conducting a Skills Gap Analysis provides organizations with valuable data that can be used to support strategic decision-making.
By understanding the skills and knowledge of their workforce, organizations can make informed decisions about hiring, training, and development.
Additionally, by identifying trends and patterns in the data, organizations can gain insights into broader workforce issues and make strategic decisions that support the long-term success of the organization.
Frequently Asked Questions
1. What is the difference between skills gap analysis and training needs analysis?
Skills gap analysis and training needs analysis are similar in that they both aim to identify the gaps between the skills and knowledge that employees have and the skills and knowledge that they need to perform their jobs effectively. However, skills gap analysis is broader in scope and takes into account the strategic goals of the organization, while training needs analysis focuses specifically on identifying the training required to fill the identified gaps.
2. How often should organizations conduct a skills gap analysis?
The frequency of skills gap analysis will vary depending on the size and complexity of the organization, as well as the rate of change in the industry or market. However, as a general rule, organizations should conduct skills gap analysis on a regular basis, such as annually or bi-annually, to ensure that the workforce is equipped with the skills and knowledge needed to meet the changing needs of the organization.
3. Who should conduct a skills gap analysis?
Skills gap analysis can be conducted by various stakeholders, including HR professionals, managers, and subject matter experts. The key is to ensure that the individuals conducting the analysis have a good understanding of the job roles and the skills and knowledge required to perform those roles effectively.
4. What types of data are needed to conduct a skills gap analysis?
To conduct a skills gap analysis, organizations will need data on the skills and knowledge required for each job role, as well as data on the skills and knowledge possessed by employees. This data can be obtained through various methods, such as surveys, interviews, and assessments.
5. How can organizations address skill gaps identified through the analysis?
Organizations can address skill gaps through a variety of methods, including training and development programs, mentoring and coaching, job rotation, and hiring of new employees with the required skills and knowledge.
6. What are some common challenges in conducting a skills gap analysis?
Some common challenges in conducting a skills gap analysis include lack of access to reliable data, difficulty in determining the specific skills and knowledge required for each job role, and resistance to change from employees who may feel threatened by the identification of skill gaps. It is important to approach the analysis with a collaborative and transparent mindset to overcome these challenges.
Conclusion
To conclude, conducting a Skills Gap Analysis is an important process for any organization that wants to ensure its workforce has the skills and knowledge needed to meet the challenging needs of today’s business scape.
By identifying skill gaps, organizations can provide targeted training and development programs that improve employee performance, increase efficiency and effectiveness, and align the workforce with the strategic goals of the organization.
Some challenges in conducting a skills gap analysis could be lack of access to reliable data, difficulty in determining the specific skills and knowledge required for each job role, and resistance to change from employees who may feel threatened by the identification of skill gaps.
Organizations that approach the process with a collaborative and transparent mindset will be better positioned to address these challenges and achieve success. It is important to approach the analysis with a collaborative and transparent mindset to overcome these challenges.
Furthermore, conducting a Skills Gap Analysis supports strategic decision-making by providing valuable data and insights into the skills and knowledge of the workforce.
Finally, investing in a Skills Gap Analysis cuts down replacement costs, duplication of training and development efforts and costs and proves to be an investment in the long-term success of the organization and its workforce.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.chrmp.com/skills-gap-analysis/
|
[
{
"date": "2023/03/30",
"position": 58,
"query": "AI skills gap"
}
] |
Unpacking NIST's New AI Risk Management Framework
|
Unpacking NIST’s New AI Risk Management Framework
|
https://govciomedia.com
|
[] |
DOL is bridging the AI skills gap through partnerships and upskilling to ensure future AI workforce readiness. 10m watch. The Department of Labor's Deputy ...
|
Video
Video Artificial Intelligence AI Foundations Driving Government Efficiency Federal agencies are modernizing systems, managing risk and building trust to scale responsible AI and drive government efficiency. 40m watch
Artificial Intelligence
Defense Navy Memo Maps Tech Priorities for the Future Fight Acting CTO’s memo outlines critical investment areas, from AI and quantum to cyber and space, as part of an accelerated modernization push. 5m read
Artificial Intelligence
Data DHA CDAO Spearheads Master Data Catalog to Boost Transparency Jesus Caban plans to boost DHA's data maturity through a new master data catalog, governance frameworks and inventory of tech tools. 5m read
Artificial Intelligence
Defense Trump Orders Spark Government-Wide Acquisition Overhaul As Trump pushes for a faster, simpler procurement system, agencies are leveraging AI and adapting strategies to meet new requirements. 5m read
Video
Video Artificial Intelligence Modernization Strategies to Enable Energy Innovation Lawrence Berkeley National Lab and Maximus experts explore the modernization strategies driving digital transformation and operational resilience within the energy sector. 33m watch
| 2023-03-30T00:00:00 |
2023/03/30
|
https://govciomedia.com/unpacking-nists-new-ai-risk-management-framework/
|
[
{
"date": "2023/03/30",
"position": 98,
"query": "AI skills gap"
}
] |
Generative AI Organizational Readiness Report
|
Avanade AI Readiness Report
|
https://www.avanade.com
|
[] |
63. %. Agree employees will need new skills for generative AI. Support is ... AI tools like Microsoft Copilot by addressing AI readiness gaps. Open the ...
|
New research from Avanade explores the readiness of organizations – leaders and their people – to introduce, adopt and scale generative AI tools such as Microsoft Copilot. We surveyed 3,000+ people in 10 countries across a range of industries and job levels to gain practical insights to enable leaders to take actions that realize value from generative AI faster.
| 2023-03-30T00:00:00 |
https://www.avanade.com/en/insights/generative-ai-readiness-report
|
[
{
"date": "2023/03/30",
"position": 99,
"query": "AI skills gap"
},
{
"date": "2023/03/30",
"position": 52,
"query": "artificial intelligence business leaders"
}
] |
|
Digital Upskilling: Preparing Your Business for the Future
|
Digital Upskilling: Preparing Your Business for the Future
|
https://www.institutedata.com
|
[
"Institute Of Data"
] |
... AI and software ... Digital upskilling is a sensitive endeavour that should be undertaken after carefully analysing a company's needs and skills gaps.
|
Data Skills, Industry training Digital Upskilling: Preparing Your Business for the Future
Stay Informed With Our Weekly Newsletter Receive crucial updates on the ever-evolving landscape of technology and innovation. By clicking 'Sign Up', I acknowledge that my information will be used in accordance with the Institute of Data's Privacy Policy. Subscribe
Digital upskilling in 2023 is no longer just an exciting idea of the digital age – it is an absolute requirement for every business that aims to profit in this fast-changing technological era. Instructors need to ensure that every employee in a company is up to date with critical skills and any changes in popular choices.
While upskilling and reskilling have always been a part of every company’s learning and development programs, most people believe that digital upskilling only applies to specific technical and IT departments in a few companies and a few industries. However, this is far from the actual situation. In fact, this concept has taken over every aspect of a business, from its general workforce and strategy to its core operating systems.
In this guide, we will learn how digital transformation helps businesses grow in a digital world and improves employee loyalty by empowering your workforce. This guide will also walk you through the best methods to implement upskilling in your company!
Why is digital upskilling important for businesses?
Digital upskilling can help businesses identify their workforce’s shortcomings and provide the right training opportunities to remedy them. The important thing is to understand different digital upskilling examples, and while many people define them as basic coding skills, they are a lot more than that.
While the specific skill set you aim for will vary from employee to employee, anything related to technology that can improve a company’s processes falls under the umbrella definition of digital skills.
There are numerous benefits that a business can experience when they pursue the right digital upskilling strategy, including productivity benefits and a more skilled workforce. However, the key benefit is usually an increase in productivity and profits once a culture of learning and trust is ingrained into the existing workforce.
The need to upskill is more significant than ever for modern companies as new developments in AI and software, like robotic process automation tools, become central to a company’s survival and growth. To understand the impact of big data analytics on modern technology, check out our guide on the topic. If you wish to stay ahead of the competition, you must differentiate between fads and actual developments and implement any changes that can give you the edge.
Companies could start by upskilling employees on the importance of CRMs or social media marketing before moving on to programming and digital marketing skills. It is also essential to ensure that the company’s employees are comfortable with any new software you are implementing and receive adequate training before they are expected to handle the tool.
Here is a detailed look into some benefits businesses are likely to experience after implementing digital upskilling for their employees:
Increase in employee retention:
Good employees are nearly as essential to business operations as a good client in most cases, and most business owners know that retaining good talent can be very challenging. This is especially true for high-performing individuals looking to grow their skills and professional experiences, which is impossible in a dead-end routine.
Digital and general upskilling can keep the flavour of learning challenges alive for such individuals, leading to increased retention levels and greater productivity.
Improved productivity for remote workers:
While we will tackle the productivity benefits of digital upskilling for in-office employees in the next section, let’s start by looking at how these learning initiatives can help remote workers. Remote working lifestyles are increasingly becoming a popular choice for many professionals, courtesy of the advancements in technical solutions, especially post Covid-19.
However, it is possible to feel isolated when working alone for long hours. It can also be tricky when you constantly manage new tools that could be virtual interruptions to a workflow.
When managers address the learning gaps these employees feel by limiting the platforms for primary communication and sticking to advanced CRMs like Hubspot that are an all-in-one solution, employees can collaborate better regardless of the physical distance.
It is essential to include remote employees in L&D programs while respecting their professional and personal boundaries, which can be a challenge for some managers and instructors.
Improved productivity in-office:
Digital upskilling can help employees feel confident about their duties, leading to growth, innovation, and improved organisational productivity rates. In addition, once upskilled, employees may feel more confident about taking up new job duties, making delegation easier.
While we have already discussed the improvement in retention rates, it is also important to note that better-skilled employees are more valuable assets for a business with more impactful attitudes to problem-solving.
To cultivate a healthy workplace culture, it is essential to make sure your employees feel that their growth is valued and their contributions are appreciated, and digital upskilling can aid with that!
How can digital upskilling empower employees?
Digital upskilling helps employees to transform their personal and professional growth as they reach a level of comfort with their digital transformation. Some benefits include improved problem-solving and job confidence.
This form of upskilling could be based on learning new skills or improving upon older skills. However, it applies to any skills and knowledge that will enhance a business’s performance and address its digital skill gaps.
While we explored the benefits of digital upskilling for companies in the earlier section, let’s look into the direct benefits that employees experience.
Job confidence:
If an employee is not confident about handling a job responsibility, it is more likely that they will fumble when put to the task. Digital upskilling can strengthen a worker’s soft skills helping them cultivate confidence and a positive attitude.
Having confidence in your abilities can benefit your personal and professional life, while your positive attitude can empower you to produce higher-quality work. In addition, by developing your confidence in the workplace, you can improve your reputation in your industry, making it easier to achieve your career goals.
Improved problem analysis:
Tapping into your problem-solving skills is essential to achieve optimal growth in your field. This includes identifying the issue after careful analysis and developing impactful solutions. This skill is essential when you are handling technology and data.
When employees learn to utilise new tools and software solutions as part of their digital upskilling training, they can strengthen their problem-solving skills using the best available tools.
What are the best ways to implement digital upskilling?
Digital upskilling is a sensitive endeavour that should be undertaken after carefully analysing a company’s needs and skills gaps. It is essential to understand that it is not just a one-off process. Evaluating specific programs’ success, increasing employee engagement, and considering if skills are being implemented in-office is crucial.
Successful digital upskilling courses can lead to a high ROI, and here are some ways you can implement it in your own business and eliminate any skill gap:
Learning and Development Programs:
Suppose you are looking for a comprehensive solution to your digital upskilling plans. In that case, an L&D program is the best way to go, as it incorporates the needs of employees who wish to study in-person or online from another location.
Before you can start delivering training content to your employees with this medium, evaluating your workforce’s digital proficiency is essential to develop the right plan that handles pain points.
It is also essential to take a systematic approach where you understand that every individual in the workforce has a specific skill set. Understanding how each employee stands out and is held back will also require a lot of analysis, but you will end up with a stronger idea of the combined skillset. For instance, this is a look into the 13 common hurdles faced by beginner data scientists!
The best thing about L&D programs is that they are ideal for large-scale projects where you need to work with a bigger workforce. Teaching multiple skills and tracking performance in these scenarios is much easier and more efficient. These programs can be created on tools like iSpring Suite, and they can utilise seminars, workshops, and lectures and might include a few secondary online courses.
Job Rotation:
If you believe your employees will appreciate a change and challenge in the work environment to learn better, you can try digital upskilling with job rotation (also known as cross-training). This will have your workers performing new roles and utilising new skill sets within the business.
It is an excellent route to follow if you wish to promote an employee or put them through an advanced L&D program, as it gives them the technical skills and knowledge required for better performance in challenging roles. It can also reduce training costs and improve workforce retention when you promote it within your company.
It is essential to ensure that trainers or senior employees supervise employees during this phase. Doing so maximises the learning opportunities from this approach and limits any potential issues.
Digital training for remote workers:
Remote digital upskilling programs need to be implemented with a lot of care and consideration regarding remote employees’ personal and professional challenges. However, implementing these changes has several benefits, including increased productivity and employee loyalty.
It is also excellent to have in-office and remote employees collaborating on a learning program, as it helps bridge the internal distance within an organisation.
It would be best to consider certain factors to ensure a successful remote learning program, including inclusion, continuous learning, and student-teacher interaction. It is also essential to evaluate whether the learned skills are being effectively applied. This requires the use of several assessment techniques and skill reviews.
Mentorships:
Another way to approach in-office training that can be worked into a more extensive L&D program later is to get your employees to perform new tasks and pick on the skills they can improve.
This will require close supervision, and a diligent mentor can help new students scale their skillset much better. In addition, supervised guidance and direct contact between a junior employee and a senior colleague will result in faster and more effective skill transfer.
This method often teaches practical skills best learned through repetition, as students can improve their work with each consecutive try. However, it is also essential to note that while mentorships are perfect as a standalone strategy, they also work well as part of a training program.
Conclusion
Digital upskilling is an undeniable necessity for modern businesses, and it can be applied to one targeted individual or the entire workforce, depending on the situation. While focusing on hard digital skills is essential, it is also vital to consider soft skills for a better overall result.
If you’re interested in upskilling into the tech industry consider booking a free career consultation with an expert member of our team.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.institutedata.com/blog/digital-upskilling-preparing-your-business-for-the-future/
|
[
{
"date": "2023/03/30",
"position": 100,
"query": "AI skills gap"
}
] |
Launching your AI/Data Career in 2023 - Phase AI
|
Data Career in 2023
|
https://phaseai.com
|
[] |
This webinar covers recent labour market trends and what they mean to students and researchers launching their data/AI careers.
|
Launching your AI/Data Career in 2023
Phase AI and Vector Institute on March 30, 2023
This webinar was recorded as a part of a webinar series in collaboration with the Vector Institute.
The 2023 job market can seem ...suboptimal... based on recent news headlines and fear of an upcoming recession. Fortunately, many employers are actively investing in data and AI capabilities.
This webinar covers recent labour market trends and what they mean to students and researchers launching their data/AI careers. Learn which employers are hiring, the skillsets with increasing demand, and how to stand out. We review tactics and advice around personal branding, how to invest in and use side projects to your advantage, and how to use non-technical skills and experiences to improve your chances of landing your dream job.
Finally, we also get advice from hiring managers across the Vector Institute’s network to understand what they are looking for and how to successfully apply as a candidate.
| 2023-03-30T00:00:00 |
https://phaseai.com/resources/vi-career-in-2023
|
[
{
"date": "2023/03/30",
"position": 68,
"query": "AI labor market trends"
}
] |
|
AI in Agriculture Market Size, Share | CAGR of 24.5%
|
AI in Agriculture Market
|
https://market.us
|
[] |
... Market Assessment, Competition Scenario, Trends, and Forecast 2023-2032 ... AI in Agriculture markets face several key obstacles, including an acute labor ...
|
Report Overview
The global AI In Agriculture market size is expected to be worth around USD 10.2 billion by 2032 from USD 1.5 billion in 2023, growing at a CAGR of 24.5% during the forecast period from 2022 to 2032.
Artificial Intelligence (AI) in agriculture refers to the application of AI technologies in various agricultural processes to improve efficiency, productivity, and sustainability. It involves the use of advanced algorithms, machine learning, computer vision, and data analytics to analyze vast amounts of agricultural data and make informed decisions.
The AI in agriculture market is witnessing significant growth as the industry recognizes the potential of AI technologies to address challenges such as climate change, population growth, and the need for sustainable food production. AI is being utilized in various aspects of agriculture, including crop monitoring and management, precision farming, agricultural robotics, predictive analytics, and yield optimization.
According to the United Nations (UN), the global population will reach 9.8 billion by 2050. As a result, artificial intelligence must be brought into agriculture to keep up with an ever-increasing demand. With limited arable land available and increased food safety requirements driving green revolution initiatives utilizing AI technology, the Internet of Things, and big data. AI-enabled apps have already found applications within agriculture, such as predictive analysis, recommendation engines, pest identification/detection, and soil monitoring.
Artificial intelligence solutions such as drones, robots, and ground-based wireless sensors are becoming more widely utilized in the agricultural industry. For example, in November 2017, Microsoft joined forces with the International Crop Research Institute of the Semi-Arid Tropics to launch an AI Sowing App. In addition, Nature Fresh Farms is another U.S. tech company using artificial intelligence technology to analyze plant data at scale and produce accurate yield and harvest forecasts; their algorithm even predicts when blossoms will ripen.
Automation in agriculture helps allocate resources such as fertilizers and water, determine ideal dates for crop sowing, detect weeds, and drive demand for artificial intelligence solutions. It can even suggest how many seeds should be planted based on long-term weather data, production data, and commodity pricing predictions. Many tech companies and start-ups are capitalizing on the multiple advantages of AI-based applications to expand their IoT-enabled devices that could be utilized for large-scale deployments of AI applications in agriculture.
Key Takeaways
The global Artificial Intelligence (AI) in Agriculture market size was estimated at USD 1.5 billion in 2023 and it is expected to surpass around USD 10.2 billion by 2032, growing at a CAGR of 24.5% from 2023 to 2033.
in 2023 and it is expected to surpass around by 2032, growing at a CAGR of from 2023 to 2033. North America leads in artificial intelligence (AI) agricultural technologies, followed by Europe and Asia Pacific.
leads in artificial intelligence (AI) agricultural technologies, followed by Europe and Asia Pacific. Asia Pacific is currently the fastest-growing market for AI in Agriculture due to the region’s rapidly increasing population and food demand.
is currently the fastest-growing market for AI in Agriculture due to the region’s rapidly increasing population and food demand. AI in Agriculture markets face several key obstacles, including an acute labor shortage, high costs of AI technologies and a need for more data.
Demand: Meeting rising population growth and food demand by increasing crop yields.
Key Trends: Farmers and agribusinesses are increasingly turning to AI technologies, and AI solutions for a range of agricultural tasks have become more widely adopted.
Drivers: The need to improve crop yields and lower costs are two key considerations when making decisions regarding crop management practices.
Restraints: Lack of skilled labor and need for additional data collection systems are major obstacles to growth.
Opportunities: The growing popularity of cloud-based AI solutions
Challenges: The high cost of AI technologies
Most prominent Artificial Intelligence (AI) in Agriculture industry players: Raven Industries Inc., Farmers Edge Inc., Deere & Company, A.A.A Taranis Visual Ltd., Gamaya SA, AGCO Corporation, Bayer AG, IBM Corporation, Ag Leader Technology, Trimble Inc., and Other Key Players.
By Technology Analysis
The market can be segmented on technology into machine learning, deep learning, predictive analytics, and computer vision. Many agribusiness companies utilize predictive analytics to deploy artificial intelligence; AgEagle Aerial Systems Inc., Microsoft, and Granular have all developed AI-enabled platforms and solutions for agriculture and farming that utilize this predictive analytics technology. Pesticide control, crop disease infestations, weather tracking, irrigation, and drainage management are significant challenges facing agriculture today. Farmers can address these issues through predictive analysis using image processing and neural networks.
Predictive analytics has enabled drone-enabled agriculture solutions, with AgEagle Aerial Systems Inc. as one example. This company utilizes artificial intelligence to boost crop yield through drone technology. Drone analytical solutions offer drone analytical solutions for crop area identification and management.
Predictive analytics has become more efficient in agricultural applications, so this segment is expected to experience a steady CAGR during the forecast period. Machine learning is being applied to sensor data in farm management systems to transform them into real artificial intelligence systems – leading to more significant production improvements. Machine learning and deep learning segments are expected to expand concurrently.
By Application Analysis
The market can be divided into four categories based on application: precision farming, drone analytics, and agriculture robots. Over the forecast period, precision farming is expected to hold a significant market share. Precision farming is an AI-enabled application proliferating in agriculture; it helps farmers reduce costs and maximize their resources.
AI is widely used in precision farming to collect, interpret and analyze digital data. For example, GPS-equipped combine harvesters use artificial intelligence to track harvest yields for field variability analysis – including differences in soil makeup or water. This analysis and prediction allow farmers to adjust fertilizers or pesticides accordingly.
AI can even control agriculture robots through artificial intelligence combined with field sensors and data analytics. As a result, they’re effective for many applications, such as harvesting crops efficiently as they weed or hoe themselves. As more businesses adopt artificial intelligence technologies along with advances in robotics technology, the segment of agriculture robots is proliferating.
By Component Analysis
The market can be divided into service, hardware, and software segments. It is anticipated that software will hold a majority share in this space. Microsoft, IBM, Deere & Company, and Deere and Company all provide AI-based solutions to the agricultural industry. This type of software helps increase crop productivity through prediction-based analysis and computer vision tools.
The software industry is witnessing an uptick in using predictive analytics-based tools. Popular programs include the Watson Decision Platform from IBM Corporation, the AI Sowing App of Microsoft, and See and Spray pesticide and insecticide distribution systems from Deere and Company. These artificial intelligence programs assist farmers with selecting when to plant crops; spotting crop diseases; tracking yield, and calculating land, fertilizers, and water requirements. In addition, AI technology has many potential uses, such as precision farming or drone analysis – further fueling demand for software within this segment of the agricultural software market.
Key Market Segments
By Technology
Machine Learning & Deep Learning
Predictive Analytics
Computer Vision
By Application
Precision Farming
Drone Analytics
Agriculture Robots
Livestock Monitoring
Labor Management
Agriculture Robots
Other Applications
By Component
Hardware
Software
Service
AI-as-a-Service
Drivers
Growth Was Driven by IoT
Daily, vast amounts of data are produced in structured and unstructured formats. This includes historical weather patterns, soil reports, new research, and drone images. All this can be sensed by IOT solutions to provide strong perceptions that boost yield. Two technologies commonly used for intelligent data fusion are Remote Sensing (proximity sensing) and Remote Sensing (remote sensing), which allows soil analysis based on beneath-surface soil at a specific place. For example, Rowbot, a hardware solution that combines data collection software and robotics, has already created the ideal fertilizer for growing corn.
Image-Based Insight Generation
Today, high-altitude farming is one of the hottest topics in agriculture. Drone-based images provide invaluable field analysis, crop observation, and scanning data. Drone data, IOT, and computer vision technology can all be combined to enable farmers to act swiftly. Aerialtronics has implemented Visual Recognition APIs and the IBM Watson IoT Platform on their commercial drones so they can perform image analysis in real time. Computer vision technology is also increasingly employed for crop readiness identification, disease detection, field management, and more – helping farmers stay ahead of their operations.
Health Monitoring of Crops
Remote sensing technologies, hyperspectral imaging, and 3d laser scanning can be utilized to generate crop metrics across thousands of acres. This technology has the potential to revolutionize how farmers view farmlands. Furthermore, this monitoring can be done throughout a crop’s entire lifecycle to detect anomalies and generate reports accordingly.
Restraints
Lack of Workers
Due to a shortage of skilled workers, aging farmers, and declining interest among young people in farming as a career path, there has been an alarming decrease in global workforce numbers. As governments and private institutions strive to automate agriculture operations using artificial intelligence technology, this trend towards decreasing labor has caused alarmingly rapid increases.
Increased Adoption of Agricultural Drones
Drones equipped with thermal, multispectral, or hyperspectral sensors can identify areas that need their irrigation schedules adjusted. These sensors use the heat signature of crops to calculate the vegetation index – an AI-based indicator of health. Chemical spraying, while not widespread, is still a necessary part of industrial agriculture. But with intelligent farming drones, it has become possible to minimize their environmental impact; UAVs (Unmanned Aerial Vehicles) measure distances with great precision just like sprayers do; this results in fewer chemicals entering groundwater sources.
Challenges
Lack of Understanding with High Tech Machine Learning Solutions
AI in agriculture has many applications, yet there is a lack of awareness regarding high-tech machine-learning solutions in farms worldwide. Adjusting farming to external factors such as weather patterns, soil conditions, and pest presence requires significant financial investment. At the same time, AI systems need vast data to train machines and make accurate predictions.
Trends
A significant trend in agriculture is the increasing use of robotics. Farming practices have become more sophisticated and modernized due to technology’s adoption. A rise in agricultural robot usage is likely due to an expanding global population, a shortage of farm workers, and automation within agriculture.
Agriculture stakeholders are focusing on increasing production productivity through modern farming practices and reducing carbon footprints, which has driven the demand for robots. Robotic companies provide products that can be applied in unstructured and dynamic agricultural settings. Since their inception, robots have been used in industrial production; however, technological advances have extended their capabilities into many sectors, such as transport, healthcare, and agriculture. Furthermore, robots play an increasingly significant role in alleviating food shortages; milking farms also use robotic systems.
An EU foresight study predicts that by 2025, approximately 50% of European dairy farms will be automated. Fullwood Paco already implemented a batch milking system in May 2022 with six robots capable of simultaneously milking 150-300 cows. Fullwood Paco can easily adjust according to their cows’ changing needs and production demands.
Smart sensors are becoming increasingly commonplace in these practices, signaling a significant trend in the market. Precision agriculture practices have seen an uptick in using sensors, enabling farmers to maximize yields with minimal resources such as seeds, fertilizers, and water. Monitoring crop growth at the microscale level helps farmers conserve valuable and expensive resources while reducing environmental impact.
Regional Analysis
North America accounted for more than 39% of the global market in 2022 due to its dominant industrial automation industry and increasing adoption of artificial intelligence solutions. In addition, North America boasts a higher purchasing power, continued investments in automation, significant investments in IoT technology, and government initiatives toward in-house AI equipment manufacturing. Furthermore, many agricultural technology providers such as Deere & Company, Microsoft, Granular Inc., and The Climate Corporation are present on this front.
Over the forecast period, Asia Pacific is expected to witness the highest compound annual growth rate due to the increasing use of artificial intelligence technology in agriculture. China and India are two emerging economies that have already adopted artificial intelligence solutions such as remote monitoring technology or predictive analysis for food industry needs. In addition, Agribusiness companies are encouraged to utilize AI-enabled services and solutions due to the growing demand for smart cities.
Note: Actual Numbers Might Vary In The Final Report
Key Regions and Countries Covered in this Report:
North America The US Canada
Europe Germany France The UK Spain Italy Russia Netherland Rest of Europe
APAC China Japan South Korea India Australia New Zealand Singapore Thailand Vietnam Rest of APAC
Latin America Brazil Mexico Rest of Latin America
Middle East & Africa South Africa Saudi Arabia UAE Rest of MEA
Key Players Analysis
Vendors offering artificial intelligence solutions to agriculture focus on growing their customer base to gain a competitive edge in the market. They often implement strategic initiatives like mergers and acquisitions and partnerships to do this. For example, Deere & Company recently joined Cultivating New Frontiers in Agriculture (CNFA) on May 26th to implement mechanization within their agriculture industry. Climate Corporation followed suit in October 2018 by joining forces with three agriculture tech firms: SoilOptix and AgCon Aerial Corp.; this collaboration allows farmers new capabilities while expanding Climate FieldView’s digital platform further.
With many local and regional players’ presence, the artificial intelligence (AI) market in agriculture is fragmented. As a result, market players are subject to intense competition from top players, particularly those with strong brand recognition and high distribution networks. As a result, companies have gained various expansion strategies, such as partnerships and product launches, to stay on top of the market. The following are some of the major players in global artificial intelligence (AI) in the agriculture industry.
Top Market Leaders
Raven Industries Inc.
Farmers Edge Inc.
Deere & Company
A.A Taranis Visual Ltd.
Gamaya SA
AGCO Corporation
Bayer AG
IBM Corporation
Ag Leader Technology
Trimble Inc.
Recent Development
June 2023, Carbon Robotics: Their LaserWeederTM was recognized as the Best AI-based Solution for Agriculture at the AI Breakthrough Awards. It’s the market’s first laser weeding robot, removing over one billion weeds. This innovation uses AI, lasers, computer vision, and robotics for precise weed management.
Their LaserWeederTM was recognized as the Best AI-based Solution for Agriculture at the AI Breakthrough Awards. It’s the market’s first laser weeding robot, removing over one billion weeds. This innovation uses AI, lasers, computer vision, and robotics for precise weed management. November 2022, DJI Agriculture: They launched the Mavic 3 Multispectral, equipped with a multispectral imaging system. This tool captures crop growth quickly, aiming for more efficient crop production. It helps reduce costs and increase income for farmers globally by catering to precision agriculture and environmental monitoring needs.
They launched the Mavic 3 Multispectral, equipped with a multispectral imaging system. This tool captures crop growth quickly, aiming for more efficient crop production. It helps reduce costs and increase income for farmers globally by catering to precision agriculture and environmental monitoring needs. October 2022, Microsoft: Microsoft Research made FarmVibes.AI open-sourced. This set of technologies and machine-learning algorithms focuses on sustainable agriculture. FarmVibes.AI works by integrating various data types, including weather, satellite, and drone imagery, to enhance agricultural practices.
Report Scope
| 2023-03-30T00:00:00 |
https://market.us/report/artificial-intelligence-ai-in-agriculture-market/
|
[
{
"date": "2023/03/30",
"position": 77,
"query": "AI labor market trends"
}
] |
|
Let's Look at LLMs: Understanding Data Flows and Risks ...
|
Let’s Look at LLMs: Understanding Data Flows and Risks in the Workplace
|
https://fpf.org
|
[
"Stephanie Wong"
] |
Ethical considerations are especially important when the AI is used in an outcome-determinative way, such as in hiring or healthcare. In some cases, such uses ...
|
Stephanie Wong
Over the last few months, we have seen generative AI systems and Large Language Models (LLMs), like OpenAI’s ChatGPT, Google Bard, Stable Diffusion, and Dall-E, send shockwaves throughout society. Companies are racing to bake AI features into existing products and roll out new services. Many Americans are worrying whether generative AI and LLMs are going to replace them in the workforce, and teachers are downloading ChatGPT specific software to ensure their students are not plagiarizing homework assignments. Some have called for a pause to AI development. But organizations and individuals are adopting LLMs more quickly, and the trend shows no signs of abating.
Organizations have quickly seen employees using generative AI and LLM tools in their workstreams. Few workers are waiting for permission to use the technologies to speed up complex tasks, get tailored answers to full-sentence questions, or draft content like marketing emails. However, the growing use of LLMs creates risks, such as privacy concerns, content inaccuracies, and potential discrimination. Use of LLMs can also be deemed inappropriate in certain contexts and create discontent–students recently criticized their university for lacking empathy when the school used ChatGPT to draft an email notice about a nearby mass shooting.
As organizations navigate these uncertainties, they are asking whether, or when, employees should be permitted to use LLMs for their work activities. Many organizations are establishing or considering internal policies and guidelines for when employees should be encouraged, permitted, discouraged, or prohibited from using such tools. As organizations create new policies, they should be aware that:
1. When workers share personal information with LLMs, it can create legal obligations for data protection and privacy, including regulatory compliance;
2. Many organizations will need to establish norms for originality and ownership, including when it is appropriate for employees to use LLMs or other generative AI systems to create novel content;
3. Organizations need to carefully evaluate any uses for potential bias, discrimination, and misinformation while also considering other potential ethical concerns.
What are LLMs?
In late 2022, OpenAI released its AI chatbot, ChatGPT, which has now undergone several versions and is available as ChatGPT-4. ChatGPT is both a generative AI and a large language model (LLM), which are two distinct but similar AI terms. A “generative AI system” is a type of AI that has been trained on data so that it can produce or generate content similar to what it has been trained on, such as new text, images, video, music, and audio. For example, a growing number of AI tools are available for generating artwork and some even create videos based on text. A “large language model” (LLM) is a type of generative AI that generates text. LLMs can perform a variety of language-related tasks, including translations, text summarization, question-answering, sentiment analysis, and more. They can also generate text that mimics human writing and speech, which have been used in various applications such as chatbots and virtual assistants. To produce human-like responses, LLMs are trained on vast quantities of text data. In ChatGPT’s case, it was trained on vast amounts of data from the internet.
#1. Legal Obligations.
a. Data protection and privacy.
In general, users of generative AI and LLMs should avoid inputting personal or sensitive information into ChatGPT or similar AI tools. ChatGPT uses the data that is input by many users to generate individual responses and further train its model for future responses to all users. If an employee inputs data that contains confidential information, such as trade secrets, medical records, or financial data, then that data may be at risk, especially if there is a data breach of the AI system that results in authorized access or disclosure. Similarly, if an individual puts personally identifiable information or sensitive data into the model, and that data is not properly protected, it could also be improperly accessed or used by unauthorized individuals.
Furthermore, personal information disclosed to LLMs could be used in additional ways that violate the expectations of the people to whom the information relates. For example, ChatGPT also continues to use and analyze this data. Thus, the sensitive information that an employee inputs about a customer or patient could potentially be revealed to another user if they pose a similar question or prompt. Further, every engagement with ChatGPT has a unique identifier–there is a login trail of people who are using it. Therefore, an individual’s use of ChatGPT is not truly anonymous, raising questions about the retention of sensitive data by OpenAI.
b. Regulatory Compliance.
LLMs are subject to the same regulatory and compliance frameworks as other AI technologies, but as LLMs become more common, they can raise novel questions of how such tools can be used in ways that comply with the General Data Protection Regulation (GDPR) and other regulations. Since ChatGPT processes user data to generate responses, OpenAI or the entities relying on ChatGPT for their own purposes may be considered data controllers under the GDPR, which means they should secure a lawful ground to process users’ personal data (such as users’ consent) and users must be informed about the controller’s ChatGPT-powered data processing activities.
OpenAI and companies relying on ChatGPT’s capabilities also need to consider how overarching GDPR principles like data minimization and fairness curtail certain data processing activities, including decisions made on the basis of algorithmic recommendations. Additionally, under the GDPR, data subjects have certain rights regarding their personal data, including the right to access, rectify, and delete their data. But can users really exercise these rights in practice? In regard to data erasure, OpenAI offers users the ability to delete their accounts, but OpenAI has stated that conversations with ChatGPT can be used for AI training. This presents challenges because while it seems that the original input can be deleted, the input can be used to shape and overall improve ChatGPT. Removing a user’s complete digital footprint and its effects on ChatGPT may be unfeasible and risks offending the GDPR’s “right to be forgotten.” Moreover, the repurposing of prompts to train OpenAI’s algorithm may raise issues relating to the GDPR’s purpose limitation principle, as well as the applicable lawful ground for service improvement after a recent restrictive binding decision from the European Data Protection Board (EDPB) concerning the lawfulness of processing for service improvement purposes.
There are questions about the future regulation of ChatGPT and similar technologies under the European Union (EU) Artificial Intelligence Act (AI Act), which is currently under review by the European Parliament. Proposed in 2021, the regulation is designed to ban certain AI uses such as social scoring, manipulation and some instances of facial recognition. However, recent developments regarding LLMs and related AI services have caused the European Parliament to reassess “high-risk” use cases and how to implement proper safeguards that were not previously accounted for in today’s rapidly developing tech environment. EU lawmakers have proposed different ways of regulating general purpose and generative AI systems during their discussions on the text of the AI Act. The consensus at the EU Council is that the European Commission should regulate such systems at a later stage via so-called ‘implementing acts’; at the European Parliament, lawmakers may include such systems in the AI Act’s high-risk list, therefore subjecting them to strict conformity assessment procedures before they are placed on the market.
#2. Ownership and Originality.
Depending on context, organizations should determine when it is appropriate or ethical for individuals or organizations to use, or take credit for, work generated by LLMs. In education, for example, some teachers are adapting their approaches (e.g., from written to oral presentations) to avoid plagiarism. Schools have even banned ChatGPT due to concerns that the technology will cause students to take shortcuts when writing or forgo doing their own research.
In many cases, these issues raise novel questions about legal rights and liability. For example, software developers have used ChatGPT to write and improve existing code. Yet LLMs, including ChatGPT, have been shown to regularly produce inaccurate content. If an employee uses the code generated by ChatGPT in a product that interacts with the public, organizations may have liability if something goes wrong. In a related issue, if employees input copyrighted, patented, or confidential information (e.g. trade secrets), into a generative AI tool, the resulting output could infringe on intellectual property rights or breach confidentiality obligations.
#3. Ethical Concerns, Bias, Discrimination, and Misinformation.
Finally, organizations must carefully consider all uses of AI, including LLMs, for possible discriminatory outcomes and effects. In general, LLMs reflect the underlying data that they are trained on, which is often incomplete, biased, or outdated. For example, AI training datasets often exclude information from marginalized and minority communities, who have historically had less access to technologies such as the internet, or had fewer opportunities to have their writings, songs, or culture digitized. ChatGPT was trained on internet data, and as a result is likely to reflect and perpetuate societal biases that exist in websites, online books, and articles.
For example, a Berkeley professor asked ChatGPT to create code to determine which air travelers pose a safety risk. ChatGPT assigned a higher “risk score” to travelers who were Syrian, Iraqi, Afghan, or North Korean. A predictive algorithm used for medical decision-making was biased against black patients because it was trained on data that reflected historical bias. Even though the deployers of the algorithm excluded race as a metric when running the system, the algorithm still perpetuated bias against black patients because it took economic factors and healthcare costs into account.
Furthermore, it is clear that generative AI and LLMs can be potentially disruptive and change the way we consume and create information. ChatGPT has demonstrated its ability to write news articles, essays, and television scripts. Supplied with a prompt loaded with disinformation or misinformation, LLMs can produce convincing content that could mislead even thoughtful readers. Audiences are at risk of consuming vast amounts of misinformation if they are not able to fact-check the information given to them or know that content was generated by an LLM or AI. Organizations that use LLMs should be aware that LLMs can generate inaccurate or misleading information, even when prompts are not intended to mislead. Vigilance is required when organizations ask LLMs or generative AI to give clients, customers, or users information solely based on the LLM.
To address ethical concerns, bias, discrimination, and misinformation, organizations have a responsibility to scrutinize their use of generative AI and LLMs. Ethical considerations are incredibly important and progress is being made on transparency in generative AI models, though complete solutions remain elusive. Ethical considerations are especially important when the AI is used in an outcome-determinative way, such as in hiring or healthcare. In some cases, such uses will risk running afoul of employment or other civil rights laws. Organizations must determine the different contexts that this type of AI use can be particularly susceptible to bias and discrimination, and will want to avoid those situations. Organizations should engage and talk to the communities that are most affected in these cases and get stakeholder input when drafting internal policies.
Conclusion
Recent developments concerning LLMs and generative AI demonstrate substantial technological advancements while also presenting many uncertainties. There are many unanswered questions and yet to be discovered risks that may result from use of AI in the workplace. However, these harms can be mitigated if organizations take the time to address these issues internally and develop best practices. We encourage organizations to be inclusive and cross-collaborative when engaging in these conversations with lawyers, engineers, customers, and the public.
| 2023-03-30T00:00:00 |
https://fpf.org/blog/lets-look-at-llms-understanding-data-flows-and-risks-in-the-workplace/
|
[
{
"date": "2023/03/30",
"position": 66,
"query": "AI regulation employment"
}
] |
|
Generative AI and the Public Sector
|
Generative AI and the Public Sector
|
https://wwps.microsoft.com
|
[] |
Generative AI can also help create a more efficient, productive, and rewarding work environment for public sector employees. Governments should carefully ...
|
Generative AI and the Public Sector Angie Heise, Corporate Vice President, Microsoft Worldwide Public Sector
Artificial Intelligence (AI) is changing the game for businesses and organizations of all types. New advanced natural language processing capabilities around generative AI and large language models have captured the world’s imagination. These capabilities have the potential to revolutionize both the way governments interact with citizens and how the public workforce addresses society’s challenges. It is imperative that public sector organizations begin to think about how to leverage and responsibly employ generative AI for government and education purposes.
Advances in generative AI demand similar progress in our consideration of the implications for society, ensuring that the applications of this powerful technology are responsible, ethical, broad-based in their benefits, and deployed in ways that provide value for society. The building blocks have already been laid for the principles and frameworks that govern responsible AI and will continue to evolve along with the technology.
Responsible AI standards can ensure that deployments value fairness, privacy and security, reliability and safety, inclusiveness, and accountability. But the public sector cannot remain frozen as AI changes the world around us. Communities deserve the more effective and efficient services that AI can bring to society, and public sector workers deserve the most effective and efficient tools to carry out their mission. Forward-thinking leaders will seek to engage these technologies in ways beneficial to their populace, and through engagement, learn to understand and harness their power for societal good.
There are moments in the evolution of technology that impact society and the economy deeply – disruptive advancements in innovation whose effects are not fully felt until years after they debut. We have seen industries changed irreversibly by the internet, smartphones, and cloud, just to name a few. Although it is hardly a new technology topic, recent advancements have catapulted AI into the firmament of game changing, disruptive technologies, and it is worth taking a step back to contemplate what the long-term implications for the public sector may be in years to come.
How Artificial Intelligence could support public sector organizations
Although advanced AI has a host of implications for the public sector, here are some relevant areas of impact for consideration:
Citizen Services: Generative AI can help governments and public sector organizations provide enhanced service experiences that make government more accessible and less time-consuming by acting as an “Information Assistant” – answering frequently asked questions, recommending services based on inputs, and even handling simple transactions.
Many governments have already experimented with chatbots to help answer simple questions about COVID vaccinations, provide support during tax time, and offer answers to common inquiries. Generative AI helps chatbots handle more open domain questions over more sophisticated and complex materials, including rapid responses to a broader range of questions at anytime from anywhere, increasing accessibility for citizens while simultaneously increasing government efficiency and reducing administrative burdens.
Citizens can even provide a narrative of their current circumstances and discover service options they previously did not know existed. These tools also free up public sector workers to focus on strategic projects instead of being tied down to mundane, repetitive functions such as responding to common questions.
Generative AI can help governments and public sector organizations provide enhanced service experiences that make government more accessible and less time-consuming by acting as an “Information Assistant” – answering frequently asked questions, recommending services based on inputs, and even handling simple transactions. Many governments have already experimented with chatbots to help answer simple questions about COVID vaccinations, provide support during tax time, and offer answers to common inquiries. Generative AI helps chatbots handle more open domain questions over more sophisticated and complex materials, including rapid responses to a broader range of questions at anytime from anywhere, increasing accessibility for citizens while simultaneously increasing government efficiency and reducing administrative burdens. Citizens can even provide a narrative of their current circumstances and discover service options they previously did not know existed. These tools also free up public sector workers to focus on strategic projects instead of being tied down to mundane, repetitive functions such as responding to common questions. Internal Efficiency: Government can be complex even for government employees! Providing public sector workers with the capacity to intuitively search and interact via chat with intranets and public sector materials in an automated fashion eases onboarding of new employees, increases efficiency between silos and departments, and minimizes administrative burdens. This capability lets public sector staff focus on their mission priorities, reducing burnout and allowing them to do more with less.
Government can be complex even for government employees! Providing public sector workers with the capacity to intuitively search and interact via chat with intranets and public sector materials in an automated fashion eases onboarding of new employees, increases efficiency between silos and departments, and minimizes administrative burdens. This capability lets public sector staff focus on their mission priorities, reducing burnout and allowing them to do more with less. Deep Data: Large language models can tackle the intersection between vast troves of data which may have been previously analyzed separately and manually. Simple prompts to the AI can yield both typical and unexpected connections between topics and domains that can help to spur the analytic process.
Insightful and succinct summaries of vast amounts of media coverage or public feedback can be generated in seconds. Generative AI helps to objectively challenge conventional wisdom – raising new angles, questions, or counterarguments that may have been implicitly screened by the bias of the author. This approach ultimately yields a stronger and more comprehensive output.
Large language models can tackle the intersection between vast troves of data which may have been previously analyzed separately and manually. Simple prompts to the AI can yield both typical and unexpected connections between topics and domains that can help to spur the analytic process. Insightful and succinct summaries of vast amounts of media coverage or public feedback can be generated in seconds. Generative AI helps to objectively challenge conventional wisdom – raising new angles, questions, or counterarguments that may have been implicitly screened by the bias of the author. This approach ultimately yields a stronger and more comprehensive output. Creative Aid: No more writer’s block! Generative AI can provide a helpful first draft of abstracts, outlines, speeches, simple correspondence, memos, frequently asked questions, whitepapers, and citizen guides. While official communications should always require a human in the loop to verify accuracy, apply human “voice,” and ensure that the information is complete and not misleading, generative AI as a creative writing aid can accelerate the process dramatically and help light the creative spark while reducing time-to-completion for common writing tasks.
By improving citizen services, increasing efficiency, better managing and analyzing data, and serving as a creative aid, generative AI can help to create a more effective, inclusive, and responsive government.
Generative AI can also help create a more efficient, productive, and rewarding work environment for public sector employees. Governments should carefully consider the implications of using AI in their operations and take appropriate measures to ensure that the technology is used ethically and responsibly. Now is the time for public sector organizations to begin leveraging and adopting generative AI capabilities, and they can and should do so from a position of engagement and experimentation.
Responsible AI in Public Sector
Artificial Intelligence (AI) has the potential to transform the public sector from improving healthcare and education to enhancing public safety and transportation. The growing interest in generative AI is clear. The availability of Azure OpenAI Service as a commercial offering has served as an accelerator to the consideration of public sector AI use cases.
However, with this ‘great power comes great responsibility’, and it is essential that AI is developed and deployed responsibly. Microsoft has taken a principled role in this area with the development of comprehensive AI responsibility policies and tools.
The responsible use of AI is, of course, a topic which public sector organizations around the world have actively addressed in recent years. Through leading discussions, developing approaches and strategies, and implementing these in their operations, the use of AI to responsibly deliver better and more inclusive public services is on the rise.
At Microsoft, we are committed to making sure AI systems are developed responsibly and in a way that is worthy of people’s trust. We drive this commitment according to six key principles which align closely with public sector priorities:
Fairness: AI systems should be designed to treat all individuals fairly, without bias or discrimination.
AI systems should be designed to treat all individuals fairly, without bias or discrimination. Reliability and safety: AI systems should be reliable and safe, with built-in mechanisms to prevent errors and minimize harm.
AI systems should be reliable and safe, with built-in mechanisms to prevent errors and minimize harm. Accountability: The creators of AI tools and the developers who leverage them should be accountable for their systems.
The creators of AI tools and the developers who leverage them should be accountable for their systems. Privacy and security: AI systems should respect individuals’ privacy and data security.
AI systems should respect individuals’ privacy and data security. Inclusiveness: AI systems should be designed to be accessible and usable by everyone, including individuals with disabilities.
AI systems should be designed to be accessible and usable by everyone, including individuals with disabilities. Transparency: AI systems should be transparent and explainable, with clear documentation of their functionality and decision-making processes.
These principles can be used by public sector organizations to evaluate AI systems and processes in use or under consideration. Within Microsoft, this responsibility is propagated by a centralized Office of Responsible AI, which sets AI governance policies for the entire company, advises our senior leadership team on AI issues, enables engineering and compliance teams across the company to build according to responsible AI principles, and ensures that as a corporation we are continuing to examine and improve our ethical stance as new capabilities and challenges arise. In June 2022, we published our internal Microsoft Responsible AI Standards for product development to share what we’ve learned so far in the form of concrete and actionable guidelines. We believe that industry, academia, civil society, and government need to collaborate to advance the state-of-the-art and learn from one another.
Public sector organizations should develop and be governed by responsible AI strategies, and these strategies should incorporate principles, practices, tools, and governance to enable those across the organization to assess, adopt, and manage AI.
This may involve:
Developing new or adopt existing policies and guidelines.
Providing training to staff to ensure they are aware of the considerations associated with AI.
Ensuring data used to train AI models is representative and assessed for bias.
Establish governance bodies to subject sensitive use cases to particularly high scrutiny and use tooling and telemetry to ensure that they are functioning as intended and not causing unintended harm.
Ensuring accountability for both the development and operations of AI capabilities and AI-enabled systems.
Staff, stakeholders, and citizens can provide feedback that helps to improve individual AI workloads and the respective responsible AI strategy.
Once potential risks are well understood and carefully managed, the public sector can realize the promise of AI. Forward-looking leaders will ensure that their commitment to responsible AI is not an afterthought but is baked into their organization’s innovation pipeline. This allows the public sector to harness the power of AI in a way that improves the services provided and benefits society as a whole.
AI Public Sector Vision and Disruption
There are moments in the evolution of technology that impact society and the economy deeply – disruptive advancements in innovation whose effects are not fully felt until years after they debut. We have seen industries changed irreversibly by the internet, smartphones, and cloud, just to name a few. Although it is hardly a new technology topic, recent advancements have catapulted AI into the firmament of game changing, disruptive technologies, and it is worth taking a step back to contemplate what the long-term implications for the public sector may be in years to come.
At the simplest level, generative AI will be a massive force multiplier for overworked government staff. Imagine social workers who can now be in contact far more frequently with their caseload using a mix of human interactions and those augmented by virtual assistants. Imagine parents and children able to access academic support and tutoring at the frequency and intensity they require without obstacles around identifying, affording, or accessing the providers of that support. Especially in the rapidly graying societies of the developed world, imagine aging populations who can interact with AI assistants designed to keep them active and engaged, optimized to combat the harmful effects of isolation. Public sector call center employees will be free to do case work once a generative AI interface can handle transactional front-line calls of all varieties. The transformative possibilities are varied and exciting.
Good government runs on high-quality interaction. Governments hire and train the best public workforce they can find to deliver excellent services, and that will never change. Yet, public sector budgets are perpetually under pressure, and the limited size of the public sector workforce is an inherent cap on the breadth and depth of services government can provide, and the speed at which they can respond to citizens’ needs. AI allows governments to radically increase capacity without dramatic new expenditures. These AI assistants will never replace their public servant practitioners, but can give them a copilot, augmenting their efforts at low cost and with high impact.
The broad span of government also makes it inherently complex to navigate, especially for citizens who only interact with public services on a sporadic basis. AI can help citizens and businesses understand and plot a course through the dense thicket of government laws and regulations, and promises to create predictive, anticipatory government services, proactively reaching out to potential beneficiaries, and identifying immediate opportunities for constituents having vaulted the bureaucratic hurdles in advance. This is a complete inversion of our delivery model for public good, with benefits automatically notifying potential recipients, instead of forcing citizens to become bureaucratic experts to even learn about the services to which they are entitled.
Another notable long-term effect for the public sector is the leap forward in accessibility AI provides. Integrated AI universal translators provide access to information independent of language preference, allowing populations all over the world to access a vast sea of knowledge in their mother tongue. But this is just the beginning. Already the public sector is experimenting with using natural language – written or spoken – to access government information and citizen services, with image and voice capabilities following quickly behind. Although the tech industry tries hard to make interfaces flexible, intuitive, and operational across a variety of devices, legacy interfaces by their nature still become a blocker to some members of society accessing needed services. Rapid, universal, knowledgeable, life-like, helpful conversation replaces interfaces. Natural interaction completely disintermediates the technology and becomes a holistic means for accessible government capabilities. For societies, language barriers become an obsolete notion, and for the public sector, a transformative capability emerges.
An additional important dynamic is the gravity these AI discoveries create between the public sector and the private industry. Public sector organizations are accustomed to keeping industry at arm’s length, pursuing separate infrastructures with dedicated instances and segregated data. However, AI thrives on broad diversity, and large language models specifically are hampered by segregation. Fencing a training set within a municipal, provincial, national, or regional boundary undermines the signature features of the model, significantly restricting its core functionality, and delivering a weaker model. This is compounded by the challenges inherent in replicating the enormous resource backbone required for training these models. Finding a way to leverage shared infrastructure for these models becomes a social imperative, as private replications of these efforts may represent an irresponsible devotion of financial and energy resources. These dynamics create a strong incentive for the private sector to provide AI models in a way that the public sector can consume compliantly, and an equally strong incentive for the public sector to find compliant ways to consume them. Democratizing access to advanced AI capabilities is the next step in Microsoft’s continuing journey to empower every person on the planet to achieve more.
AI technologies have already evolved to heretofore unseen maturity and prevalence, and these are early days. Bing’s chat interface for search, Viva Sales suggested responses, GitHub Copilot’s ease of code generation, Teams’ automated meeting summaries, and Microsoft 365 Copilot’s varied array of productivity accelerators all have broad applicability both inside and outside the public sector today. But our imagination should not be limited by these early paces in the AI marathon. It behooves us now to dream about the long-term transformative effect the AI revolution will have on the way government interacts with its citizens, and to start to build those dreams for the benefit of society.
To find out more:
About the Center of Expertise Microsoft’s Public Sector Center of Expertise brings together thought leadership and research relating to digital transformation in the public sector. The Center of Expertise highlights the efforts and success stories of public servants around the globe, while fostering a community of decision makers with a variety of resources from podcasts and webinars to white papers and new research. Join us as we discover and share the learnings and achievements of public sector communities. Questions or suggestions?
Related posts Episode 47: Preparing tax operations for new technologies On this episode, host Olivia Neal meets Prof. Dennis Weber and Dr. Dennis Post. They share insights from the CPT research project (cashless, platform-based and technology-driven) on the impacts and opportunities for tax operations of emerging technologies, such as cryptocurrencies, blockchain, and artificial intelligence. Read more on Episode 47
Episode 48: Technology Trends and Decision Advantage in Defense On this episode, guest host AT Ball speaks to Retired Vice Admiral Ann E. Rondeau, President of the Naval Postgraduate School. Rondeau offers an inside look into how defense organizations can adopt digital tools and adapt with emerging technology. Read more on Episode 48
| 2023-03-30T00:00:00 |
https://wwps.microsoft.com/blog/ai-public-sector
|
[
{
"date": "2023/03/30",
"position": 76,
"query": "AI regulation employment"
},
{
"date": "2023/03/30",
"position": 4,
"query": "government AI workforce policy"
}
] |
|
Policies
|
Vector Institute for Artificial Intelligence
|
https://vectorinstitute.ai
|
[] |
Government · Current Partners · Insights. Insights. Insights · Vector Insights ... Drug And Alcohol Free Workplace Policy · Employee Privacy And Confidentiality ...
|
Country
Please select the country you are located in Afghanistan Albania Algeria American Samoa Andorra Angola Anguilla Antarctica Antigua and Barbuda Argentina Armenia Aruba Australia Austria Azerbaijan Bahamas Bahrain Bangladesh Barbados Belarus Belgium Belize Benin Bermuda Bhutan Bolivia Bonaire, Sint Eustatius and Saba Bosnia and Herzegovina Botswana Bouvet Island Brazil British Indian Ocean Territory Brunei Darussalam Bulgaria Burkina Faso Burundi Cabo Verde Cambodia Cameroon Canada Cayman Islands Central African Republic Chad Chile China Christmas Island Cocos Islands Colombia Comoros Congo Congo, Democratic Republic of the Cook Islands Costa Rica Croatia Cuba Curaçao Cyprus Czechia Côte d'Ivoire Denmark Djibouti Dominica Dominican Republic Ecuador Egypt El Salvador Equatorial Guinea Eritrea Estonia Eswatini Ethiopia Falkland Islands Faroe Islands Fiji Finland France French Guiana French Polynesia French Southern Territories Gabon Gambia Georgia Germany Ghana Gibraltar Greece Greenland Grenada Guadeloupe Guam Guatemala Guernsey Guinea Guinea-Bissau Guyana Haiti Heard Island and McDonald Islands Holy See Honduras Hong Kong Hungary Iceland India Indonesia Iran Iraq Ireland Isle of Man Israel Italy Jamaica Japan Jersey Jordan Kazakhstan Kenya Kiribati Korea, Democratic People's Republic of Korea, Republic of Kuwait Kyrgyzstan Lao People's Democratic Republic Latvia Lebanon Lesotho Liberia Libya Liechtenstein Lithuania Luxembourg Macao Madagascar Malawi Malaysia Maldives Mali Malta Marshall Islands Martinique Mauritania Mauritius Mayotte Mexico Micronesia Moldova Monaco Mongolia Montenegro Montserrat Morocco Mozambique Myanmar Namibia Nauru Nepal Netherlands New Caledonia New Zealand Nicaragua Niger Nigeria Niue Norfolk Island North Macedonia Northern Mariana Islands Norway Oman Pakistan Palau Palestine, State of Panama Papua New Guinea Paraguay Peru Philippines Pitcairn Poland Portugal Puerto Rico Qatar Romania Russian Federation Rwanda Réunion Saint Barthélemy Saint Helena, Ascension and Tristan da Cunha Saint Kitts and Nevis Saint Lucia Saint Martin Saint Pierre and Miquelon Saint Vincent and the Grenadines Samoa San Marino Sao Tome and Principe Saudi Arabia Senegal Serbia Seychelles Sierra Leone Singapore Sint Maarten Slovakia Slovenia Solomon Islands Somalia South Africa South Georgia and the South Sandwich Islands South Sudan Spain Sri Lanka Sudan Suriname Svalbard and Jan Mayen Sweden Switzerland Syria Arab Republic Taiwan Tajikistan Tanzania, the United Republic of Thailand Timor-Leste Togo Tokelau Tonga Trinidad and Tobago Tunisia Turkmenistan Turks and Caicos Islands Tuvalu Türkiye US Minor Outlying Islands Uganda Ukraine United Arab Emirates United Kingdom United States Uruguay Uzbekistan Vanuatu Venezuela Viet Nam Virgin Islands, British Virgin Islands, U.S. Wallis and Futuna Western Sahara Yemen Zambia Zimbabwe Åland Islands
| 2023-03-30T00:00:00 |
https://vectorinstitute.ai/policies/
|
[
{
"date": "2023/03/30",
"position": 58,
"query": "government AI workforce policy"
}
] |
|
Programs
|
Vector Institute for Artificial Intelligence
|
https://vectorinstitute.ai
|
[] |
Vector's AI programs, courses, and projects in machine learning & deep learning are designed to boost AI literacy ... Build skills for the workforce.
|
Equip and scale your business with AI
Advance AI literacy, fluency and access the talent necessary to build and innovate with AI.
Build skills for the workforce
Access to jobs, acquire and advance in-demand skills, and network.
| 2023-03-30T00:00:00 |
https://vectorinstitute.ai/programs/
|
[
{
"date": "2023/03/30",
"position": 75,
"query": "machine learning workforce"
}
] |
|
Workers at The Guild to Join IATSE Local 906
|
Workers at The Guild to Join IATSE Local 906
|
https://iatse.net
|
[
"Iatse Communications"
] |
Its provincial mandate is to engage new, emerging, and professional artists, creative industries, and community organizations. IATSE Local 906, which has ...
|
CHARLOTTETOWN, PE – After achieving overwhelming support, the workers at The Guild signed authorization cards to join IATSE Local 906 in Charlottetown. The authorization cards were filed with the Prince Edward Island Labour Relations Board on September 23rd, 2022. Based on the high level of support for representation indicated on the cards, the province’s labour legislation dictates that a vote is not required. The Board’s decision, issued on March 23, awarded Local 906 sole bargaining rights for all stage employees.
The Guild is a not-for-profit registered charity, featuring an intimate 110-seat black box performance space. The venue, located in downtown Charlottetown, presents and produces first-class music, theatre, dance, and comedy throughout the year. Its provincial mandate is to engage new, emerging, and professional artists, creative industries, and community organizations.
IATSE Local 906, which has represented Charlottetown stagehands for decades, is excited to welcome these new members into the union.
For more information or to arrange an interview, please contact:
Krista Hurdon, IATSE International Representative
[email protected]
| 2023-03-31T00:00:00 |
2023/03/31
|
https://iatse.net/workers-at-the-guild-to-join-iatse-local-906/
|
[
{
"date": "2023/03/30",
"position": 28,
"query": "AI labor union"
}
] |
Inclusive AI governance
|
Inclusive AI governance
|
https://www.adalovelaceinstitute.org
|
[
"Christine Galvagna"
] |
Philippe Saint-Aubin finds that national trade unions are interested in standards that impact workers more tangibly, such as those dealing with health and ...
|
Executive summary
This discussion paper contributes to the conversation around European Union (EU) AI standards by clarifying the role technical standards will play in the AI governance framework created by the EU’s Artificial Intelligence Act (the ‘AI Act’), and how this may diverge from the expectations of EU policymakers.
In the AI Act, EU policymakers appear to rely on technical standards to provide the detailed guidance necessary for compliance with the Act’s requirements for fundamental rights protections. However, standards development bodies seem to lack the expertise and legitimacy to make decisions about interpreting human rights law and other policy goals.
This misalignment is important because it has the potential to leave fundamental rights and other public interests unprotected.
The research presented in this paper is not conclusive; it is based on the limited, publicly available information about the development of technical standards for the AI Act, as well as feedback from a small number of experts.
However, this information and feedback point to several policy strategies that may be helpful and necessary for the successful implementation of the AI Act. This paper can therefore inform the interinstitutional negotiations (‘trilogues’) on the AI Act and help the European Commission explore these policy strategies.
One approach is to boost civil society participation in the standardisation process, which would improve the diversity of viewpoints and representation of public interests. However, since this is unlikely to provide the political and legal guidance needed to interpret essential requirements, institutional innovations are also proposed.
This discussion paper may also help policymakers outside the EU to understand the feasibility of implementing AI policy through technical standards when developing their own AI regulations. For similar reasons, civil society organisations considering their positions on AI policy proposals may find it informative.
This paper begins by exploring the role of standards in the AI Act and whether the use of standards to implement the Act’s essential requirements creates a regulatory gap in terms of the protection of fundamental rights. It goes on to explore the role of civil society organisations in addressing that gap, as well as other institutional innovations that might improve democratic control over essential requirements.
This is followed by conclusions and recommendations for adapting the EU’s standardisation policy to the goals of the AI Act.
Information about this topic was gathered through legislative and policy analysis, as well as interviews with experts involved in standards development for the AI Act and civil society organisations with expertise relevant to the AI Act. A detailed description of the methodology appears below.
Recommendations and open questions for EU policymakers
Our analysis finds that EU standardisation policy and the AI Act create a regulatory gap. Lawmakers expect that technical standards will clarify and implement the Act’s essential requirements. However, neither the legislative text, nor the technical standards implementing the legislation, are likely to answer the challenging legal and political questions raised by these essential requirements.
Although the European Commission’s standardisation request to Joint Technical Committee 21 (JTC-21) says that adequate fundamental rights expertise and other public interests must be represented in the standards-setting process, most experts identified prohibitive barriers to meaningful civil society participation. These barriers include, but are not limited to: the time commitment, the opacity and complexity of the standardisation process and the dominance of industry voices in that process.
These findings suggest that EU policymakers should explore institutional innovations to fill the regulatory gap, as well as strategies to boost civil society participation.
This paper explores three strategies for EU policymakers to expand civil society participation in JTC-21:
Amend the Regulation on European Standardisation to broaden the categories of Annex III organisations eligible for funding and mandated participation, increasing funding for organisations’ participation in line with this.
to broaden the categories of Annex III organisations eligible for funding and mandated participation, increasing funding for organisations’ participation in line with this. Fund more individuals from civil society organisations with the Commission’s specialised StandICT grants, which provide funding for European standardisation experts to participate in standards development, including for participation in national delegations.
with the Commission’s specialised StandICT grants, which provide funding for European standardisation experts to participate in standards development, including for participation in national delegations. Create or fund a central hub to support civil society participation. This would institutionalise activities already carried out by organisations such as the European Trade Union Confederation (ETUC) and the European Consumer Voice in Standardisation (ANEC) that aim to facilitate the contribution of subject-matter experts to standards-setting processes.
The European Commission should also consider institutional innovations to improve democratic control over essential requirements. These include the creation of:
Common specifications: The Commission could leverage its right to develop common specifications, which would address the safety and fundamental rights concerns that are not captured by the technical standards that implement EU legislation (known as ‘harmonised standards’).
The Commission could leverage its right to develop common specifications, which would address the safety and fundamental rights concerns that are not captured by the technical standards that implement EU legislation (known as ‘harmonised standards’). A benchmarking institute: The proposed AI benchmarking institute could take up the questions that JTC-21 avoids or answers inadequately, complementing JTC-21’s procedure- and documentation-oriented standards with more substantive standards.
Further questions
As originally conceived, the EU’s New Legislative Framework (NLF) ensures political decisions remain within EU institutions and decisions made within European Standards Organisations (ESOs) are ‘purely technical’.[1]
The Commission’s Explanatory Memorandum implies this is true of the AI Act, describing harmonised standards as ‘precise technical solutions’[2] for designing AI that complies with essential requirements. Yet, the AI Act effectively delegates political decisions to ESOs. This scenario is unlikely to ensure fundamental rights protections and related policy goals are realised.
This research therefore raises a broader question about the AI Act and the NLF – what role do EU institutions expect standards to play in AI governance?
Before voting on the AI Act, EU policymakers should ask the following questions:
How far is the EU delegating political power to private entities?
Which private entities are being empowered?
Are amendments necessary to safeguard public interests?
These questions will be of particular importance for parliamentarians voting on the AI Act and other institutional players during the ‘trilogue’ negotiations.
There may be a better solution that avoids relying on European standards at all. This path prompts bigger questions:
Is a new political theory of AI governance necessary and, if so, what should it be?
How could a governance framework be designed to effectively protect fundamental rights and better safeguard the public interest from conflicting corporate interests?
How can it balance the incorporation of technical expertise with effective democratic control?
We hope this research will generate discussion among EU policymakers, civil society organisations and standards bodies, about how to expand civil society participation within standards development for the AI Act. For EU policymakers in particular, there are broader questions to consider around the role of standards in AI governance alongside this. Detailed analysis and next steps for policymakers can be found in the chapter on ‘How to fill the regulatory gap’.
Introduction
The Artificial Intelligence Act (AI Act)[3] represents the European Union’s (EU’s) proposed framework to regulate artificial intelligence broadly, beyond specific areas like medical devices. The European Commission’s proposal is designed to achieve several overarching goals: the protection of EU values and citizens’ fundamental rights, health and safety; fostering an innovative and globally competitive AI market; and setting global legal standards and norms.[4]
Fundamental rights protections are particularly prominent in the AI Act. In addition to contributing to the Commission’s ‘ultimate aim’ of ensuring AI ‘increas[es] human well-being’, the Commission expects strong fundamental rights protections to promote uptake and growth of the AI market by fostering public trust in AI.[5]
Much of the legislation outlines substantive rules for the protection of fundamental rights and other public interests, along with requirements for demonstrating compliance with these substantive rules. These rules apply to AI identified in the legislation as ‘high-risk’, meaning it poses a significant risk to fundamental rights, health or safety.[6]
However, the requirements for high-risk systems, known as essential requirements, are phrased in highly general and vague terms in the legislative text of the AI Act. For example, a biometric identification system must feature an ‘appropriate level of accuracy’ to mitigate risks to fundamental rights.[7]
Ambiguous instructions for software design can ‘conflict deeply with [. . .] [a] computer scientist’s mindset’,[8] which relies on precision and clarity. This may make it difficult for AI providers – people or entities who develop AI or have AI developed for marketing or use under their name or trademark – to interpret and operationalise essential requirements, resulting in insufficient protections for fundamental rights and other public interests.[9]
It appears that the Commission intends for standards development bodies to clarify essential requirements by operationalising them in technical standards for use by developers.[10] As in some other product safety legislation, the AI Act empowers the European Commission to request the development of technical standards by private standards development bodies to facilitate compliance with essential requirements.
This is seemingly based on the assumption that standards development bodies are equipped to grapple with questions about human rights and other public interests implicated by the AI Act.
However, standards development bodies typically rely on employees of large technology companies for their outputs and see minimal participation by civil society organisations and other stakeholders.[11] This means they are unlikely to benefit from the legal and policy expertise relevant to the AI Act’s essential requirements.
This situation also creates the possibility that decisions will be made in companies’ best interests, even when they conflict with the public interest.
If neither the legislative text of the AI Act nor standards clarify how to comply with the AI Act’s essential requirements for fundamental rights and other public interests, AI designers may not implement them effectively, leaving the public unprotected.
Whether this is the case is unclear. Little information about the development of standards for the AI Act is publicly available. AI is also a relatively new area in standards development, which makes it difficult to trace the impacts of AI standards on individuals and society, or to understand how AI experts approach these issues in standards development.
What are standards? A standard is a document that ‘describes the best way of doing something. It could be about making a product, managing a process, delivering a service or supplying materials – standards cover a huge range of activities’.[12] A standard ‘provides rules, guidelines or characteristics for activities or for their results, aimed at achieving the optimum degree of order in a given context. It can take many forms. Apart from product standards, other examples include: test methods, codes of practice, guideline standards and management systems standards’.[13] Companies can access and license these documents through standards development bodies, which are intended for industry-wide use. For example, electronics companies have standardised the design of electric power plugs and sockets within entire countries and regions, enabling one to use a device manufactured by one company after plugging it into a socket manufactured by another.
What is clear from research in other areas of standards development is that standards can create significant sociopolitical impacts, including fundamental rights impacts, and can be highly contested for political and economic reasons by different stakeholders.[14]
If standards are to play a significant role in the EU’s new approach to AI governance, research is needed about AI standards to assess the AI Act’s suitability. Several questions remain unanswered:
Whether the AI Act creates a regulatory gap for the protection of fundamental rights and other public interests. Will providers of AI systems find it difficult or impossible to comply with these requirements, given the ambiguity of the legislative text and the apparent lack of authoritative guidance from technical standards bodies? If there is a regulatory gap, is civil society participation in standardisation helpful or even necessary to fill it? Civil society organisations with expertise in human rights law and other policy areas may be able to provide the non-technical expertise necessary to implement the AI Act’s essential requirements in technical standards. They may also help to ensure the public interest is not disregarded in the pursuit of commercial interests. Assuming there is a regulatory gap for the protection of fundamental rights and other public interests, and that civil society participation can fill this gap, how can policymakers enhance the effective participation of civil society in the development of standards for the AI Act? Few civil society organisations are able to participate in standards development and those that do find it difficult to influence the process. Policymakers may be able to provide them with additional resources and legislative support.
Sources of information
Several types of information can shed light on these questions. This research used legislative analysis and document review, as well as interviews with civil society organisations and participants in standards development.
To understand whether a regulatory gap exists, the AI Act’s text was analysed in conjunction with documentation related to other elements of the European standardisation system. Based on their experience, those involved in standards development are best placed to understand whether and how civil society organisations can provide missing legal and policy expertise in standards development for the AI Act.
Interviews with experts (i.e., interviewees) involved in the development of standards for the AI Act, as well as experts with experience in standards development more generally, helped to answer these questions. Interviewees were mainly experts who are part of working groups of Joint Technical Committee 21 (JTC-21), which is responsible for developing standards to implement the AI Act. JTC-21 is a technical committee created by two of the three European Standards Organisations (ESOs): the European Committee for Standardization (CEN) and the European Committee for Electrotechnical Standardization (CENELEC), jointly referred to as CEN-CENELEC.
JTC-21 working group experts include both representatives of civil society organisations and technologists from industry and academia. Most experts are employees of companies, acting as delegates of the national members of CEN-CENELEC to JTC-21.
Civil society organisations shared insight into the barriers to and facilitators of their participation in standards development. Interviews, workshops and polls – with representatives of organisations both with and without experience in standards development – provided guidance on the resources, policies and norms that can promote or undermine their effective participation.
A major limitation to this research was the small number of interviewees and workshop participants. The names of JTC-21 experts are generally not publicly available, which made it difficult to identify potential interviewees. In the civil society workshop, few participants felt confident contributing actively due to a lack of familiarity with European standardisation and AI.
For more information about interviewees and workshop participants, and the methods used in this research, see the ‘Methodology’ chapter below.
Does the AI Act create a regulatory gap?
The AI Act’s fundamental rights and other public interest protections may be ineffective, due to the discretion the legislative text apparently affords industry in their interpretation.
Modelled on the New Legislative Framework (NLF), the AI Act is designed in a way that assumes standards development bodies will develop the crucial details of high-level rules for the protection of fundamental rights and other policy goals. In the absence of standards, those decisions generally fall to individual companies.
In theory, the NLF restricts political and legal decisions to EU institutions and allocates technical questions about the implementation of legislation to standards development bodies.
In practice, the legislation leaves open many questions about how to operationalise fundamental rights protections and other policy goals, which leaves highly political questions to standards development bodies or companies that generally lack the expertise and incentive to implement them effectively.
What is the New Legislative Framework?
Like other EU legislation regulating certain technologies, such as boats and explosives, the AI Act is modelled on the NLF. The European Commission and Parliament have published several detailed descriptions of the logic behind the NLF and how it works.[15]
NLF legislation features essential requirements, which ‘define the results to be attained, or the hazards to be dealt with, [without] specify[ing] the technical solutions for doing so’.[16] The European Commission requests the development of technical standards, known as harmonised standards, by European Standards Organisations (ESOs) to operationalise essential requirements, providing the ‘precise technical solution’[17] to achieve the desired result.
Harmonised standards help companies to comply with essential requirements by operationalising policy language in a way technologists can understand. Alternatively, a provider can develop their own technical solution ‘in accordance with general engineering or scientific knowledge laid down in engineering and scientific literature’,[18] or by using other technical standards.
While voluntary, the NLF incentivises the use of harmonised standards by offering additional legal certainty, known as a presumption of conformity. This means a Market Surveillance Authority must begin with an assumption that any product designed in line with a harmonised standard complies with the relevant essential requirements, making it more challenging to punish a provider for non-compliance. Though they do not completely shield a manufacturer from liability for failure to meet essential requirements, harmonised standards offer authoritative guidance for satisfying essential requirements that are approved by the European Commission.[19] The Commission creates a presumption of conformity by citing a potential harmonised standard in the Official Journal of the European Union.[20]
This regulatory framework was developed as an alternative to including technical specifications in legislation, as the EU’s legislative process was too slow to meet industry needs.[21]
However, EU institutions consider it imperative to draft NLF laws in a way that ensures all political decisions remain with them, and only technical decisions are made by ESOs. [22]
What do ideal essential requirements look like?
EU institutions explain that they maintain the boundary between political and purely technical decisions by defining essential requirements precisely in legislation.[23] Failure to define essential requirements precisely and preclude misinterpretation by ESOs would risk ‘delegat[ing] political powers to the ESOs and their members’,[24] which EU institutions aim to avoid.
For example, it is the European Parliament’s responsibility to define the maximum permissible level of exposure to a hazard in legislation.[25]
Another element of the NLF that helps to minimise ambiguity is that essential requirements typically set health and safety standards for physical products with limited ranges of use.[26] For example, an essential requirement in an NLF law regulating watercraft specifies maximum decibel levels for noise emissions.[27]
Although there is little general information about how the Commission determines whether a harmonised standard satisfies essential requirements, this determination is apparently based on whether the standard or design reflects the ‘state of the art’.[28] According to the Commission, the ‘assessment of whether requirements have been met or not [is] based on the state of technical know-how at the moment the product is placed on the market’.[29]
What is the role of civil society organisations in standards development?
The Regulation on European Standardisation, which underpins the NLF, requires ESOs to include civil society organisations representing certain societal stakeholders in the development of harmonised standards.[30] This helps to ensure that the interests of people and groups affected by standards are taken into account during their development.
Annex III of the Regulation lists the categories of stakeholder groups that ESOs must consult in the standardisation process. So-called ‘Annex III organisations’ include those representing consumer rights, workers’ rights, environmental protection and small and medium enterprises (SMEs).[31] The Regulation on European Standardisation also empowers the European Commission to fund their participation.[32] A recital justifies this funding and mandatory participation by describing civil society participation as ‘necessary’[33] for the safety and wellbeing of EU citizens, given the broad impact standards can have on society.
Why the AI Act does not conform to the New Legislative Framework
While the AI Act is structured as an NLF law, it diverges from EU institutions’ characterisations of the NLF in several consequential ways.
Essential requirements in the AI Act are ambiguous, potentially leaving them open to interpretation by ESOs. They are worded imprecisely, and sources of clarification outlined in the AI Act and elsewhere appear to be insufficient. Substantively, they cover fundamental rights and other policy areas that are not as easily quantified and operationalised as safety standards.
Additional sources of clarification from public authorities and international standards are likely to be insufficient.
Finally, ESOs’ existing stakeholder representation is unlikely to cover all affected public interests. This is inconsistent with the logic behind the inclusion of Annex III organisations, which is to represent interests affected by NLF legislation.
Unclear essential requirements
Essential requirements for high-risk AI systems appear in Title III, Chapter 2 of the AI Act.[34] High-risk systems are categories of AI deemed to pose a particularly high risk to human health, safety or fundamental rights, such as AI used in education, worker management, biometric surveillance and access to essential services.[35]
As in other NLF legislation, the AI Act’s essential requirements address human health and safety. Unlike most NLF laws, they also broadly address fundamental rights and apply to technologies that affect other policy goals, like the administration of elections.[36]
Essential requirements in the AI Act tend to be worded ambiguously. According to Article 9, the overall level of risk to fundamental rights and health and safety following a risk mitigation process must be ‘acceptable’.[37] Training datasets must be assembled using ‘relevant design choices’.[38] High-risk systems must exhibit an ‘appropriate level of accuracy, robustness and cybersecurity’.[39]
The ambiguity of essential requirements is inconsistent with the Commission’s description of harmonised standards, which must be defined precisely to avoid delegating political power to ESOs.
For example, the Commission specifically uses the choice of a maximum hazard exposure level as an example of a political choice that must remain with lawmakers. In contrast, the AI Act leaves decisions about acceptable levels of risks related to fundamental rights to ESOs and providers.
Moreover, human rights law is far less amenable to quantification, and far more open to interpretation, than safety standards. This is likely to create new challenges for industry technologists trying to operationalise essential requirements.
Inadequate alternative sources of clarification
The AI Act and the EU’s standardisation strategy potentially provide sources of clarification for ambiguous essential requirements, these include: references to the state of the art; European Commission and member state guidance; international standards; and stakeholder representation. However, it is doubtful that any of these sources will be sufficient to meet the needs of providers of high-risk systems. Each source is explored in detail below.
The state of the art
As in other NLF laws, the AI Act implies that the state of the art can help providers and ESOs understand how to comply with essential requirements. However, this is largely inapplicable where fundamental rights are concerned.
Article 9, which describes the risk management system used to determine the overall level of risk to fundamental rights permitted in a high-risk system, states that the designer should ‘take into account the generally acknowledged state of the art’.[40]
Similarly, Recital 49 explains that high-risk systems must ‘meet an appropriate level of accuracy, robustness and cybersecurity in accordance with the generally acknowledged state of the art’.
The Commission sought to clarify the meaning of ‘state-of-art’ in its draft standardisation request to CEN-CENELEC. Here they said the term ‘should be understood as a developed stage of technical capability at a given time as regards products, processes and services, based on the relevant consolidated findings of science, technology and experience and which is accepted as good practice in technology. The state of the art does not necessarily imply the latest scientific research still in an experimental stage or with insufficient technological maturity.’[41]
More generally, the Commission’s Explanatory Memorandum accompanying the AI Act proposal states that the ‘precise technical solutions to achieve compliance with [essential] requirements may be provided by standards or […] otherwise be developed in accordance with general engineering or scientific knowledge at the discretion of the provider of the AI system’.[42]
During a discussion at a panel event in 2021 hosted by the Center for Data Innovation with members of the European Parliament and others, a Microsoft representative confirmed that the Commission will accept design solutions to address essential requirements that are based on the state of the art.[43]
However, an allusion to the state of the art is unlikely to answer questions about what constitutes an acceptable level of risk to fundamental rights, or what constitutes an appropriate level of accuracy. Unlike the measurement of noise emissions with decibel levels, there is no agreed, one-dimensional metric for measuring risk to fundamental rights, and any metric that is developed will be highly contested.
Whether a rule or practice violates human rights law tends to be context dependent and determinations typically involve balancing various rights and interests. Unlike hearing loss injuries, human rights violations usually cannot be easily quantified or reduced to either-or decisions to demarcate acceptable from unacceptable risk levels.
Furthermore, even if state of the art standards in human rights law and related policy areas existed, the lack of relevant legal and policy expertise in ESOs would make it difficult to identify them.
This means that the state of the art is unlikely to provide sufficient guidance for operationalising essential requirements related to fundamental rights.
Guidance from the European Commission and Member States
The AI Act also envisions ways in which the European Commission and EU member states can provide authoritative interpretations of essential requirements directly to providers. These include common specifications; guidance from a European Artificial Intelligence Board; harmonised standards (HAS) consultants; regulatory sandboxes; and a dedicated communication channel.
However, few details are provided in the legislation or elsewhere about whether or how these resources will be provided. Without information about their implementation, it is difficult to predict whether any will be sufficient to clarify essential requirements. Based on the information available, this appears doubtful.
European Commission guidance
Several aspects of the AI Act and the EU’s standardisation policy enable the Commission to provide guidance for interpreting essential requirements.
Article 41 of the AI Act empowers the Commission to essentially create its own harmonised standards, called common specifications, for providers to use if ESOs’ harmonised standards are incomplete or insufficient. However, there are no publicly available plans in place to develop common specifications, so it is unlikely these will be available to industry when the AI Act comes into effect.
Article 58(c) describes the tasks of a newly established European Artificial Intelligence Board, part of which is to ‘issue opinions, recommendations or written contributions on matters related to […] technical specifications […] regarding [essential] requirements’.
This language suggests that the Board could issue specifications that operationalise essential requirements like appropriate accuracy levels and acceptable levels of risk to fundamental rights for various types of high-risk systems.
While there are no detailed, publicly available plans in place for the Board, it is unlikely the Board would be sufficiently responsive to providers’ questions while juggling advisory work with other administrative tasks.[44]
On 5 December 2022, the Commission issued a draft request to CEN-CENELEC to develop harmonised standards to support the AI Act.[45] . This is the first formal step in the process of developing harmonised standards.
In line with its existing standardisation strategy, the European Commission can provide HAS consultants to ESOs during the standards development process to help interpret essential requirements.[46]
HAS consultants are private contractors from a consultancy firm who play two key roles in European standardisation. First, at certain stages of the standardisation process, they can provide feedback about whether existing drafts conform to an NLF law’s essential requirements.[47] Second, they help the Commission to assess a standard to determine whether it should be cited in the Official Journal, creating a presumption of conformity.[48]
However, it is questionable that private contractors can or should make such weighty decisions as to what constitutes an acceptable level of risk to fundamental rights, such as in the development of a biometric surveillance system used in the processing of asylum seekers.
It is unclear whether HAS consultants for AI Act standards would have expertise in human rights law or other policy goals, like the administration of elections. Calls for expressions of interest from consultants typically require a master’s degree or experience in the relevant industrial sector, for example, but not in human rights law or other areas of public policy.[49]
Member State guidance
The AI Act also calls on EU member states to provide guidance for compliance. Articles 53 and 55 require or encourage member states to provide guidance or help through regulatory sandboxes (e.g. test beds) and ‘dedicated channel[s] for communication’ for smaller providers, respectively.[50]
However, as in the case of guidance from the Commission, the lack of detail makes it unclear how responsive this guidance will be to providers’ needs.
International standards
Another potential source of clarification is international standards.
A large proportion of harmonised standards originates as international standards, later adopted by ESOs because of agreements between ESOs and their international counterparts to prioritise these standards.[51] This means that, if an international standard on a topic already exists, an ESO generally cannot develop a conflicting standard on the same topic.
However, there is no indication that international standards currently under development will address the political facets of essential requirements.[52] Also, the lack of civil society participation suggests international standards are likely to suffer from similar shortcomings in terms of legal and policy expertise and will not provide the necessary guidance for AI Act compliance.[53]
Stakeholder representation
Stakeholder representation within ESOs could potentially facilitate the interpretation of essential requirements for fundamental rights and other public interests.
However, Annex III organisations include only those representing consumer rights, workers’ rights, environmental interests and SMEs. These represent merely a fraction of the fundamental rights and other public interests implicated by the AI Act.
Nevertheless, civil society participation in the development of harmonised standards is likely to be the most promising strategy to fill the AI Act’s apparent regulatory gap. It appears this is the only source of non-technical expertise with a record (discussed below) of providing advice about the protection of fundamental rights and other public interests to ESOs.
As such, policymakers would benefit from a better understanding of civil society organisations’ current and future roles in European standardisation. In particular, it is important to understand whether rules governing their participation must be updated to accommodate an expanded remit in the development of harmonised standards for the AI Act.
Open questions An analysis of the AI Act’s text reveals a possible regulatory gap. Although a core goal of the Act is to protect fundamental rights and other public interests beyond health and safety, it does not guarantee that clear rules or authoritative guidance will be available to providers to ensure this goal is realised. This leaves open the questions of whether civil society participation in European standardisation could fill the gap and, if so, how policymakers can bolster this participation.
Experts’ views on civil society participation
Interviews and reviewed documents exposed high barriers to effective participation by civil society organisations, as well as several existing and potential facilitators of participation.
While interviews with standardisation experts revealed perceived benefits to civil society participation, these generally did not include the interpretation of legislation or human rights law. This is largely due to Joint Technical Committee 21’s (JTC-21) avoidance of these topics.
For more information on the methodology, as well as a list of experts who were interviewed, see the ‘Methodology’ chapter below.
High barriers to effective civil society participation
Civil society representatives both with and without experience in European standardisation identified several significant barriers to effective participation. These include restrictive eligibility criteria for existing opportunities, burdensome time commitments, an inability to navigate complicated standardisation processes, industry dominance and a lack of awareness and interest.
Limited opportunities for civil society participation
Opportunities for participation by civil society organisations in JTC-21 are limited. These include participating as an Annex III organisation, a CEN-CENELEC liaison organisation, and direct or indirect participation through a National Standardisation Body (NSB). Even when an organisation qualifies for one of these opportunities, formal and practical impediments prevent it from wielding significant influence.
Participation as a liaison organisation
CEN-CENELEC conditions for liaison participation prevent most civil society organisations with expertise relevant to the AI Act’s fundamental rights protections and policy goals from participating in JTC-21.
An organisation can apply to CEN-CENELEC for permission to participate in JTC-21 as a liaison organisation to represent interests affected by its standardisation activities.[54]
One eligibility criterion is that the organisation must have representatives in at least four CEN-CENELEC NSB member states, and those representatives must be businesses or organisations, rather than individuals.[55]
In a survey of workshop participants whose organisations have relevant expertise but are not involved in JTC-21, less than a quarter satisfied this requirement.
Interviewees, including both technologists and civil society representatives, could name only one liaison organisation currently involved in JTC-21. It is called ForHumanity and specialises in the independent auditing of AI and autonomous systems.[56] Few if any other liaison organisations represent non-commercial interests.[57]
Participation as an Annex III organisation
Few civil society organisations receive funding from the European Commission for participation in European standardisation.
As discussed above, the European Commission funds the participation of civil society groups representing consumer and labour rights, as well as environmental interests, and requires ESOs to include them in standardisation activities.[58] They are called Annex III organisations because the categories of organisations eligible for funding are listed in Annex III of the Regulation on European Standardisation.
However, the eligibility conditions are restrictive and the Commission funds only one organisation per stakeholder category. In the workshop held for civil society organisations, none met the eligibility requirement of having mandates from organisations in at least two-thirds of EU member states.
In theory, each Annex III organisation represents the views of their national counterparts. For example, the European Trade Union Confederation (ETUC) collects and represents the views of national trade unions in standardisation activities, including JTC-21 work. However, Annex III organisations find it challenging to interest their national counterparts in education and research on standards, according to interviewees Philippe Saint-Aubin, a JTC-21 expert working on behalf of ETUC, and Chiara Giovannini of ANEC, who represent their respective Annex III organisations in standards development.
Participation as a National Standardisation Body (NSB)
While eligibility criteria for participation in NSBs may be less strict, civil society organisations find it difficult to influence national standardisation activities.
At the national level, civil society organisations usually have opportunities to participate directly or indirectly in JTC-21 activities through their NSB’s mirror committee or through public comments. A mirror committee exists to gather national stakeholders’ views about the activities of a European or international technical committee, such as JTC-21.
Though the rules of NSBs vary, a civil society organisation generally has an opportunity to contribute feedback in a mirror committee and can potentially act as an NSB’s delegate to JTC-21.[59] A delegate represents the positions of an NSB in standardisation activities, as NSBs make up the membership of CEN-CENELEC.
However, it can be difficult for civil society organisations to join and wield influence in an NSB mirror committee.
Interviewee Chiara Giovannini of ANEC, an Annex III organisation representing consumer rights, finds that the consumer voice is ‘frequently absent and disregarded’ in NSBs. Contributions from Giovannini’s national counterparts in NSBs have been disregarded because, by missing meetings, the organisations lost good standing, in accordance with the NSB’s rules.
Even when they are able to participate, civil society representatives are usually vastly outnumbered and outvoted by company representatives. It was because of civil society’s ‘weak’ representation in NSBs, relative to industry, that the European Parliament recognised the need for financial and political support for what are now known as Annex III organisations.[60]
NSBs also offer members of the public – including civil society representatives – the opportunity to read and comment on draft standards after registering for an account on the NSB’s website.[61] This is possible during a limited period of time, after a CEN-CENELEC technical committee has completed a draft standard, and before all suggested amendments are considered in the comment resolution stage.
NSBs can consider public comments and decide whether to submit them to the CEN-CENELEC technical committee for consideration in the comment resolution stage. While most or all AI-related standards are not yet available for public review and comment, this option appears to be used rarely in all standardisation categories.
Giovannini also points to a lack of dedicated funds for civil society participation in NSBs as a barrier.
Time commitment
As a time-intensive process, European standardisation excludes many organisations that cannot afford to commit full-time personnel. The development of a European or international standard generally requires between two and five years, according to interviewees David Filip, of the Organization for Standardization (ISO), and Philippe Saint-Aubin, who both participate in JTC-21’s work. New areas like AI require closer to five years.
Saint-Aubin, a representative of the ETUC, an Annex III organisation, finds that each standard requires between two and ten hours per month for meetings, comments and reading. Earlier stages require less time, while the more significant comment resolution stage, during which proposed changes to a draft standard are negotiated and resolved, requires closer to ten hours.
Saint-Aubin judges that standardisation is too time-consuming for most trade unionists, who are already ‘overbooked’. Interviewee Mary Towers, of the Trades Union Congress (TUC) in Britain, confirms this view, finding it difficult to juggle standardisation work with her many other responsibilities.
Participation in standardisation must also be continuous to be effective. In the experiences of civil society representatives interviewed, it was essential to attend every, or nearly every, meeting of a working group developing a standard to maintain the credibility necessary to influence the group.
According to Saint-Aubin, it is important to begin contributing as early as possible, during less critical stages of the process, to develop the standing necessary to influence the more important later stages; otherwise, their views will be disregarded. Early and continuous participation gives other experts confidence that one can be trusted to bring a valuable perspective to the process.
On a practical level, Mary Towers describes how, given the complexity of standards development, missing a single meeting or joining halfway through can also cause a civil society representative without extensive experience to feel confused about the proposal under consideration.
Additionally, a technical committee typically develops multiple standards at any given time, causing even Annex III organisations to refrain from contributing to many of them.
As such, Saint-Aubin reports that, despite their funding from the European Commission, even Annex III organisations lack the human resources necessary to participate in every working group of a technical committee. An organisation would likely require more than one full-time expert to participate actively in the development of all AI standards relevant to its mission.
Moreover, organisations like the ETUC are responsible for participating in standards development in areas outside of AI.
A small survey of civil society representatives not participating in JTC-21 activities, but whose organisations have expertise relevant to the AI Act’s fundamental rights protections, revealed that none were certain their organisations could make this time commitment. Most were certain their organisations could not spare this much time, and only one was unsure. This time commitment was also the most frequently listed barrier to their potential participation in a question with open answers.
Opacity and complexity
The opacity and complexity of the standards development process can be particularly challenging to those without extensive experience. Mary Towers finds standards development to be ‘distant’ and ‘difficult to navigate’. Even jargon is ‘a real barrier’ that can make the process ‘inaccessible’.
Lack of awareness and interest
A lack of awareness and interest in standards development emerged as another key challenge for civil society representation.
Mary Towers has the impression that there is low awareness among trade unionists about the relevance of standards to their work. This is likely to be because standards development happens outside of their workplaces and does not fall within the realm of most workers’ immediate experiences.
Philippe Saint-Aubin finds that national trade unions are interested in standards that impact workers more tangibly, such as those dealing with health and safety or human resources, and do not prioritise AI standards.
A consumer rights representative from the Annex III organisation ANEC has found it difficult to interest a coalition of civil society groups specialising in AI policy in standards development. Chiara Giovannini attempted to solicit feedback from the fifteen organisations in the coalition about how to reword ambiguous essential requirements, due to concerns about how they would be interpreted by ESOs, but received no feedback.
Industry dominance
Civil society representatives often find themselves unable to influence final decisions made in standards development because they are vastly outnumbered by industry representatives. This is problematic because industry preferences can conflict with the public interest.
Most experts in CEN-CENELEC working groups are employees of large companies, sent as delegates to represent NSBs. This is because few organisations, besides large companies, have the resources to pay full-time staff to work on standardisation, according to David Filip. When industry and civil society opinions diverge, industry views take precedence.
Decisions made by industry representatives can undermine the public interests civil society organisations aim to promote. For example, in European standardisation, Chiara Giovannini of ANEC finds that industry representatives tend to interpret ambiguous essential requirements in line with existing industry practices, even when these practices are inconsistent with the spirit of the legislation.
In the development of an international standard that defined maximum surface temperatures for household appliances, Giovannini found that industry representatives preferred to codify existing norms, despite rigorous empirical evidence that ANEC had gathered from scientific experts in burns hospitals demonstrating that these norms were unsafe. She believes this was because it would be more expensive to use alternative or thicker materials to prevent burns.
Giovannini also participated in the development of a European standard that the European Commission declined to reference in the Official Journal due to its failure to meet accessibility requirements.
Part of the standard addressed the degree of colour contrast featured in lift button panels and was intended to implement an EU Directive on lifts and lift safety components.[62] Those drafting the standard were primarily representatives of five dominant lift manufacturers in Europe, and they chose a colour contrast level that was deemed too low for visually impaired people.
Civil society representatives have little recourse in these situations. While delegates of NSBs – who are almost always industry representatives – have voting rights in CEN and CENELEC, civil society organisations do not.[63] Giovannini finds influencing a vote on a standard to be even more challenging than influencing the content of a standard.
While Annex III organisations have the right to appeal a decision, Giovannini finds that the process is too labour-intensive to exercise it as often as ANEC otherwise would.
NSBs may give civil society organisations voting rights when developing views for the NSB to bring to ESO technical committees, but industry votes usually or always outnumber them, according to Giovannini.
This lack of influence is reflected in standards’ content. After contributing feedback to a 60-page standard, Saint-Aubin found that the ETUC’s suggestions appeared in only one footnote. He says that this work can be disappointing. Giovannini recalls six years of ANEC contributions to the development of one standard, which resulted in the modification of only one line.
At the same time, according to David Filip, who participates in JTC-21’s work, even industry actors and technologists are ‘lucky’ if their contributions appear in one-to-three lines of a final product, given the intensive editing process involved.
Facilitators of civil society participation
Civil society organisations also shared views about what does or would facilitate their participation in JTC-21, or European standardisation generally. These include a central resource for information to facilitate ad hoc participation, funding and education.
Central resource for information
By acting as a hub for information and activity, Annex III organisations facilitate participation of national civil society organisations in standards development.
Mary Towers of the TUC in Britain participates in a standardisation committee for trade unions, as well as an AI taskforce, both organised by the ETUC, an Annex III organisation.[64] ETUC representatives share information and documents related to standardisation activities at the European and international levels via email, giving members of the committee and taskforce opportunities to provide feedback without participating in standardisation directly. This enables Towers to participate when she has enough time to do so.
In addition to gathering the perspectives of national organisations, Annex III organisations can also funnel positions to national organisations.
Chiara Giovannini describes ANEC as a hub of information used by national consumer rights advocates participating in NSB activities. ANEC provides research and positions to national counterparts that would like to participate in NSB activity but lack the resources to do so independently.
Funding
Many interviewees identified funding as a vital resource for expanding civil society participation in European standardisation.
Giovanni points out that sufficient funding can enable organisations to set up specialised departments on standards development, hire experts to attend more meetings, organise lobbying campaigns and commission scientific studies to provide empirical evidence.
Likewise, Philippe Saint-Aubin, an expert working on behalf of the ETUC, thinks additional funding would be useful for organisations to hire more experts to participate, and Mary Towers identified funding as a critical resource.
Given how crucial it is, Giovannini also argues that policymakers must choose to either significantly increase funding for civil society participation to represent the public interest adequately in standardisation or refrain from implementing public policy through standards.
Education and training
Raising awareness of the relevance of AI standards to civil society organisations, as well as training them to participate in European standardisation, is also likely to be essential in promoting effective civil society participation.
According to Philippe Saint-Aubin, even with more funding for civil society participation, organisations would still be hampered by a lack of potential experts. While national trade union members could potentially supply these experts to represent labour interests, they do not prioritise standardisation. This means few trade unionists are willing and able to navigate the AI standards development process.
Those without extensive experience and training that do venture into standards development often stop participating because of confusion about the process. Saint-Aubin thinks more education is needed about the importance of standards to workers, as is training in the procedures of standards development.
Similarly, Mary Towers identifies a need for more education about the relevance of standards within trade union affiliates, as well as training in the process of standards development. After organising a training session with ETUC representatives, Towers found that several of her colleagues became interested enough in standards development to attend a workshop about the design of the Alan Turing Institute’s AI Standards Hub.[65]
The value of civil society participation
Interviews with JTC-21 experts, most of whom are technologists, focused on the benefit civil society organisations bring to AI standards development, as well as the costs. There was a particular focus on whether civil society organisations can support JTC-21 to interpret ambiguous key terms from essential requirements that relate to the protection of fundamental rights and other public interests.
While most participants found inclusivity to be helpful by providing otherwise missing perspectives and information, the interpretation of ambiguous essential requirements was not identified as a benefit.
Providing diversity of viewpoints and building consensus
Standardisation experts generally found civil society participation in standards development beneficial or even essential.
David Filip, the convenor of a working group on AI trustworthiness in the ISO, has found Philippe Saint-Aubin’s contributions to various standardisation activities valuable.
Filip noticed that the ETUC representative shaped the working group’s agenda. Saint-Aubin contributed to the development of a roadmap for the group’s standardisation activities and highlighted opportunities to promote the 8th UN Sustainable Development Goal (SDG), which focuses on decent work and economic growth.[66]
This is relevant because the ISO encourages the development of standards that help users address SDGs, and others in Filip’s working group tend to focus mainly on the 9th SDG, which addresses industry, innovation and infrastructure.[67]
Based on these experiences, Filip thinks it is important to have a more ‘representative’ and ‘balanced’ standardisation process, because ‘the stakes are too high’ in the field of AI to exclude non-industry voices.
He finds that having the right team in place from the beginning of a standardisation project is the most important factor in the project’s success, and that a more inclusive group with civil society representation can help the group to see an issue from every angle.
While chairing a working group in the Institute of Electrical and Electronics Engineers (IEEE) that is developing a standard for algorithmic bias considerations, Ansgar Koene, who represents the British Standards Institution (BSI) in JTC-21, has noticed civil society representatives and others with non-technical backgrounds making unique contributions to high-level thought and planning.
Participants without computer science backgrounds sparked the idea for annexes covering cultural dimensions of bias and different jurisdictions’ legal approaches, which would otherwise not have been included. The annex on varying cultural norms is intended to help providers adjust risk assessments for bias in different cultural contexts.
Participants with social science backgrounds led the stakeholder identification activities, helping Koene’s group to identify stakeholders beyond the more obvious categories of people with specific legal protections.
Koene finds civil society input particularly useful for the ‘cultural dimensions’ of standards development and identifying sensitivities. He says that lived experience shared by civil society representatives can be the most valuable input.
Adam Leon Smith, another BSI representative in JTC-21, who also gained experience in international AI standardisation prior to JTC-21, finds civil society participation beneficial when the participants have relevant subject-matter expertise. For example, he would find it helpful to have an expert in homelessness involved in the development of a standard related to banking, given the particular challenges this group might face, but not necessarily an expert in voting rights.
Another benefit of civil society participation, according to David Filip, is that it helps to build a more durable consensus. If a standard is developed to reflect the views of all affected interests, it is less likely that excluded interests will identify and object to shortcomings at a later stage.
Even when standards developers focus only on implementing legislation, rather than interpreting it, Chiara Giovannini of ANEC finds broad stakeholder participation beneficial. For example, a standard for recordkeeping procedures may not require experts to interpret human rights law directly, but decisions they make can indirectly affect a person’s human rights, such as the right to an effective remedy. In these cases, it is useful to have civil society representatives present to spot issues and make recommendations.
There were few perceived downsides to participation by civil society organisations. While David Filip finds that greater inclusivity increases the amount of time needed to reach a consensus, he judges that its benefits outweigh the time costs.
Avoiding legislative interpretation
Interviewees report that JTC-21 working group experts tend to avoid making more granular decisions about interpreting ambiguous legislative terms pertaining to fundamental rights and related public interests. Experts, including both technologists and civil society representatives, feel that these decisions should be made primarily by lawmakers. As a result, they do not seek this input from civil society representatives.
Ansgar Koene observes that JTC-21 working group experts ‘dance around’ questions raised by the interpretation of terms like ‘appropriate level of accuracy’. His sense is that experts feel they ‘do not have the right’ to make these decisions, as the issues are too ‘sensitive’, and JTC- 21 has not been authorised to define societal norms.
Instead, his working group and others in JTC-21 focus on procedures and documentation that will enable public authorities to assess a system’s compliance with policies they have made, such as thresholds they have set for accuracy or risk levels. These standards will instruct a provider about which steps to take, or which boxes to tick, to demonstrate that issues like fundamental rights have been considered fully, and how to document these steps. They will not specify thresholds or benchmarks to meet.
Adam Leon Smith witnessed a similar tendency in the development of an international standard on algorithmic bias. Although this standard does not implement legislation, the committee frequently discussed whether or how to address fairness. Ultimately it avoided defining fairness because there was too much cultural variation in its meaning.
From David Filip’s perspective, there are two major challenges to standardising human rights protections.
The first challenge is that human rights risks in AI are multi-dimensional, making it infeasible to develop a single metric to measure risk to fundamental rights. In contrast, product safety standards developed for most New Legislative Framework (NLF) legislation typically address one-dimensional risks to human life or physical injuries.
Where fundamental rights are concerned, multiple rights may be implicated by AI. A developer may need to make difficult legal assessments about a design feature that protects one right but interferes with another right. Legal balancing tests and similar analyses normally fall within the purview of a constitutional court or legislature, which have the expertise and legitimacy to make such determinations.
According to Filip, a technical committee can determine how to minimise the number of workers killed by machinery, for example, but not which degree of privacy intrusion is acceptable to prevent a worker from being injured. This is an ‘unsolvable problem’ for which JTC-21 cannot and will not take responsibility.
The second challenge is that the standardisation of risk management for a product depends on the sequential development of several interdependent standards.
For example, Filip’s ISO working group on trustworthiness first defines qualitative characteristics of trustworthiness in standards, such as robustness, and then determines how to measure them in subsequent standards. From his perspective, only after these steps are complete does it make sense to require a certain threshold of a characteristic in law.
Equivalent preliminary standards would be necessary to develop the standards envisioned in the AI Act. However, that work has not yet been completed, and will not be complete before the AI Act goes into effect, in 2023 or 2024.
Similarly, James Davenport, a representative of the BSI, thinks that, in the absence of operationalised definitions of risks to human rights that are produced by lawmakers or otherwise socially accepted, JTC-21 cannot develop standards for acceptable levels of risk.
Davenport illustrates this point with the hypothetical example of avoiding gender-based discrimination resulting from the use of hiring software (a type of high-risk AI system). He points out that no UK or EU law specifies whether the output of a shortlisting programme should be a list in which there are equal numbers of applicants with each gender, the proportion of each gender reflects the original applicant pool, or some other pattern.
Yet ‘no answer is not good enough for a computer programme’, says Davenport; they ‘need to have an answer’. He thinks it is ‘not reasonable’ for policymakers to ask something of standards development bodies that policymakers have not done themselves.
Without operationalised definitions of risk to fundamental rights, questions about what constitutes acceptable or appropriate levels are ‘not scientifically sound’, according to Davenport. For this reason, he thinks that it is not helpful to have civil society organisations available to help interpret these provisions of the AI Act.
On the other hand, Davenport is confident that JTC-21 can deliver process-oriented standards. Representatives of Annex III organisations hold similar views.
Philippe Saint-Aubin, an ETUC expert, states that ‘nobody wants standards to replace law and policy’, so standards development organisations aim to avoid specifying what should be covered in national laws. Rather than creating substantive rules that overlap with regulation, Saint-Aubin encourages the incorporation of social dialogue in international standards affecting workers’ rights. This is because different national trade unions may have different views, and some workers may end up in a worse position with a uniform set of rules.
How to fill the regulatory gap: analysis and next steps for policymakers
Summary of the research findings
An analysis of the AI Act and documents pertaining to EU standardisation policy suggests that the AI Act does create a regulatory gap. Neither the legislative text, nor harmonised standards implementing the legislation, are likely to answer challenging legal and political questions raised by essential requirements.
Little information is available about most other potential sources of authoritative interpretations of essential requirements, but the evidence suggests they will be inadequate to meet providers’ needs.
Although Joint Technical Committee 21 (JTC-21) aims to avoid interpreting the AI Act’s essential requirements for fundamental rights and related public interests when developing standards, most of the standardisation experts interviewed value inclusive civil society representation. Their expertise can provide otherwise missing viewpoints and knowledge and facilitate consensus-building.
However, civil society organisations face significant barriers to effective participation in JTC-21 and standards development generally. While there are several opportunities for direct civil society participation in JTC-21, most civil society organisations are ineligible to take advantage of them, and those that do face major barriers to participating effectively.
Challenges include the size and inflexibility of the time commitment, the opacity and complexity of the standardisation process, disempowerment by industry dominance in the standardisation process and a lack of awareness about the relevance of European and AI standards. Though eligibility criteria for public comments can be less restrictive, this option limits participation to a narrow window of time, and civil society groups appear to be unaware of or uninterested in it.
Feedback from civil society representatives suggests several resources could increase the amount and effectiveness of their participation in standards development. These include education about the relevance of standards to organisations’ missions, training in how to participate and funding for participants.
However, even with increased civil society participation in JTC-21, the ambiguity of the AI Act’s essential requirements for fundamental rights protections and other public interests limits the types of standards deliverables JTC-21 can produce.
This means JTC-21’s harmonised standards are unlikely to clarify how providers can comply with the AI Act’s essential requirements for the protection of fundamental rights and related public interests. This leaves challenging political and legal questions to providers.
These findings suggest that EU policymakers should explore strategies to boost civil society participation, while also exploring institutional innovations to fill the regulatory gap.
Expanding civil society participation in JTC-21
The European Commission and Parliament can explore several strategies to bolster civil society participation in JTC-21. These include increasing the number and diversity of Annex III organisations, expanding eligibility criteria for Commission grants to individuals and creating or incentivising the creation of a civil society hub.
This could increase JTC-21’s viewpoint diversity and balance the relative representation of public and commercial interests.
Why increase civil society participation?
There are several reasons why the European Commission and Parliament should develop strategies to boost the number and effectiveness of civil society organisations in JTC-21.
First, civil society representatives with expertise in human rights law and public policy provide valuable input, even if that input does not involve interpreting legislation or human rights law.
They can provide missing perspectives and information, such as different cultural perspectives on ethical questions or lived experience, which Ansgar Koene, who represents the BSI in JTC-21, found useful in the development of a standard on algorithmic bias considerations.
As an ANEC representative pointed out, they can identify and make recommendations for indirect human rights impacts, such as the ways in which record-keeping practices can impact the enforcement of human rights protections.
Second, a more equal balance of civil society representatives and employees of large companies could avert decisions made in companies’ interests that conflict with the public interest.
JTC-21 may be less likely to design standards in line with existing industry practice when empirical evidence shows that alternative interpretations produce better outcomes for the public (although nothing suggests that this is currently a problem in JTC-21). Whereas a lone ANEC representative may be unable to influence a working group dominated by industry representatives who have voting rights, as Chiara Giovannini of ANEC has found, a coalition of civil society representatives may be more successful.
Even if expanded participation may prolong the consensus-building process, the benefits for increasing the quality of the standard will likely outweigh the time cost, according to JTC-21 participant David Filip. This is particularly relevant where harmonised standards are concerned; the Commission frequently declines to cite potential harmonised standards in the Official Journal since harmonised standards (HAS) consultants find they do not conform to essential requirements.[68]
How can civil society representation be increased?
In light of these benefits, the European Commission and Parliament should explore strategies to increase the representation of civil society organisations in JTC-21.
Several options have emerged from this research, including:
broadening the categories of Annex III organisations eligible for funding and mandated participation by amending the regulation on European Standardisation, and increasing funding for organisations’ participation in line with this
funding more individuals from civil society organisations with the Commission’s specialised StandICT grants, including for participation in national delegations
exploring ideas for the creation of a central hub to support civil society participation.
Amend the regulation on European Standardisation
Annex III of the Regulation on European Standardisation lists the types of civil society organisations eligible for EU funding and mandated involvement in European standardisation. Currently the list includes groups representing consumer, environmental, small and medium enterprises (SMEs) and social interests, with social interests defined as employees’ and workers’ rights.[69]
Parliament could amend the Regulation to add new categories of stakeholder groups to Annex III.[70] Categories could correspond to each of the fundamental rights and policy areas implicated by the AI Act’s essential requirements and high-risk systems, such as privacy and surveillance, fair elections and the right to an education.
The logic behind the Regulation on European Standardisation arguably demands this amendment. The Regulation justifies the participation of Annex III organisations by standards’ ‘broad impact on society’,[71] making it ‘necessary [to strengthen] the role and the input of societal stakeholders’.[72]
Yet the shortlist of Annex III organisations was created a decade ago, when New Legislative Framework (NLF) laws dealt mainly with single-use manufactured products, and essential requirements dealt mainly with health and safety.
Given that the AI Act will expand the scope of standards’ societal impacts on fundamental rights generally, as well as a variety of new policy areas, the breadth of interests represented by Annex III organisations should expand correspondingly. Otherwise, stakeholder input would reflect only a narrow portion of standards’ societal impacts.
Consequently, the European standardisation system would privilege environmental interests over students’ interests in the development of standards for AI used in education, for instance, which would not prioritise the interests most affected.
Amending Annex III would mitigate some of the challenges to effective civil society participation identified in this research. It would create new funding opportunities, particularly for organisations that wish to hire experts to focus on standards development full-time, as civil society representatives often struggle to meet the demanding time commitment along with their other responsibilities.
Increasing the number of potential Annex III organisations could also help to balance the numbers of experts representing public and company interests. Another outcome might be an increase in more ad hoc participation by creating new hubs for civil society activity.
One Annex III organisation, the European Trade Union Confederation (ETUC), solicits feedback from national trade unions and some civil society organisations and experts focused on labour rights to inform its work in European and international standardisation. Another, ANEC, feeds information to national consumer rights groups that wish to participate in National Standardisation Bodies (NSBs).
New Annex III organisations could play these roles for different interests impacted by the AI Act. As a result, harmonised standards developed by JTC-21 would be more likely to successfully implement the AI Act’s essential requirements.
Expand StandICT grant eligibility
Through the StandICT.eu Fellowship Programme, the European Commission provides funding for European standardisation experts to participate in standards development. Funds can be used for travel expenses or time to participate in or prepare for meetings.
While the most recent call for applications welcomes those with expertise in some areas relevant to the AI Act’s essential requirements, such as data governance, privacy and justice, it does not reference fundamental rights generally.[73]
With its influence, the Commission could encourage the programme to expand eligibility criteria to include those who have expertise in additional fundamental rights and policy areas.
Additionally, the StandICT website states that funds are only available for international standardisation activities, suggesting they are available for work in the International Organization for Standardization (ISO) but not in CEN-CENELEC. However, funds can be granted for work in CEN-CENELEC and other standardisation organisations. This should be clarified so that civil society organisations wishing to participate in JTC-21 or NSB mirror committees know they can apply for funding.
Dedicated civil society hub
The European Commission could also create or fund a hub for civil society participation in European standardisation. This hub could institutionalise activities already carried out by the ETUC and ANEC that enable organisations and experts to contribute to European standardisation when they otherwise could not. Its design could be based on best practices derived from other central resources created for standardisation.
A civil society hub could be designed to mitigate several of the challenges to effective civil society participation.
Through outreach to civil society organisations focusing on fundamental rights and public interests beyond health and safety, the hub could make organisations aware of the relevance of European standardisation to their organisations’ missions. This would mitigate a major challenge to civil society participation, which is that most organisations are unaware of its importance, according to interviews with civil society representatives.
The hub could provide training and continued support on procedures, terminology, English language translations and other aspects of the standardisation process that tend to intimidate or frustrate the efforts of newcomers and ad hoc participants. This would mitigate problems observed by Mary Towers of the Trades Union Congress (TUC) and Philippe Saint-Aubin, an ETUC expert, in the chapter on ‘Experts’ views on civil society participation’.
It could also provide technical expertise to enable those without technical backgrounds to better understand standards’ contents, reducing another barrier to effective civil society participation.
To facilitate ad hoc participation by organisations excluded by the time requirements, one or more point persons in the hub could collect and represent civil society views continuously throughout the standardisation process.
When designing the hub, the Commission could look to the successes and failures of other attempts to create central resources for participation in standards development.
One of these is the European Multi-Stakeholder Platform on ICT Standardisation, which is established by the Commission.[74] The Multi-Stakeholder Platform appoints very few civil society members, most of which are Annex III organisations.[75]
Another example is the Alan Turing Institute’s AI Standards Hub. Although the Hub is new, one of its stated aims is to educate and train stakeholders, including civil society, in international standards development.[76] The Commission may be able to learn about best practices and pitfalls to avoid.
Summary of strategies for increasing civil society participation
Whilst some policymakers or industry representatives may object to these policies, arguing that they would require additional EU funding or improper interference with private entities, improved civil society representation can help to ensure essential requirements uphold fundamental rights and other public interests.
According to Chiara Giovannini of ANEC, if policymakers wish to implement public policy through standards while relying on civil society to represent the public interest, then civil society participation must be funded adequately; otherwise, policymakers must disentangle standards from public policy.
Even with these changes, JTC-21’s understandable reluctance to make political decisions on standards could create a fatal flaw in the AI Act’s regulatory strategy, necessitating deeper reforms to the standards development process.
Institutional innovations for democratic control over essential requirements
If the AI Act continues to rely on a decades-old regulatory framework designed for product safety legislation, the European Commission and Parliament should explore possibilities for institutional innovations that adapt the NLF to the AI Act.
As things stand, the AI Act’s harmonised standards will not fulfil their intended function, which is to clarify for providers how to design AI in accordance with requirements about fundamental rights and other public interests. Neither the legislation nor other sources of clarification are likely to deliver this information.
Lacking authoritative interpretations of essential requirements, providers will face legal uncertainty in their attempts to comply with the AI Act. This would both negate the purpose of the NLF and endanger fundamental rights and other public interests.
Institutional innovations designed to answer tricky political and legal questions could fill this regulatory gap, while also creating opportunities for stronger democratic control and the inclusion of more legal and policy expertise in standardisation. This would be likely to result in the more successful implementation of the AI Act’s public interest protections.
Why are institutional innovations required?
Preliminary interviews with JTC-21 experts revealed that they are generally unwilling to develop harmonised standards for essential requirements that involve political judgements, due to a perceived lack of legitimacy.
This aligns with EU institutions’ views on the NLF, according to which ‘essential requirements […] should be defined precisely in order to avoid misinterpretation on the part of the ESOs or leaving them to make political choices’.[77] It is imperative to avoid the risk of ‘delegat[ing] political powers to the ESOs’.[78]
Though the AI Act includes other potential sources of clarification for essential requirements, there is uncertainty about whether they will meet providers’ needs.
A new European Artificial Intelligence Board will be empowered to provide advice about the implementation of the AI Act, including technical specifications related to essential requirements.[79] However, the high-level outline of the Board’s responsibilities in the proposal does not guarantee that the Board will fill the gaps left by JTC-21.
Even if the Board attempts to provide this guidance, it will juggle this task with other responsibilities, such as the coordination of member state enforcement and administration of regulatory sandboxes.[80] Whether the Board will have the resources and vision necessary to carry out all of these tasks effectively remains to be seen.
Additionally, the Commission can clarify essential requirements by issuing common specifications. Common specifications are implementing acts – a type of streamlined EU legislation – that are functionally equivalent to harmonised standards. They are permissible when harmonised standards are absent or insufficient to implement the AI Act.[81]
Finally, while HAS consultants may be on hand to clarify legislative terms and legal matters to JTC-21, this will not fill the regulatory gap if JTC-21 continues to avoid political questions. Were JTC-21 to reverse its position, this would raise concerns about the legitimacy of its decisions.
For the NLF to work with the AI Act, providers will need additional sources of authoritative guidance for essential requirements that have sufficient democratic or political legitimacy.
How could institutional innovations be implemented?
The European Commission can explore the possibilities of common specifications and a benchmarking institute to provide missing guidance in the implementation of the AI Act. These mechanisms could also create opportunities to build effective democratic control or oversight into the EU’s AI governance policy, along with sufficient legal and policy expertise.
Common specifications
The European Commission could use the AI Act as an opportunity to create a novel standardisation process that incorporates sufficient legal and policy expertise, while allowing for more democratic control.
Re-designing procedures for common specifications in a way that ensures civil society organisations and other experts are consulted more widely than in ESOs would be one way to do this.
Choosing the route of common specifications was seemingly ruled out when the Commission issued a draft request for harmonised standards in December 2022. Article 3 of this request compels CEN-CENELEC to ensure the appropriate involvement of ‘civil society
organisations, and the gathering of relevant expertise in the area of fundamental rights’ in its standardisation processes. It remains to be seen how CEN-CENELEC will achieve this, but they will be required to provide relevant evidence in their final report.
If relevant safety and fundamental right protections are deemed inadequate in the harmonised standards, the Commission should withhold, and possibly leverage, the right to use common specifications instead. This process should gather the views of relevant bodies or expert groups that are not necessarily tied to an industrial sector. It could consult civil society organisations with expertise in a larger proportion of the legal and policy areas implicated by the AI Act’s essential requirements.
The Commission could also explore the possibility of regularly consulting organisations that engage the public in policymaking when developing common specifications. This would introduce a higher degree of democratic control than would otherwise exist in decision-making by political appointees and civil servants or private contractors.
Though representatives of EU member states will have the opportunity to vote on the adoption of common specifications, national representatives in similar decision-making processes are usually not elected officials. Instead, they tend to represent trade and economy ministries.[82]
Given that common specifications take the form of implementing acts, the public can potentially provide feedback via the Commission’s ‘Have your say’ website, which would create new opportunities for ad hoc civil society participation in standardisation.[83] This could expand participation by organisations like the TUC that are effectively excluded by the time commitments typically required for standards development.
Benchmarking institution
The European Commission could explore similar ideas in a more targeted benchmarking institution.
This institution could take up the questions that JTC-21 avoids, complementing JTC-21’s procedure- and documentation-oriented standards with more substantive standards. It could provide guidance about questions like how to measure risk to fundamental rights, and which thresholds are ‘acceptable’ or ‘appropriate’.
The European Parliament’s Committee on Industry, Research and Energy has proposed amendments that would prompt the European Artificial Intelligence Board to either design an independent benchmarking institution or house a benchmarking authority within the Board.[84]
At least one JTC-21 expert, Ansgar Koene, felt that a benchmarking authority could answer the more political questions about compliance with essential requirements left open by the committee’s focus on procedure and documentation.
Summary of institutional innovations
Common specifications and a benchmarking institution are only two examples of institutional innovations the European Commission and Parliament can explore to fill the regulatory gap created by the AI Act’s NLF. Regardless of the particular strategy chosen, institutional innovations that modernise the NLF are probably necessary to ensure JTC-21 and providers have access to otherwise absent authoritative guidance on the interpretation of essential requirements.
EU institutions can take advantage of this modernisation by promoting more effective civil society participation. This would help to ensure essential requirements are interpreted in accordance with the views of experts in human rights law and relevant policy areas.
They can also use the opportunity to create new forms of democratic control over a rulemaking process that is currently dominated by private actors, which is arguably necessary to legitimise decisions in standards-setting that are more overtly political.
Further questions
These conclusions and suggestions are tentative, given how limited public information is about Joint Technical Committee 21 (JTC-21) experts and activities, and consequently, how difficult it is to gather empirical evidence through interviews and other means. This gives rise to its own questions:
Do EU institutions have a responsibility to publicise (or require CEN-CENELEC to publicise) JTC-21’s activities, given how crucial they are to a landmark piece of legislation that directly implicates fundamental rights and other public interests?
For those who are or could be involved in the development of EU standards, including JTC-21 participants and civil society organisations, this paper raises questions about the role of civil society in the development of the AI Act. There are many approaches that would facilitate their involvement – this would support the protection of fundamental rights and therefore fulfil one of the primary goals of the AI Act.
This research also raises broader questions about the AI Act and EU’s New Legislative Framework (NLF) – what role do EU institutions expect standards to play in AI governance?
As originally conceived, the NLF ensures political decisions remain within EU institutions and decisions made within European Standards Organisations (ESOs) are ‘purely technical’.[85] The Commission’s Explanatory Memorandum implies this is true of the AI Act, describing harmonised standards as ‘precise technical solutions’[86] for designing AI that complies with essential requirements.
However, the AI Act effectively delegates political decisions to ESOs, who are unequipped to make these decisions, leaving them to individual providers. This scenario is unlikely to ensure fundamental rights protections and related policy goals are realised. Nevertheless, the choice of the NLF for the AI Act implies that Parliament does not wish to make these granular decisions for industry.
Before voting on the AI Act, the European Parliament must understand the degree to which it is delegating consequential political power to private entities, which private entities are being empowered and whether amendments are necessary to safeguard public interests.
Parliament must also consider whether the NLF is suitable for AI governance and the protection of fundamental rights and other public interests. Rather than reforming European standardisation and the decades-old NLF to accommodate the AI Act, policymakers could avoid relying on European standards at all.
This raises broader questions for EU policymakers:
Is a new political theory of AI governance necessary and, if so, what should it be?
How could a governance framework be designed to effectively protect fundamental rights and better safeguard the public interest from conflicting corporate interests?
How can it balance the incorporation of technical expertise with effective democratic control?
Methodology
Several strategies were used to determine whether a regulatory gap exists in the AI Act, whether the gap can be filled by civil society participation in Joint Technical Committee 21 (JTC-21) and how to bolster civil society participation.
Legislative analysis and other policy analysis was used to determine whether a regulatory gap exists in the AI Act, particularly where the protection of fundamental rights and other public interests are concerned.
Interviews with JTC-21 working group experts and others with experience in standardisation were intended to clarify whether they consider it helpful or crucial to have civil society representatives involved in the interpretation and operationalisation of the AI Act’s essential requirements.
The goal behind interviews with civil society representatives experienced in European or AI standardisation was to understand what facilitates or hinders their effective participation. This information informed a workshop with civil society organisations lacking this experience, in order to understand what would be necessary for them to participate effectively.
Additional information was gathered through document review.
Legislative and policy analysis
An analysis of the AI Act’s text was carried out to reveal whether the legislation creates a regulatory gap, by depending on European Standards Organisations (ESOs) to operationalise ambiguously worded protections of fundamental rights and other public interests.
The legislation was analysed in conjunction with other sources and descriptions of EU standardisation policy, such as the Regulation on European Standardisation and the Commission’s Blue Guide.
Semi-structured interviews with Joint Technical Committee 21 experts
Interviews with participants in JTC-21, the ESO technical committee responsible for AI Act standards, were designed to elucidate how the committee goes about interpreting the Act’s essential requirements concerning fundamental rights and policy areas like election administration.
The goal was to understand whether JTC-21 working group experts will struggle to implement essential requirements in harmonised standards, and the degree to which civil society participation can help.
Although the European Commission’s first standardisation request to JTC-21 is not yet finalised, the recently formed committee has begun preliminary work in anticipation of the first standardisation request. Experts include both representatives of civil society organisations and technologists from industry and academia.
Questions in semi-structured interviews with standardisation experts were built, in part, around understanding how experts plan to operationalise essential requirements related to fundamental rights and issues like election administration.
They asked, for example, about how working groups within the committee are approaching terms like ‘appropriate level of accuracy’, whether they have the legal and policy expertise needed to interpret and operationalise them, and what role civil society organisations play or have played in similar standards development.
Interviews with civil society representatives also focused on the barriers to and facilitators of their participation.
Interviews were held in the spring of 2022 through Zoom and Microsoft Teams, with follow-up questions sent by email.
Interviewees
The target group for interviews was JTC-21 working group experts and those with experience in European standardisation or AI standards development.
Because the names of JTC-21 participants are not publicly available, most interviewees were identified through news articles, websites and LinkedIn profiles after searching for variations of ‘JTC-21’. Several interviewees were referred to the author of this paper by an interviewee or were already known to her.
Interviewees included:
James Davenport, a computer science and mathematics professor at the University of Bath, and a representative of the British Standards Institution (BSI), the United Kingdom’s National Standardisation Body (NSB), in JTC-21.
David Filip, who focuses on global standardisation strategy for the Huawei Ireland Research Centre. He is a JTC-21 participant who also convenes a working group focused on trustworthiness in AI in the International Organization for Standardization (ISO) and International Electrotechnical Commission (IEC).
Chiara Giovannini, a Deputy Secretary General and Senior Manager of Policy & Innovation at the European Consumer Voice in Standardisation (ANEC). She has experience in European and international standardisation.
Ansgar Koene, the Global AI Ethics and Regulatory Leader at Ernst & Young. He represents the BSI in JTC-21, in which he convenes a working group on conformity assessment. He also chairs a working group in the Institute of Electrical and Electronics Engineers (IEEE) that is developing a standard on algorithmic bias considerations.
Adam Leon Smith, the Chief Technology Officer of Dragonfly, who represents the BSI in JTC-21. He has experience in international AI standards development.
Philippe Saint-Aubin, a JTC-21 expert working on behalf of the European Trade Union Confederation (ETUC), who has experience in AI standards development in the ISO and IEC.
Mary Towers, an employment rights policy expert with the Trades Union Congress. She has represented her organisation in international standards development, with guidance from the ETUC.
Limitations
There were several limitations to these interviews. The number of interviewees was limited by the fact that the identities of JTC-21 participants are not publicly available. Of the experts whose names are publicly available, most declined interview requests.
Most NSBs did not respond to emails asking for referrals to their JTC-21 representatives. Most interviewees were based in the UK or Brussels, as most experts were referred or introduced to the interviewer by other interviewees.
Also, JTC-21 activity had only recently begun, and had done so before the European Commission finalised its first standardisation request. This means experts had relatively few experiences to draw from and were not certain about the exact scope of the work they would be asked to do.
Finally, because so few civil society groups are involved in JTC-21 and European standardisation broadly, the number of civil society representatives interviewed was necessarily small.
Workshop with civil society representatives
The views of civil society representatives that are not involved in European standardisation, but whose organisations’ missions will be impacted by essential requirements, were gathered in a workshop.
Held online as part of RightsCon on 9 June 2022, the workshop both informed participants about the relationship between the fundamental rights, the AI Act and European standardisation, and also elicited feedback from participants about their organisations’ abilities to engage effectively with JTC-21.
Questions were designed to understand what would be necessary or helpful for these organisations to participate in JTC-21 and were based on information gleaned in interviews and document review.
For example, one question asked participants whether they could meet the average time commitment for the development of a harmonised standard, which was information derived from interviews, with the options of ‘yes’, ‘no’ and ‘not sure’. Another asked which organisations satisfied the eligibility criteria for CEN-CENELEC liaison organisation status, which was information derived from document review.
Answers were submitted through two Mentimeter polls. One poll was directed to European civil society organisations, and another to other participants. Only the former is referenced in this paper.
Participants
Participants from at least one civil society organisation in each CEN-CENELEC member country (which includes countries that are not EU member states) were invited to the workshop. Representatives of organisations with expertise in each high-risk category were invited, as were representatives with organisations in fundamental rights more broadly. Invitations were also sent to organisations specialising in technology policy and human rights.
For example, representatives of anti-poverty organisations were invited to share their perspective on access to essential public services, a high-risk AI category.
Participants included an expert in the use of automation in the administration of justice; a policy analyst and a human rights lawyer from organisations specialising in human rights and technology policy; a representative of an organisation specialising in the use of technology to document human rights violations; and a representative of an organisation that promotes media freedom. Several participants contributed anonymously.
Additional RightsCon participants joined the workshop, which took the total number of participants to 25.
Limitations
There were several limitations to the workshop.
Although most invitees were from organisations that did not specialise in technology policy, most of the participants that accepted invitations were from such organisations. Those lacking familiarity with AI or technology policy generally tended not to reply, or to reply saying that they felt uncomfortable discussing a topic outside of their area of expertise.
Those that did join attended on the condition that they would listen rather than actively contribute.
Though 25 participants attended the workshop, less than half answered questions in the Mentimeter polls and contributed to group discussions.
Document review
Additional information about European standardisation was gathered through the review of documents, such as publications from the European Commission and CEN-CENELEC rules of procedure.
Acknowledgem
| 2023-03-30T00:00:00 |
https://www.adalovelaceinstitute.org/report/inclusive-ai-governance/
|
[
{
"date": "2023/03/30",
"position": 48,
"query": "AI labor union"
}
] |
|
AI and the Future of Health - Microsoft Research
|
AI and the Future of Health
|
https://www.microsoft.com
|
[
"Brenda Potts",
"Desney Tan",
"Corporate Vice President",
"Managing Director",
"Microsoft Research Redmond"
] |
In this blog, we will share some of our research team's work to make healthcare more data-driven, predictive, and precise.
|
The emergence of increasingly capable large-scale AI models, such as the recently released GPT-4, is one of the most significant advances in computing in decades. These innovations are rapidly transforming every aspect of the value we get from technology, as demonstrated through Microsoft’s integration of GPT-4 into Bing, Edge, Microsoft 365, Power Platform, GitHub, and other offerings. More recently, Nuance has announced DAX Express, which uses a unique combination of conversational, ambient, and generative AI to automatically draft clinical notes after patient visits – helping to reduce care providers’ cognitive burdens and increase the joy of practicing medicine (whilst releasing time for care).
We are at an inflection point for the use of AI in healthcare – one of society’s most critical sectors. The significance of this moment is reflected in Peter Lee’s recent article in the New England Journal of Medicine on the potential future clinical applications of GPT-4. At Microsoft Research’s Health Futures organization, the multidisciplinary group dedicated to discovery in this space, we see this as the continuation of a journey, and a major milestone in the long process of innovating to help address the greatest challenges in healthcare.
In this blog, we will share some of our research team’s work to make healthcare more data-driven, predictive, and precise – ultimately, empowering every person on the planet to live a healthier future.
Enabling precision medicine and connected care
We are today at a unique moment in history where medicine, biology, and technology are converging on a large scale. This presents immense possibilities to revolutionize healthcare and the practice of medicine with the aid of trustworthy AI. While we embrace the potential of AI, we understand that the practice of medicine is an intricate balance of “art” and “science.” We recognize and honor the enduring physician-patient relationship, which is fundamental and timeless. Our diverse team comprises researchers, scientists, engineers, biotechnologists, designers, social scientists, strategists, healthcare experts, and medical professionals who collaborate globally and inclusively to reimagine and transform the lives of the patients and public we serve.
As we consider how technologies have shaped the practice of medicine over the centuries, from the individual to the ecosystem level, we are reminded that no technology exists in a vacuum. Our core understanding of biological systems is rapidly evolving, and with it, our understanding of what technologies are relevant and useful. Simultaneously, the use of technology across the health and life science industries, and the way healthcare is delivered, are also rapidly changing – reshaping our traditional healthcare delivery model from one of diagnosis and treatment, to one that prioritizes prevention and precise individualized care.
Microsoft research podcast Ideas: AI and democracy with Madeleine Daepp and Robert Osazuwa Ness As the “biggest election year in history” comes to an end, researchers Madeleine Daepp and Robert Osazuwa Ness and Democracy Forward GM Ginny Badanes discuss AI’s impact on democracy, including the tech’s use in Taiwan and India. Listen now Opens in a new tab
Recent advancements in machine learning and AI have fueled computational technologies that allow us to aggregate complex inputs from multiple data sources, with the potential to derive rich insights that rapidly expand our knowledge base and drive deeper discovery and faster innovation. At the same time, it remains an open question how to best use and regulate these technologies in real-world settings and at scale across healthcare and the life sciences. Nonetheless, we believe that we are on a path to delivering on the goal of precision medicine – a change in clinical practice which will be enabled by precision diagnostics, precision therapeutics, and connected care technologies.
To achieve this goal, we seek to collaborate with health and life sciences organizations with a similar appetite for transformation, complementary expertise, and a commitment to propel the change required. We are also engaged with the broader community in pursuing responsible and ethical use of AI in healthcare. Our diverse team has been successful in bridging the gap between the fields of medicine, biology and chemistry on one hand, and computing on the other. We act as “translators” between these fields, and through a process of ongoing collaboration and feedback, we have discovered new challenges and innovative solutions.
Below are some examples of our collaborative research approach:
Multimodal foundation models for medicine: an example from radiology
The field of biomedicine involves a great deal of multimodal data, such as radiology images and text-based reports. Interpreting this data at scale is essential for improving care and accelerating research. Radiology reports often compare current and prior images to track changes in findings over time. This is crucial for decision making, but most AI models do not take into account this temporal structure. We are exploring a novel self-supervised framework that pre-trains vision-language models using pairs of reports and sequences of images. This includes handling missing or misaligned images and exploiting temporal information to learn more efficiently. Our approach, called BioViL-T, achieves state-of-the-art results on several downstream tasks, such as report generation, and interpreting disease progression by focusing on relevant image regions across time. BioViL-T is part of ongoing collaboration with our colleagues at Nuance to develop scalable and flexible AI solutions for radiology that can empower care providers and augment existing workflows.
Project InnerEye: Democratizing Medical Imaging AI
Project InnerEye (opens in new tab) is a research project that is exploring ways in which machine learning has the potential to assist clinicians in planning radiotherapy treatments so that they can spend more time with their patients. Project InnerEye has been working closely with the University of Cambridge and Cambridge University Hospitals NHS Foundation Trust to make progress on this problem through a deep research collaboration. To make our research as accessible as possible, we released the InnerEye Deep Learning Toolkit (opens in new tab) as open-source software. Cambridge University Hospitals NHS Foundation Trust and University Hospitals Birmingham NHS Trust (opens in new tab) led an NHS AI in Health and Care Award to evaluate how this technology could potentially save clinicians’ time, reduce the time between the scan and commencing treatment, and scale this to more NHS Trusts. Any clinical use of the InnerEye machine learning models remains subject to regulatory approval.
Immunomics: Decoding the Immune System to Diagnose Disease
The human immune system is an astonishing diagnostic engine, continuously adapting itself to detect any signal of disease in the body. Essentially, the state of the immune system tells a story about virtually everything affecting a person’s health. What if we could “read” this story? Our scientific understanding of human health would be fundamentally advanced. More importantly, this would provide a platform for a new generation of precise medical diagnostics and treatment options. We are partnering with Adaptive Biotechnologies to develop the machine learning and biotechnology tools that will allow us to realize this dream.
Fundamental advances towards new medicines and therapeutics
Protein Engineering
Several research groups are delving into the potential of machine learning to enhance our comprehension of proteins and their pivotal role in various biological processes. We are also using AI to design new proteins for therapeutics and industry. By applying machine learning to extract patterns from databases of sequences, structures, and properties, Microsoft hopes to train models that can make protein engineering by directed evolution more efficient, and directly generate proteins that will perform desired functions. The ability to generate computationally distinct yet viable protein structures holds tremendous promise for uncovering novel biological insights and developing targeted therapies for previously untreatable illnesses.
Investigating the Cancer Microenvironment through Ex Vivo Research
Microsoft is working on ways to identify specific characteristics of cancer cells and their surrounding microenvironments that might be targeted for treatment. By studying how cancer cells and their surroundings interact with each other, the team aims to create a more precise approach to cancer treatment that takes into account both genetic and non-genetic factors.
Accelerating biomedical research
Microsoft and the Broad Institute – combining their expertise in genomics, disease research, cloud computing and data analytics – are developing an open-source platform to accelerate biomedical research using scalable analytical tools. The platform is built on top of the Broad Institute’s Terra platform, providing a user-friendly interface for accessing and analyzing genomic data. Leveraging Microsoft’s Azure cloud computing services, the platform will enable secure storage and analysis of large datasets. Additionally, the platform will incorporate machine learning and other advanced analytical tools to help researchers gain insights into complex diseases and develop new treatments.
Advancing clinical interpretation and exploration through multimodal language models
In the quest for precision medicine and accelerating biomedical discovery, Microsoft is committed to advancing the state of the art in biomedical natural language processing (NLP). A crucial factor in future-facing, data-driven health systems is the accessibility and interpretability of multimodal health information. To meet this need, Microsoft has laid a solid foundation across multiple modalities in biomedical NLP building on our deep research assets in deep learning and biomedical machine reading.
One significant achievement is our development and application of large language models (LLMs) in biomedicine. Microsoft was among the first to create and assess the applicability of LLMs, such as PubMedBERT and BioGPT, which are highly effective in structuring biomedical data. However, to address the inherent limitations of LLMs, Microsoft is developing methods to teach them to fact-check themselves and provide fine-grained provenance. Additionally, Microsoft is exploring ways to facilitate efficient verification with humans in the loop.
Besides text, other modalities such as radiology images, digital pathology slides, and genomics contain valuable health information. Microsoft is developing multimodal learning and fusion methods that incorporate these modalities. These methods include predicting disease progression and drug response, with the ultimate goal of delivering safe and high-quality healthcare.
Observational data in biomedicine is often plagued by confounders, making it challenging to draw causal relationships. To overcome this obstacle, Microsoft is developing advanced causal methods that correct implicit biases and scale biomedical discovery. These methods will allow Microsoft to leverage real-world evidence and contribute to the creation of more effective healthcare delivery systems. For our end-to-end biomedical applications, we have made exciting progress in deep collaborations with Microsoft partners such as The Jackson Laboratory and Providence St. Joseph Health.
Empowering everyone to live a healthier future
Microsoft has pursued interdisciplinary research that enables people to reach the full potential of their health for many years, but we’ve never been more excited about the possibilities than we are today. The latest developments in AI have inspired us to accelerate our efforts across these and many other projects, and we look forward to even more innovation and collaboration in this new era.
Opens in a new tab
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.microsoft.com/en-us/research/blog/ai-and-the-future-of-health/
|
[
{
"date": "2023/03/30",
"position": 7,
"query": "AI healthcare"
}
] |
How low-paid workers in Madagascar power French tech's ...
|
How low-paid workers in Madagascar power French tech’s AI ambitions
|
https://theconversation.com
|
[
"Clément Le Ludec",
"Maxime Cornet"
] |
A January 2023 investigation by Time magazine revealed that Kenyan workers paid less than US$2 an hour were given the job of trying to ensure that the data ...
|
A January 2023 investigation by Time magazine revealed that Kenyan workers paid less than US$2 an hour were given the job of trying to ensure that the data used to train the AI platform ChatGPT was free from discriminatory content.
AI models need to be trained, with the input of an enormous critical mass of data, for them to learn to recognise and interact with the human environment. These inputs need to be collected, sorted, verified, and formatted. Such time-consuming and undervalued tasks are generally outsourced by technology companies to an army of precarious workers, usually based in the Global South.
This data work takes several different forms, depending on the purpose of the final algorithm. For example, it might involve outlining people in images captured on video camera to teach the algorithm how to recognise a human. Or one might be checking the outputs of an automatic invoice-processing tool, and correcting errors manually to help the computer in with its task.
To explore the identity of these data workers, their roles and working conditions, and enrich the debate around regulating the AI sector, we set up an investigation conducted between Paris and Antananarivo, capital of Madagascar.
Our study also shows the reality of AI, French style: one the one hand, France’s tech companies depend on the Big Five (Google, Apple, Facebook, Amazon and Microsoft) hosting services and processing power; on the other, data tasks performed by workers in former French colonies, notably Madagascar, confirming well-established trends in outsourcing. There has already been research, incidentally, comparing the tech sector with mining and textiles.
A study in AI globalisation
Our research project kicked off in Paris in March 2021. We first set out to understand what involvement French AI houses had in data work activity, and what processes were in place to ensure sufficiently high-quality data sets are produced for training computer models. We carried out interviews with 30 founders and employees working in 22 Parisian firms in the AI ecosystem. One finding rapidly emerged from this initial exploration – most of the data work was outsourced to Malagasy contractors.
For a second part of the study, conducted at first remotely, then in situ in Antananarivo, we interviewed 147 workers, managers and directors at ten Malagasy companies. At the same time we sent out a questionnaire to 296 data workers based in Madagascar.
Precarious work for well-educated city youth
Our initial enquiries showed that AI data workers were part of a much wider IT service sector, ranging from call-centre staff to web content moderators, to search-engine optimisation (SEO) copywriters.
Questionnaire responses showed that the majority of workers employed in the sector are male (68%), young (87% were less than 34 years old), urban-dwelling and educated (75% had gone through, attained or had had at least some higher education). When the work was within the formal, rather than the black or grey economy, respondents were generally permanent staffers. The minimal protections offered by Madagascan, as opposed to French employment law, workers’ ignorance of their rights, and the weakness of trade unions and worker representation in Malagasy companies heightened the precariousness of their position. They mostly earned between 96 and 126 euros a month, with a huge gap between their pay and that of team supervisors: who also tend to be Madagascan, working in-country, but taking home 8 to 10 times as much.
The shop-floor workers find themselves at the end of an extremely long outsourcing chain, which partly explains the miniscule pay even by Malagasy standards. The AI production line involves three different players: data hosting services/processing power offered by the Big Five tech companies, French companies that sell the AI models, and companies offering the data annotation services delivered by Madagascan workers. Each level takes its cut.
The companies wrangling the data are generally very dependent on their French clients, who manage the outsourced workforce in a quasi-direct manner, imposing middle-managers working with the interests of Parisian start-ups in mind. The domination of these roles by foreigners – either employed by the client companies in France, or expats working in Antananarivo – represents a serious block on career progression for the workers, who remain ignominiously stuck at the bottom of the value chain.
Profiting from post-colonial France-Madagascar links
The AI sector benefits from a specific policy – “tax-free zones” created in 1989 for the textile industry. Since the start of the 1990s, French businesses have been setting up satellites in Madagascar, notably for the digital-publishing industry. The special zones, the equivalent of which can be found in many other developing countries, pull in investment by offering highly attractive tax exemptions.
Today, out of 48 businesses offering digital services in the tax-free zones, only nine are owned by Madagascans, compared to 26 owned by French people. Aside from the situation with formally constituted companies, the sector has developed a practice of cascade subcontracting, with grey-economy businesses and entrepreneurs at the bottom of the pecking order, poorly treated and chivvied into action when there are workforce shortages elsewhere in the sector.
As well as cheap labour, this outsourced industry profits from a well-educated workforce – most have been to university and speak fluent French, which they learned at school, online or at Institut Francais classes. This latter institution of induction into French language and culture, set up in 1883, was originally intended to extend imperial power through language to the colonised population.
This scenario aligns with what researcher Jan Padios labels “colonial recall”. Former colonies with linguistic and cultural ties to countries that used to hold sway now supply them with business services.
Making AI workers visible to better understand how they function
Behind the recent explosion in commercialised AI projects in the Global North, one uncovers growing numbers of data workers. The recent controversy around “intelligent security cameras” at the Paris Olympics focused mostly on the ethics of blanket surveillance. There is a need to better account for the vital component of human labour that goes into training AI models, especially because it raises new questions about working conditions and right to a private life.
To make the roles of these workers visible is to ask probing questions about globalised production chains. These are more familiar in the manufacturing industry, but are also a feature of the digital sector. These workers are essential to the functioning of our digital infrastructure – they are the invisible cogs of our digital lives.
It also makes visible the impact of their work on the AI models. One part of algorithmic bias lies in the nature of how data work is conducted, although the reality of this is largely kept under wraps by AI companies. A truly ethical AI must therefore set ethical standards for AI sector working conditions.
Le projet The HUman Supply cHain behind smart technologies – HUSH est soutenu par l’Agence nationale de la recherche (ANR), qui finance en France la recherche sur projets. Elle a pour mission de soutenir et de promouvoir le développement de recherches fondamentales et finalisées dans toutes les disciplines, et de renforcer le dialogue entre science et société. Pour en savoir plus, consultez le site de l’ANR.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://theconversation.com/how-low-paid-workers-in-madagascar-power-french-techs-ai-ambitions-202421
|
[
{
"date": "2023/03/30",
"position": 60,
"query": "artificial intelligence workers"
}
] |
How to use AI ethically and effectively in the workplace
|
How to Use AI Ethically in the Workplace
|
https://www.phoenix.edu
|
[] |
According to Baker, many marketing professionals, content creators and even job applicants are leveraging AI chatbot technologies to enhance their work. “So far ...
|
It seems just about anytime new technologies enter the workplace, employees are wary of the implications. After all, if AI can do the same tasks humans do but with greater accuracy and efficiency, wouldn’t that nullify human workers?
According to Baker, it doesn’t typically work out that way. “People have been worried about technology taking their jobs since the ’70s,” she says. “In truth, technology will often change the nature of our work and may even remove processes from our day-to-day. But if anything, it allows professionals to take on more robust projects.”
Baker says technology often removes the menial aspect from a person’s responsibility and replaces it with more technical work, usually in the form of managing the technology and reporting on its use.
Still, AI technology may shift job demand in certain sectors. “Copywriters, technical writers and content generators may be in less demand in the future, but organizations will be expected to produce the same if not more content,” Baker predicts.
Thus, Baker encourages those entering the workforce to learn a variety of skill sets. “The average career these days contains four to five significant shifts in role. People no longer do the same role for the same company for decades on end,” she says.
Instead, it’s become important to obtain a broad education that gives you various hard and soft skills and exposes you to different technologies. While employers may not require proficiency in using them, Baker suggests job applicants become familiar with these emerging technologies.
Take coding, for instance. According to Baker, “A few decades ago, only software developers and IT specialists were expected to know coding languages. Now, many employers expect even their new hires to be familiar with code.”
The nature of work in any industry will likely continue to evolve given the speed at which AI technologies are being implemented. The best course of action is to understand how these technologies can improve our work processes and how an organization’s policies and protocols can ensure their ethical use.
| 2023-03-30T00:00:00 |
https://www.phoenix.edu/blog/how-to-use-ai-ethically-and-effectively-in-the-workplace.html
|
[
{
"date": "2023/03/30",
"position": 69,
"query": "artificial intelligence workers"
},
{
"date": "2023/03/30",
"position": 27,
"query": "artificial intelligence business leaders"
}
] |
|
AI: friend or foe of workers?
|
AI: friend or foe of workers?
|
https://www.furious-squad.com
|
[
"Furious Erp"
] |
AI should actually be seen as a suite of tools that can help solve problems faster and instantly interpret complex data once the right questions have been ...
|
2023 will see the democratization ofArtificial Intelligence.
At least, that’s what many professionals agree, given the various trends that are beginning to emerge: open source, generative AI, specific regulations on the subject…
Proof of this is that by now, almost everyone has heard of ChatGPT, and prevention and detection systems have already been put in place to prevent certain types of fraud.
The fact that Google and Microsoft have decided to launch their own conversational robots only confirms that AI has a bright future ahead of it.
Don’t believe in myths
Artificial intelligence is often perceived as a danger to humankind or to jobs because of its association with science-fiction films such as “Terminator” or “I Robot”.
But that doesn’t have to be the case.
In the digital age, where billions of pieces of data are created every day, AI should actually be seen as a suite of tools that can help solve problems faster and instantly interpret complex data once the right questions have been asked and the tool is properly configured.
An invaluable aid for workers who will simply correlate a large amount of data faster than a human being could.
An analogy could well be made with land cultivation a century ago. Back then, farmers cultivated small plots of land with the tools at their disposal, such as ploughs and spades. Later, with the advent of technology, tools were developed that enabled thousands of hectares to be cultivated with less effort.
Technological advances have come to relieve human labor, not replace it.
We need to adapt AI to our business, not the other way round
Of course, certain professions and sectors are more likely than others to adopt this technology.
Take, for example, companies that process large amounts of data on their customers and operations.AI and ERP now combine to deliver real added value, providing accurate information, proactive recommendations and much faster analysis than manual processing.
Instead of replacing workers, AI can accompany them in their work by helping them understand complex data.
Let’s take the example of a baker a step further. In principle, he will have no immediate need for AI. His expertise is irreplaceable: flours and ferments are living materials, too changeable and irregular to be mastered by artificial intelligence.
But if it ever needs to process large volumes of data on its customers or operations, then there will undoubtedly be added value to be found with AI.
It’s easy to see how cash technology will evolve to secure and facilitate the transaction, freeing up the customer’s and the saleswoman’s attention.
The central cash register can be increasingly intelligent, with a diversification of business applications: remote order management, inventory, purchasing, e-commerce site, hygiene and traceability procedures, consumer information (ingredients, allergens), sales recommendations, etc.
The user experience at the point of sale and the integration of digital tools will be at the heart of innovation, enriching the commercial relationship.
The human race still has a long way to go
It’s quite understandable that certain job categories fear for their future. But rather than panic, let’s look at this as an opportunity to learn new subjects and bring their touch of humanity that no artificial intelligence yet possesses.
In 2019, the OECD stated that, “Only 14% of existing jobs are at risk of complete automation, not nearly 50% as other research suggests.” Furthermore, 32% of jobs could “profoundly change”, without actually disappearing.
There is still a huge gap to be bridged before we can achieve AI that is comparable to human intelligence, particularly in terms of its ability to understand the context of interactions between individuals and/or with objects. That’s why integrating these new technologies with a strategic approach is essential if we are to manage our business effectively and keep pace with changes in the world of work.
AI is and will remain the result of a software architecture (type of neural networks, number of layers, learning methods, etc.) derived from human logic.
Repetitive, uncomplicated tasks should therefore be left to the machine, and the development of concepts and projects to man.
The development of AI is not destined to work against human beings, as there will always be a need for human beings to ask the right questions and bring the work of these intelligences to fruition.
So it’s important to understand its added value now, and use it strategically to support employees’ work and help them evolve rather than replace them.
This article by Davy Tessier, CEO and founder of Furious, can be found in Forbes.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.furious-squad.com/en/ai-friend-foe-workers/
|
[
{
"date": "2023/03/30",
"position": 74,
"query": "artificial intelligence workers"
}
] |
The impact of AI on businesses
|
The impact of AI on businesses
|
https://www.thinkwithgoogle.com
|
[] |
As artificial intelligence (AI) becomes more present in our daily lives, its benefits, combined with human expertise, are transforming business productivity ...
|
Want to create a new Google Ads account?
You're about to create a new Google Ads account. You can create multiple campaigns in the same account without creating a new account.
| 2023-03-16T00:00:00 |
2023/03/16
|
https://www.thinkwithgoogle.com/marketing-strategies/automation/impact-of-ai/
|
[
{
"date": "2023/03/30",
"position": 26,
"query": "artificial intelligence business leaders"
}
] |
Business Ethics and the Integration of Artificial Intelligence ...
|
Business Ethics and the Integration of Artificial Intelligence (AI)
|
https://balancedscorecard.org
|
[
"Terry Sterling",
"Root",
"--M-A-Box-Bp",
"--M-A-Box-Bp-L",
".M-A-Box",
"Width",
"Margin-Top",
"Important Margin-Right",
"Important Margin-Bottom",
"Important Margin-Left"
] |
When designing and implementing AI into an organization, leaders must be mindful of this potential effect on employees, customers, and stakeholders and be ...
|
As artificial intelligence (AI) becomes more advanced, it is important to consider its impact on society and the environment, as well as the legal and ethical implications of its use.
So, what is all the buzz about? What is artificial intelligence (AI)? AI refers to the development of computer systems capable of performing tasks typically requiring human intelligence. Examples would include learning, reasoning, problem-solving, perception and natural language processing. AI systems accomplish this through the utilization of algorithms and complex statistical models which make them capable of analysis and learning. They are able to identify patterns, perform forecasting, and complete complex tasks with incredible speed and accuracy. AI has a wide range of applications and already being used in the fields of healthcare, finance, transportation, customer service, and more.
Ethic Concerns
One of the biggest concerns with the continued improvement in capabilities of the AI platforms is in the realm of ethics. There exists a potential to perpetuate biases and discrimination into the systems. This can occur when the algorithms input into the AI systems are trained on biased data, which leads to biased outcomes. It is essential companies take proactive steps to ensure their AI systems are tested to be fair, transparent and unbiased.
Workforce
Another ethical consideration in the integration of AI is the potential impact on the workforce. As AI can greatly increase efficiency and productivity, there exists the probability of job displacement and inequality. When designing and implementing AI into an organization, leaders must be mindful of this potential effect on employees, customers, and stakeholders and be proactive in mitigating any negative consequences.
Privacy and Security
Privacy and security are also major concerns with it comes to AI. As AI systems mature, they become more sophisticated in nature and able to collect and analyze vast amounts of personal data. Organizations must put steps in place to ensure this data is used ethically and responsibly. Safeguarding this information and preventing data breaches or unauthorized access and usage are essential.
Accountability
Lastly is the issue of accountability. As AI continues to develop and become more autonomous, it may become increasingly difficult to assign responsibility when things don’t go as planned. Organizations must establish clear lines of authority and responsibility for the actions and consequences of their AI systems.
Balanced Scorecard Can Help
In order to develop a sound strategy to encompass these concerns, the balanced scorecard (BSC) can be utilized as an effective tool to help companies address these issues. One way the BSC can address the problem of AI ethics is by incorporating ethical considerations into the Organizational Capacity perspective. Including these considerations at this level can promote a culture of ethics and responsibility to help ensure AI systems are developed and utilized in a responsible and ethical manner.
Another way the BSC can help address the issue of AI ethics is by including ethical considerations in the Internal Processes perspective. Including ethical considerations in this perspective which primarily focuses on processes and systems, organizations are able to ensure AI systems are designed and implemented in an ethical and responsible manner building in compliance routines with relevant polices, procedures, laws and regulations.
Finally, the BSC can be used an effective system for developing, tracking and measuring the performance of AI systems against ethical guidelines and considerations. By including KPIs around the principles of ethics in the Financial and Customer perspectives, organizations are able to ensure their AI systems are delivering value from an ethical and responsible viewpoint in addition to objectives focused on profit, customer service and other typical objectives seen in these two perspectives. An example of a Key Performance Indicator (KPI) in this area might be the percentage of AI-generated recommendations accepted by accountable parties and implemented.
In conclusion, the BSC is a powerful tool that can be incorporated by businesses as they struggle to ensure ethics are a part of their AI development and not an afterthought. Embark on your AI journey by checking out our AI course, Generative AI Essentials for Strategic Advantage and Competitive Edge. You can also connect with us via email or call us at 919-460-8180 for more information.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://balancedscorecard.org/blog/business-ethics-and-the-integration-of-artificial-intelligence-ai/
|
[
{
"date": "2023/03/30",
"position": 53,
"query": "artificial intelligence business leaders"
}
] |
Enhancing Business Value with Human Ingenuity
|
Scale AI + Accenture: Enhancing Business Value with Human Ingenuity
|
https://scale.com
|
[] |
Artificial Intelligence (AI) has been a game-changer for everyone. Together with data, AI has become a key component of a robust digital core—the main ...
|
Artificial Intelligence (AI) has been a game-changer for everyone. Together with data, AI has become a key component of a robust digital core—the main source of competitive advantage for companies today. The advent of generative AI marks the beginning of a new era, one where businesses reinvent how they work. Just search for ChatGPT if you haven’t already, and you’ll get an idea of the possibilities. ChatGPT is derived from a large language model (LLM)—GPT4—developed by Open AI, which is a foundation model capable of generating human-like language and carrying out complex tasks across a number of functions.
We are entering an era of AI industrialization, where entire industries stand to be transformed by new, innovative applications of generative AI. One of the highest barriers to unlocking business value using generative AI and LLMs, however, is customizing and fine-tuning the pre-trained foundation models for their unique needs, using their own data. That’s why Accenture is partnering with Scale AI.
video
Generative AI partner spotlight: Scale AI
Accenture’s collaboration with Scale AI focuses on helping enterprises use their own data on general purpose models, customizing them to suit their business needs. According to CEO and founder Alexandr Wang, Scale AI has been “quietly powering this generative AI wave, providing the data and infrastructure for many of the top companies to actually build large-scale foundation models, including Open AI.”
Accenture and Scale AI are collaborating to provide an enterprise LLM platform for enterprise and government clients to fine-tune generative AI models that can learn from human input through a process called Reinforcement Learning from Human Feedback (RLHF). The result is generative models optimized for human interaction that are able to improve how people live and work.
For example, Scale AI was able to help retail clients gain higher shopping conversion and sales by using AI-generated product images for their newest products. And with social media clients, AI-generated content led to more than 100 million impressions.
Could humans have done this? Absolutely – but at what cost to the business?
This is business augmentation at the intersection of human and machine. By freeing up employees from automatable, routine tasks, we can redirect energy and focus to more strategic creative work that requires human intuition, decision-making and problem-solving skills - work that generative AI cannot do—at least not yet. The combination of human plus machine results in more efficient processes, improved decision-making and greater innovation.
Success with generative AI depends as much on people and training as it does on technology. It’s up to business leaders to take the lead in upskilling employees and reshaping jobs and tasks to get the most out of technologies like generative AI.
Thanks to partnerships like this one with Scale AI, Accenture helps leaders create business value with generative AI technology quickly and at scale.
| 2023-03-30T00:00:00 |
https://scale.com/blog/scale-and-accenture
|
[
{
"date": "2023/03/30",
"position": 73,
"query": "artificial intelligence business leaders"
}
] |
|
The Future is Now - AI and Machine learning for recruitment
|
AI and Machine learning for recruitment
|
https://wearemercury.com
|
[
"Daniel Fox"
] |
The future of recruitment and staffing is one where AI can analyse enormous amounts of data to identify trends, activity, and even personal circumstances.
|
Ever wondered how many hours are wasted on tasks that take away from building your business and achieving more? Then it’s time to embrace the power of AI, machine learning, and Automation to make your teams more effective.
Microsoft is investing billions of dollars in AI technology to make us more efficient and effective. The fruits of that investment are already evident in MS Teams and other parts of the platform.
One example is conversation transcription and intelligence, where AI can analyse conversations, phone calls, and meetings to identify keywords, phrases, tone of voice, and emotions to provide feedback and insights.
So, imagine using AI to analyse your meetings and phone calls to confirm that agenda items have been covered, decisions have been made, actions completed, and essential details captured.
This technology can also partner with Automation to trigger next-step actions, such as booking meetings, sending follow-up emails, setting reminders, and updating your ATS or CRM, saving you time and ensuring you don’t miss any follow-up actions.
Chat GPT has been a hot topic recently and amazed everyone with its ability to generate text quickly in many writing styles. At Mercury, we leverage this technology to help generate candidate profiles, original and engaging job descriptions and adverts and even start a candidate search to ensure you get to the best people first.
The future of recruitment and staffing is one where AI can analyse enormous amounts of data to identify trends, activity, and even personal circumstances to seek out passive candidates who have the propensity to move before they even signal that they’re looking. Predictive recruitment will identify the passive candidates worth spending time on!
Using Mercury already leverages Microsoft’s pioneering AI and Machine Learning technology, allowing you to unleash the power behind your data AND your people. So why wait? The future is now. Please speak to one of our experts today to build a more effective team.
Written by Daniel Fox, Marketing Manager at Mercury.
| 2023-03-27T00:00:00 |
2023/03/27
|
https://wearemercury.com/the-future-is-now-ai-and-machine-learning-for-recruitment-and-staffing/
|
[
{
"date": "2023/03/30",
"position": 21,
"query": "artificial intelligence hiring"
}
] |
Modern Hire wins 2023 AI Excellence Award
|
Modern Hire wins 2023 AI Excellence Award
|
https://www.hirevue.com
|
[
"The Hirevue Team"
] |
Commitment to Ethical AI in Hiring ... All of Modern Hire's (now part of HireVue) recent advances with AI have been developed within the framework of our ...
|
We’re honored to be recognized for our leadership in artificial intelligence by Business Intelligence Group, which has selected Modern Hire (now part of HireVue) for a 2023 AI Excellence Award. The AI Excellence Award highlights organizations that are developing and using unique, practical AI solutions to solve real world problems. With our advanced selection science and ethical AI, Modern Hire (now part of HireVue) is transforming hiring for enterprises worldwide and helping them significantly reduce bias in talent acquisition.
Innovative Application of AI in Interviewing
Each year, Business Intelligence Group highlights market-changing AI innovation. Last year, Modern Hire (now part of HireVue) deployed Automated Interview Scoring and Automated Interview Creator (AIC), two applications that utilize cutting-edge AI to reduce bias and improve decision-making in candidate interviews.
Though interviewing is a foundational hiring practice, its disadvantages are well known: Interviewing can be time-consuming, prone to human bias, and a low-ROI exercise for both companies and candidates. Modern Hire’s (now part of HireVue) team, which includes almost 50 PhD-level psychologists, harnessed the power of AI to improve interviewing’s flaws.
Automated Interview Scoring (AIS) automatically scores interview responses like trained human experts but does so with more than 3x less bias than human interviewers, which significantly increases fairness and objectivity in the hiring process. AIS helps interviewers avoid unconscious bias by providing a standardized, consistent, and objective selection methodology that brings the focus to the job-relevant aspects of candidates’ responses. Using proven industrial/organizational psychology methods and innovative AI, AIS reliably replicates the judgment of professionally trained experts. Modern Hire’s (now part of HireVue) AIS models were rigorously developed and found to have extremely high levels of accuracy replicating expert raters. In short, AIS enables hiring teams to score more interview responses faster with much less bias.
Automated Interview Creator (AIC) makes it easy for hiring teams to identify the ideal questions for interviews using an AI-driven search engine integrated with a robust library of questions directly linked to job requirements. Modern Hire’s (now part of HireVue) I-O team developed the library using insights from hundreds of Modern Hire (now part of HireVue) validation studies over decades and across numerous industries and jobs. With AIC, hiring teams have confidence that they are asking the interview questions that will lead to the best hiring outcomes.
Commitment to Ethical AI in Hiring
All of Modern Hire’s (now part of HireVue) recent advances with AI have been developed within the framework of our commitment to ethical AI in hiring. Our focus has always been and always will be to develop beneficial AI and deploy it in a safe, ethical, and humane manner for organizations and for individuals. To that end, we developed six core principles for ethical AI and algorithms that are rigorously followed as we evolve our platform and assessments. These principles establish a sound footing for industry practice that is grounded in our research and decades of experience in measuring human performance. We believe that for AI to be truly transformative, its development and deployment must be guided by a deep understanding of its impact on people.
Our thanks go to Business Intelligence Group for recognizing our team’s achievement in advancing AI that has a positive impact on candidates, hiring teams, organizations and people.
Read more about Modern Hire’s (now part of HireVue) glass-box approach to AI, and how our principles of ethical AI come to life in our intelligent hiring platform.
| 2023-03-30T00:00:00 |
https://www.hirevue.com/blog/hiring/modern-hire-wins-2023-ai-excellence-award
|
[
{
"date": "2023/03/30",
"position": 52,
"query": "artificial intelligence hiring"
}
] |
|
Hire Elite Artificial Intelligence Engineers
|
Hire Artificial Intelligence Engineers
|
https://www.fullstack.com
|
[] |
As AI technology continues evolving and increasingly integrating into businesses, the demand for qualified AI professionals has grown exponentially. However, ...
|
Artificial Intelligence Hiring Guide
Introduction
As AI technology continues evolving and increasingly integrating into businesses, the demand for qualified AI professionals has grown exponentially. However, hiring for AI positions can be challenging, as the industry requires a unique blend of technical expertise and creativity. FullStack has a wide range of AI professionals available to join your team. Still, if you want to recruit directly, we'll provide you with a comprehensive resource for attracting and hiring top talent in AI. We'll cover three essential areas of the hiring process, including AI Conversational Interview Questions, AI Technical Interview Questions, and an AI Job Posting Template. By the end of this guide, you'll be better equipped to identify and attract the best candidates for your organization.
{{interview-qa-header="/hiring-docs/ai"}} 1. What motivated you to become an AI professional, and what skills do you bring to this field? I've always been passionate about technology and using it to make people's lives better. AI provides an incredible opportunity to do just that. I have a degree in computer science and several years of experience working with machine learning algorithms and natural language processing. I'm also proficient in programming languages like Python and R, and I have a strong background in data analysis. 2. What challenges have you faced when working with AI, and how have you overcome them? One of the most significant challenges when working with AI is ensuring the accuracy of the data used to train the algorithms. I've worked on projects where the data was noisy or unstructured, making it difficult to achieve the desired outcomes. To overcome these challenges, I've developed data preprocessing techniques to clean the data and make it more suitable for training the algorithms. I've also worked collaboratively with data scientists and domain experts to develop more robust models. 3. How do you stay current with the latest advancements in AI technology, and what industry resources do you rely on? As AI technology is constantly evolving, staying up to date is essential. I regularly attend conferences and workshops, read research papers, and follow AI thought leaders on social media. I also participate in online forums and communities dedicated to discussing AI and continuously experimenting with new tools and techniques. 4. What programming languages and AI frameworks are you proficient in, and how have you used them in your past work? I am proficient in programming languages such as Python, Java, and C++. I have also worked with popular AI frameworks like TensorFlow, PyTorch, and Keras. I've used these tools in my previous roles to build natural language processing models, image recognition models, and recommendation systems. 5. How do you approach solving complex AI problems, and what steps do you take to ensure accuracy and reliability in your solutions? When approaching complex AI problems, I break them down into smaller, more manageable pieces. I also ensure that I deeply understand the data and the business problem at hand. I always test my models thoroughly, using cross-validation and A/B testing techniques. I also collaborate closely with domain experts and other stakeholders to ensure that the solutions I develop are accurate, reliable, and meet the needs of the business. 6. What experience do you have with unsupervised learning, and how have you used it in your work? I have worked with unsupervised learning techniques such as clustering and anomaly detection to identify patterns in large datasets. In one project, I used clustering to segment customer data and identify different user personas, which helped our marketing team create more targeted campaigns. In another project, I used anomaly detection to detect fraud in financial transactions. 7. How do you approach feature engineering, and what techniques have you used to improve the accuracy of your models? Feature engineering is a crucial step in the AI modeling process. I approach feature engineering by first understanding the underlying business problem and then brainstorming features that might be relevant. I then use techniques such as feature scaling, dimensionality reduction, and feature selection to refine the features and improve the model's accuracy. 8. What is the difference between supervised and unsupervised learning? In supervised learning, the machine is trained on labeled data, and the goal is to predict the label of new, unseen data. In contrast, in unsupervised learning, the machine is trained on unlabeled data, and the goal is to discover underlying patterns or structure in the data. 9. What is overfitting, and how can you avoid it? Overfitting occurs when a machine learning model is too complex and fits the training data too closely, resulting in poor performance on new, unseen data. To avoid overfitting, you can use regularization, early stopping, and data augmentation techniques. 10. Can you explain the bias-variance tradeoff? The bias-variance tradeoff is a fundamental concept in machine learning that refers to the tradeoff between a model's ability to fit the training data (bias) and its ability to generalize to new, unseen data (variance).
{{tech-qa-header="/hiring-docs/ai"}} 1. What is backpropagation, and how does it work? Answer: <p span class="guide_indent-text">Backpropagation is a method used to train neural networks by computing the gradient of the loss function concerning the network weights. It works by first performing a forward pass to compute the output of the network, then computing the error between the output and the true label, and finally propagating the error back through the network to update the weights.</p> <div style="padding-bottom: 2.85rem;"></div> 2. What is the difference between a generative and discriminative model? Answer: <p span class="guide_indent-text">A generative model learns the joint probability distribution of the input features and the output labels. In contrast, a discriminative model learns the conditional probability of the output labels given the input features.</p> <div style="padding-bottom: 2.85rem;"></div> 3. What is transfer learning, and how does it work? Answer: <p span class="guide_indent-text">Transfer learning is a technique used to leverage pre-trained models to improve the performance of a model on a new task. It works by fine-tuning the pre-trained model on the new task or using the pre-trained model as a feature extractor.</p> <div style="padding-bottom: 2.85rem;"></div> 4. What is reinforcement learning, and how does it work? Answer: <p span class="guide_indent-text">Reinforcement learning is a type of machine learning where an agent learns to take actions in an environment to maximize a reward signal. It works by iteratively interacting with the environment, observing the state of the environment, taking action, and receiving a reward signal.</p> <div style="padding-bottom: 2.85rem;"></div> 5. What is the difference between batch normalization and layer normalization? Answer: <p span class="guide_indent-text">Batch normalization is a technique used to normalize the inputs of a neural network layer by computing the mean and variance over the entire batch of examples. In contrast, layer normalization is a technique used to normalize the inputs of a neural network layer by computing the mean and variance over the features of each.</p>
{{job-qa-header="/hiring-docs/ai"}} Introduction In today's competitive job market, it's essential to have a well-written job posting to attract top talent. This guide will provide you with tips and tricks for creating an excellent AI job posting template that will help you find the best candidates for your organization. <div style="padding-bottom: 2.85rem;"></div> Job Title The job title is the first thing potential candidates will see and should be clear and concise. Avoid using jargon or acronyms that may not be familiar to everyone. Consider including the word "AI" in the job title to help with search engine optimization. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> AI Engineer <div style="padding-bottom: 2.85rem;"></div> Job Description The job description should summarize the position's purpose and responsibilities. Be sure to highlight the most important aspects of the job and provide a clear picture of what the role entails. Use active language and strong verbs to make the job exciting and engaging. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> <p span class="guide_indent-text">We are looking for an experienced AI Engineer to join our team and help us develop innovative AI solutions. The AI Engineer will work closely with our data science team to design, build, and deploy AI models that will drive our business forward.</p> <div style="padding-bottom: 2.85rem;"></div> Key Responsibilities In this section, outline the primary duties and responsibilities of the position. Be specific and concise, and avoid using vague language. Use bullet points to make it easy for candidates to scan the information. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> Develop and implement AI models and algorithms to solve complex business problems
Collaborate with cross-functional teams to integrate AI solutions into existing systems
Analyze and interpret data to identify patterns and trends
Research and stay up-to-date with the latest advancements in AI technology <div style="padding-bottom: 2.85rem;"></div> Requirements The requirements section should include both the technical skills and experience necessary to perform the job successfully. Be sure to include any mandatory qualifications, such as education or certification. Use bullet points to make it easy for candidates to read and understand. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> Bachelor's or Master's degree in Computer Science or related field
Minimum of 3 years of experience in AI development and implementation
Proficiency in programming languages such as Python, Java, or C++
Knowledge of machine learning algorithms and techniques
Familiarity with data visualization tools such as Tableau or Power BI <div style="padding-bottom: 2.85rem;"></div> Preferred Qualifications This section should include any additional skills or experience that would be beneficial but optional. Be sure to prioritize the most important qualifications. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> PhD in Computer Science or related field
Experience with cloud-based AI solutions such as AWS or Azure
Familiarity with natural language processing (NLP) or computer vision (CV)
Strong problem-solving and analytical skills
Ability to communicate complex technical concepts to non-technical stakeholders <div style="padding-bottom: 2.85rem;"></div> Benefits In this section, outline the benefits of working for your organization. Be sure to highlight any unique perks or benefits that set your company apart. Use bullet points to make it easy for candidates to read and understand. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> Competitive salary and benefits package
Flexible work hours and remote work options
Opportunity to work on cutting-edge AI solutions
Collaborative and inclusive company culture
Professional development and training opportunities <div style="padding-bottom: 2.85rem;"></div> How to Apply In this section, you should provide clear instructions on how to apply for the position. Be sure to include any necessary documents, such as a resume or cover letter, and the contact information for the person responsible for hiring. <div style="padding-bottom: 1.14rem;"></div> <span class="guide_indent-text">Example:</span> To apply for this position, please send your resume and cover letter to [email protected]. Please include "AI Engineer" in the subject line. We look forward to hearing from you! <div style="padding-bottom: 2.85rem;"></div> Job Template Conclusion Creating an excellent AI job posting template can be challenging, but finding the right candidate for your organization is worth the effort. By following these guidelines, you can create a compelling job posting that resonates with potential candidates. <div style="padding-bottom: 2.85rem;"></div>
Conclusion
| 2023-03-30T00:00:00 |
https://www.fullstack.com/talent/capabilities/artificial-intelligence
|
[
{
"date": "2023/03/30",
"position": 58,
"query": "artificial intelligence hiring"
}
] |
|
What Are the Pitfalls of Using AI in the Recruitment?
|
What Are the Pitfalls of Using AI in the Recruitment?
|
https://www.recruitninjas.com
|
[
"Kimberly Morrison"
] |
Using Artificial intelligence in recruitment can significantly reduce the time and cost involved in hiring by automating tasks such as resume screening ...
|
With the rise of technology, artificial intelligence (AI) has been increasingly utilized in various industries, including recruitment. However, is it always practical and efficient?
Artificial intelligence in recruitment has been on the rise, with many companies seeking to streamline their hiring processes and improve their candidate selection. However, there may be better approaches than relying solely on AI.
While AI can bring some benefits to recruitment, such as reducing bias and increasing efficiency, some pitfalls must be considered. In this article, we’ll explore the potential drawbacks of using AI in recruitment and why human oversight is still crucial in hiring.
Benefits of AI in Recruitment
Time And Cost-Saving Benefits
Using Artificial intelligence in recruitment can significantly reduce the time and cost involved in hiring by automating tasks such as resume screening, scheduling interviews, and communicating with candidates. AI recruitment tools can also analyze large amounts of data to identify top candidates, reducing the need for human intervention and saving time.
Objectivity And Fairness In The Hiring Process
AI recruitment tools can remove human biases from the hiring process by analyzing candidates based on predetermined criteria, such as skills and qualifications. This can lead to a more objective and fair hiring process, reducing the risk of discrimination.
Increased Efficiency In Candidate Screening
AI can quickly and accurately screen resumes and applications, identifying candidates who meet the job requirements and eliminating those who do not. This saves time and ensures that hiring managers are only presented with the most qualified candidates, reducing the risk of overlooking quality candidates due to human error.
Pitfalls of Using Artificial Intelligence in Recruitment
Biases In The Algorithms
AI systems are only as good as the data they are trained on. If the training data is biased, then the AI algorithm will also be limited. Biases can arise from the historical data used to prepare the AI, the subjective criteria for defining success, or the algorithms’ design. This can result in discrimination against certain groups of people, such as women, minorities, and people with disabilities.
How Can Biases Be Introduced Into AI Algorithms?
Data Bias: If the data used to introduce an algorithm is biased, the algorithm is likely to produce partial results. For example, if a facial recognition algorithm is trained on predominantly white data, it may have difficulty accurately identifying people with darker skin tones.
Algorithm Bias: Biases can also be introduced through the design of the algorithm itself. For example, if an algorithm is designed to prioritize specific characteristics, such as educational qualifications, it may unfairly disadvantage candidates without access to the same educational opportunities.
Human Bias: Humans who design and implement AI algorithms may also introduce their own biases consciously or unconsciously. For instance, a programmer from a particular background may have a worldview that unconsciously shapes their design algorithm.
Lack of Transparency In Decision-Making
AI systems can sometimes make difficult decisions to explain. This lack of transparency can make it challenging to identify and address biases and lead to distrust in the recruitment process.
Additionally, when AI makes hiring decisions, it can be difficult to know the criteria used to make those decisions.
Limited Emotional Intelligence In AI
AI systems lack emotional intelligence, which can be a significant drawback in recruitment. Emotional intelligence is an essential component of a successful employee. AI may be able to analyze and interpret data to identify candidates’ qualifications and experiences, but it cannot evaluate traits such as communication skills, teamwork abilities, and personality traits.
Risk of Legal And Ethical Issues
AI systems used in recruitment can create legal and ethical issues. For example, using facial recognition software to assess candidates’ personalities or suitability for a job could violate privacy laws. AI systems could also lead to unintended discrimination against protected classes or failure to accommodate disabilities. Therefore, organizations must ensure that their AI systems comply with legal and ethical guidelines.
Risk of Legal and Ethical Issues Arising From Lack of Transparency
Discrimination: If AI recruitment tools are not transparent in their decision-making processes, they may perpetuate biases and discriminate against certain groups, leading to legal and ethical issues. Privacy: Lack of transparency can also lead to privacy concerns, as individuals may need to learn how their personal information is used in AI decision-making processes. Accountability: A lack of transparency can make it challenging to hold organizations accountable for the decisions made by their AI recruitment tools, leading to legal and ethical issues.
Importance of Ensuring Diversity and Inclusivity In AI Design:
Fairness: Ensuring diversity and inclusivity in AI design is crucial to preventing discrimination and ensuring everyone is treated fairly. Accuracy: Diverse and inclusive data sets can help ensure that AI algorithms are accurate and effective for all users. Innovation: Diverse teams working on AI design can lead to more innovative solutions that consider the needs and perspectives of different communities. Ethical Considerations: Ensuring diversity and inclusivity in AI design is a moral imperative that can help prevent harm to vulnerable communities.
Conclusion
While Artificial intelligence in hiring can revolutionize recruitment processes and improve efficiency, it is essential to be aware of the potential pitfalls. Bias in data sets, lack of transparency in algorithms, and ethical concerns must be addressed to ensure that AI is used responsibly and moderately.
By understanding these challenges and taking steps to mitigate them, organizations can harness the power of AI while avoiding unintended consequences. Ultimately, a thoughtful approach that balances technology with human expertise will improve outcomes for employers and job seekers.
Do you have questions about the potential pitfalls of Artificial Intelligence in Recruitment? Ask us today! Our Author is more than happy to answer your questions!
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.recruitninjas.com/blog/pitfalls-of-using-ai-in-recruitment/
|
[
{
"date": "2023/03/30",
"position": 59,
"query": "artificial intelligence hiring"
}
] |
Careers at Vector
|
Vector Institute for Artificial Intelligence
|
https://vectorinstitute.ai
|
[] |
Explore career opportunities at Vector. Join some of the world's top minds in AI, and help make a positive impact on Canadian lives ... Dedication to hiring ...
|
Why Work Here?
People are the key to our success
Our top priority is to foster a rewarding, flexible, and overall amazing work culture that encourages growth, development and achievement amongst a diverse and inclusive team.
We value your work
With highly competitive benefits including an 8% employer-sponsored GRRSP, health and wellness spending accounts, and a generous parental leave top-up, a flexible hybrid work environment, and a culture that encourages collaboration, innovation, and recognition.
Learning is core to our culture
We make strategic investments to give our professionals and researchers the opportunity to learn every day. This means access to continuous learning through research, commercialization talks, events, courses and employee-selected professional development to accelerate their careers.
| 2023-03-30T00:00:00 |
https://vectorinstitute.ai/about/opportunities/
|
[
{
"date": "2023/03/30",
"position": 90,
"query": "artificial intelligence hiring"
}
] |
|
As AI booms, tech firms are laying off their ethicists
|
As AI booms, tech firms are laying off their ethicists
|
https://www.washingtonpost.com
|
[
"Gerrit De Vynck",
"Will Oremus",
"Kevin Schaul",
"Szu Yu",
"Nitasha Tiku",
"Joseph Menn",
"Pranshu Verma"
] |
Twitch, Microsoft and Twitter are among firms that have laid off workers who studied the negative sides of AI.
|
Last year, Amazon-owned streaming platform Twitch acknowledged it had a problem. For much of the company’s 12-year history, women and people of color had argued the platform was biased. Sexist and racist harassment were endemic, and critics said the company’s all-important recommendation algorithms, which use artificial intelligence to decide which streamers to promote to viewers, were amplifying the problem.
As part of its response, the company set up a responsible AI team to look specifically at the algorithms. At its semiannual conference, TwitchCon, the team’s principal product manager told Twitch streamers, “We are committed to being a leader in this area of responsible and fair recommendations.” He urged them to fill out demographic surveys to track potential discrimination.
But last week, the handful of people who made up the responsible AI team were laid off, part of a broader round of cuts that hit about 400 of the company’s 2,500 employees. Others who worked on the issue as part of their current jobs have been moved to other topics, according to a former member of the responsible AI team, who spoke on the condition of anonymity to discuss internal company matters.
Advertisement
“We wanted to make Twitch more equitable and also more safe for creators from all backgrounds,” the former employee said. “This is very much a step back.”
Twitch isn’t the only company to cut its responsible AI team in recent months. Twitter did the same in November, as Elon Musk took over the company and cut three-quarters of the workforce. And Microsoft cut its Ethics and Society team, which was one of the groups that led research on responsible AI at the company, as part of its massive round of layoffs in January.
Together, the moves form a pattern of companies rethinking or pulling back on ethical AI research, often as part of broader cost-cutting, even as new applications of the technology are booming. Ethical AI experts say the breakup of these teams could result in products that are harmful being released before their consequences are fully examined.
Advertisement
“To me, it feels like they’re in a race, and they just want to win the race, and anybody who’s doing anything else is useless,” said Timnit Gebru, a computer scientist who once helped lead Google’s ethical AI team, before she was controversially ousted in December 2020.
Fewer than 10 people lost their jobs when Microsoft cut its team, and some former members are now working on the company’s other groups focused on developing AI responsibly, Microsoft spokesman Frank Shaw said. “We have hundreds of people working on these issues across the company,” he added.
A Twitch spokesperson declined to comment on the company’s approach to AI and pointed to a blog post from its CEO that said the broader economic environment led to its layoffs. Twitter did not respond to a request for comment.
The cuts are coming just as a new wave of “generative” AI technology takes the tech world by storm, spurring a flurry of excitement, investment and product launches. Generative AI tools like OpenAI’s ChatGPT, Midjourney’s image generator and Google’s Bard chatbot can create images, write computer code and hold humanlike conversations.
Advertisement
OpenAI, a smaller company that was founded as a nonprofit, began pushing its products out to the public last year, giving regular people the chance to interact with tools that had previously been confined to the testing labs of giants like Google and Microsoft.
The wild success of those start-ups’ tools prompted a wave of concern at the most powerful companies that they were falling behind the cutting edge, according to conversations with current and former employees of Facebook and Google, who spoke on the condition of anonymity to discuss internal company conversations. Companies that had moved more cautiously, taking feedback from internal teams that asked probing questions about the social ramifications of new products, are now moving faster to keep up with competitors and ride the wave of hype surrounding the technology.
On Tuesday, a large group of academics and business leaders including Musk, veteran AI researcher Yoshua Bengio and Apple co-founder Steve Wozniak signed a letter asking AI companies to pause the training of new, more powerful chatbots.
“Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable,” the letter said.
Gebru, who went on to start a nonprofit dedicated to researching AI’s potential harms and seeking solutions, said she has come to view tech companies’ internal AI ethics efforts as “window dressing” that they’re quick to cast aside when it’s inconvenient or when they’re cutting costs. Since firing Gebru, Google has also dismissed two other leading AI researchers over the publication of critical papers. One of them, Margaret Mitchell, was hired by New York-based AI start-up Hugging Face in November.
Advertisement
A Google spokesperson declined to comment on its approach to responsible AI, but the company has a “Responsible AI and Human Centered Technology” team that does research on the impacts of AI tech and works with product teams at the company, according to its website. At the time Gebru left the company, a Google executive posted a memo online saying Gebru did not follow the company’s guidelines for publishing research, though other employees said those guidelines were not generally enforced for other people.
The company has been rushing to launch generative AI products in the past few months, working to keep up with archrival Microsoft and hold on to its reputation as the top AI company in the world, according to current and former employees. All of its blog posts and product launches have mentioned the importance of developing the tech responsibly, and the company has been careful to call new, unproven products “experiments” or “previews” even as it makes them available to more and more people.
Rumman Chowdhury led Twitter’s acclaimed META team — an acronym for Machine Learning, Ethics, Transparency and Accountability — until Musk laid her off in November, along with every member of her 18-person team except one.
Advertisement
The team had been credited with innovative programs such as a “bias bounty,” in which the company offered prizes to outsiders who could demonstrate bias in its systems.
AI ethics is “seen as a cost center, not a revenue center,” Chowdhury said. “I think smart companies know this will cost them in the long run. But a lot of them are thinking short-term right now.”
Still, there could be upsides to integrating AI ethics work more closely into product development, Chowdhury said, if companies like Microsoft and Facebook parent Meta are serious about doing so.
After Facebook was accused of allowing foreign governments to use its platform to post propaganda that influenced American voters during the 2016 election, tech companies invested heavily in teams that dug into the broader societal impacts of their products. AI tech, which helps run social media recommendation algorithms for Facebook, Twitter and YouTube, was a core part of those teams’ research. Employees put out papers detailing negative side effects of the tech and showing how human biases had worked their way into products used by millions of people.
Advertisement
Some of the ethics cuts are coming as waves of layoffs strike the tech industry.
A former employee at the social media firm Snap, who spoke on the condition of anonymity to discuss personnel matters, said the company’s layoffs last summer included one of its only employees working full time on machine-learning fairness, derailing a nascent internal working group on the topic.
Snap spokeswoman Rachel Racusen said the company does not have a dedicated AI ethics team but continues to invest in employees focused on developing products safely and responsibly, including AI. Racusen confirmed one employee’s departure but said it did not derail the working group, which she said went on to complete its work on time.
There’s a lot of attention on the big questions of whether sentient AI may be developed soon and what risks could come with that, as shown by the letter signed by Musk and other leaders asking for a pause in AI development. But focusing on those future questions may distract from problems that are real right now, Chowdhury said.
Advertisement
“I think it’s easy when you’re working in a pure research capacity to say that the big problem is whether AI will come alive and kill us,” Chowdhury said. But as these companies mature, form corporate partnerships and make consumer products, she added, “they will face more fundamental issues — like how do you make a banking chatbot not say racial slurs.”
Those kinds of issues were the ones that slowed the public launch of unproven AI tools in the past. When Microsoft put out its AI chatbot “Tay” in 2016, it was quickly manipulated into spouting racism and denying the Holocaust. The company took Tay offline.
The new publicly available bots have had problems of their own. When Microsoft launched its Bing chatbot in February, some users quickly discovered that the bot would adopt an alternate persona with an aggressive tone, contradicting the human asking it questions and calling itself “Sydney.” Microsoft said the problem happened because of people making leading prompts and pushing the bot into a certain conversational direction. The company limited the number of questions users could ask Bing in a row.
Advertisement
The bots also repeatedly make up information and present it as fact, mixing it with legitimate information. Microsoft and Google have begun proactively pointing out this flaw in new-product announcements.
OpenAI, which helped kick off the current wave of AI excitement by launching its DALL-E image generator and ChatGPT conversation bot to the public before Big Tech companies had done the same with their own tools, is increasing its investments in responsible AI along with its investments in the technology, spokesperson Hannah Wong said. “While the entire company works closely together to develop and release safe and advanced AI systems, we are continuing to grow our teams dedicated to policy research, alignment, and trust and safety, which are critical to this work.”
Ethical AI researchers who remain inside of companies will have to adapt and realize that they need to show their employers why listening to them will ultimately help the company avoid problems and make more money down the line, the former Twitch employee said.
“We need to make sure that communication is done in a manner such that it doesn’t seem like people who are talking about the responsible application [of AI] are gatekeeping, which we are not,” they said. “We are advocating for the safe and sustainable development of products.”
| 2023-03-30T00:00:00 |
2023/03/30
|
https://www.washingtonpost.com/technology/2023/03/30/tech-companies-cut-ai-ethics/
|
[
{
"date": "2023/03/30",
"position": 4,
"query": "artificial intelligence layoffs"
}
] |
Lessons and Tools for Teaching About Artificial Intelligence
|
Lessons and Tools for Teaching About Artificial Intelligence
|
https://www.commonsense.org
|
[] |
We've uncovered a great set of classroom resources for teaching students about the tech behind AI. These resources, which we've curated below, unpack how AI ...
|
It can be tough for teachers to prepare students for the jobs of the future. Who knows what lies ahead 10 or 20 years? Whatever the future holds, it's likely that artificial intelligence (AI), machine learning, and language models like ChatGPT or Bard will be a big part of it. Thankfully, we've uncovered a great set of classroom resources for teaching students about the tech behind AI. These resources, which we've curated below, unpack how AI can be used and its current and future economic, cultural, and social impacts. Thankfully, most are free and have ready-to-use lessons and activities. Several also feature games or interactive features that help students build and tinker with their own AI- or machine learning-driven tools.
| 2023-03-30T00:00:00 |
https://www.commonsense.org/education/lists/lessons-and-tools-for-teaching-about-artificial-intelligence
|
[
{
"date": "2023/03/30",
"position": 45,
"query": "artificial intelligence education"
}
] |
|
The AI Classroom: The Ultimate Guide to Artificial ...
|
The AI Classroom: The Ultimate Guide to Artificial Intelligence in Education
|
https://www.goodreads.com
|
[] |
This thought-provoking book provides practical strategies for incorporating AI tools into your teaching practices, while exploring the potential of AI.
|
Educators will have a vital role to play in the rapidly emerging artificial intelligence revolution. Humanity and technology are teaming up to unleash a brand-new world of possibilities filled with groundbreaking advances that will allow us to reimagine teaching and learning! Are you an educator looking to stay ahead in the ever-changing world of education? Look no further than The AI Classroom , the ultimate guide for navigating the complexities of AI in education. This thought-provoking book provides practical strategies for incorporating AI tools into your teaching practices, while exploring the potential of AI to transform traditional models of teaching and learning. Discover how AI can help you create inclusive and accessible learning environments, personalize learning, reach more students, and get your time back. Let’s unlock the full potential of artificial intelligence and embrace its transformative power to take your craft to the next level! In The AI Classroom you will “... pedagogical methods, ethical effectiveness, and trailblazing strategies that force us to rethink how we design learning experiences.” - Jennifer Womble, Conference Chair, FETC
“...this comprehensive guide is a great way to learn and understand all about the future of AI in the classroom.” - Lee Parkinson, Mr P ICT “...The AI Classroom will empower educators to do the thinking while giving them the tools to let technology do the doing." - Nicolas Cole, Author and Co-founder of Ship 30 for 30 “...the literature equivalent of capturing lightning in a bottle.” - David Price OBE, Author of the bestselling book The Power of Us.
| 2023-03-30T00:00:00 |
https://www.goodreads.com/book/show/125172711-the-ai-classroom
|
[
{
"date": "2023/03/30",
"position": 89,
"query": "artificial intelligence education"
}
] |
|
Preparing the Workforce for an AI-Driven Economy
|
AI and the Future of Work: Preparing the Workforce for an AI-Driven Economy
|
https://www.uschamber.com
|
[
"Brent Orrell"
] |
A recent University of Pennsylvania study found that 80 percent of American jobs are likely to see at least 10 percent of their tasks altered by AI while almost ...
|
To paraphrase Mark Twain, reports of the “end of work” have been greatly exaggerated – more than once. Throughout history, the arrival of new technology has been regarded as a threat to human work and, in every instance, new technology has been integral to unlocking new work, new value, and rising incomes.
This hopeful view is not the same thing, however, as saying that new technology, like artificial intelligence, will be all upside for every worker, all the time, everywhere. The recent report from the U.S. Chamber’s Commission on Artificial Intelligence Competition, Inclusion, and Innovation acknowledges that the effects of AI on employment will be both uneven and hard to predict. The report emphasizes that, at its core, AI tools are informing and expanding, not replacing, human labor and, “if developed and deployed ethically, [AI] has the ability to augment human capabilities and empower people to do much more.”
How Workers and Businesses Can Prepare for the AI Economy of the Future
By its nature, technological innovation requires businesses and workers to learn and adapt—and learning and adaptation can be hard. Sometimes, it means upskilling within an existing job and at other times finding a whole new job in a different sector.
This learning and adaptation process is likely to be particularly demanding when it comes to AI. A recent University of Pennsylvania study found that 80 percent of American jobs are likely to see at least 10 percent of their tasks altered by AI while almost 20 percent of jobs will see at least 50 percent of their tasks altered. Another study by Goldman Sachs largely echoed these findings estimating that 18 percent of jobs globally could be computerized with “knowledge” and “information” tasks especially exposed.
During one of the AI Commission’s field hearings, Cheryl Oldham, vice president of education policy at the U.S. Chamber, emphasized that if we’re going to minimize any labor market disruptions and build new and effective pathways that lead to AI-related jobs, “we need to proactively lean into workforce development.”
To do so, the report recommends:
Training and Reskilling: The creation of new programs that can help ease worker transitions find and improve incentives for businesses to invest in retraining as necessary.
The creation of new programs that can help ease worker transitions find and improve incentives for businesses to invest in retraining as necessary. Educating the Future Workforce: Urging students and workers to prepare early and to continuously upgrade their knowledge, skills, and abilities.
Urging students and workers to prepare early and to continuously upgrade their knowledge, skills, and abilities. Economic Policies: Encouraging Congress to adopt tax policies that support “human labor augmentation” within firms rather than ones that incentivize the substitution of technology for human labor and skill.
AI is neither the end of work nor a future delivered on a golden platter. Rather, it is a new tool that, just like new tools of the past, will take time, effort, and practice to master.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://www.uschamber.com/technology/artificial-intelligence/ai-and-the-future-of-work
|
[
{
"date": "2023/03/31",
"position": 13,
"query": "artificial intelligence employment"
},
{
"date": "2023/03/31",
"position": 13,
"query": "government AI workforce policy"
},
{
"date": "2023/03/31",
"position": 4,
"query": "artificial intelligence workers"
},
{
"date": "2023/03/31",
"position": 10,
"query": "artificial intelligence employers"
},
{
"date": "2023/03/31",
"position": 14,
"query": "artificial intelligence business leaders"
}
] |
Want to work in AI? This job pays six figures
|
Want to work in AI? This job pays six figures — English speakers preferred
|
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"
] |
One role now showing up in job listings: "prompt engineer." The job's main function is to help train the emerging crop of AI, also known as large language ...
|
Study finds that artificial intelligence could replace the equivalent of 300 million jobs
Artificial intelligence tools such as Chat GPT and Dall-E are sparking fears of the technology automating people out of a job, yet like previous waves of innovation, the advent of so-called generative AI is also starting to create new kinds of work.
"The good news is that worker displacement from automation has historically been offset by creation of new jobs, and the emergence of new occupations following technological innovations accounts for the vast majority of long-run employment growth," Goldman Sachs analysts said in a recent report that also forecast a sizable economic boost from AI.
One role now showing up in job listings: "prompt engineer." The job's main function is to help train the emerging crop of AI, also known as large language models (LLMs), to deliver more accurate and useful responses to the natural-language queries that people pose. More generally, the goal is to make AI smarter and more capable of accomplishing a wide array of professional tasks.
Notably, and unlike many higher-level jobs in tech, working as a prompt engineer doesn't necessarily require an engineering or coding background. One job listing for a prompt engineer describes the role as an "art" that's "a hybrid between programming, instructing and teaching."
Hot new programming language: English
Andrej Karpathy, a founding member of ChatGPT maker OpenAI and former senior director of AI at Tesla, recently tweeted that a prompt engineer can also be thought of "as a kind of LLM psychologist."
"The hottest new programming language is English," he tweeted in January after ChatGPT was publicly released, a reference to the fact that LLMs are trained based on prompts written in plain English, rather than computer code.
The hottest new programming language is English — Andrej Karpathy (@karpathy) January 24, 2023
The good news for job seekers? Some companies are willing to pay big bucks for such jobs, also referred to colloquially by some prompt engineers as an "AI whisperer."
"We are all amateur prompt engineers, but there is definitely a nuanced understanding to these models," said Edward Tian, a student at Princeton University who built GPTZero, an app that can detect whether a text was written by a human being or ChatGPT.
For example, LLMs are better at spitting out text in a certain style — say, in the voice of an elementary school student or a comedian — if they are shown an example, Tian explained.
"You'll get better results if you say to ChatGPT: 'Here is an example of elementary school writing and then you make the ask,'" he said. "It significantly improves results."
Prompt engineering is also typically less structured than traditional research experiments, which begin with hypotheses.
"With prompt engineering, no one really knows what the results are going to be, so we try a bunch of things and hopefully the LLM responds in a positive way," Tian said.
Seeking "creative hacker spirit"
A range of companies and industries are recruiting prompt engineers.
Anthropic, an AI research company and maker of Claude, an AI assistant, is currently seeking a "prompt engineer and librarian," according to a job posting on the company's website. The role involves building a library of prompts that get LLMs to accomplish different tasks.
Requirements for the position at the San Francisco company include familiarity with how LLMs work, excellent communication skills and what Anthropic describes as "a creative hacker spirit," among other qualifications. Basic programming skills and the ability to write small Python programs are also desirable. The pay: Between $175,000 and $335,000 a year.
Anthropic's job listing says the field of prompt engineering is less than two years old, making the role challenging to hire for. Anthropic
British law firm Mishcon de Reya is hiring a "GPT legal prompt engineer." The role will focus on helping the business "increase our understanding of how generative AI can be used within a law firm, including its application to legal practice tasks and wider law firm business tasks," the job posting states.
Klarity, a company that helps automate contract review, is hiring its own AI whisperer, who will earn between $130,000 and $230,000 a year to fine-tune LLM applications within the company.
Boston Children's Hospital in Boston is hiring an AI prompt engineer to work on its digital health platform. The desired candidate will have a strong background in both AI and machine learning (a subset of AI), as well health care research experience. The job entails designing AI prompts for LLMs "as they emerge for health care research studies and clinical practice."
"Super important" skill
To be sure, any job related to an AI chatbot requires a high level of familiarity and understanding of how LLMs work.
"They have to understand how to code, leverage AI models and understand how to talk to them," Gabor Soter, founder of Generative Nation, a site that educates the public about generative AI, told CBS MoneyWatch.
That said, Soter expects to see a raft new AI jobs.
"Some people underestimate what it takes, but these are front engineers getting hired for hefty salaries," he said. "I think it's a skill that's going to be super important for everyone, and I would highly encourage everybody who is not a data scientist to play around with these models."
| 2023-03-31T00:00:00 |
https://www.cbsnews.com/news/ai-artificial-intelligence-chatgpt-jobs-prompt-engineer/
|
[
{
"date": "2023/03/31",
"position": 25,
"query": "artificial intelligence employment"
},
{
"date": "2023/03/31",
"position": 47,
"query": "AI job creation vs elimination"
},
{
"date": "2023/03/31",
"position": 3,
"query": "generative AI jobs"
},
{
"date": "2023/03/31",
"position": 6,
"query": "AI employment"
},
{
"date": "2023/03/31",
"position": 55,
"query": "artificial intelligence hiring"
}
] |
|
AI and the Coming Productivity Paradox
|
AI and the Coming Productivity Paradox
|
https://www.steveglaveski.com
|
[] |
According to a study by the World Economic Forum, the adoption of AI is expected to create 133 million new jobs by 2022, primarily in industries such as ...
|
Artificial Intelligence (AI) has been a topic of debate among experts, policymakers, and the general public alike.
There are two schools of thought on the matter — one believes that AI will replace humans, leading to mass unemployment and social upheaval, while the other argues that AI will make us more productive, freeing us from tedious and repetitive tasks and enabling us to focus on higher-level work.
Let’s explore these two perspectives and analyze the potential impact of AI on the future of work.
Technology has historically made us more productive
Throughout human history, technology has been pivotal in making us more productive. Consider the transition from hunting and gathering to agriculture, which allowed humans to settle in one place and produce surplus food. This surplus led to the development of trade and specialization of labor, resulting in innovation and new industries and the emergence of artisans, craftsmen, and other specialized workers.
Similarly, the industrial revolution led to the mechanization of production, enabling factory workers to produce goods at an unprecedented scale and speed. This led to the mass production of goods, increased efficiency, and reduced costs, benefiting both businesses and consumers like nothing before.
Moving into the digital age, technology has made white-collar knowledge workers out of most of us. This shift has allowed us to leverage our creativity and problem-solving skills, collaborate with people globally, and work remotely. And instead of merely replacing jobs, new jobs emerged due to recent technological shifts such as the internet and mobile that did not exist 25 years ago. Think social media managers, app developers, and data scientists.
The past isn’t always the best predictor of the future
Advocates of AI will use such facts to argue that we have nothing to worry about. They argue that technology has historically made us more productive. They will say, in a very libertarian tone, that it is up to us to adapt and upskill ourselves to take advantage of these new opportunities.
But while disruptive paradigm-shifting technologies have undoubtedly made us more productive over time, they also historically created what economists call a productivity paradox. This refers to a period of time where society reorients around disruptive technologies in a way that can lead to negative economic growth and significant disruptions in the labor market.
For example, the transition from steam power to electricity in the late 19th and early 20th centuries led to a significant shift in the labor market. According to a study by the National Bureau of Economic Research, the introduction of electricity caused a 6% decline in the employment of steam-powered industries between 1899 and 1914.
However, this period was also marked by the emergence of new industries, such as electrical equipment manufacturing, which more than offset the job losses in steam-powered industries. As a result, employment in the electrical equipment manufacturing industry grew by a staggering 265% between 1899 and 1914, creating many new jobs and opportunities.
According to AI, here are just some jobs that AI threatens to displace in the short term.
Will we be replaced, augmented, or changed?
Today the rise of automation and artificial intelligence has led to concerns about job displacement and unemployment.
However, as history has shown us above, while temporary job losses may occur during the transition period, new industries and jobs emerge over time.
According to a study by the World Economic Forum, the adoption of AI is expected to create 133 million new jobs by 2022, primarily in industries such as healthcare, education, and renewable energy. AI is admittedly expected to displace 75 million jobs in the same time period.
But this time could be fundamentally different.
One fundamental difference between AI and previous technological shifts is that AI systems are self-learning mechanisms that operate as closed-loop systems — an argument posted by Chamath Palihapitiya on the popular All-In podcast.
This means they can process vast amounts of data, learn from their own experiences, and continuously improve their performance. This is in contrast to previous technological shifts where machines were programmed to perform specific tasks and could not learn or adapt on their own without human input and interaction.
AI has the potential to mimic and improve human judgment in ways that we cannot fathom. For example, AI can analyze large datasets and identify patterns and insights that most humans aren’t able to.
This ability to process and analyze vast amounts of data and make better decisions gives AI an unprecedented level of insight into human behavior and decision-making.
While there is potential for AI to create new jobs and industries, there is also a real concern that it could replace most of what humans do, and create a vacuum that won’t be filled overnight with new jobs that AI cannot do, leading to a long and unprecedented period of mass unemployment and social upheaval.
For example, a study by McKinsey Global Institute found that up to 375 million workers worldwide may need to switch occupational categories and learn new skills by 2030 due to automation and AI.
A rising tide lifts all boats?
Despite the potential challenges posed by AI, it has the potential to create significant economic opportunities and wealth for humanity in a way this lifts the living standards of all humans.
According to a study by PwC, AI could add up to $15.7 trillion to the global economy by 2030, creating new opportunities for economic growth and prosperity. Such models, it must be said, forecast the future based on what we know of the world today, not on what we know about it tomorrow. For example, a 1985 study on future economic growth would have not accounted for the impact of the internet, cloud, or mobile.
Nonetheless, the increased economic growth and wealth generation that AI promises could be redistributed to lift the economic standards for all humans.
Policies such as progressive taxation and universal basic income can ensure that the benefits of AI are shared more equally across society.
Moreover, this wealth creation could free humanity up to focus on what truly matters in life.
With the potential for increased wealth and productivity, humans may have more time and resources to devote to their passions, relationships, and personal growth.
Rather than being tied to mundane and repetitive tasks, humans could focus on pursuing their dreams, enjoying new experiences and places, and forging meaningful connections with others. This could lead to a more fulfilling and satisfying life, where individuals have the freedom to pursue their passions and live life to the fullest without the concern of financial outcomes.
If you ask someone “what job would you do if money was no issue?”, most people will tell you something other than what they actually do — they might say something like be a musician, a writer, a nurse or work with kids in developing economies. AI might give them the opportunity to do just that, driven purely by the intrinsic benefits derived and not at all by economic outcomes.
Final thoughts
In conclusion, while the impact of AI on society is uncertain, it could free humanity up to focus on what truly matters in life.
By harnessing the potential of AI and working to create a more equitable and prosperous society, we can create a future that benefits all humans, but it is up to us to harness the potential of AI and ensure that its benefits are shared widely across society.
Maybe the real question isn’t “will AI take our jobs?” but “will AI liberate our lives?”.
| 2023-03-31T00:00:00 |
https://www.steveglaveski.com/blog/ai-and-the-coming-productivity-paradox
|
[
{
"date": "2023/03/31",
"position": 93,
"query": "artificial intelligence employment"
},
{
"date": "2023/03/31",
"position": 70,
"query": "automation job displacement"
}
] |
|
What To Do About AI-Driven Job Displacement
|
What To Do About AI-Driven Job Displacement
|
https://www.peoplespolicyproject.org
|
[
"Matt Bruenig"
] |
As artificial intelligence continues to advance, it may lead to job displacement and lower wages for some workers. To help those affected by these changes, ...
|
The recent splash of Large Language Model (LLM) applications like GPT has generated considerable discourse around how society and government should respond to the technology.
Some worry that LLM technology will create AI companions that could become a new type of vice in the sense that some people could get so sucked into them that it may disrupt their normal functioning in harmful ways, especially when it comes to creating and maintaining important social ties. Others worry that LLM technology could be used by malicious actors or perhaps become so advanced that it becomes capable of independent malicious action.
But right now, the most common concern you hear, which is also the most immediate, is about LLMs being used as labor-saving technology that results in widespread job loss and displacement.
Every time a new technology or a new economic proposal requires a significant reallocation of labor — such as the phasing out of fossil fuels or the creation of a universal public health insurance system — we see this exact same discourse. It’s a strange discourse in that it never really changes but we also treat every instance of it as if it is a novel thing that requires a novel response.
The problem of job reallocation is a general one that is rooted in the fact that our national income is primarily doled out using factor payments to labor and capital. When people lose their jobs, their labor factor payments are reduced to $0 until such time as they find a new job. Finding a new job may also be difficult if the kinds of jobs a person is capable of doing are shrinking in number due to technological shifts. Once a new job is found, the factor payments that flow to it may also be significantly lower than the factor payments that flowed to the person’s prior job.
This constellation of issues is not constrained to a small group of people nor is it constrained to unique mass job loss events. In a typical year, there are around 20 million unemployment events in the US, defined as the number of times a person went from employed in one month to unemployed in the next month.
The solution to this problem is fairly straightforward and well-known. Give unemployed people cash benefits to replace their prior wages. Give them job search and retraining assistance to help them find new work. And, possibly, give them wage insurance to ensure that, if they do end up reallocated into a lower-paying job, they can receive benefits to make up for some of the difference, at least for some time.
When you ask ChatGPT “what kinds of welfare programs could help people whose suffer job loss and lower pay due to being displaced by artificial intelligence,” it actually gives the same answer:
As artificial intelligence continues to advance, it may lead to job displacement and lower wages for some workers. To help those affected by these changes, governments can implement various welfare programs aimed at easing the transition and supporting workers as they adapt to the new job landscape. Some potential welfare programs include: 1. Unemployment benefits: Providing financial assistance to workers who have lost their jobs, allowing them to meet basic needs while they search for new employment opportunities. 2. Wage insurance: As previously mentioned, wage insurance programs can help workers who find new jobs with lower pay by compensating them for a portion of the difference between their previous and current wages for a limited period. 3. Job training and reskilling programs: Investing in training programs to help displaced workers acquire new skills that are in demand, making them more competitive in the job market. 4. Education subsidies and grants: Offering financial assistance for workers to pursue further education, including university degrees or vocational training, to improve their job prospects. 5. Career counseling and job placement services: Providing guidance and support to help workers navigate the job market, identify new opportunities, and find suitable employment.
To this, I would add a couple of points.
Wage insurance is the conceptually clear answer to how to cushion the income shock from someone being reallocated into a lower-paying job, but this is a very uncommon program in the world. I actually don’t know of any country that has a significant wage insurance program in their welfare state.
As a general matter, how possible it is for someone to be reallocated into a job that pays much less than their current job is a function of how compressed or uncompressed a society’s wage scale is and how much of each person’s income and consumption bundle depends on their personal employment. In societies with very compressed wages and robust universal welfare states — like the Nordic societies — the ultimate differences between different labor market positions are relatively small, making it mathematically difficult for people to experience a major cut in their standard of living due to changing jobs. In the US, the opposite is true.
My writing frequently comes back to this same point, but that’s because it really is the solution to so much of the economic distress people experience and worry about in the US. An egalitarian society with a robust welfare state creates the kind of stability and minimum living standards that takes the financial sting out of things like unemployment, labor reallocation, disability, old age, and having children. We need this kind of society at all times, not just during splashy labor reallocation events like the one LLMs might cause.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://www.peoplespolicyproject.org/2023/03/31/what-to-do-about-ai-driven-job-displacement/
|
[
{
"date": "2023/03/31",
"position": 94,
"query": "artificial intelligence employment"
},
{
"date": "2023/03/31",
"position": 57,
"query": "government AI workforce policy"
},
{
"date": "2023/03/31",
"position": 71,
"query": "artificial intelligence workers"
}
] |
Industrial robots on workers: Winners and losers
|
Industrial robots on workers: Winners and losers
|
https://cepr.org
|
[] |
Directly affected workers are those employed in tasks that can be performed by robots and thus face a risk of displacement (Acemoglu and Restrepo, 2020). Labour ...
|
According to the International Standards Organization, an industrial robot is an actuated mechanism programmable in two or more axes, with a degree of autonomy, moving within its environment, to perform intended tasks. Industrial robots have already automated a variety of production tasks, from painting to welding, sorting and assembling, and they are on the rise. In the US, for example, the number of robots per 10,000 industrial workers increased from 35 in 1993 to 149 in 2014 and to 255 in 2020. The increase has been even starker in the Netherlands, where the number of robots per thousand industrial workers increased from 12 in 1993 to 209 in 2020.
Previous Vox columns and a burgeoning literature recognise that automation should have heterogeneous impacts on workers. For example, Golin and Rauh (2023) indicate that perceived automation risk strongly relates to workers’ preferences for redistribution and employment responses. Prettner and Bloom (2020) point out that robots mainly replace the routine tasks of low-skilled workers, while wealthier capital owners are likely the beneficiaries. The fact that industrial robots particularly affect routine and low-skilled workers is one of the reasons why Rebelo et al. (2020) advocate a robot tax, at least in the short run, as a way to protect workers who cannot acquire non-routine skills. These perspectives notwithstanding, there is little empirical evidence on whether industrial robots indeed negatively impact certain groups of workers – and whether some other types of workers simultaneously benefit.
In a recent paper, we study the effects of the adoption of industrial robots on workers in the Netherlands (Acemoglu et al. 2023). The Dutch economy provides an interesting context. In addition to being at the forefront of the spread of industrial robotics, as the numbers provided above suggest, the Dutch labour market has extensive labour market regulations that are meant to protect workers against disruptions and job loss. Lessons from the Dutch context can thus inform us both on the heterogeneous effects of robot adoption and on whether labour market regulations can successfully shield the most affected workers from negative consequences.
We use data from the trade register to obtain reliable information on robot adoption by tracking imports of manufacturing firms. We combine this with high-quality matched employer-employee data, covering about a million Dutch workers in manufacturing between 2009 and 2020.
Our results first confirm that the firm-level effects of robot adoption are similar in the Netherlands to those in other industrialised economies. Employment and value-added increase and labour share declines at robot-adopting firms. This overall pattern and the quantitative magnitudes of our estimates are very similar to those presented in Acemoglu et al. (2020) for France and Koch et al. (2021) for Spain. Moreover, as in French and Spanish manufacturing, these positive effects among adopters are only one side of the coin. The other side are significant negative effects on their competitors in the same industry, which experience lower value added and employment. This pattern also raises questions as to whether the effects on workers will be heterogeneous not just by skill but also by whether they are employed at robot-adopting or non-adopting firms.
To explore these questions, we distinguish directly affected workers from those that are indirectly affected. Directly affected workers are those employed in tasks that can be performed by robots and thus face a risk of displacement (Acemoglu and Restrepo, 2020). Labour market implications of robot adoption depend not just on displacement but also on the productivity gains that they bring. These productivity effects imply that indirectly affected workers (who should not be displaced from their tasks) should benefit from robot adoption.
We construct three complementary measures of directly affected workers. The first is blue-collar workers employed in routine tasks — the ones in which robots are now most commonly employed. The second measure is based on the replaceability index of Graetz and Michaels (2018), and, similarly, captures workers in occupations that involve tasks that robots can perform. The third measure simply focuses on the highest completed level of education by a worker, since lower-education workers are more likely to specialise in manual tasks substitutable with robots.
The results are very similar with all three measures and also when we include worker fixed effects so as to trace impacts on the same workers over time. As shown in Figure 1, directly affected workers experience lower hourly wages after robot adoption, while those who are not directly impacted enjoyed higher earnings.
Figure 1 Effects of robot adoption on workers’ wages
For example, in Panel A, without worker fixed effects, the wages of directly affected workers, in this instance measured as those performing blue-collar routine tasks, fall by about 6% following robot adoption, while indirectly affected workers enjoy wage gains of about 3.5%. The quantitative implications are somewhat smaller when worker fixed effects are included, presumably because this controls for worker selection. The results are similar for other measures of directly affected workers.
The negative employment and value-added changes at competitors suggest that to obtain a holistic picture of the worker-level implications of industrial robots, we also need to consider the impact on workers in other firms. When we do this, the patterns are broadly similar. Indirectly affected workers employed at competitors gain, while directly affected workers do not. These results suggest that not just opportunities at robot-adopting firms, but, relative to other workers, overall market opportunities deteriorate for workers specialized in tasks substitutable to industrial robots.
There are also heterogeneous effects on employment, though these are somewhat less precisely estimated, perhaps partly because of the slow adjustment in the heavily regulated Dutch labour market.
In sum, robot adoption appears to have highly heterogeneous effects on workers, in line with theoretical expectations. Whether we use the measure of workers performing blue-collar routine tasks or replaceable tasks, or focus on differences by worker education, directly affected workers seem to lose from robot adoption, while indirectly affected workers gain. These patterns thus reiterate the major distributional consequences of automation.
References
Acemoglu, D, H R A Koster and C Ozgen (2023), “Robots and workers: Evidence from the Netherlands”, NBER Working Paper 31009.
Acemoglu, D and P Restrepo (2020), “Robots and Jobs: Evidence from US labor markets”, Journal of Political Economy 128(6): 2188-2244.
Acemoglu, D, C Lelarge and P Restrepo (2020), “Competing with robots: Firm-level evidence from France”, AEA Papers and Proceedings 110: 383-388.
Golin, M and C Rauh (2023), “Workers’ responses to the threat of automation”, VoxEU.org, 8 March 8.
Graetz, G and G Michaels (2018), “Robots at work”, Review of Economics and Statistics 100(5): 753-768.
Koch, M, I Manuylov and M Smolka (2021), “Robots and firms”, Economic Journal 131(638): 2553-2584.
Prettner, K and D Bloom (2020), “The macroeconomic effects of automation and the role of COVID-19 in reinforcing their dynamics”, VoxEU.org, 25 June.
Rebelo, S, P Teles and J Guerreiro (2020), “Robots should be taxed, for a while”, VoxEU.org, 20 August.
| 2023-03-31T00:00:00 |
https://cepr.org/voxeu/columns/industrial-robots-workers-winners-and-losers
|
[
{
"date": "2023/03/31",
"position": 38,
"query": "automation job displacement"
}
] |
|
Beijing Welcomes Its New Robot Coworkers: China's Aging ...
|
Beijing Welcomes Its New Robot Coworkers: China's Aging Crisis and Automation
|
https://hir.harvard.edu
|
[
"Sam Meacham Is A Staff Writer For The Hir. He Is Interested In Conflict",
"Conflict Resolution",
"Political Economy",
"Economic Development."
] |
If automation works too well, a scarcity of labor may not be sufficient to save Chinese production workers from the threats automation may pose to countries ...
|
China’s population is falling.
In 2022, for the first time since 1961, more people died than were born in China. For years, observers have been clamoring about a coming demographic crisis, as a steady decline in the birth rate, combined with continued population aging, transforms the size and structure of the Chinese population. In accordance, China’s new economic normal was destined to include a smaller labor force, more elderly citizens dependent on the younger generations for their well-being, and strained welfare and pension systems. With the new data, the heralded crisis appears to have arrived.
The Roots of the Crisis
To some extent, China’s troubling demographic landscape is not unique. There is a well-documented negative correlation between per capita income and fertility rates across countries and periods of time, showing that, as a country becomes richer, it should expect fewer births per woman. At the same time, higher per capita incomes are associated with greater longevity. The Chinese experience bears this out, as state health authorities project that the proportion of the population over 65 years of age will increase from below 20 percent today to over 30 percent by 2035.
The demographic trends associated with China’s past four decades of rapid economic growth is roughly in line with the experiences of other countries such as Japan, as lower fertility and greater longevity combine to create a proportionally older population. But the Chinese experience includes one distinctive force that has magnified the size of the demographic crisis: the one-child policy.
In 1979, Chinese leaders, fearing the country’s then-rapid population growth would outrun the ability of the economy and state welfare systems to provide for Chinese citizens, instituted a policy limiting the vast majority of families to a single child. Legally effective from 1980 until its termination in 2016, the policy was enforced by restricting contraceptive access, imposing economic sanctions, and, in some cases, mandating sterilizations and abortions.
The one-child policy—and the culture of fear it produced—succeeded in achieving the Chinese government’s stated goal of reducing the fertility rate. Over the course of the one-child policy’s lifetime, fertility declined from 2.74 births per woman in 1980 to just 1.77 in 2016. And despite active governmental efforts to increase fertility, including a 2021 “three-child policy” and new financial incentives for having more children, China’s fertility rate has fallen further to 1.18 births per woman in 2022. This places China below the population replacement rate of 2.1 births per woman. China’s persistently low fertility rate in spite of these measures reveals the difficulty Beijing will have in changing the culture of reluctance to have children forged by years of legal and social sanction. Below-replacement fertility rates, combined with the unwillingness of individual families to have more children, all but ensure that aging and population decline will be irreversible.
The Demographic Disaster
A forty-year shortfall of new births accompanied by more elderly retirees has created a perfect storm for China. The country’s age pyramid is becoming increasingly skewed toward older adults, who will make up a larger and larger proportion of the Chinese population. China will likely face an absolute decline in the working-age population by about 260 million by 2050. Furthermore, China’s dependency ratio—the ratio of the population not of working age (aged zero to 14 and 65 and older) to the working-age population—will increase to over 76 percent in 2055, up from 45 percent in 2021. Such an age structure would place China well above the projected global average of 61 percent dependency in 2055, creating new risks for China’s labor market. Population aging is associated across countries with lower labor supply and slower economic growth, as cohorts of older adults exhibit lower labor force participation and tend to be less productive.
In practice, this will mean a greater burden on the backs of those of working age; this burden can take many forms. Younger workers may have to spend more time and money caring for aging family members. An older population means a higher proportion of GDP spent on healthcare. And, to address what is perhaps the concern most directly associated with a rising dependency ratio, pension funds—which rely on the contributions of younger workers to pay for current retirees—will come under greater strain as the number of retirees per worker grows. Indeed, Chinese state pension funds may run dry by 2035, owing to the declining workforce.
Facing pension and healthcare crises, the Chinese government might be forced into the unenviable position of choosing between lower living standards for the elderly, higher corporate or personal taxes, and reduced government spending in other areas—each one a threat to economic growth. Labor shortfalls, too, may play a role in slowing growth. The World Economic Forum projects an annual labor shortage of 11.8 million people over the next decade, and, while some of this gap is due to shortfalls in education and skills, most is attributable to falling birth rates.
It is extremely difficult for any country to sustain robust economic growth with a shrinking workforce. This is particularly true for China, whose rapid growth over the past several decades was driven by low-cost production and abundant labor. The International Monetary Fund projects China’s growth to continue to slow to an average of three percent after 2027, far below its past trajectory. This slow-growth trajectory would mean stagnating living standards in one of the world’s most populous countries, as well as dire consequences for global economic growth, which has been buoyed by a developing China.
Automation: A Balm for China?
China, of course, is not taking this crisis lying down. But, going through some of the potential ways to rejuvenate the labor force, one might be forgiven for remaining pessimistic. Immigration, a surefire way to address declines in domestic fertility, appears an infeasible solution; China’s net migration is currently negative, meaning more people leave the country than enter on an annual basis, and the Chinese government appears committed to its restrictive immigration policies. Increasing the birth rate has been met with resistance by families, and comes with a twenty-year time lag. And the Chinese government itself has admitted that the prospective raising of the retirement age will have a negligible effect on the labor force, serving, at best, as a temporary solution.
But one potential solution stands out: robots. Often viewed in the West as an antagonist—the fears of “robots taking our jobs” have become pervasive in the news media and US presidential campaigns alike—labor-saving automation could be the key to renovating China’s economic prospects. These technologies, ranging from industrial robots automating assembly-line production to emerging chatbots which may reduce the demand for white-collar workers, can substitute for human labor in the tasks they perform, enabling companies to produce the same output with less available labor.
Countries facing aging populations often avert the worst potential economic consequences by shifting productive tasks to robots. Within manufacturing, firms tend to respond to the scarcity of middle-aged production workers and the consequent increase in labor costs by automating certain tasks. And, in these aging countries, automation tends to have positive effects on labor productivity within the manufacturing sector. Where labor is plentiful, the fears that robots will outcompete human workers is plausible. Where labor is scarce, as will be the case for China in the near future, robots seem more likely to augment human labor, helping firms reap the economic benefits.
At least for now, the Chinese government seems to recognize the potential for automation to contribute to economic growth in a world where labor is more scarce. In 2022, the government released a five-year plan calling for China to become a global leader in industrial automation. The specific problems China faces as a result of its increasing dependency ratio could be meaningfully addressed by automation. Enhanced productivity could ensure young workers higher pay and greater ability to contribute to pension funds. And maintaining a higher growth rate than currently projected could help China to manage its fiscal affairs more easily, balancing the imperative of healthcare spending and social services for the elderly with sufficient spending in other areas.
But the path to a new robotic industrial economy will not necessarily be a smooth one. Already, concerns are being raised within China’s manufacturing sector about the devaluation of skilled labor associated with the installment of industrial robotics and the adoption of advanced manufacturing techniques. Because of the advanced nature of many new industrial technologies, these technologies can perform the tasks previously performed by skilled workers, demoting them to more routine, lower-paying positions.
If automation works too well, a scarcity of labor may not be sufficient to save Chinese production workers from the threats automation may pose to countries with higher labor costs, such as the United States or United Kingdom, including pay cuts, a reduction in worker bargaining power, and increased unemployment. Research on robot adoption in China backs this up, suggesting that increased firm-level adoption of robots decreases the probability of employment for manufacturing workers. Already some Chinese firms have expressed their desire to use automation not only to make up for a scarcity of labor, but to replace existing labor. Though, at the firm level and the national level, automation may do more good than it does harm, it may not be individually beneficial for much of China’s working class.
As China transitions to a service- and consumption-driven economy and begins to de-emphasize its traditional economic core of manufacturing, the government is betting big on automation to offset the population decline and aging crisis it is experiencing today. The rise of the industrial robot and the chatbot shows us that no job is safe, but this new reality may be a saving grace for China even as it presents a threat in the United States and Western Europe.
The data tells us that, where countries weather the storm of aging and low fertility, they typically have automation to thank. China appears to recognize this potential, and may be headed in the right direction in safeguarding the economy against stagnation. But this does not excuse the government from taking into account the distributional consequences of automation and the potential for displacement to overwhelm the augmentation of labor. As long as robots serve to enhance human well-being, though, current investments are more than worth it.
Despite the traditional fears associated with technological advancements in the workplace, Chinese workers perhaps ought to welcome their new robot overlords—or, to be more accurate, their new robot coworkers. The future of their country may demand it.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://hir.harvard.edu/beijing-welcomes-its-new-robot-coworkers-chinas-aging-crisis-and-automation/
|
[
{
"date": "2023/03/31",
"position": 85,
"query": "automation job displacement"
}
] |
Artificial Intelligence | Education
|
Artificial Intelligence
|
https://vocal.media
|
[] |
Lack of ability to generalize from one task to another. Eliminates human jobs, increasing unemployment rates. Strong AI vs. weak AI. AI can be categorized as ...
|
Artificial intelligence is the simulation of human intelligence processes by machines, especially computer systems. Specific applications of AI include expert systems, natural language processing, speech recognition and machine vision.
How does AI work?
As the hype around AI has accelerated, vendors have been scrambling to promote how their products and services use it. Often, what they refer to as AI is simply a component of the technology, such as machine learning. AI requires a foundation of specialized hardware and software for writing and training machine learning algorithms. No single programming language is synonymous with AI, but Python, R, Java, C++ and Julia have features popular with AI developers.
In general, AI systems work by ingesting large amounts of labeled training data, analyzing the data for correlations and patterns, and using these patterns to make predictions about future states. In this way, a chatbot that is fed examples of text can learn to generate lifelike exchanges with people, or an image recognition tool can learn to identify and describe objects in images by reviewing millions of examples. New, rapidly improving generative AI techniques can create realistic text, images, music and other media.
AI programming focuses on cognitive skills that include the following:
Learning. This aspect of AI programming focuses on acquiring data and creating rules for how to turn it into actionable information. The rules, which are called algorithms, provide computing devices with step-by-step instructions for how to complete a specific task.
Reasoning. This aspect of AI programming focuses on choosing the right algorithm to reach a desired outcome.
Self-correction. This aspect of AI programming is designed to continually fine-tune algorithms and ensure they provide the most accurate results possible.
Creativity. This aspect of AI uses neural networks, rules-based systems, statistical methods and other AI techniques to generate new images, new text, new music and new ideas.
Differences between AI, machine learning and deep learning
AI, machine learning and deep learning are common terms in enterprise IT and sometimes used interchangeably, especially by companies in their marketing materials. But there are distinctions. The term AI, coined in the 1950s, refers to the simulation of human intelligence by machines. It covers an ever-changing set of capabilities as new technologies are developed. Technologies that come under the umbrella of AI include machine learning and deep learning.
Machine learning enables software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values. This approach became vastly more effective with the rise of large data sets to train on. Deep learning, a subset of machine learning, is based on our understanding of how the brain is structured. Deep learning's use of artificial neural networks structure is the underpinning of recent advances in AI, including self-driving cars and ChatGPT.
Why is artificial intelligence important?
AI is important for its potential to change how we live, work and play. It has been effectively used in business to automate tasks done by humans, including customer service work, lead generation, fraud detection and quality control. In a number of areas, AI can perform tasks much better than humans. Particularly when it comes to repetitive, detail-oriented tasks, such as analyzing large numbers of legal documents to ensure relevant fields are filled in properly, AI tools often complete jobs quickly and with relatively few errors. Because of the massive data sets it can process, AI can also give enterprises insights into their operations they might not have been aware of. The rapidly expanding population of generative AI tools will be important in fields ranging from education and marketing to product design.
THIS ARTICLE IS PART OF
A guide to artificial intelligence in the enterprise
Which also includes:
AI regulation: What businesses need to know in 2023
4 main types of artificial intelligence: Explained
12 key benefits of AI for business
DOWNLOAD
1
Download this entire guide for FREE now!
Indeed, advances in AI techniques have not only helped fuel an explosion in efficiency, but opened the door to entirely new business opportunities for some larger enterprises. Prior to the current wave of AI, it would have been hard to imagine using computer software to connect riders to taxis, but Uber has become a Fortune 500 company by doing just that.
AI has become central to many of today's largest and most successful companies, including Alphabet, Apple, Microsoft and Meta, where AI technologies are used to improve operations and outpace competitors. At Alphabet subsidiary Google, for example, AI is central to its search engine, Waymo's self-driving cars and Google Brain, which invented the transformer neural network architecture that underpins the recent breakthroughs in natural language processing.
What are the advantages and disadvantages of artificial intelligence?
Artificial neural networks and deep learning AI technologies are quickly evolving, primarily because AI can process large amounts of data much faster and make predictions more accurately than humanly possible.
While the huge volume of data created on a daily basis would bury a human researcher, AI applications using machine learning can take that data and quickly turn it into actionable information. As of this writing, a primary disadvantage of AI is that it is expensive to process the large amounts of data AI programming requires. As AI techniques are incorporated into more products and services, organizations must also be attuned to AI's potential to create biased and discriminatory systems, intentionally or inadvertently.
Advantages of AI
The following are some advantages of AI.
Good at detail-oriented jobs. AI has proven to be as good or better than doctors at diagnosing certain cancers, including breast cancer and melanoma.
Reduced time for data-heavy tasks. AI is widely used in data-heavy industries, including banking and securities, pharma and insurance, to reduce the time it takes to analyze big data sets. Financial services, for example, routinely use AI to process loan applications and detect fraud.
Saves labor and increases productivity. An example here is the use of warehouse automation, which grew during the pandemic and is expected to increase with the integration of AI and machine learning.
Delivers consistent results. The best AI translation tools deliver high levels of consistency, offering even small businesses the ability to reach customers in their native language.
Can improve customer satisfaction through personalization. AI can personalize content, messaging, ads, recommendations and websites to individual customers.
AI-powered virtual agents are always available. AI programs do not need to sleep or take breaks, providing 24/7 service.
Disadvantages of AI
The following are some disadvantages of AI.
Expensive.
Requires deep technical expertise.
Limited supply of qualified workers to build AI tools.
Reflects the biases of its training data, at scale.
Lack of ability to generalize from one task to another.
Eliminates human jobs, increasing unemployment rates.
Strong AI vs. weak AI
AI can be categorized as weak or strong.
Weak AI, also known as narrow AI, is designed and trained to complete a specific task. Industrial robots and virtual personal assistants, such as Apple's Siri, use weak AI.
Strong AI, also known as artificial general intelligence (AGI), describes programming that can replicate the cognitive abilities of the human brain. When presented with an unfamiliar task, a strong AI system can use fuzzy logic to apply knowledge from one domain to another and find a solution autonomously. In theory, a strong AI program should be able to pass both a Turing test and the Chinese Room argument.
What are the 4 types of artificial intelligence?
Arend Hintze, an assistant professor of integrative biology and computer science and engineering at Michigan State University, explained that AI can be categorized into four types, beginning with the task-specific intelligent systems in wide use today and progressing to sentient systems, which do not yet exist. The categories are as follows.
Type 1: Reactive machines. These AI systems have no memory and are task-specific. An example is Deep Blue, the IBM chess program that beat Garry Kasparov in the 1990s. Deep Blue can identify pieces on a chessboard and make predictions, but because it has no memory, it cannot use past experiences to inform future ones.
Type 2: Limited memory. These AI systems have memory, so they can use past experiences to inform future decisions. Some of the decision-making functions in self-driving cars are designed this way.
Type 3: Theory of mind. Theory of mind is a psychology term. When applied to AI, it means the system would have the social intelligence to understand emotions. This type of AI will be able to infer human intentions and predict behavior, a necessary skill for AI systems to become integral members of human teams.
Type 4: Self-awareness. In this category, AI systems have a sense of self, which gives them consciousness. Machines with self-awareness understand their own current state. This type of AI does not yet exist.
four types of ai.DAVID PETERSSON
These are commonly described as the four main types of AI.
What are examples of AI technology and how is it used today?
AI is incorporated into a variety of different types of technology. Here are seven examples.
Automation. When paired with AI technologies, automation tools can expand the volume and types of tasks performed. An example is robotic process automation (RPA), a type of software that automates repetitive, rules-based data processing tasks traditionally done by humans. When combined with machine learning and emerging AI tools, RPA can automate bigger portions of enterprise jobs, enabling RPA's tactical bots to pass along intelligence from AI and respond to process changes.
Machine learning. This is the science of getting a computer to act without programming. Deep learning is a subset of machine learning that, in very simple terms, can be thought of as the automation of predictive analytics. There are three types of machine learning algorithms:
Supervised learning. Data sets are labeled so that patterns can be detected and used to label new data sets.
Unsupervised learning. Data sets aren't labeled and are sorted according to similarities or differences.
Reinforcement learning. Data sets aren't labeled but, after performing an action or several actions, the AI system is given feedback.
Machine vision. This technology gives a machine the ability to see. Machine vision captures and analyzes visual information using a camera, analog-to-digital conversion and digital signal processing. It is often compared to human eyesight, but machine vision isn't bound by biology and can be programmed to see through walls, for example. It is used in a range of applications from signature identification to medical image analysis. Computer vision, which is focused on machine-based image processing, is often conflated with machine vision.
Natural language processing (NLP). This is the processing of human language by a computer program. One of the older and best-known examples of NLP is spam detection, which looks at the subject line and text of an email and decides if it's junk. Current approaches to NLP are based on machine learning. NLP tasks include text translation, sentiment analysis and speech recognition.
Robotics. This field of engineering focuses on the design and manufacturing of robots. Robots are often used to perform tasks that are difficult for humans to perform or perform consistently. For example, robots are used in car production assembly lines or by NASA to move large objects in space. Researchers also use machine learning to build robots that can interact in social settings.
Self-driving cars. Autonomous vehicles use a combination of computer vision, image recognition and deep learning to build automated skills to pilot a vehicle while staying in a given lane and avoiding unexpected obstructions, such as pedestrians.
Text, image and audio generation. Generative AI techniques, which create various types of media from text prompts, are being applied extensively across businesses to create a seemingly limitless range of content types from photorealistic art to email responses and screenplays.
components of ai.
AI is not just one technology.
What are the applications of AI?
Artificial intelligence has made its way into a wide variety of markets. Here are 11 examples.
AI in healthcare. The biggest bets are on improving patient outcomes and reducing costs. Companies are applying machine learning to make better and faster medical diagnoses than humans. One of the best-known healthcare technologies is IBM Watson. It understands natural language and can respond to questions asked of it. The system mines patient data and other available data sources to form a hypothesis, which it then presents with a confidence scoring schema. Other AI applications include using online virtual health assistants and chatbots to help patients and healthcare customers find medical information, schedule appointments, understand the billing process and complete other administrative processes. An array of AI technologies is also being used to predict, fight and understand pandemics such as COVID-19.
AI in business. Machine learning algorithms are being integrated into analytics and customer relationship management (CRM) platforms to uncover information on how to better serve customers. Chatbots have been incorporated into websites to provide immediate service to customers. The rapid advancement of generative AI technology such as ChatGPT is expected to have far-reaching consequences: eliminating jobs, revolutionizing product design and disrupting business models.
AI in education. AI can automate grading, giving educators more time for other tasks. It can assess students and adapt to their needs, helping them work at their own pace. AI tutors can provide additional support to students, ensuring they stay on track. The technology could also change where and how students learn, perhaps even replacing some teachers. As demonstrated by ChatGPT, Bard and other large language models, generative AI can help educators craft course work and other teaching materials and engage students in new ways. The advent of these tools also forces educators to rethink student homework and testing and revise policies on plagiarism.
AI in finance. AI in personal finance applications, such as Intuit Mint or TurboTax, is disrupting financial institutions. Applications such as these collect personal data and provide financial advice. Other programs, such as IBM Watson, have been applied to the process of buying a home. Today, artificial intelligence software performs much of the trading on Wall Street.
AI in law. The discovery process -- sifting through documents -- in law is often overwhelming for humans. Using AI to help automate the legal industry's labor-intensive processes is saving time and improving client service. Law firms use machine learning to describe data and predict outcomes, computer vision to classify and extract information from documents, and NLP to interpret requests for information.
AI in entertainment and media. The entertainment business uses AI techniques for targeted advertising, recommending content, distribution, detecting fraud, creating scripts and making movies. Automated journalism helps newsrooms streamline media workflows reducing time, costs and complexity. Newsrooms use AI to automate routine tasks, such as data entry and proofreading; and to research topics and assist with headlines. How journalism can reliably use ChatGPT and other generative AI to generate content is open to question.
AI in software coding and IT processes. New generative AI tools can be used to produce application code based on natural language prompts, but it is early days for these tools and unlikely they will replace software engineers soon. AI is also being used to automate many IT processes, including data entry, fraud detection, customer service, and predictive maintenance and security.
Security. AI and machine learning are at the top of the buzzword list security vendors use to market their products, so buyers should approach with caution. Still, AI techniques are being successfully applied to multiple aspects of cybersecurity, including anomaly detection, solving the false-positive problem and conducting behavioral threat analytics. Organizations use machine learning in security information and event management (SIEM) software and related areas to detect anomalies and identify suspicious activities that indicate threats. By analyzing data and using logic to identify similarities to known malicious code, AI can provide alerts to new and emerging attacks much sooner than human employees and previous technology iterations.
AI in manufacturing. Manufacturing has been at the forefront of incorporating robots into the workflow. For example, the industrial robots that were at one time programmed to perform single tasks and separated from human workers, increasingly function as cobots: Smaller, multitasking robots that collaborate with humans and take on responsibility for more parts of the job in warehouses, factory floors and other workspaces.
AI in banking. Banks are successfully employing chatbots to make their customers aware of services and offerings and to handle transactions that don't require human intervention. AI virtual assistants are used to improve and cut the costs of compliance with banking regulations. Banking organizations use AI to improve their decision-making for loans, set credit limits and identify investment opportunities.
AI in transportation. In addition to AI's fundamental role in operating autonomous vehicles, AI technologies are used in transportation to manage traffic, predict flight delays, and make ocean shipping safer and more efficient. In supply chains, AI is replacing traditional methods of forecasting demand and predicting disruptions, a trend accelerated by COVID-19 when many companies were caught off guard by the effects of a global pandemic on the supply and demand of goods.
Augmented intelligence vs. artificial intelligence
Some industry experts have argued that the term artificial intelligence is too closely linked to popular culture, which has caused the general public to have improbable expectations about how AI will change the workplace and life in general. They have suggested using the term augmented intelligence to differentiate between AI systems that act autonomously -- popular culture examples include Hal 9000 and The Terminator -- and AI tools that support humans.
Augmented intelligence. Some researchers and marketers hope the label augmented intelligence, which has a more neutral connotation, will help people understand that most implementations of AI will be weak and simply improve products and services. Examples include automatically surfacing important information in business intelligence reports or highlighting important information in legal filings. The rapid adoption of ChatGPT and Bard across industry indicates a willingness to use AI to support human decision-making.
Artificial intelligence. True AI, or AGI, is closely associated with the concept of the technological singularity -- a future ruled by an artificial superintelligence that far surpasses the human brain's ability to understand it or how it is shaping our reality. This remains within the realm of science fiction, though some developers are working on the problem. Many believe that technologies such as quantum computing could play an important role in making AGI a reality and that we should reserve the use of the term AI for this kind of general intelligence.
Ethical use of artificial intelligence
While AI tools present a range of new functionality for businesses, the use of AI also raises ethical questions because, for better or worse, an AI system will reinforce what it has already learned.
This can be problematic because machine learning algorithms, which underpin many of the most advanced AI tools, are only as smart as the data they are given in training. Because a human being selects what data is used to train an AI program, the potential for machine learning bias is inherent and must be monitored closely.
Anyone looking to use machine learning as part of real-world, in-production systems needs to factor ethics into their AI training processes and strive to avoid bias. This is especially true when using AI algorithms that are inherently unexplainable in deep learning and generative adversarial network (GAN) applications.
Explainability is a potential stumbling block to using AI in industries that operate under strict regulatory compliance requirements. For example, financial institutions in the United States operate under regulations that require them to explain their credit-issuing decisions. When a decision to refuse credit is made by AI programming, however, it can be difficult to explain how the decision was arrived at because the AI tools used to make such decisions operate by teasing out subtle correlations between thousands of variables. When the decision-making process cannot be explained, the program may be referred to as black box AI.
In summary, AI's ethical challenges include the following: bias, due to improperly trained algorithms and human bias; misuse, due to deepfakes and phishing; legal concerns, including AI libel and copyright issues; elimination of jobs; and data privacy concerns, particularly in the banking, healthcare and legal fields.
components of responsible AI use.
These components make up responsible AI use.
AI governance and regulations
Despite potential risks, there are currently few regulations governing the use of AI tools, and where laws do exist, they typically pertain to AI indirectly. For example, as previously mentioned, U.S. Fair Lending regulations require financial institutions to explain credit decisions to potential customers. This limits the extent to which lenders can use deep learning algorithms, which by their nature are opaque and lack explainability.
The European Union's General Data Protection Regulation (GDPR) is considering AI regulations. GDPR's strict limits on how enterprises can use consumer data already limits the training and functionality of many consumer-facing AI applications.
Policymakers in the U.S. have yet to issue AI legislation, but that could change soon. A "Blueprint for an AI Bill of Rights" published in October 2022 by the White House Office of Science and Technology Policy (OSTP) guides businesses on how to implement ethical AI systems. The U.S. Chamber of Commerce also called for AI regulations in a report released in March 2023.
Crafting laws to regulate AI will not be easy, in part because AI comprises a variety of technologies that companies use for different ends, and partly because regulations can come at the cost of AI progress and development. The rapid evolution of AI technologies is another obstacle to forming meaningful regulation of AI, as are the challenges presented by AI's lack of transparency that make it difficult to see how the algorithms reach their results. Moreover, technology breakthroughs and novel applications such as ChatGPT and Dall-E can make existing laws instantly obsolete. And, of course, the laws that governments do manage to craft to regulate AI don't stop criminals from using the technology with malicious intent.
Milestones in AI from 1950 to present.
AI has had a long and sometimes controversial history from the Turing test in 1950 to today's generative AI chatbots like ChatGPT.
What is the history of AI?
The concept of inanimate objects endowed with intelligence has been around since ancient times. The Greek god Hephaestus was depicted in myths as forging robot-like servants out of gold. Engineers in ancient Egypt built statues of gods animated by priests. Throughout the centuries, thinkers from Aristotle to the 13th century Spanish theologian Ramon Llull to René Descartes and Thomas Bayes used the tools and logic of their times to describe human thought processes as symbols, laying the foundation for AI concepts such as general knowledge representation.
The late 19th and first half of the 20th centuries brought forth the foundational work that would give rise to the modern computer. In 1836, Cambridge University mathematician Charles Babbage and Augusta Ada King, Countess of Lovelace, invented the first design for a programmable machine.
1940s. Princeton mathematician John Von Neumann conceived the architecture for the stored-program computer -- the idea that a computer's program and the data it processes can be kept in the computer's memory. And Warren McCulloch and Walter Pitts laid the foundation for neural networks.
1950s. With the advent of modern computers, scientists could test their ideas about machine intelligence. One method for determining whether a computer has intelligence was devised by the British mathematician and World War II code-breaker Alan Turing. The Turing test focused on a computer's ability to fool interrogators into believing its responses to their questions were made by a human being.
1956. The modern field of artificial intelligence is widely cited as starting this year during a summer conference at Dartmouth College. Sponsored by the Defense Advanced Research Projects Agency (DARPA), the conference was attended by 10 luminaries in the field, including AI pioneers Marvin Minsky, Oliver Selfridge and John McCarthy, who is credited with coining the term artificial intelligence. Also in attendance were Allen Newell, a computer scientist, and Herbert A. Simon, an economist, political scientist and cognitive psychologist. The two presented their groundbreaking Logic Theorist, a computer program capable of proving certain mathematical theorems and referred to as the first AI program.
1950s and 1960s. In the wake of the Dartmouth College conference, leaders in the fledgling field of AI predicted that a man-made intelligence equivalent to the human brain was around the corner, attracting major government and industry support. Indeed, nearly 20 years of well-funded basic research generated significant advances in AI: For example, in the late 1950s, Newell and Simon published the General Problem Solver (GPS) algorithm, which fell short of solving complex problems but laid the foundations for developing more sophisticated cognitive architectures; and McCarthy developed Lisp, a language for AI programming still used today. In the mid-1960s, MIT Professor Joseph Weizenbaum developed ELIZA, an early NLP program that laid the foundation for today's chatbots.
1970s and 1980s. The achievement of artificial general intelligence proved elusive, not imminent, hampered by limitations in computer processing and memory and by the complexity of the problem. Government and corporations backed away from their support of AI research, leading to a fallow period lasting from 1974 to 1980 known as the first "AI Winter." In the 1980s, research on deep learning techniques and industry's adoption of Edward Feigenbaum's expert systems sparked a new wave of AI enthusiasm, only to be followed by another collapse of government funding and industry support. The second AI winter lasted until the mid-1990s.
1990s. Increases in computational power and an explosion of data sparked an AI renaissance in the late 1990s that set the stage for the remarkable advances in AI we see today. The combination of big data and increased computational power propelled breakthroughs in NLP, computer vision, robotics, machine learning and deep learning. In 1997, as advances in AI accelerated, IBM's Deep Blue defeated Russian chess grandmaster Garry Kasparov, becoming the first computer program to beat a world chess champion.
2000s. Further advances in machine learning, deep learning, NLP, speech recognition and computer vision gave rise to products and services that have shaped the way we live today. These include the 2000 launch of Google's search engine and the 2001 launch of Amazon's recommendation engine. Netflix developed its recommendation system for movies, Facebook introduced its facial recognition system and Microsoft launched its speech recognition system for transcribing speech into text. IBM launched Watson and Google started its self-driving initiative, Waymo.
2010s. The decade between 2010 and 2020 saw a steady stream of AI developments. These include the launch of Apple's Siri and Amazon's Alexa voice assistants; IBM Watson's victories on Jeopardy; self-driving cars; the development of the first generative adversarial network; the launch of TensorFlow, Google's open source deep learning framework; the founding of research lab OpenAI, developers of the GPT-3 language model and Dall-E image generator; the defeat of world Go champion Lee Sedol by Google DeepMind's AlphaGo; and the implementation of AI-based systems that detect cancers with a high degree of accuracy.
2020s. The current decade has seen the advent of generative AI, a type of artificial intelligence technology that can produce new content. Generative AI starts with a prompt that could be in the form of a text, an image, a video, a design, musical notes or any input that the AI system can process. Various AI algorithms then return new content in response to the prompt. Content can include essays, solutions to problems, or realistic fakes created from pictures or audio of a person. The abilities of language models such as ChatGPT-3, Google's Bard and Microsoft's Megatron-Turing NLG have wowed the world, but the technology is still in early stages, as evidenced by its tendency to hallucinate or skew answers.
AI tools and services
AI tools and services are evolving at a rapid rate. Current innovations in AI tools and services can be traced to the 2012 AlexNet neural network that ushered in a new era of high-performance AI built on GPUs and large data sets. The key change was the ability to train neural networks on massive amounts of data across multiple GPU cores in parallel in a more scalable way.
Over the last several years, the symbiotic relationship between AI discoveries at Google, Microsoft, and OpenAI, and the hardware innovations pioneered by Nvidia have enabled running ever-larger AI models on more connected GPUs, driving game-changing improvements in performance and scalability.
The collaboration among these AI luminaries was crucial for the recent success of ChatGPT, not to mention dozens of other breakout AI services. Here is a rundown of important innovations in AI tools and services.
Transformers. Google, for example, led the way in finding a more efficient process for provisioning AI training across a large cluster of commodity PCs with GPUs. This paved the way for the discovery of transformers that automate many aspects of training AI on unlabeled data.
Hardware optimization. Just as important, hardware vendors like Nvidia are also optimizing the microcode for running across multiple GPU cores in parallel for the most popular algorithms. Nvidia claimed the combination of faster hardware, more efficient AI algorithms, fine-tuning GPU instructions and better data center integration is driving a million-fold improvement in AI performance. Nvidia is also working with all cloud center providers to make this capability more accessible as AI-as-a-Service through IaaS, SaaS and PaaS models.
Generative pre-trained transformers. The AI stack has also evolved rapidly over the last few years. Previously enterprises would have to train their AI models from scratch. Increasingly vendors such as OpenAI, Nvidia, Microsoft, Google, and others provide generative pre-trained transformers (GPTs), which can be fine-tuned for a specific task at a dramatically reduced cost, expertise and time. Whereas some of the largest models are estimated to cost $5 million to $10 million per run, enterprises can fine-tune the resulting models for a few thousand dollars. This results in faster time to market and reduces risk.
AI cloud services. Among the biggest roadblocks that prevent enterprises from effectively using AI in their businesses are the data engineering and data science tasks required to weave AI capabilities into new apps or to develop new ones. All the leading cloud providers are rolling out their own branded AI as service offerings to streamline data prep, model development and application deployment. Top examples include AWS AI Services, Google Cloud AI, Microsoft Azure AI platform, IBM AI solutions and Oracle Cloud Infrastructure AI Services.
Cutting-edge AI models as a service. Leading AI model developers also offer cutting-edge AI models on top of these cloud services. OpenAI has dozens of large language models optimized for chat, NLP, image generation and code generation that are provisioned through Azure. Nvidia has pursued a more cloud-agnostic approach by selling AI infrastructure and foundational models optimized for text, images and medical data available across all cloud providers. Hundreds of other players are offering models customized for various industries and use cases as well.
George Lawton also contributed to this article.
This was last updated in March 2023
Continue Reading About artificial intelligence (AI)
10 top AI and machine learning trends
Microsoft launches AI-powered Security Copilot
Don't count out Google and its AI chatbot Bard from AI race
Businesses benefit from AI-infused Industry 4.0 practices
ServiceNow's latest Now Platform focuses on AI, automation
Related Terms
AI hallucination
An AI hallucination is when a large language model (LLM) generates false information. See complete definition
variational autoencoder (VAE)
A variational autoencoder (VAE) is a generative AI algorithm that uses deep learning to generate new content, detect anomalies ... See complete definition
What is generative AI? Everything you need to know
Generative AI is a type of artificial intelligence technology that can produce various types of content, including text, imagery,... See complete definition
Dig Deeper on AI technologies
AI vs. machine learning vs. deep learning: Key differencesDavidPetersson
By: David Petersson
Artificial intelligence vs. human intelligence: How are they different?MichaelBennett
By: Michael Bennett
A guide to artificial intelligence in the enterpriseLindaTucci
By: Linda Tucci
How to become an artificial intelligence engineerLindaRosencrance
By: Linda Rosencrance
Sponsored News
Exploring AI Use Cases Across Education and Government
–Dell Technologies
Unlock the Value Of Your Data To Harness Intelligence and Innovation
–HPE
See More
Vendor Resources
Human-like AI quest drives general AI development efforts
–TechTarget ComputerWeekly.com
AI: Beyond the hype
–TechTarget ComputerWeekly.com
| 2023-03-31T00:00:00 |
https://vocal.media/education/artificial-intelligence-1r18y03x7
|
[
{
"date": "2023/03/31",
"position": 84,
"query": "AI unemployment rate"
}
] |
|
A Look at Projected Employment in Professional, Scientific, ...
|
A Look at Projected Employment in Professional, Scientific, and Technical Services, 2021‒31 : Spotlight on Statistics : U.S. Bureau of Labor Statistics
|
https://www.bls.gov
|
[] |
The professional and business services major industry sector is projected to grow 7.3 percent over the 2021–31 decade, which is slightly faster than the 5.5 ...
|
A Look at Projected Employment in Professional, Scientific, and Technical Services, 2021‒31
Lindsey Ice
Every day, millions of workers provide professional and business services that keep American businesses and the economy running. Demand for these services has grown significantly over the last several decades, resulting in fast job growth.
Professional, scientific, and technical services is the largest sector within professional and business services and employed about 1 in every 15 jobs in 2021. These establishments specialize in performing professional, scientific, and technical activities such as advertising and public relations, accounting and tax preparation, computer systems design, architectural and engineering services, and much more. These services typically require a high degree of expertise and training and many of the occupations employed in this sector earned wages above the $45,760 median annual wage for all occupations in 2021.
In this Spotlight on Statistics, we look at employment in the professional, scientific, and technical services sector and the projected employment growth for the 2021–31 decade for some of its detailed industries and top-employing occupations.
| 2023-03-31T00:00:00 |
https://www.bls.gov/spotlight/2023/a-look-at-projected-employment-in-professional-scientific-and-technical-services-2021-31/home.htm
|
[
{
"date": "2023/03/31",
"position": 15,
"query": "job automation statistics"
}
] |
|
How AI and Automation Enhance Healthcare, From ...
|
How AI and Automation Enhance Healthcare, From Medical Diagnosis to Supply Chains
|
https://cloudwars.com
|
[
"Ronak Mathur"
] |
... automation and other innovative technologies to improve the delivery of care. For instance, by using AI to automate data entry and appointment scheduling ...
|
The pressure has been rising for healthcare systems to handle data from an expanding array of internal and external sources more quickly and accurately. At the same time, an already acute shortage of trained medical professionals was exacerbated by Covid-19.
By automating routine tasks, streamlining operations, and enhancing patient care, technologies including artificial intelligence (AI) and automation are helping to optimize resources and improve efficiency in healthcare. These benefits, in turn, are helping to offset the impact of talent shortages.
Why Healthcare Needs Automation
A recent study revealed that many healthcare workers are experiencing burnout and administrative tasks have been a big contributor: survey respondents reported that they spend 34% of their time on administrative work.
Additionally, a study on “Medical Error Reduction and Prevention” found that medical errors have become a leading cause of death in the United States, resulting in approximately 100,000 fatalities annually. These statistics highlight serious problems in the healthcare industry that require urgent attention. They also demonstrate the need for healthcare organizations and policymakers to prioritize investments in automation and other innovative technologies to improve the delivery of care.
For instance, by using AI to automate data entry and appointment scheduling, healthcare organizations can reduce the administrative burden on staff, freeing them to focus on more complex tasks that require human interaction or intervention. Similarly, by using predictive analytics to optimize staffing levels, healthcare organizations can ensure they have the right number of staff members available at the right time, which can help to improve patient outcomes and reduce burnout.
Which companies are the most important vendors in AI and hyperautomation? Check out the Acceleration Economy AI/Hyperautomation Top 10 Shortlist.
Hyperautomation Benefits
Hyperautomation technology has the potential to address many of the challenges outlined above by improving efficiency, reducing costs, and enhancing patient outcomes.
Hyperautomation entails the automation of human workflows while guiding a sequence of related tasks. With hyperautomation, multiple technologies work together to overcome obstacles presented by a single technology.
For example, robotic process automation (RPA) — and other forms of automation — offer great promise for increasing both business agility and operational efficiencies in the healthcare context. Although RPA has great potential, it cannot be used alone to adapt to the evolving healthcare environment. AI, machine learning (ML), natural language processing (NLP), and intelligent document processing are all examples of technologies that lend a cognitive layer to RPA.
Unlike RPA, which is limited in its ability to automate the processing of unstructured data, intelligent automation (IA) draws on AI to incorporate analysis, logic, judgment, and decision-making into automation for higher-order tasks. With all of these technologies working together, administrative and other tasks can be automated, freeing up time for healthcare workers to focus on higher-level tasks, especially better patient care.
4 Healthcare Use Cases
Within the healthcare industry, there is a strong emphasis on patient-centered care. So, healthcare providers are turning to digital platforms that have the potential to introduce exciting new methods of providing medical treatment. This allows for specialized approaches that are enhancing patient care. Below, I’m highlighting four use hyperautomation cases including two specifically tied to patient care.
1. Medical Diagnosis with AI
By combining hyperautomation with other technologies, such as computer vision, ML, and smart processes, healthcare firms can generate reliable reports in record time. To identify a medical condition, for instance, computer vision and ML-based solutions analyze radiology scans. Subsequently, the automated workflow can assign cases based on specialization, departments, reading capacity, and more. Then, it can prioritize them accordingly.
After checks have been made, the doctors can have diagnoses sent back to the patient electronically and incorporated into electronic medical records (EMRs). AI can then analyze patient data from EMRs, including medical history and lab results to help doctors make more accurate diagnoses and treatment recommendations. Some AI-powered diagnostic tools, such as Merative (formerly known as IBM Watson Health), can do this job with ease.
2. Remote Patient Monitoring
In recent years, we’ve experienced physical access to healthcare facilities being restricted by barriers and lockdowns. In these types of scenarios, remote patient monitoring (RPM) enables healthcare providers to track patients’ health outside of traditional clinical settings. RPM typically involves the use of wearable devices, sensors, or mobile applications to collect patient data and transmit it to healthcare providers for analysis.
The goal of RPM is to allow healthcare providers to monitor patients in real time and detect any concerning trends or abnormalities that may require intervention. This can help improve patient outcomes, reduce hospital re-admissions, and lower healthcare costs by detecting the onset of health issues earlier and providing more personalized care.
High-risk patients, such as those with chronic conditions or who are receiving post-acute care, can benefit from wearable devices to track vital signs, such as blood pressure and glucose levels. As data analytics power alerts and provide suggestions for patient engagement plans, digital health assistants can drive adherence to treatment recommendations to handle individualized care.
3. Administrative Tasks
The patient experience and operational productivity can be improved with AI, RPA, process mining, and data analytics. From my experience, AI and RPA help automate repetitive and time-consuming tasks such as data entry and appointment scheduling so healthcare professionals can spend more time focusing on patient care.
Process mining and data analytics can help with identifying inefficiencies in workflows and processes, supporting data-driven decisions and improving operational productivity. For example, appointment scheduling can be implemented using virtual health bots, such as Microsoft’s Azure Healthcare Bot.
Microsoft’s virtual health bot provides AI capabilities and is very easy to set up. It can be used to detect missing eligibility data. Further, it connects with external applications to gather missing information during the appointment and patient registration process.
Based on my experience working with this Microsoft healthcare bot, here are five steps to assist with proper implementation so you get maximum benefit from the bot:
Define the use case: This could include tasks such as appointment scheduling, symptom checking, medication management, and more.
This could include tasks such as appointment scheduling, symptom checking, medication management, and more. Develop the bot: Use Microsoft’s Bot Framework to build and train the bot. This involves defining the bot’s conversational flows, developing natural language processing capabilities, and integrating the bot with relevant back-end systems such as EMR systems.
Use Microsoft’s Bot Framework to build and train the bot. This involves defining the bot’s conversational flows, developing natural language processing capabilities, and integrating the bot with relevant back-end systems such as EMR systems. Deploy the bot: Deploy the bot to the desired platforms, such as the organization’s website, mobile app, or messaging.
Deploy the bot to the desired platforms, such as the organization’s website, mobile app, or messaging. Test and refine: Test the bot in a controlled environment to ensure it is functioning as intended. Refine the bot’s responses and workflows based on user feedback and data analysis.
Test the bot in a controlled environment to ensure it is functioning as intended. Refine the bot’s responses and workflows based on user feedback and data analysis. Scale and maintain: As usage of the bot increases, scale the bot to meet demand. Monitor the bot’s performance and regularly update it with new features and capabilities.
4. Supply Chains
In supply chains, coordinating the flow of goods and services from suppliers to customers can be a complex and time-consuming process. In the healthcare industry, the supply chain is responsible for the timely delivery of various materials.
AI algorithms are used to analyze demand patterns and forecast future demand, enabling organizations to optimize their inventory levels and reduce waste. Automation is also used to streamline the procurement process, reducing the time and effort required to order and receive goods.
Final Thoughts
Hyperautomation is rapidly becoming more of a necessity than a novelty in many industries. In healthcare, not only is hyperautomation improving efficiency as part of the industry’s rapid transformation in response to the pandemic, but it is also having a beneficial effect on patient treatment and health outcomes.
In healthcare, hyperautomation can give businesses new ways to deliver measurable business value through significant operational improvements and ROI. When it comes to day-to-day operations in the healthcare sector, such as patient registrations, notifications, and recommendations, this technology can be of assistance to many departments within healthcare organizations. With increased use of AI and automation, more organizations will experience improved outcomes, including reduced dependence on human labor and improved precision.
Looking for real-world insights into artificial intelligence and hyperautomation? Subscribe to the AI and Hyperautomation channel:
| 2023-03-31T00:00:00 |
2023/03/31
|
https://cloudwars.com/ai/how-ai-and-automation-enhance-healthcare-from-medical-diagnosis-to-supply-chains/
|
[
{
"date": "2023/03/31",
"position": 81,
"query": "job automation statistics"
}
] |
27 Insightful HR Statistics for a Better Workplace
|
27 Insightful HR Statistics for a Better Workplace
|
http://goremotely.net
|
[] |
HR statistics projected that jobs for HR managers would grow 6% over a decade. That's about 13,300 job openings every year. The role of HR is crucial because it ...
|
Unlike other teams, the HR department works behind the scenes, providing a solid support system in the background.
The unique skillset needed for this role must be why jobs are growing. HR statistics projected that jobs for HR managers would grow 6% over a decade. That’s about 13,300 job openings every year.
The role of HR is crucial because it pieces together every division within the company, from the C-level suite members to new employees. It keeps everything together by building systems and policies that benefit employees and the company.
That’s why it’s the pillar of every organization.
Let’s learn more about our HR team through these statistics.
Fascinating HR Statistics (Editor’s Choice)
83% of HR managers find retaining employees more challenging than hiring them.
80% of HR leaders believe that remote work stimulates e-Presenteeism.
95% of HR managers believe burnout has the most severe consequences for employee retention.
This year, 59% of HR leaders will prioritize upskilling and reskilling.
92% of HR professionals plan to use people analytics in 2023.
68% of HR managers lack the budget to adopt AI.
LinkedIn remains the best recruiting platform for professional roles in 2023.
67% of HR professionals believe that AI will benefit and have a positive impact on the recruitment process.
General HR Stats
To be part of the HR team means to be a problem-solver. Various problems face HR leaders, such as high turnover, disengaged employees, and outdated HR solutions. Let’s examine how HR leaders resolve these issues and some recent exciting stats.
1. The median salary for HR managers was $154,549 as of February 2023.
(Salary)
The job of HR professionals is taxing. However, they’re also well compensated. As of February 2023, the average annual salary of a human resources manager salary is $80.11 per hour or $154,549 yearly. HR managers in the top industries, such as technical service industries, earned up to $205,720 annually.
Now that organizations are starting to pick up from the throes of the pandemic, many will hire new employees. Therefore, job opportunities will open. According to the BLS, the demand for HR managers will increase by 6% from 2019 to 2029.
2. Based on 2022 human resources industry statistics, 47% of HR functions would focus on employee experience.
(Future-of-Commerce)
The year 2020 was transformational. Moving to remote work wasn't the only drastic thing. HR’s focus changed. A survey shared that 48% of HR leaders would focus on enhancing the employee experience.
Meanwhile, 41% of HR functions would center on workplace technology development, like deploying AI and automation, 35% on performance management, and 38% on applying people analytics.
3. 47% of HR would prioritize employee experience as their top agenda should their HR budgets double.
(Future-of-Commerce)
HR statistics 2022 highlighted how vital employee experience is for HR leaders. When asked about their future visions under the condition that their budgets were doubled, 47% of HR leaders responded that employee experience would be their top priority.
It's followed by leadership development (35%), learning transformation (34%), and next-generation leadership development (31%). All of these HR objectives point toward developing employees. That said, organizations are seriously considering providing the best experience to their workers.
4. 42% of HR leaders want to prioritize their future workplace strategy in 2023.
(Softworks)
One of the notable human resources trends is the adoption of AI and automation. As the current trend suggests, technology will shape the future of workplaces. Hence, 42% of HR leaders want to concentrate on preparing companies for the future of work, which includes more technological integrations. Despite several companies deploying automation and AI, 62% don’t have a clear strategy for modernizing their workforce systems.
5. 59% of HR leaders prioritized building critical skills and competencies for the company in 2022.
(HR Inspire)
HR statistics in 2021 have uncovered that 36% of HR leaders need to learn the skills gap with their current talents. This is why 59% of HR professionals prioritize building critical skills and competencies.
According to 40% of hr leaders, they need help to quickly build skills development solutions to satisfy the changing talent requirements. Since 2018, the skills required for finance, sales, and information technology have increased by 6.3% annually.
6. 58% of HR leaders consider finding, attracting, and retaining talents their biggest challenge.
(PWC)
Human resources stats exposed the array of challenges HR leaders face to ramp up their organization’s overall condition. Approximately 58% find talent acquisition and retention the most challenging HR tasks. Some 43% find developing people's full potential a significant concern.
Other equally challenging concerns are enhancing employee experience (47%), creating collaborative work environments (40%), workforce planning (42%), and ensuring diversity, inclusivity, and well-being (34%).
7. Employee retention statistics indicate that 63.3% of HR leaders find retaining employees more challenging than recruiting them.
(Zenefits)
Retention is a perpetual concern of the recruitment team. Despite the tight competition in the job market, employees are fearless in leaving a job when they see fit. Many HR leaders and companies have built a solid strategy around retention.
Organizations offer incentives, promotions, increased wages, and personal growth benefits to keep employees from resigning. While this may attract older workers who want career stability, companies may need to develop a different strategy to retain younger workers.
8. Human resources facts share that 80% of HR leaders think that the extended period of home-based work has encouraged e-Presenteeism.
(Linkedin)
E-Presenteeism refers to a culture where remote workers feel they should always be available, even if it's out of hours or they don't feel well. This work culture has adversely impacted mental health, leading to burnout, stress, and anxiety.
Most HR leaders think that remote work has spurred e-Presenteeism, which is the need for employees to be online all the time. Working from home may have compromised productivity. However, organizations should distinguish between work and personal time and honor their employees’ out-of-work interests.
9. 58% of HR leaders fear COVID-19's impact on employees' mental health will lead to burnout.
(The Undercover Recruiter)
Some statistics for HR professionals spotlighted the impact of COVID-19 on employees' mental health. Nearly three in five HR managers think the pandemic would increase turnover as burnout could affect employees. Approximately 54% of HR professionals believe that anxiety, burnout, loneliness, isolation, and other mental health concerns have become during the pandemic.
10. Leader and manager effectiveness is the top priority of 60% of HR leaders this 2023.
(Gartner, Softworks)
Employee development statistics share that L&D programs this year will center on leadership and management.
A top priority for 60% of HR leaders says their leadership development approach needs to prepare leaders for the future of work. They stated that leaders must be more understanding, approachable, empathetic, and adaptive to succeed in today’s work environment.
Recruiting Industry Statistics
Through recruitment, the HR teams can influence the organization’s future, either in a good or a wrong way. So what’s happening in the industry? Here are the latest stats to keep you updated.
11. As of 2020, only 49% of employees say their promotion and career routes are clear.
(TINYpulse)
Career pathing is one of the integral human resources benchmarks. It may be meaningless for employees who only treat their job as a means of living. However, for those looking to build a career, a clear career path is a crucial variable that keeps them happy and motivated in their jobs.
A survey revealed that only nearly 5 in 10 workers see and understand the next level of promotion and career paths in their companies.
12. One in every two applicants has had negative experiences while applying for jobs as of 2023.
(Career Plug)
Hiring stats shared that half of the jobseekers had poor experiences during the hiring process. As a result, 50% also declined a job. Contrary to what many people envision, negative experiences during hiring don’t only include discrimination or bias.
Other cited bad experiences by applicants include unexpectedly low compensation and benefits (24%), negative experience with interviewers (22%), roles and responsibilities that were out of expectations (22%), and dissatisfaction with the work environment (16%).
( Career Plug)
Job search statistics shared that three out of four applicants would accept a job offer if, during the hiring process, they have a pleasing experience.
One of the priorities of HR is providing a positive candidate experience. They invest in HR tech because automation and AI can simplify HR functions like recruitment and onboarding. HR leaders can provide a positive experience by writing clear job descriptions, making applications accessible, and allowing candidates to leave feedback.
14. The US has between 708 to 908 active PEOs operating as of 2023.
(My Shortlister)
But what is PEO? In short, it stands for Professional Employer Organization.
They help small businesses develop 7 to 9% faster and provide services to about 156,000 to 180,000 SMBs.
Firms that utilize a PEO have 40% better revenue growth, 14-16% lower turnover rates, and are 50% less likely to go out of business than enterprises that do not employ a PEO.
Overseas businesses use International PEO to quickly employ staff overseas and in new territories.
(Career Plug)
Not getting any response after applying for a job can be depressing. Therefore, keeping an active line and being responsive are both helpful in creating a positive hiring experience. Other dynamics that influence a candidate's decision to accept a job offer are the hiring process transparency (21%), interviewer experience (16%), and work atmosphere (16%).
16. 61% of employees consider diversity and inclusion tactics helpful and vital.
(Quantum Workplace)
Recent diversity and inclusion statistics suggest that most workers feel strongly optimistic about having diversity and inclusion strategies in the workplace. It's a known fact that a diverse and inclusive workplace is more productive and engaged. Apart from this, as high as 75% of employees are adamant that diversity and inclusion are equally significant. So, there’s no reason why HR leaders shouldn’t have diversity and inclusion strategies.
17. Employees receiving recognition are nearly twice as likely to trust their HR department as of 2022.
(Work Human)
Human resources statistics enumerate the various benefits of giving recognition, and one of these is building trust.
A survey report on employee retention stated that 68% of organizations with employee recognition reported a direct positive impact on retention.
If employees get recognized for their contributions at work, they're twice as likely to develop confidence in their HR team. They're also 89% happier, 96% safer, and 81% more likely to trust their executive leaders to make the right decisions. Employees place high importance on recognition because it keeps them motivated to do their best.
18. On a scale of 1 to 10, small companies were rated over 5 points by their employees when it came to giving recognition.
(TINYpulse)
Small business HR statistics concluded that employees in small companies, with only up to 10 workers, were happier because their managers were more appreciative of them. In a survey, employers with this workforce size received 5.6 points out of 10.
The same can be said for working in organizations with only 11 to 50 workers. Employers with this size received 5.7 points out from their employees. In comparison, workers in large enterprises with over 1,000 workers hardly get recognized for their efforts. It’s not surprising that companies of this size only got 2.7 points.
19. Based on employee loyalty statistics, more than 50% of workers say that wage/salary is the most influential factor for their loyalty to the company in 2022.
(HR Digest)
A survey pointed out that half of the employees consider salary and other benefits an essential yardstick for loyalty. For some 55% of workers, it's the work that they do that influences their loyalty. Various factors drive employees' loyalty. HR leaders must improve workplace aspects, including wages, benefits, culture, and strategies to increase retention and loyalty.
20. Performance management statistics determined that annual reviews didn't improve the performance of 55% of employees in 2022.
(What To Become)
The number of companies conducting annual performance reviews dropped from 82% to 54% in 2019. Annual reviews have been an essential barometer for many HR professionals to evaluate work performance. But that is changing due to how employees perceive it.
More than half of the workers mentioned that reviews were only indicative of some of the tasks that they do in the workplace. Moreover, 55% said that they didn't boost their work performance.
21. 56% of employees have witnessed or experienced sexual harassment, and 39% mistrust their HR staff.
(Gitnux)
Some human resource problems in companies still need to be solved because employees need more trust to confide in their HR managers. This is apparent in the number of workers who report harassment issues.
56% of employees have witnessed or experienced sexual harassment in the workplace, while 50% are harassed based on gender, with a higher percentage of women affected.
Over 70% of women and two-thirds of LGBT individuals who experience sexual harassment do not report it due to fear of job or career harm.
Looking at the figures, it's clear that not all reported cases were investigated. So, it's no wonder many employees lose confidence in their HR leaders to solve workplace issues.
HR Technology Statistics 2023
HR teams use AI technology to streamline their tasks from recruitment to onboarding. Let’s see what else is there in HR tech.
22. 92% of HR professionals plan to use people analytics in 2023.
( Darwinbox )
Data is now deemed more expensive than the most lucrative resource in the world: oil. Nowadays, people exploit data and analytics to create well-designed business strategies, and it’s happening in the human resource field.
According to HR professional statistics, leaders use people analytics for various benefits, such as identifying high potential employees (34%), analyzing benefits (32%), achieving fair pay and incentives (26%), and projecting future talent needs (25%).
23. 94% of companies are either already using cloud-based HR systems or in the process of applying them as of 2023.
(Zippia)
HR statistics specified that the deployment of cloud-based applications could be very beneficial. Cloud users shared that it has boosted productivity by 44% compared to only an 18% increase without using the cloud. Furthermore, it has also helped reduce costs by 35%, in contrast to only 14% cost reduction without it. Other benefits of using the cloud entail better employee experience (40%) and an increase in the effectiveness of attracting and retaining workers (34%).
24. 68% of HR staff consider budget a fundamental barrier to adopting AI.
(EC.Europa, HR)
The use of AI has a lot of benefits; however, approximately two-thirds of HR professionals need help with their budget. Due to this, many can only partially implement AI in their process.
Furthermore, based on HR department statistics, only 12% consider themselves enormously knowledgeable about AI in improving their talent acquisition strategies. It can be expensive and hard to find appropriately educated or skilled people. That said, we can see where the bottleneck of deploying AI appears.
25. As of 2023, 82% of HR leaders believe personalizing employee learning is the best way to deploy AI.
(Darwinbox)
Over the years, technology has impacted HR practices, from simple fax machines to integrating AI. Indeed, HR trends have evolved significantly. HR leaders are now keen to personalize employee learning (43%) and enhance employee self-service (42%) through artificial intelligence. Moreover, other HR objectives where the use of AI is seen as beneficial are recruiting new hires (36%), enhancing onboarding processes (34%), and giving career path recommendations (27%).
26. Based on human resource technology trends, 74% of companies had planned to increase HR tech spending in 2023.
(User Guiding)
A recent survey revealed that most companies were pumped to invest in HR tech by increasing their spending. This was apart from the already $310 per employee annual spend on the such initiative.
With the entire hiring process moving over virtually, companies should spend a decent portion of their budget on technological advancements to improve their operations.
27. HR automation statistics specify that by 2023, another 47% of organizations will use AI-based solutions.
(Abdalslam)
In 2022, 30% of organizations already used AI-based solutions. It's predicted that in 2023, another 47% will upgrade their existing systems to integrate AI. The most cited reasons for the revamp are cost savings, better data-based decisions, and enhanced employee experience. With the pandemic still going on, HR leaders may accelerate their technological upgrade to catch up on the trend.
How Can These HR Statistics Improve Your Organization?
As part of the HR team, these latest statistics can give you ideas on the current trend. It comes down to whether you will apply the concepts presented by these statistics or ignore them.
These days, the world is moving in a fast-paced rhythm. Therefore, even if your company is in a good state today, you’ll be run over if you don’t keep innovating your strategies. Who will spearhead these innovations? It’s no other than the HR team. More than the marketing or the R&D team, HR understands your company’s goals and challenges above others. Your HR professionals may be working in the background, but they can reshape the company’s future through their strategies.
| 2023-03-31T00:00:00 |
http://goremotely.net/blog/hr-statistics/
|
[
{
"date": "2023/03/31",
"position": 88,
"query": "job automation statistics"
}
] |
|
Careers at Oss. Join the experts in logistics automation
|
WITRON: Careers at Oss. Join the experts in logistics automation
|
https://careers.witron.com
|
[
"Marc",
"Alex"
] |
Your secure job for tomorrow. Apply at the WITRON site at Oss. The experts for automated logistics are looking forward to your support.
|
The logistics automation professionals with a global reputation for excellence. As a supplier of highly automated logistics systems, we ensure the supply of everyday goods to entire regions.
WITRON is a down-to-earth family business and at the same time a global technology leader in the field of storage and picking systems. Our customers value our reliability and our commitment to the highest quality. The values we live by and the working culture within the team offer stability, motivation and clear orientation for every employee.
| 2023-03-31T00:00:00 |
https://careers.witron.com/locations/oss
|
[
{
"date": "2023/03/31",
"position": 100,
"query": "job automation statistics"
}
] |
|
Benefits Of Training Employees On Artificial Intelligence
|
Benefits Of Training Employees On Artificial Intelligence
|
https://magnimindacademy.com
|
[] |
Automation saves money by automating processes that were used to need human help or intervention. For example, compliance checks for certain contracts and other ...
|
Artificial intelligence (AI) is quickly changing the corporate landscape, and businesses that don’t use it risk falling behind. AI has many advantages, but some companies hesitate to take the decision of utilizing AI in daily operations due to a lack of knowledge. Here, we will talk about the benefits of training employees on artificial intelligence, since we believe that if a company, from managers to employees, knows how AI can benefit them, they will be more likely to solve their problems with AI.
Benefits of AI for Businesses
AI is used in several industry fields and businesses, including manufacturing, financial services, consumer goods, retail, marketing, medical diagnosis, and so on. Among the advantages of AI are:
Increased productivity and efficiency
AI can automate routine tasks to speed up operations. Employees now have more time to work on challenging or creative projects. Businesses can become more adaptable and better able to quickly address customer needs with the use of technology. Thanks to automation, this can result in both higher revenue and lower costs.
Understanding customer better
AI can assist organizations in better understanding their consumers’ requirements and preferences, resulting in better customer service. It can also help businesses make personalized suggestions based on real-time data analysis from multiple sources, such as social media or online shopping behavior.
Saving money
Automation saves money by automating processes that were used to need human help or intervention. For example, compliance checks for certain contracts and other legal documents that may need to be reviewed by multiple people within an organization can now be done automatically. Over time, this helps cut costs and eliminate redundant processes.
Better insights and decisions
Through the application of artificial intelligence, computers are able to make conclusions based on data analysis as opposed to only human intuition. Businesses can benefit from this by learning crucial information they otherwise wouldn’t be able to about their clients, staff, and daily operations that can help them make better decisions.
Why Businesses Should Adopt AI
AI is contributing a lot to many aspects of life, and companies need to start using it as soon as they can to stay competitive. Here are some advantages that businesses can gain from implementing AI in their daily operations.
It costs less than hiring new workers
Due to the present labor shortage and high turnover rates, businesses are seeking ways to minimize expenses and save money. One way to do this is to hire fewer people by automating some tasks with software or by outsourcing jobs that don’t require high-level skills. AI can help businesses increase productivity while lowering labor costs, even though hiring new employees can be expensive.
It makes organizations more productive
As we’ve already mentioned, AI can help streamline activities that would normally be very labor-intensive for people. This means that employees will have more time to focus on strategic priorities instead of routine tasks. This will help them work more efficiently for the company.
It helps businesses stay competitive
AI is being used more and more by businesses in all fields because they know it will help them stay competitive in today’s fast-paced world. By using AI to automate some tasks, businesses can save time and money while also improving the overall customer experience.
It makes more money
When businesses use AI, they can better find out what their customers want and give them what they want. Giving each customer a more individualized experience, helps them make more money.
Importance of Providing AI Training to Employees
Artificial intelligence is expanding swiftly, enabling businesses to increase productivity by streamlining and automating a variety of processes. But AI is not a magic bullet that can solve all business problems right away. AI will only be effective if the company and its people are skilled at using it.
Employers can hire data scientists and AI experts. Or instead, they can teach their staff about AI. They need to train their employees on AI so they can use it in their jobs. There are a number of ways for businesses to train their employees in AI: workshops, online courses, and corporate AI training programs.
Since each company has different goals and problems, they should choose the right training sessions that fit the needs of the company and its employees. They can cover everything from AI basics to more advanced applications. Employees must have a thorough understanding of AI, including both its potential benefits and drawbacks, for businesses to successfully integrate and deploy it within the organization.
Companies can help their employees learn more about AI by letting them go to industry-specific events and giving them access to online training materials. Businesses need to give their employees real-world experience using AI tools like machine learning algorithms.
Now, let’s talk about these programs:
Internal training programs
Companies can create their own internal training programs to give employees the AI knowledge and skills they need. These programs can be created by training experts who work for the company or by AI-focused training companies that work for the company outside of the company. These programs can have both online and hands-on components and are typically offered as part of a larger business course that covers topics like data analytics and machine learning. As these courses become more popular, some businesses may decide to work with an outside company to create their internal program.
Training from outside the company
Businesses can also work with outside groups, like universities or training providers, to give their employees AI training. Most of the time, these courses have both online and hands-on components. They can be a part of a bigger business course or stand-alone.
Online resources
Employees may acquire knowledge about AI on their own by using online tools such as courses, tutorials, and webinars. These materials are useful for employees who need a short overview of a topic or a refresher, but they aren’t ideal for studying more in-depth knowledge.
On-the-job learning
Providing employees the opportunity to work on AI-related projects and tasks can also help them get a better grasp of AI and its applications. Workers should be encouraged to inquire about the projects they are working on and how they connect to artificial intelligence. They may be required to communicate their findings to the organization or team as well.
Conclusion
In conclusion, businesses should think about giving their employees some AI training, even if it’s just the basics. Businesses can’t ignore the many advantages of AI. AI training makes employees more skilled, productive, and competitive. Training employees on artificial intelligence can also help them understand the technology and its potential, which could help them come up with new ideas. Employees can also learn about AI through online courses, workshops, and internal training. Businesses can succeed in the rapidly changing digital landscape by training their employees in AI.
. . .
To learn more about variance and bias, click here and read our another article.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://magnimindacademy.com/blog/benefits-of-training-employees-on-artificial-intelligence/
|
[
{
"date": "2023/03/31",
"position": 70,
"query": "AI job creation vs elimination"
},
{
"date": "2023/03/31",
"position": 23,
"query": "artificial intelligence workers"
}
] |
Generative AI for Human Resources — and 18 Intelligent ...
|
Phenom Unveils Phenom X+ — Generative AI for Human Resources — and 18 Intelligent Talent Experience Platform Innovations at IAMPHENOM
|
https://www.phenom.com
|
[] |
... jobs, company information, hiring status, and potential future career pathing opportunities. ... and shares reminders at the right time to eliminate any ...
|
PHILADELPHIA – March 31, 2023 – During its IAMPHENOM Product Innovation Keynote, Phenom announced Experience+ (X+), a new platform-wide generative AI capability that bolsters efficiencies by automating content creation, surfacing actionable intelligence, and eliminating time-consuming tasks for candidates, employees, recruiters, managers, HR and HRIS teams. In addition, the company unveiled 18 platform intelligence and automation innovations to further transform the way talent acquisition and talent management teams hire, develop, and retain talent.
Introducing Phenom X+
The most critical task human resources (HR) must address is how their companies will empower individuals to transfer their potential into the skills and competencies needed for current and future markets. Every company is on a journey of transformation, and requires intelligence and automation to deliver phenomenal experiences.
Phenom X+ is designed to dynamically support an organization’s specific hiring, retention and growth needs by leveraging an ensemble of AI models that consists of: a Foundation Model (any Natural Language Understanding [NLU], DeepLearning, or Large Language Model [LLM] such as GPT, Bard, or Cohere), Specialized Model, and Contextual Model. Phenom X+ differentiates with its ability to take additional context into account — including vertical, market, job zone (e.g., frontline/hourly or knowledge worker), company, team and user data — delivering an unparalleled level of personalization, precision and experience.
“The next decade will be dominated by intelligence, automation and experience,” said Mahe Bayireddi, Phenom CEO and co-founder. “With Phenom X+ and our Intelligent Talent Experience platform innovations, HR teams and managers will reach unprecedented levels of productivity and efficiency — all while enriching the experiences of candidates and employees.”
For talent acquisition, Phenom X+ automatically:
Generates contextually relevant job descriptions based on role requirements, past ideal candidates, and current high-performing employees
Auto-generates on-brand content and optimizes discoverability via search (SEO)
Offers a natural language search experience for candidates
Highlights best-fit external and internal candidates for any open role
Writes and personalizes emails, SMS, WhatsApp messages and campaigns to candidates
Schedules, reschedules, and cancels interviews using natural language
Develops individualized interview questions and guides
Publishes comprehensive interview feedback in real time for decision makers
Provides hiring teams with interview transcripts, candidate responses, summaries and actionable insights
Interprets notes and creates tasks to be completed
Analyzes Chatbot questions and generates appropriate responses
Scales multilingual experiences
Recommends optimizations to hiring workflows
For talent management, Phenom X+ automatically:
Provides performance insights across teams with next steps
Identifies succession planning opportunities for high-performing employees
Flags employee flight risks and provides prescriptive guidance
Detects skills gaps and surfaces upskilling and reskilling opportunities
Generates personalized emails and campaigns, as well as audience segments to foster development
Interprets and communicates organizational talent trends and ways to stay on pace
New Intelligence Announcements for Talent Acquisition and Talent Management
The Product Innovation Keynote at IAMPHENOM established that insights for knowledge workers are critical to optimize performance and process. To appropriately address the needs of the modern organization, Phenom introduced new technology that improves the hiring cycle for candidates, interview process for internal stakeholders, and growth and retention aspirations of talent management and managers:
Interview Intelligence disrupts the traditional interview process by bringing transparency to hiring teams with recordings, transcriptions, and key takeaways to move the process forward faster and improve decision making. Analysis of interview sentiment, talk speed, talk-to-listen ratio and voice energy are available to inform interview training opportunities and improvements for hiring teams.
Candidate Hub is a one-stop-shop that helps candidates understand where they are in the hiring process and prepare for next steps. Taking context into account, it gives exposure to relevant jobs, company information, hiring status, and potential future career pathing opportunities. Candidates can easily schedule and reschedule interviews, and access a digital interview coach that provides them with a preparation checklist.
Workforce Intelligence provides talent management teams with context and oversight into talent within their organization to ensure they are appropriately onboarded, retained and developed. A main dashboard provides hiring trends, churn rate, retention risks and high performers. Talent management can further drill down into three key areas: 1) Dynamic role architecture to analyze skills, competencies, and additional contexts to determine which employees are available to upskill or reskill into future roles, and initiate upskilling/reskilling initiatives; 2) Comprehensive employee profiles to identify tenure, performance, growth trajectory, fit for openings and progressions, and options for succession planning; and 3) Skills intelligence to determine where gaps and training needs exist, providing visibility into endorsed skills, self-reported skills, open jobs and roles that require skills, and the learning opportunities, mentors and gig projects available to address gaps. With workforce intelligence at their disposal, Employee Relationship Management (ERM) enables talent management and people managers to take appropriate action such as initiating an upskilling project to acquire new skills to enhance one’s job performance or career advancements.
Succession Planning facilitates growth, development, and movement within the organization, providing a means to plan for the future. It identifies existing employees who are suitable for succession for specific roles, and determines eligibility and readiness based on tenure, performance, skills, competencies, and other relevant signals. This feature makes it easy to add new employees to a succession plan, evaluate which successors have been assigned to specific roles, and move and grow employees in the organization.
People Manager provides business leaders with the actionable intelligence they need to build high-performing teams by surfacing an employee’s current sentiment, career growth plans, learning opportunities, recommendations for upskilling/reskilling, and overall talent retention effectiveness. It also simplifies the process of endorsing a direct report’s skills.
New Automation Announcements for Talent Acquisition and Talent Management
Phenom also announced new automation technology for frontline and hourly workers that will empower them to reduce friction and connect candidates with jobs faster, foster employee development, and reduce tedious, manual tasks for recruiters.
Automation Engine is the powerful backend behind phenomenal hiring, growth and retention experiences. It provides the framework and components to identify, build, implement, and monitor automation workflows into new or existing talent lifecycle processes (e.g., hiring, career development, and retention). It includes workflow intelligence for constant monitoring and qualitative analysis of workflow performance and provides recommendations for optimization. Process mining capabilities identify opportunities to optimize further — leading to outcomes such as improved conversion rates and higher volume of hires in less time.
Talent Companio n provides an always-on, omnichannel approach to engage candidates throughout the hiring process — facilitating a streamlined application, interview and hiring experience. It provides real-time responses to questions, helps prepare for interviews and shares reminders at the right time to eliminate any guesswork.
High-Volume Hiring delivers full end-to-end automation of the hiring process, from first interaction to hire. It is designed specifically for industries such as retail, transportation, hospitality, and manufacturing that require a fast and frictionless candidate onboarding experience. Using AI-based workflows, High-Volume Hiring removes redundant processes that can clog the volume hiring pipeline. It also reduces the strain on recruiting teams by automating for high-volume and seasonal staffing surges so they can shift their focus to lengthier knowledge worker hiring cycles.
Requisition and Offer Management for High-Volume Hiring enables hiring managers to autonomously raise requisitions and extend offers to candidates, accelerating the process of making opportunities available to candidates, while reducing reliance on other stakeholders and decreasing time to hire.
Career Pathing for Frontline gathers an employee’s experience, tenure and behaviors and surfaces their next best-fit role within their organization. Growth trajectories can be tailored based on an organization’s unique role requirements.
Alumni Network re-engages former employees to strengthen and maintain positive long-term company relationships. The network can be leveraged from a recruitment perspective to make alumni employees aware of new openings that can bring them back to the company — supporting aspirations to rehire already trained talent and provide potential career advancement opportunities.
New Platform Experience Announcements
Phenom designed additional platform enhancements, including: Design Studio which provides talent and brand marketers with high-fidelity career design within a no-code framework; People Analytics that puts data behind every hiring, growth and retention decision; AI Control Center that enables organizations with controls and configurations to maximize the full potential of intelligence across the platform based on individual preferences and requirements; Connector Studio which improves integration with critical third-party applications and technology to improve business performance.
New Phenom Service Experience For Improved Global Customer Care
To better support customers’ evolving needs, Phenom announced a new multi-tiered support model — Phenom Service Experience. By adding more self-service capabilities and a direct line to support, Phenom is accelerating problem resolution and increasing customer satisfaction. Built to provide exceptional support and phenomenal moments, Phenom Service Experience includes: Support Portal, Service Hub, Platform Status Page, Learning Academy, User Community, Global Office Hours, Premium Support Plans, and Managed Services Plans.
With Phenom, candidates find and choose the right job faster, employees develop their skills and evolve, recruiters become wildly productive, managers build stronger-performing teams, HR aligns employee development with company goals, and HRIS easily integrates existing HR tech to create a holistic infrastructure.
To learn more, register for our live event: Experience Phenom X+, Generative AI for Human Resources Demonstration.
About Phenom
Phenom has a purpose of helping a billion people find the right job. Through AI-powered talent experiences, employers are using Phenom to hire employees faster, develop them to their full potential, and retain them longer. The Phenom Intelligent Talent Experience platform seamlessly connects candidates, employees, recruiters, hiring managers, HR and HRIS — empowering over 500 diverse and global enterprises with innovative products including Phenom Career Site, Chatbot, CMS, CRM, AI Scheduling, Video Assessments, Campaigns, University Recruiting, Talent Marketplace, Career Pathing, Gigs, Mentoring, and Referrals.
Phenom has earned accolades including: Inc. 5000’s fastest-growing companies (3 consecutive years), Deloitte Technology's Fast 500 (4 consecutive years), five Brandon Hall ‘Excellence in Technology’ awards including Gold for ‘Best Advance in AI for Business Impact,’ Business Intelligence Group's Artificial Intelligence Excellence Awards (3 consecutive years), and a regional Timmy Award for launching and optimizing HelpOneBillion.com (2020).
Headquartered in Greater Philadelphia, Phenom also has offices in India, Israel, the Netherlands, Germany and the United Kingdom.
For more information, please visit www.phenom.com. Connect with Phenom on LinkedIn, Twitter, Facebook, YouTube and Instagram.
| 2023-03-31T00:00:00 |
https://www.phenom.com/press-release/phenom-unveils-phenom-x-generative-ai-for-human-resources-and-18-intelligent
|
[
{
"date": "2023/03/31",
"position": 84,
"query": "AI job creation vs elimination"
}
] |
|
How to Bridge the Digital Skill Gap for Better Productivity in ...
|
How to Bridge the Digital Skill Gap for Better Productivity in 2023
|
https://emeritus.org
|
[
"Anwesha Barari",
"About The Author",
"Read More About The Author",
"Niladri Pal",
"Sanmit Chatterjee"
] |
How can companies address the glaring skill gap to better meet organization needs? Read on for a complete guide on strategies and benefits.
|
How to Use Technology to Plug the Skill Gaps You Have in 2023
A 2021 Salesforce report claims that 14 G20 countries would have lost out on $11.5 trillion in cumulative GDP growth due to the digital skill gap being faced by the corporate sector. The report further defines the skill gap as the divide between the skills a company needs and what the dominant workforce offers. Simply put, in a digital-first world, there aren’t enough people with appropriate digital skills to power the technological transformation of companies. Corporations and governments need to fortify the business landscape by promoting a sustainable skill development path for employees. This blog provides an in-depth view of the present conditions of the skill gap, its governing factors, and some crucial workforce optimization strategies.
The State of the Skill Gap in 2023
A 2023 Wiley Report, ‘Closing the Skills Gap’, shares in-depth insight into the talent shortage problem regarding how the demand for rapidly evolving skills, specifically digital, is evolving too fast for companies to keep up. Here is a summarized capsule of relevant statistics from the report:
69% of the surveyed HR professionals believe their respective organizations suffer from a skill gap, which is a 14% rise from 2021
The talent shortage results in up to 20% of unfulfilled job postings
At least 50% of the interviewed professionals claimed that in the current job market, hard skills have a shelf life of merely two years
The expertise of soft skills alongside hard technical skills is critical to arresting the digital skill gap
A look at these facts makes it evident that the parameters of measuring workforce competencies are also evolving along with the needs of the market. So what explains the difference between the in-demand organizational skills and what employees possess right now? The answer may be found in the success or failure to adapt to the disruptive force of technology.
ALSO READ: What are the 15 Top Jobs in Demand Today?
What Is the Role of Technology in the Skill Gap?
A 2022 Forbes article pointed out an interesting contradiction to explain why the skill gap exists. Despite Gen Z being the first truly ‘digital native’ generation, 55% of them admitted to having deficiencies in understanding the core tech trends of the time, namely, Artificial Intelligence (AI), cybersecurity, edge computing, or quantum computing.
Intel’s general manager Trish Blomfeld holds traditional academic disciplines responsible for this hard skill/soft skill disparity among the workforce. On the one hand, students from traditional STEM (Science, Technology, Engineering, and Mathematics) backgrounds lack soft skills in communication, creativity, and design thinking. On the other hand, studying only arts subjects fails to empower learners with the necessary tools to leverage technology to its maximum potential.
A holistic technical education that accommodates the latest soft-skill requirements is the best way to navigate this climate of digital transformation. Replacing STEM subjects with STEAM—where A stands for ARTS—would be an appropriate response within mainstream education to remedy this widening skill gap.
At a more advanced stage, the talent shortage can be tackled by educating the workforce.
ALSO READ: Top 5 Soft Skills You Should List on Your Resume
Addressing the Skill Gap through Workforce Education
Workforce education comprises the following:
Employee development initiatives
In-house training resources
Strong awareness of this skill disparity among the leadership
However, executing learning and development systems can be quite a challenge for companies. Referring to the same Wiley Research report, over 40% of companies said they do not have the resources to implement strong employee upskilling strategies. Nevertheless, platforms such as Emeritus also exist in the upskilling roadmap alongside the following:
Scholarships awarded by companies
Course discounts sponsored by universities
Granting paid leaves for training purposes
Internships
Tuition reimbursement
Apprenticeships in other branches of an organization
Online company-sponsored training courses
As more employers offer these benefits, they can assume greater employee retention. A 2022 SHRM study states that 76% of professionals expressed willingness to stay in an organization that offers continuous training. This will eventually lead to the development of an agile workforce that can weather contemporary technological changes and ensure consistent business growth. Moreover, with remote opportunities becoming the norm, the talent pool will broaden and diversify with time. All of this indicates that capitalizing on workforce education is an effective remedy to fill the persisting skill gap.
Upskilling for the Future of Work
The pandemic has upended the professional world. Today’s competitive business environment requires a strong work culture powered by technically-equipped individuals who also have strong emotional intelligence (EQ) skills. EQ enables a strong understanding of client needs and arms you with the necessary tools to understand company data in its full context. In short, the requirement concerns multidisciplinary professionals with hard and soft skills.
Which Skillsets Have the Highest Demand?
Here is a list of hard skills that recruiters actively seek in candidates in 2023:
Data analysis skills
Digital communication skills
Project management
Coding skills
Machine operations
Research skills
Engineering
As far as soft skills are concerned, HR professionals list the following as having the highest demand:
Problem-solving
Time management
Change management
Leadership skills
Managerial skills
Creativity
Teamwork
Adapting to Innovation
ALSO READ: What Top Trending Digital Skills are Employers Looking for in 2023?
The Benefits of Addressing the Skill Gap
Let’s look at how addressing the skill gap affects organizations and individuals in different ways:
Organizational Benefits
Provides deep insights into the existing workforce
Streamlines the recruitment process
Offers a clear understanding of company needs and their alignment with long-term business objectives
Enables strategic workforce planning
Boosts competitive advantage
Diverse talent pools attract better creative solutions to new business challenges
Employee Benefits
Opportunity to partake in a continuous learning environment
Better communication skills lead to maximum management-employee synergy and higher productivity
Psychological empowerment leads to more professional confidence
Opportunity to future-proof one’s career and thoroughly understand market needs
Closing the Skills Gap with Emeritus
Emeritus collaborates with the most prestigious institutions across the globe, bringing the highest-quality technical education to you. Acquire the new-generation toolbox of soft and hard skills with these online courses from Emeritus and learn more about our enterprise solutions to upskill your workforce.
Write to us at [email protected]
| 2023-03-31T00:00:00 |
2023/03/31
|
https://emeritus.org/blog/career-skill-gap/
|
[
{
"date": "2023/03/31",
"position": 11,
"query": "AI skills gap"
}
] |
What is Upskilling?
|
What is Upskilling?
|
https://www.imocha.io
|
[] |
This approach reduces skills gaps to help employees perform better and take on new challenges. . Upskilling helps improve the existing employees' skill sets ...
|
What is Upskilling?
Upskilling is a process of expanding an employee's skills and strengths through training and development. This approach reduces skills gaps to help employees perform better and take on new challenges.
Upskilling helps improve the existing employees' skill sets through training, enabling workers to advance in their careers and explore new roles within the company. Employees can boost their value at work and improve their job security, job satisfaction, and earning potential by keeping up on the most recent business developments and technological advances.
As technology creates new job opportunities, companies must find candidates with relevant, specialized skill sets to fill these roles. Through upskilling, organizations can address the talent gap and fill open positions while retaining their current workforce. At the same time, it also provides employees with opportunities for growth and development.
What is the Potential of Upskilling Employees?
Employers increasingly recognize the importance of ongoing training and upskilling in the workplace. It helps by broadening their job pool by including employees who may not have the requisite experience but are willing to learn new skills. A larger pool of candidates can be obtained for their open positions by focusing on individuals who demonstrate the qualities an organization desires.
On the other hand, organizations can also overcome the challenge of talent shortage in the global market by training and upskilling their employees. It enables them to fill positions through internal hiring to achieve their objectives.
Comparison Between Upskilling and Reskilling
Definition
It is the process of acquiring new skills or enhancing the current skill set.
It is the process of acquiring new cross-functional skills.
Purpose
It teaches new skills to help employees optimize their performance.
It trains employees to adapt to the demands of a different job role within the company.
Benefits of Upskilling
Upskilling offers various benefits for both businesses and employees. Here are some of the significant advantages of upskilling in your company:
Real-Time Adaptability: By implementing internal upskilling programs, you can train and deploy existing talent to fill the gaps as they arise. It ensures that your company is not entirely reliant on the labor market and can quickly respond to changes in business needs.
By implementing internal upskilling programs, you can train and deploy existing talent to fill the gaps as they arise. It ensures that your company is not entirely reliant on the labor market and can quickly respond to changes in business needs. Time and Resource Saving: This process also enables you to save time and resources. Internal learning and development costs are much lower than hiring and onboarding a new employee.
This process also enables you to save time and resources. Internal learning and development costs are much lower than hiring and onboarding a new employee. Improved Productivity, Engagement, and Retention: By incorporating upskilling methodology, your employees can become more efficient, productive, and agile, staying relevant and up-to-date. Offering upskilling opportunities helps employees envision themselves staying with the company long-term and prevents them from feeling trapped in their current role.
Having difficulty determining the ROI of your learning program? Learn how AmaliTech’s team enhanced their training programs using iMocha’s skills evaluation reports. Start your free trial now!
Types of Upskilling
Some of the common types of upskilling techniques include:
Agile Online Training – This training focuses on speed, flexibility, collaboration, and more.
This training focuses on speed, flexibility, collaboration, and more. In-Person Training – It focuses on individualized learning.
It focuses on individualized learning. Blended Learning – It combines two primary learning options - online and classroom training - to provide a personalized upskilling experience.
It combines two primary learning options - online and classroom training - to provide a personalized upskilling experience. Formal Education with External Courses – It entails high-quality, accredited training to support career growth within the organization.
It entails high-quality, accredited training to support career growth within the organization. Mentorship, Coaching, and Shadowing – They focus on one-on-one guidance and support to employees to develop leadership and soft skills.
They focus on one-on-one guidance and support to employees to develop leadership and soft skills. Microlearning – It delivers small, bit-sized learning modules to help employees learn new skills and knowledge and a quicker pace.
It delivers small, bit-sized learning modules to help employees learn new skills and knowledge and a quicker pace. Hands-On Opportunities – Employees apply their newly-acquired skills into practice, providing the company with immediate return on investment.
Terms Related to Upskilling
Reskilling: It is the process of acquiring new skills or knowledge to adapt to changing work requirements or job roles.
Cross-training: It is a practice that involves teaching employees skills beyond their primary job responsibilities to increase their flexibility and enhance their abilities.
Microlearning: It is an instructional approach that uses short and focused learning activities to achieve specific learning goals.
Skills gap analysis: It identifies the gaps between the current workforce's skills and knowledge and the requirements of their job roles.
Competency assessment: It evaluates employees' skills, knowledge, and abilities to determine their proficiency in specific job roles or tasks.
Learning management system: It is software that delivers, manages, and tracks learning content and activities for organizations and individuals.
| 2023-03-31T00:00:00 |
https://www.imocha.io/glossary/what-is-upskilling
|
[
{
"date": "2023/03/31",
"position": 93,
"query": "AI skills gap"
}
] |
|
How AI Will Impact the Future of Work: Insights from CEE
|
How Is Artificial Intelligence Shaping the Future of Work? CEE Founders Share Their Insights
|
https://therecursive.com
|
[
"Eva Slonkova"
] |
“AI is not only bringing enormous value in operational savings and revenue improvements, but it also creates jobs in three categories.
|
How AI will impact the future of work has become a topic of global interest. The latest reports are projecting that the AI market is set to experience explosive growth, with a staggering jump from nearly $100 billion in 2021 to an estimated $2 trillion by 2030. Moreover, becoming one of the fastest-growing technologies, AI is predicted to have a $15.7 trillion potential contribution to the global economy by the end of the decade.
AI has already started to transform the workforce landscape, and in this article, The Recursive will explore how humans can take advantage of the escalating innovation wave.
When considering how AI will impact the future of work, it is essential to examine the different areas of the technology, including machine learning, natural language processing, and advanced language models. While these technologies are poised to enhance and streamline our work processes, it is equally important to acknowledge the continued significance of human intelligence in the modern workforce.
AI and the future of work
The World Economic Forum (WEF) recently published a report that predicted the growth of AI in the labor market and identified tasks that are more likely to be automated in the future. These tasks include, for example, data collection and performing simple, repetitive assignments. However, tasks that require abstract thinking, problem-solving, and human touch will likely remain the domain of human beings for the foreseeable future.
In extreme scenarios, some science fiction novels and movies have painted a picture of a world where AI has taken over humans’ jobs entirely, leaving many people unemployed. While AI can change the future of work, it is still one component of a larger workforce.
As we continue to navigate the societal challenges of AI and the labor market, it is essential to remember that AI is not a replacement for human beings. Instead, it is a tool that can help us perform tasks once thought impossible with the right skills and willingness. Considering the challenges of climate change and other societal issues we continue to face, we can use the technology to create a better future for ourselves and the planet.
To dive deeper into the effects of AI on the way humans work, we have sat down with CEE AI startup founders, analyzing some of the main impacted areas. The insights were provided by:
Filip Dvořák: CEO and founder of Czech automation platform Filuta AI
Dominik Mate Kovacs: CEO and founder of Hungarian text-to-video solution Colossyan
Milan Mahovský: CEO and founder of Czech AI-powered hiring platform dream.jobs
Adam Gonczarek: CTO and co-founder of Polish automate document processing platform Alphamoon
AI will help us understand human bias in recruitment and speed up the process.
Humans naturally bring bias to recruiting, whether intentionally or not. And as humans provide data sets to AI, the bias can be transferred. Therefore, AI needs to be programmed correctly. In such cases, AI can help to understand and promote no-bias recruitment in two key views, as Milan Mahovský, the CEO and founder of dream.jobs, explains.
“First is intentional bias, for example, when a hiring manager requires to hire a man or a good-looking employee. The second is not intentional. People discriminate subconsciously without realizing it. We focus on understanding skills matching, how many years of experience the person has, or if they have managerial experience. AI does not take into consideration such bias factors if the training of AI is programmed not to include copying or simulating human behavior.”
“Another view on non-bias is that current job portals or career pages ask the candidates to choose a category of job adverts. Very often the job is in a different category, and they do not find it. AI allows search based on CV; the categories (boxes) are not needed. So the candidate can find all relevant jobs,” adds Milan Mahovský.
Milan Mahovský further comments on recruitment efficiency, “AI has huge potential to speed up recruitment. It can match a CV with a job advert 24/7 daily with better accuracy than full-text and categorizations. Moreover, AI-powered job alerts notice candidates about relevant jobs. Nowadays, recruitment, on average, takes 41 days. For many types of positions, it takes a few months. AI has the power to shorten the time to hire by 50 to 80%.”
AI automation will save us time to focus on other tasks and boost work efficiency.
By taking on repetitive and mundane tasks, AI allows people to focus on more complex and high-value tasks that require human skills, such as creativity, critical thinking, and problem-solving. With AI taking care of routine tasks, we can streamline processes, reduce errors, and improve productivity.
For example, in the medical industry, AI advances data analysis or streamlines administrative tasks, allowing doctors and nurses more time to solve complex medical problems. In another case, AI advances in machine learning skills and computing power have enabled the development of autonomous vehicles, such as autonomous cars, boosting transportation and mobility industries.
Filip Dvořák, the CEO and founder of Filuta AI, notes, “one of the most substantial areas of applying AI in companies is intelligent automation – replacing manual processes in the company with automated optimization systems that not only automate but also optimize operations. Intelligent automation is growing into an enormous $1T in 2026, and it is also the primary market of Filuta AI. Many other areas will benefit from AI, such as customer experience personalization, predictive maintenance, or career management.”
“AI assists and simplifies mundane tasks. By releasing people from repetitive tasks that create little value, AI companies help their clients tap into the new potential of their existing teams. We have insights from our clients at Alphamoon who say document AI software increased team morale (work became more interesting and easier) and gave them time to tackle more challenging issues. Automation helps find information faster and lets our clients focus on building a better experience,” says Adam Gonczarek, the CTO and co-founder of Alphamoon.
“AI will be the force shaping many industries in a matter of months, not years. Bringing AI to internal processes will likely mean staying ahead of the curve, which might be the most crucial benefit of all,” adds Adam Gonczarek.
Competition vs. cooperation: Why human-AI collaboration will dominate the future of work.
While AI promotes more efficient workflow, human workers can provide the context and intuition that AI may lack. As a result, the cooperation between AI technology and human thinking can bring better decision-making and more innovative solutions to complex problems. Moreover, humans can adapt to changing situations and act based on ethical considerations.
“AI is already the right-hand tool for people working in various areas such as engineering, design, finance, or art. For example, writer’s block is a common problem in writing, and AI is already helping authors have a base foundation for their work. Humans are primarily exceptional at making high-level decisions and solving complex problems. The current AI system won’t be able to replace this critical thinking, at least as long as they are designed restrictedly,” says Dominik Mate Kovacs, the CEO and founder of Colossyan.
AI will create brand-new jobs.
According to recent findings, the current speed of AI development will affect hundreds of millions of jobs worldwide. While the impact is likely going to result in job losses, the long-term effects forecast positive growth of the global economy. Similar to previous technological advancements like the Industrial Revolution, AI will also ultimately lead to the adaptation of current jobs and the creation of new ones.
Despite fears that AI will replace human workers, the reality is that AI systems are being designed to augment human labor rather than replace it entirely. In fact, the job market is expected to see significant job growth in AI, with over half of all jobs created in the commercial world expected to require AI skills in the future.
“AI is not only bringing enormous value in operational savings and revenue improvements, but it also creates jobs in three categories. First, there are going to be jobs related to the applications of AI itself – trainers, explainers, auditors, ethics, and risk managers. New jobs are going to form around AI-augmented-human positions, artists, designers, healthcare professionals, and educators. And finally, AI researchers and engineers will drive forward the capabilities of AI itself to help across all the fields,” Filip Dvořák adds.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://therecursive.com/how-ai-will-impact-the-future-of-work/
|
[
{
"date": "2023/03/31",
"position": 10,
"query": "future of work AI"
},
{
"date": "2023/03/31",
"position": 74,
"query": "machine learning workforce"
},
{
"date": "2023/03/31",
"position": 24,
"query": "artificial intelligence workers"
},
{
"date": "2023/03/31",
"position": 76,
"query": "artificial intelligence hiring"
}
] |
About Timothy B. Lee
|
Understanding AI
|
https://www.understandingai.org
|
[
"Timothy B. Lee"
] |
... AI. Building on my reporting for Full Stack Economics, I've written about how generative AI could affect the labor market and the broader economy. I've ...
|
About Timothy B. Lee
I’m a reporter who has written about technology, economics, and public policy for more than a decade. Before I launched Understanding AI, I wrote for the Washington Post, Vox.com, and Ars Technica. I have a master’s degree in computer science from Princeton.
I’m working on Understanding AI full-time, and I have no outside investors or donors. Since I started it in 2023, paying subscribers have accounted for a large majority of my income (you can see full details on my source of income on my disclosure page). Their support allows me to work on the newsletter full-time.
About Understanding AI
Fifteen years ago, I was surprised by the rapid progress of self-driving cars. During the 2010s, I was surprised by the rapid progress of image recognition software and voice assistants like Amazon’s Alexa.
But none of those technologies surprised me as much as ChatGPT did when I first tried it late 2022. Then I was surprised again when OpenAI released its impressive o1 model in 2024.
LLMs still have significant weaknesses, but still I think the pace of progress over the last five years has been stunning. And not just in chatbots. We’ve seen rapid progress in everything from self-driving cars to predicting the three-dimensional structure of proteins.
Between 2021 and 2023, I wrote a newsletter that covers the economy in a “full-stack” way, writing about important economic developments in the worlds of business, policy, finance, technology, and so forth. Understanding AI aims to do the same thing for the AI industry:
I have a master’s degree in computer science and I have written in-depth explainers about how AI works.
Drawing on two decades of experience writing about tech policy, I’ve written about the legal and policy landscape for AI.
Building on my reporting for Full Stack Economics, I’ve written about how generative AI could affect the labor market and the broader economy.
I’ve written written about the philosophical issues raised by generative AI. How does artificial intelligence compare to human intelligence. What kinds of data will AI systems need to achieve human-level intelligence?
I’ve found that pproaching these issues from multiple directions yields insights that you wouldn’t get from a newsletter that only focuses on one of these angles. Writing technology explainers sharpens my thinking about philosophy and policy questions. Writing about startups and the labor market helps me figure out which models and techniques are truly adding value.
Understanding AI is a daily newsletter that helps you “keep up” with every new development in the AI world. I publish about one article a week that helps readers understand the most important trends and debates in the AI world.
If that sounds interesting, please click here and subscribe to Understanding AI.
Subscription policy
I publish two to six times per month, with about half of my posts being limited to paying subscribers.
To cancel your subscription, log in, click your account icon in the upper-right hand corner of the screen, and choose “manage subscription.” Scroll down to the bottom of the page and you’ll see the sentence “To cancel your paid subscription, click here.”
Pro-rated refunds are available upon request.
| 2023-03-31T00:00:00 |
https://www.understandingai.org/about
|
[
{
"date": "2023/03/31",
"position": 75,
"query": "AI labor market trends"
}
] |
|
HR and AI: How can HR use AI effectively and ethically?
|
HR and AI: How can HR use AI effectively and ethically?
|
https://www.hrmagazine.co.uk
|
[
"Millicent Machell"
] |
It outlined five key principles that companies should follow in their use of AI: safety, security and robustness; transparency and explainability; fairness.
|
The government published a whitepaper on Wednesday (29 March) which promised to regulate artificial intelligence (AI).
AI has been a popular topic of discussion due to new generative AI tools such as ChatGPT.
There are, however, concerns regarding bias in AI, especially when used in decision-making, for example in recruitment practices, due to the flawed data it learns from. This means that there could be serious DEI failings if AI is used incorrectly.
More about AI:
AI used as a training tool to help improve employee pitches
Businesses warned employees lack skills to handle AI
UK workers believe AI offers better career support than people
The whitepaper did not establish new regulation but called on regulators to apply existing rules.
It outlined five key principles that companies should follow in their use of AI: safety, security and robustness; transparency and explainability; fairness; accountability and governance; and contestability and redress.
So how can HR teams effectively use AI while adhering to these principles?
Perry Timms, chief energy officer, PTHR
“Generative AI has captured our attention since the widely accessible ChatGPT from Open AI, Microsoft’s enhanced Bing search and now Bard from Google. I’ve experimented a little – with mixed results – and I know the talent acquisition world particularly has been using ChatGPT in a range of ways (CV data entered to show a match for role profiles as one example).
“We’ve heard about AI processing power, but now have our hands on it and it’s potentially amazing and potentially volatile.
“As people professionals we have to remember this is not just processing. People’s lives and livelihoods are in our hands on some of the decisions we make to hire, develop, review, assess and deploy people’s skills, energy, will and creativity.
“AI cannot do everything. Nor can we. In a time of emerging discovery let’s not get carried away but be experimental and with safety and fairness at the top of our minds.
“We cannot opt out totally, so we have to be assured and confident and that only comes from wisely being “in the arena".
Gosia Adamczyk, director of HR, Verve Group
“AI is here to stay and HR teams should learn to embrace its ability to increase efficiency and save time.
“There are uses for AI at every stage of the employee lifecycle. For example, we can use generative AI to create simple and specific job descriptions that hone in on the competencies needed for a role. We could then go on to generate job interview questions that are based around those competencies. We can even use it in internal communications, for example to adjust the tone of voice on some information and make it more fun for employees to read.
“However, we must remember that AI is there to support us, not replace our jobs. We can’t blindly communicate anything produced by AI, we have to check everything and make sure it is fully in line with our values.
“No one has the answer yet on how to use AI perfectly and it is imperative not to trust it completely and remain aware of its flaws.”
Manny Athwal, founder, School of Coding
“One positive aspect of AI is its ability to analyse large amounts of data quickly and objectively, allowing HR professionals to make data-driven decisions. It can also reduce bias when hiring by removing subjective factors like gender or race from resumes, and can assist with identifying qualified candidates who may have been overlooked.
“There are also potential negatives associated with AI. Algorithms used in AI systems can perpetuate bias if they are trained on biased data or programmed without careful consideration of DEI concerns. Additionally, AI may not be able to fully capture the nuances of human behaviour and may miss critical factors in decision-making processes.
“To ensure AI used in HR does not have negative effects on DEI, HR professionals should be aware of potential biases in the data used to train the algorithms and carefully monitor the results to identify any potential biases. It’s also essential to involve diverse perspectives in the development and implementation of AI systems and to regularly evaluate their impact.”
Kelly Thomson, employment partner, RPC
"AI technology can be very useful, including as a potential way to disrupt the impacts of unconscious biases in human decision-making. But there is clear evidence that bias from an underlying data set can become entrenched in an AI algorithm. The danger is creation of an apparently neutral decision-maker which, in reality, has bias built into its DNA.
“The new AI framework doesn't change the legal obligations on AI users not to discriminate against individuals. Nor does it speak to the use of AI to proactively improve equity. Instead, it simply encourages sector regulators to ensure that regulated entities are complying with laws on discrimination by taking steps to avoid bias arising within AI.
“Human understanding and continuous oversight of AI technology and processes will be critical to doing this. But, at the same time, this emphasises the importance of proactively minimising the potential for the biases of those humans to find their way into the technology being created, reviewed and updated."
Listen to the HR Most Influential Podcast's episode (S2, E4) dedicated to the human impact of AI here.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://www.hrmagazine.co.uk/content/news/hr-and-ai-how-can-hr-use-ai-effectively-and-ethically/
|
[
{
"date": "2023/03/31",
"position": 30,
"query": "AI regulation employment"
},
{
"date": "2023/03/31",
"position": 72,
"query": "government AI workforce policy"
}
] |
Generative AI in the modern workplace
|
Generative AI in the modern workplace
|
https://kpmg.com
|
[] |
The modern workplace can now be supported by AI capable of generating new data based on a set of learned patterns, principles, and rules.
|
There is a very good possibility that you or your colleagues have heard of at least one of the numerous iterations of generative artificial intelligence (AI) that have rapidly pervaded the modern workplace. This sudden influx of AI technology has gained so much traction that the World Economic Forum in Davos recently acknowledged the importance of generative AI and its possible effects on society as a whole.
Zeroing in specifically on the field of modern work, AI has the capacity to transform how we go about our day-to-day tasks. While the emerging technology that supports creative functionality is still in early, exploratory phases, organizations and employees have begun to tap into the opportunities afforded by weaving generative AI throughout common workplace practices. Many use cases have been presented, ranging from summarizing text to more advanced capabilities like the generation of naturally flowing written answers to emails, or supplying full modules of code. With AI now a steadfast contributor to aid productivity, and often already integrated in day-to-day computing, generative AI is distinguished through its ability to produce new content with relatively simple input.
The modern workplace can now be supported by AI capable of generating new data based on a set of learned patterns, principles, and rules. Images, text, and music are all within the capability of generative or “creational” AI, bolstering the production of creative output. Employees now have added help on their side to help spark creativity and productivity.
Many organizations (including KPMG) are already exploring how they can leverage this technology. Microsoft's recent investment in OpenAI and the subsequent announcements about Microsoft 365 Copilot are merely starting points exhibiting how this technology is becoming more thoroughly incorporated in day-to-day occurrences in the workplace.
How can generative AI revolutionize the future of work?
Generative AI already exhibits the potential to transform the current workplace into one geared towards increased productivity by automating tasks that can help free up employees’ time, allowing them to focus on more complex, higher-value work. In turn, organizations can improve their performance and drive business results by fostering innovation and working collaboratively with AI to optimize usage.
Looking deeper at Microsoft’s recent decision to embed OpenAI technology into their core set of products – namely Microsoft 365 Copilot and Viva Sales – organizations are able to leverage opportunities to boost productivity. For example, asking the AI to generate a sales email to customers using real-time, live data about prices and stock information from back-office systems can help save time and effort. Taking advantage of the full opportunity will require guidance and support as this a transformational era for the modern workplace.
Going forward, there are deeper exploratory usages of generative AI that are important to consider as businesses begin implementing this technology.
1. Augmenting the workforce
By asking a generative AI tool to draft a letter or summarize existing content, there is intrinsic value in freeing up time that would otherwise be spent completing general administrative tasks. Given the current level of quality output, generative AI is capable of assisting workers in their day-to-day routines; that said, at this stage, human review is still necessary and mandatory, fostering a collaborative environment between man and machine.
Human creativity remains the essential core of creative output, with generative AI providing enhancements to already-promising ideas. Generative AI can assist with a range of options that act as starting points for human creativity, but that human element is necessary to curate and fine-tune the output.
Despite the increasingly widespread practice of embedding AI into major workplace technologies, responsible use and ethical judgement is imperative.
2. Democratizing AI
Generative AI is also often referred to as “prompt AI,” where you only need a simple query input to generate quality results – no tweaking of models or parameters required. This ease of use supports the potential to more broadly leverage the AI that was once typically reserved for coders exclusively. Generative AI could be compared to the first low-code platforms, but with the added elements of user-friendliness and high-quality output, making it more accessible than its predecessors.
Generative AI will likely reach deeply into the workforce for many different use cases, from frontline workers to back-office staff. With free/low-cost models, developers, researchers and entrepreneurs may leverage the power of these models without having to invest in expensive hardware and data sets.
Looking ahead, the ongoing democratization of AI will require continued investigation and heightened focus on the underlying issues of data privacy and security and ethics.
3. Impact across industries and business functions
Preparing the workforce to work more closely with generative AI is less a question of “if” and more a matter of “how and when.” Use cases are broad, covering various industries and business functions. Generative form of AI has already begun appearing through:
Sales – permitting improved communication between workers using real-time data from back-office systems about clients and products.
Marketing & Communications – producing content from copywriting to videos that address customers more personally (i.e., via writing style and tonality).
Research and development (R&D) – supporting to identify creative new combinations as a new R&D starting point for product creation.
Risk and Legal – providing suggestions to complex questions more quickly, pulling from vast amounts of legal documentation, and drafting and reviewing annual reports.
The list of use cases continues to expand as our understanding of generative AI capabilities evolves, especially since programs such as ChatGPT have already begun changing the way we learn, code and generate content.
"Generative AI will likely change the way our clients run their businesses in the future. It can allow us to automate repetitive tasks, make more informed decisions and ultimately help drive growth and efficiency in the workplace. It's not about replacing human jobs; it’s about augmenting teams and creating new opportunities for businesses to thrive." – Dr. Sven Röhl, Global Alliance Lead – Microsoft Modern Work, KPMG International
| 2023-03-31T00:00:00 |
https://kpmg.com/xx/en/our-insights/ai-and-technology/generative-ai-in-the-modern-workplace.html
|
[
{
"date": "2023/03/31",
"position": 49,
"query": "AI regulation employment"
},
{
"date": "2023/03/31",
"position": 83,
"query": "government AI workforce policy"
}
] |
|
'Responsible AI' in the Military Domain: Implications for ...
|
‘Responsible AI’ in the Military Domain: Implications for Regulation
|
http://opiniojuris.org
|
[] |
Currently there is no legally binding, specific international regulation of AI applications in any domain, as discussions about the role of AI technologies in ...
|
31.03.23 |
This post is based on the regulation subpanel of the Realities of Algorithmic Warfare breakout session, held at the REAIM Summit 2023. Watch the full breakout session here.
This contribution also appears on the AutoNorms website.
The global debate on military applications of artificial intelligence (AI) and autonomy is gradually expanding beyond autonomous weapon systems (AWS) towards the concept of ‘Responsible AI’. Proponents of this framing often argue that AI technologies offer unprecedented opportunities for the defence sphere, while recognising the challenges and risks associated with military uses of AI. The overall narrative is that since applications of AI in the military and weapon systems are here to stay, we must find ways of developing and using these technologies responsibly.
What exactly this implies, however, remains debated. The ambiguity of the Responsible AI concept was visible during the REAIM Summit, held by the Government of the Netherlands together with the Republic of Korea on 15-16 February 2023 in The Hague. The Summit brought together different stakeholders including governments, militaries, researchers, the private sector, and civil society to consider opportunities and risks associated with military AI, as well as the potential for regulation in this area.
Throughout the REAIM plenary and breakout sessions, actors displayed various understandings and interpretations of this term, and crucially, what it means for global governance. There is agreement on the importance of using AI responsibly, for instance by retaining human control over the use of force, but not what this responsibility means exactly. There are particular uncertainties around concrete ways forward to ensure this responsibility. Overall, the Responsible AI frame allows actors to be vague in their proposals for global governance and regulation. It potentially risks undermining efforts for the setting of binding legal norms on the development, testing, and use of AI in the military domain.
What is Responsible AI in the Military?
Many portrayals of (anthropomorphic) AI in science-fiction feature humanoid robots and androids which are depicted as beings with their own conscience. This gives the wrong impression that AI applications can be legal subjects, and thus are legally, morally, and ethically responsible for their actions or thoughts.
But as pointed out by Virginia Dignum, Responsible AI is not about AI being responsible. It is all about humans and the “human responsibility for the development of intelligent systems along fundamental human principles and values”. As Dignum writes, “it is socio-technical system of which the [AI] applications are part of that must bear responsibility and ensure trust”. The socio-technical system is formed via human-machine interaction and encompasses not only technical aspects, but also societal, ethical, normative, legal, and political ones. Yet, human-machine interaction is becoming increasingly more complex, especially in the spheres of security and warfare. Defining Responsible AI in the military is therefore also a complex process. It is much more than a catch-all term used for political declarations.
As argued by Vincent Boulanin and Dustin Lewis, the concept of Responsible AI so far “appears to be more or less an empty shell”. Only a few states have published guidelines and clarifications on what they consider to be responsible applications of AI and autonomy in the military. Research by UNIDIR demonstrates that “the global AI policy landscape is still at a nascent stage,” although “gradually evolving”.
This includes the US Department of Defense’s “Ethical Principles for Artificial Intelligence” (2020), “Responsible AI Intelligence Strategy and Implementation Pathway” (2022), and more recently, the US Political Declaration on Responsible Military Use of Artificial Intelligence and Autonomy (2023). The United Kingdom released its guidelines on the Ambitious, Safe, and Responsible use of AI along its Defence AI Strategy in June 2022. The French Ministère des Armées, meanwhile, published an AI Task Force report in 2019, with then Defence Minister Florence Parly declaring that “the path we choose is that of responsibility, of protecting both our values and our fellow-citizens while embracing the amazing opportunities that AI offers”.
While such initiatives are valuable contributions to the debate, more is needed and expected from experts, scholars, and industry. At one REAIM session, Elke Schwarz argued that Responsible AI should be beyond “abstract ideas about what responsible is or could be”. It should also be about considering situations when not to use AI-based systems, especially when these concern life and death decisions. It should also be about having a broader discussion about the uncertainty and unpredictability associated with AI technologies.
At another panel, AI scholar Stuart Russell suggested that the main question should be: will we use military AI in a responsible way? Evidence from both the civilian and military spheres suggests that the answer to Russell’s question, at least in the near future, is no. In that case, Russell said, we need to think about our policy responses, especially in terms of setting binding international norms and regulations.
The Implications for Responsible AI for Regulation
Currently there is no legally binding, specific international regulation of AI applications in any domain, as discussions about the role of AI technologies in our societies are ongoing. The uses of AI in the military sphere raise particular questions surrounding the roles of humans and machines in the use of force, as well as concerns from different perspectives, including legal, ethical, and security.
However, legal aspects are often in the focus. At the Realities of Algorithmic Warfare session, Jessica Dorsey outlined some of the key questions from a legal point of view: is it possible to ensure legal accountability of machines making targeting decisions? How can humans review algorithms and data in black-boxed AI applications? What happens between the input and output? What is the minimum acceptable level of human control to ensure legitimate military operations?
With the absence of binding international legal norms on AI and autonomy in the military, ongoing practices of armed forces around the world have been gradually transforming the nature of human-machine interaction in warfare, for example in a way that limits the critical reflection space of human operators of weapon systems.
Scholars have suggested that International Humanitarian Law (IHL), which regulates armed international conflict, might be insufficient to address some of the complex issues related to the growing normalization of AI and autonomy in security and defence. Some industry actors agree: at one REAIM plenary session, the Chief Technology Officer of Saab, Petter Bedoire, indicated that governments should provide more guidance about accountability and responsibility, as “IHL is not precise enough”.
Yet, the Responsible AI framing is not necessarily more helpful when it comes to regulation. On the contrary, there is a risk that this trope undermines efforts to move towards global legally binding norms.
As Samar Nawaz argued at the Realities of Algorithmic Warfare session, moving forward with regulatory frameworks requires precise definitions and conceptions of key notions. The definitional debates surrounding autonomy which have been ongoing for years have been delaying the regulatory discussion, both in the civilian and in the military sectors. The ambiguity of the Responsible AI concept gives states the opportunity to subjectively define what is responsible and what is not.
The frame also allows for different interpretations of the policy responses necessary to address the broad discussions related to human responsibility in security and warfare. Based on their definitions of responsibility, increasingly more actors prioritise unilateral declarations over multilateral governance frameworks and common definitions. Many stakeholders argue that voluntary, national codes of conduct, or guides of best practices are best suited for regulating military uses of AI (see figure 1 below).
The Responsible AI trope also allows framing global regulation and norm-setting as a zero-sum game where someone wins, and someone loses. During REAIM, many state officials continued to push the narrative that only some states’ uses of AI in the military are responsible, whereas others’ will automatically be irresponsible. This discourse is fueled by the perception of an ongoing ‘AI race’ and the conviction that it is crucial to develop cutting-edge military AI and autonomy to surpass adversaries.
Figure 1. Results of survey conducted among the audience during the Realities of Algorithmic Warfare session.
Political declarations such as the one released by the US have been described as potential “building blocks” towards a more coordinated effort at the international level, for instance common standards which reflect existing military applications of AI. Such measures could be good first steps in broadening the debate beyond futuristic AWS.
But given the vagueness of the Responsible AI trope, unilateral measures risk becoming pathways for states who do not want to sign up to legal rules while wanting to “appear as though they are doing something”. As Tobias Vestner and Juliette François-Blouin write, the REAIM Call to Action “is relatively unspecific regarding concrete measures and prudent in terms of commitment,” symbolizing well this approach of demonstrating responsible unilateral action rather than global norm-setting.
Relying on voluntary measures, however, is insufficient to consider the global implications of military uses of AI. Setting legally binding global norms on responsible uses of military AI and autonomy would be a common good and win-win situation for everyone.
Prospects for Global Regulation
Recent events have demonstrated some signs of progress towards norms on AI and autonomy in the military. REAIM was followed by a regional conference held in and organised by Costa Rica. In the Belén Communiqué, 33 states from Latin America and the Caribbean agreed on “on the urgent need to negotiate a legally binding instrument, with prohibitions and regulations, on autonomy in weapons systems in order to guarantee meaningful human control”. The Communiqué was also endorsed by Andorra, Portugal and Spain at the 2023 Ibero-American Summit in March 2023.
Meanwhile, the ongoing debate about autonomous weapons at the UN Convention on Certain Conventional Weapons (UN CCW) has stalled since adopting the 11 Guiding Principles in 2019. However, the latest meeting of the Group of Governmental Experts (GGE) on AWS in March 2023 demonstrated the possibility of a more constructive and substantial discussion, generating optimism among delegations and civil society.
Many states seem to converge on the two-tiered approach of both prohibiting AWS which cannot be used in compliance with IHL and regulating other forms of AWS. However, there is no consensus on this way forward, with states such as India, Israel, Russia, and Türkiye being opposed.
The Responsible AI narrative does not facilitate the norm-setting process within the CCW forum. It reinforces the perception that global norms necessarily create winners and losers, which in turn fuels the position that unilateral codes of conduct and political declarations are sufficient to address challenges related to military applications of AI.
As part of Responsible AI, abstract discussions should be complemented with concrete actions from states willing to demonstrate moral leadership and set legally binding rules. States also have other options, including regional initiatives, to launch normative processes and set in stone some agreed principles of military uses of AI and autonomy, even without the immediate sign-up of major military developers.
| 2023-03-31T00:00:00 |
2023/03/31
|
http://opiniojuris.org/2023/03/31/responsible-ai-in-the-military-domain-implications-for-regulation/
|
[
{
"date": "2023/03/31",
"position": 85,
"query": "AI regulation employment"
}
] |
We are in the Age of AI Economies
|
We are in the Age of AI Economies
|
https://www.holisticai.com
|
[] |
... regulating the use of AI by companies, which must follow the established rules. ... As a result, there is also a new and rapidly growing AI job market in ...
|
With the expansion of computational power observed in the last ten years, artificial intelligence (AI) models have been gaining more and more space in various sectors of industry and academia. In an article written in 2021 and signed by a relevant group of researchers (including our co-founders, Adriano Koshiyama and Emre Kazim), it was stated that we are starting the Age of Algorithms (whether they are AI, machine learning or similar). This statement logically leads to the idea that we are now increasingly close to the Age of AI Economies. Meaning that work processes, the way that different markets are organised, the consumption patterns of economic agents, the way in which economic phenomena occur and are analysed, all are permeated by algorithms that generate impacts that are as of now still unknown.
The relationship between government, households, and companies in an AI Economy
In the last few months, large language models (LLMs) such as ChatGPT and GPT-4 have rapidly become household names and have moved markets that once seemed stable. New businesses have been developed (in the areas of entertainment, health, education, content production for social networks, productivity systems, etc.), as well as new professions (such as prompt engineering).
Figure 1: Representing Circular-Flow to AI Economy
In this new Age, algorithms bring challenges for regulators, researchers, companies, and society. We are facing a movement with repercussions in different economic and social sectors, and within the context of Industry 5.0, it will bring possibilities for advances in areas such as medicine, industrial automation, geoengineering, biotechnology, and more, through the integration between machines and humans. Industry 5.0 is a concept that aims to integrate the benefits of Industry 4.0 technologies (connecting machines and systems through AI and internet of things) with human-centred values (such as creativity, sustainability, and collaboration).
Figure 1 presents a simplification of how an economy in which artificial intelligence is a central element in the decision-making process of households, companies, and governments, is organised. The dark purple (counterclockwise) flow represents the circulation of real assets, meaning that AI workers offer their labour and skills in an AI Market for Factors of Production, and companies buy this labour and skills to create their AI systems. Following the same flow, companies offer their AI products in an AI Market for Goods and Services (software and hardware for AI), and households buy these goods and services.
The light purple (clockwise) flow presents the financial circulation associated with the AI Economy. Companies pay salaries to AI workers, and this received salary becomes income. The income is spent on purchasing or using AI goods and services. Finally, the income of AI workers becomes revenue (and profit) for the companies.
The relationship between the government, households, and companies was not built in the traditional form of tax payment but rather by households requesting more responsible AI systems (fair, explainable, robust, and secure) to increase well-being, and by regulating the use of AI by companies, which must follow the established rules.
This flow summarises how the main economic agents behave within an AI-based system. The interrelation between them becomes clear, as does the need for governments to act as mediators of any conflicts of interest that may exist between households and companies.
Governments strategies for artificial intelligence
In the case of AI models, there are some points that must be treated with care. Among these points, we can highlight the presence of biases (gender, race, age, nationality, etc.) in the data used to train the models, the difficulty of explaining the results in a humanly understandable way, issues such as privacy and security, and ethical aspects.
Through this conflicting situation, important initiatives (such as the Defense Advanced Research Projects Agency, part of the United States Department of Defense) have emerged to mitigate the adverse effects in the use of AI systems. The development of methods that make the models safety and transparent to end-users is a major challenge that is posed for the coming years and will make the use of artificial intelligence even more present in our daily lives.
These advances are not escaping the notice of governments around the world. The widespread use of AI models by market agents can generate adverse systemic effects that are already being discussed and investigated by regulators in several countries. In September 2021, the UK government launched a program called the National AI Strategy. This initiative aims to define guidelines and analyse how the use of AI can help governments and private institutions have increasingly resilient processes, with greater productivity, addressing ethical issues and collaborating for economic growth and innovation.
In addition, several countries are developing their own strategies and regulations for AI, such as Spain, China, and the Netherlands, and it's not just developed economies that are proposing to advance in this area. The Brazilian government launched the Brazilian Artificial Intelligence Strategy (EBIA in Portuguese) in April 2021. Guided towards the development of research and innovations in AI, EBIA has 73 strategic actions ranging from legislative and regulatory adaptation for the use of AI to the process of training and capacitating professionals to work in the field.
The increase (and necessity) of interdisciplinary approaches to AI
The debate surrounding the use of AI, especially among thinkers in the humanities and social sciences, is also rapidly expanding. This is a topic that is no longer limited to the codes and mathematical models developed by computer scientists and engineers, but is increasingly on the research agenda for philosophers, sociologists, anthropologists, economists, among others.
This is due to the interdisciplinarity that the advancement of the topic and its widespread use by society bring. As a result, there is also a new and rapidly growing AI job market in developed and developing economies.
The AI job market can be explored at a research level (specialised professionals for building computational models), operational level (professionals who deal with regulatory compliance, risk management, etc.), and abstract level (with professionals who are able to discuss and propose solutions for debates related to the ethical use of data and algorithms).
Summary
We are facing a scenario in which artificial intelligence is materialising in everyday society with increasing depth. And this materialisation is occurring rapidly, reshaping our way of interacting with technology and each other. At this moment of transition, it is up to society to discuss what the right path for this technological advancement is, especially in the case of artificial intelligence and its applications.
The existing relationships between governments, households, and companies are important for exploring the flows of real assets (labour, goods, and services) and the financial flow associated with an AI economy. In addition, the role of governments within this system is important for building a balance between the well-being of society and the benefits of the technology.
It is important to highlight the importance of governments continuing to act to mitigate adverse effects generated by the misuse of AI systems. It is necessary for countries to continue to develop regulations for the ethical use of AI that does not harm the most vulnerable in society, as well as ensuring that these systems act to increase fairness, explainability, robustness, and security.
| 2023-03-31T00:00:00 |
https://www.holisticai.com/blog/age-of-ai-economies
|
[
{
"date": "2023/03/31",
"position": 88,
"query": "AI regulation employment"
}
] |
|
March 2023 U.S. Tech Policy Roundup | TechPolicy.Press
|
March 2023 U.S. Tech Policy Roundup
|
https://techpolicy.press
|
[
"Kennedy Patlan",
"Rachel Lau",
"Carly Cramer"
] |
Public Opinion Spotlight · 62 percent agree that using AI in the workplace can save time and resources · 56 percent say AI generated written work can produce bias ...
|
Kennedy Patlan,
Rachel Lau,
Carly Cramer /
Apr 1, 2023
Kennedy Patlan, Rachel Lau, and Carly Cramer work with leading public interest foundations and nonprofits on technology policy issues at Freedman Consulting, LLC. Alondra Solis and Sofia Rhodes, Freedman Consulting Phillip Bevington policy & research interns, also contributed to this article.
U.S. Secretary of State Antony Blinken speaks during the Summit for Democracy on March 30, 2023, in Washington, D.C. State Department photo by Chuck Kennedy/ Public Domain
In March, TikTok and Congress faced off on the Hill as an increasing number of lawmakers from both sides of the aisles called for a ban of the platform. Notably, the Biden administration publicly expressed support for a bill that could force TikTok’s separation from its Beijing-headquartered owner, ByteDance, the administration’s first public foray into legislation related to the company’s fate. The month concluded with TikTok CEO Shou Chew testifying before the House Energy and Commerce Committee.
Additionally, ahead of the Summit for Democracy, the White House issued an executive order banning U.S. federal government entities from operationally deploying commercial spyware “that pose[s] significant counterintelligence or security risks to the U.S. Government or significant risks of improper use by a foreign government or foreign person.” Also on the surveillance front, the House Intelligence Committee established the Foreign Intelligence Surveillance Act (FISA) Working Group this month to take on the arduous task of reauthorizing Section 702 of FISA.
March was also a busy month for the Federal Trade Commission (FTC), which reached a $7.8 million settlement with BetterHelp after the online mental health company was found sharing customer data with third parties for advertising purposes. The agreement also banned BetterHelp from sharing consumers’ health data for advertising in the future. The agency also led investigations into Twitter’s data, privacy, and management practices following Elon Musk’s purchase of the company. The investigation was met with criticism from Republican members of the House Judiciary Select Subcommittee on the Weaponization of the Federal Government during a hearing, and in a related interim staff report. Separately, Politico reported on the FTC's intent to bring federal antitrust suits against Amazon, the likely outcome of active investigations into potential privacy, antitrust, and advertising violations by the company. These activities and other needs resulted in an FTC request to Congress to increase appropriations to the agency by more than 400 percent, potentially boosting its total budget by about 37 percent. (Much of the agency’s budget is covered by merger fees, which were boosted last year to support enforcement.)
Meanwhile, the Federal Communications Commission (FCC) faced another delay in filling the commission’s fifth seat after Gigi Sohn announced her withdrawal from the nomination process following an arduous 16-month process.
The below analysis is based on techpolicytracker.org, where we maintain a comprehensive database of legislation and other public policy proposals related to platforms, artificial intelligence, and relevant tech policy issues.
TikTok Faces Congress Amid Push for a Total Ban
Other Relevant Legislation
Federal Agencies Act on AI Harms; Congress Studies AI Issues
Summary: In March, federal agencies took steps to protect consumers and workers from AI-driven harms. Regulators at the National Labor Relations Board (NLRB) and the Consumer Financial Protection Bureau have unveiled a new information sharing agreement that aims to protect American consumers and workers from illegal employer surveillance and employer-driven debt. NLRB General Counsel Jennifer Abruzzo argued that some uses of employee surveillance and artificial intelligence tools could prevent workers from exercising their labor rights, and that a "whole-of-government approach" would be critical in ensuring that "workers are able to fully and freely exercise their rights without interference or adverse consequence." Meanwhile, the FTC warned of the dangers of artificial intelligence and synthetic media in regards to deepfakes and voice cloning, and cautioned companies against unfair or deceptive practices involving these tools. The Commission indicated that fraudsters are already employing generative AI tools to create hype realistic fake content rapidly and at low cost. A week later, the Commission reiterated the danger, issuing a consumer alert due to scammers using voice-cloning technology to extort individuals who believe they are speaking with a loved one. And in late March, FTC Chair Lina Khan also spoke about the agency’s intent to focus more on AI developments.
Meanwhile both the House and Senate held hearings on AI. Suresh Venkatasubramanian, a professor at Brown University and a former advisor to the White House Office of Science and Technology Policy (OSTP) on its Blueprint for an AI Bill of Rights, testified before the Senate Committee on Homeland Security and Government Affairs alongside RAND Corp President and CEO Jason Matheny and Center for Democracy and Technology President and CEO Alexandra Reeve Givens on March 8th, urging Congress to take action to protect civil rights while allowing for the responsible deployment of AI strategies. The House Oversight Committee’s hearing featured former Google CEO Eric Schmidt, IBM’s Scott Crowder, and Merve Hickok from the Center for AI and Digital Policy.
Additionally, the U.S. Chamber of Commerce's AI Commission on Competitiveness, Inclusion, and Innovation released its long-awaited report on the promise of AI, calling for a risk-based regulatory framework that balances potential harms with global economic competitiveness. While the report indicates some of the same concerns reflected by Venkatasubramanian's testimony, such as potential impacts on individual rights, it places a much heavier emphasis on the benefits of such technologies, pointing to uses such as patient monitoring in hospital settings, mapping wildfire paths, and creating new avenues for credit.
The Winding Path to a Potential 702 Extension
White House Limits Government Use of Commercial Spyware
The following bills progressed in the Senate in March:
The Moving Americans Privacy Protection Act (S. 758, sponsored by Sen. Steve Daines (R-MT)): This bill would protect the personally identifiable information of people moving to the U.S. by amending the manifest disclosure process of the Tariff Act of 1930. Currently, U.S. Customs and Border Protection publicly releases manifest sheets documenting household goods imported to the U.S. The act would ensure that the publicly disclosed information no longer includes personally identifiable information like names, addresses, social security numbers, and passport numbers. The bill passed the Senate in March by unanimous consent.
(S. 758, sponsored by Sen. Steve Daines (R-MT)): This bill would protect the personally identifiable information of people moving to the U.S. by amending the manifest disclosure process of the Tariff Act of 1930. Currently, U.S. Customs and Border Protection publicly releases manifest sheets documenting household goods imported to the U.S. The act would ensure that the publicly disclosed information no longer includes personally identifiable information like names, addresses, social security numbers, and passport numbers. The bill passed the Senate in March by unanimous consent. Preventing Child Sex Abuse Act of 2023 (S.724, sponsored by Sen. Chuck Grassley (R-IA)): This bill would expand the definition of child sexual abuse beyond physical contact to include intent of harm through internet platforms, online chat rooms, and webcams. The section would expand the definition by including individuals with any intent to engage in any illicit sexual conduct with another person as opposed to individuals with a motivating purpose to engage in these behaviors. The bill passed the Senate in early March by unanimous consent. The House companion bill was introduced in January by Rep. Tim Burchett (R-TN) as H.R. 454 and it has not yet progressed further.
(S.724, sponsored by Sen. Chuck Grassley (R-IA)): This bill would expand the definition of child sexual abuse beyond physical contact to include intent of harm through internet platforms, online chat rooms, and webcams. The section would expand the definition by including individuals with any intent to engage in any illicit sexual conduct with another person as opposed to individuals with a motivating purpose to engage in these behaviors. The bill passed the Senate in early March by unanimous consent. The House companion bill was introduced in January by Rep. Tim Burchett (R-TN) as H.R. 454 and it has not yet progressed further. Informing Consumers about Smart Devices Act (S. 90, sponsored by Sen. Ted Cruz (R-TX) and Sen. Maria Cantwell (D-WA)): This act, introduced in the Senate in January, would require manufacturers to disclose when internet-connected devices contain cameras or microphones. In March, the Senate Commerce Committee advanced the bill for consideration by the full Senate. The House passed the companion bill, H.R. 538, in February 406-12.
The following bill passed the House in March:
Protecting Speech from Government Interference Act (H.R. 140, sponsored by Rep. James Comer (R-KY)): This bill would prohibit federal employees from using their authority to advocate for censorship of speech, including speech on third party platforms or private entities. The bill defines “censorship” as “influencing or coercing, or directing another to influence or coerce, for the removal of lawful speech, the addition of disclaimers, or the restriction of access with respect to any interactive computer service (e.g., social media).” The measure applies to executive branch employees acting in an official capacity, and there are exceptions for legitimate law enforcement related to child pornography, human trafficking, controlled substances, or classified national security information. H.R. 140 passed the House on a party line vote (219-206) with all Republicans voting for the bill, but is unlikely to make progress in the Senate.
The following bills were introduced in March:
Facial Recognition and Biometric Technology Moratorium Act of 2023 (S. 681, sponsored by Sens Edward J. Markey (D-MA), Elizabeth Warren (D-MA), Bernie Sanders (I-VT), and Ron Wyden (D-OR)): This bill would prohibit any federal agency or official to use biometric surveillance. Individuals harmed by the use of surveillance would have the right to sue the entity believed to be at fault.
(S. 681, sponsored by Sens Edward J. Markey (D-MA), Elizabeth Warren (D-MA), Bernie Sanders (I-VT), and Ron Wyden (D-OR)): This bill would prohibit any federal agency or official to use biometric surveillance. Individuals harmed by the use of surveillance would have the right to sue the entity believed to be at fault. Upholding Protections for Health and Online Location Data (UPHOLD) Privacy Act of 2023 (S.631, sponsored by Sens. Amy Klobuchar (D-MN), Elizabeth Warren (D-MA), and Mazie Hirono (D-HI)): The UPHOLD Act would prohibit health data collected from any source to be used in commercial advertising without consent from the user. The entities collecting data will also be required to publish a privacy policy outlining the purpose of the data collected, how it's being used, and a specific list of third parties the entity discloses data to. The act would create more regulations on data minimization and disclosure restrictions and eliminate data brokers’ sale of precise location data.
(S.631, sponsored by Sens. Amy Klobuchar (D-MN), Elizabeth Warren (D-MA), and Mazie Hirono (D-HI)): The UPHOLD Act would prohibit health data collected from any source to be used in commercial advertising without consent from the user. The entities collecting data will also be required to publish a privacy policy outlining the purpose of the data collected, how it's being used, and a specific list of third parties the entity discloses data to. The act would create more regulations on data minimization and disclosure restrictions and eliminate data brokers’ sale of precise location data. Data and Algorithm Transparency Agreement Act (DATA) Act (S.688, sponsored by Sen. Rick Scott (R-FL)): This bill would require internet platforms to inform users of data being collected regarding their habits, traits, preferences, beliefs, or location and require explicit consent to data collection. The bill would create a private right of action for individuals to bring civil action for violations of the act, establish a right to delete for users to request the deletion of their personal data, and prohibit the selling or sharing of data to third parties without the user’s explicit consent. This bill is not related to H.R. 1153, the Deterring America’s Technological Adversaries (DATA) Act.
(S.688, sponsored by Sen. Rick Scott (R-FL)): This bill would require internet platforms to inform users of data being collected regarding their habits, traits, preferences, beliefs, or location and require explicit consent to data collection. The bill would create a private right of action for individuals to bring civil action for violations of the act, establish a right to delete for users to request the deletion of their personal data, and prohibit the selling or sharing of data to third parties without the user’s explicit consent. This bill is not related to H.R. 1153, the Deterring America’s Technological Adversaries (DATA) Act. Combating Cartels on Social Media Act of 2023 (sponsored by Rep. Abigail Spanberger (D-VA), Michael Burgess (R-TX), and Juan Ciscomani (R-AZ)): This bill would require the Secretary of Homeland Security to develop and implement a strategy improving coordination and collaboration between the appropriate agencies to prevent criminal organizations from utilizing social media platforms to recruit people in the United States to engage in illicit activities. It is a companion to Senate legislation, S. 61, introduced by Sens. Kyrsten Sinema (I-AZ), Mark Kelly (D-AZ), and Bill Hagerty (R-TN) in January.
(sponsored by Rep. Abigail Spanberger (D-VA), Michael Burgess (R-TX), and Juan Ciscomani (R-AZ)): This bill would require the Secretary of Homeland Security to develop and implement a strategy improving coordination and collaboration between the appropriate agencies to prevent criminal organizations from utilizing social media platforms to recruit people in the United States to engage in illicit activities. It is a companion to Senate legislation, S. 61, introduced by Sens. Kyrsten Sinema (I-AZ), Mark Kelly (D-AZ), and Bill Hagerty (R-TN) in January. Advertising Middlemen Endangering Rigorous Internet Competition Accountability (AMERICA) Act (sponsored by Sens. Mike Lee (R-UT), Amy Klobuchar (D-MN), Ted Cruz (R-TX), Richard Blumenthal (D-CT), Marco Rubio (R-FL), Elizabeth Warren (D-MA), Eric Schmitt (R-MO), Josh Hawley (R-MO), Lindsey Graham (R-SC), JD Vance (R-OH), and John Kennedy (R-LA)): The AMERICA Act would amend the Clayton Act “to prevent conflicts of interest and promote competition in the sale and purchase of digital advertising” by creating transparency and fair access requirements for digital ad companies that process more than $5 billion in digital ad transactions and prohibiting digital ad companies that process more than $20 billion in transactions from “owning more than one part of the digital ad ecosystem.”
(sponsored by Sens. Mike Lee (R-UT), Amy Klobuchar (D-MN), Ted Cruz (R-TX), Richard Blumenthal (D-CT), Marco Rubio (R-FL), Elizabeth Warren (D-MA), Eric Schmitt (R-MO), Josh Hawley (R-MO), Lindsey Graham (R-SC), JD Vance (R-OH), and John Kennedy (R-LA)): The AMERICA Act would amend the Clayton Act “to prevent conflicts of interest and promote competition in the sale and purchase of digital advertising” by creating transparency and fair access requirements for digital ad companies that process more than $5 billion in digital ad transactions and prohibiting digital ad companies that process more than $20 billion in transactions from “owning more than one part of the digital ad ecosystem.” To provide authorities to prohibit the provision of services by social media platforms to individuals and entities on the Specially Designated Nationals List and certain officials and other individuals and entities of the People's Republic of China, and for other purposes (H.R. 1714, sponsored by Rep. Brian Mast (R-FL)): No bill text was publicly available at the time of publication.
Public Opinion Spotlight
A Washington Post poll administered among 1,027 U.S. adults from March 17-18, 2023 focused on public opinions on TikTok. It found that:
41 percent of Americans support a federal ban on TikTok, while 25 percent oppose a ban
Those who do not use TikTok are more likely to support the ban (54 percent) while those who use TikTok every day or have used the app in the past month are more likely to oppose the ban (54 percent and 45 percent respectively).
72 percent of Americans believe it is likely that the platform hurts teens’ mental health
65 percent of Americans believe that TikTok likely collects personal data on Americans for the Chinese government
56 percent of Americans believe it is likely that China controls what American users see on TikTok
51 percent of Republicans and 33 percent of Democrats support the TikTok ban
43 percent of Americans believe that TikTok collects “about the same amount” of user data as other social media platforms
Global Strategy Group administered a public opinion survey from February 23 - February 27, 2023 with 1,000 registered voters regarding the state of misinformation. They found that:
78 percent of voters say they encounter misinformation somewhat or very often
53 percent of voters are very worried about misinformation
“Americans are unlikely to say they see misinformation on the cable news networks they frequently watch: just 23 percent of frequent Fox News viewers say they see misinformation on the channel, as do just 21 percent of CNN viewers on CNN and 14 percent of MSNBC viewers on MSNBC. However, frequent social media users are most likely to say they see misinformation on Facebook (52 percent).”
48 percent of voters are very worried about the impact of misinformation on climate change, 47 percent are worried about impact on crime, 44 percent on issues of gender and sexuality, and 42 percent on the impact on science and the strength of American democracy
In an Ipsos poll conducted from February 28-March 1, 2023 among 1,105 U.S. adults on AI, they found that:
62 percent agree that using AI in the workplace can save time and resources
56 percent say AI generated written work can produce bias or inaccuracies
46 percent think it’s likely AI will change their jobs in the next five years
42 percent do not believe that AI will create new jobs and opportunities to make up for the jobs that are lost
64 percent agree that the government should take action to prevent the potential loss of jobs due to AI
50 percent believe that increased use of AI will lead to more income inequality and a more polarized society
Morning Consult conducted a poll from February 17-March 19, 2023 with 2,200 U.S. adults to understand awareness and interest in AI. They found that:
“57 percent of consumers said they have heard of AI chatbots in the news, up from 50 percent just a month ago”
“Nearly 2 in 3 (65 percent) consumers said companies that develop AI models bear at least some responsibility for doing so ethically” 28 percent of consumers say that the Federal Trade Commission or other regulators are very responsible for ethical development 24 percent of consumers place say that state governments are very responsible for ethical development 24 percent of consumers say that lawmakers in Congress are very responsible for ethical development 22 percent of consumers say that the U.S. president and his administration are very responsible for ethical development
“More than a third (35 percent) of consumers completely or mostly trust AI search to provide unbiased results, up from 27 percent a month ago, and trust in companies to develop AI responsibly is also up 8 points.”
Advocacy organizations Accountable Tech and LOG OFF conducted a poll with 912 American teenagers to understand social media usage habits. They found that:
“66 percent feel they are losing track of time on social media, with Black and Hispanic teenagers being disproportionately affected
50 percent lose sleep because they feel ‘stuck’ on social media
43 percent of teens don't do as much homework or school work as they wanted because they got stuck on social media
50 percent bought things they didn’t really want due to targeted ads
75 percent received ads for things they just talked about”
In a Morning Consult poll among 2,205 U.S. adults conducted from February 17-19, 2023 on bias and misinformation associated with AI, they found that:
89 percent of respondents believe data privacy is important when selecting a search engine
36 percent of respondents would not trust a search engine that uses AI to use unbiased algorithms
39 percent of respondents would not trust a search engine that uses AI to respect their data privacy
- - -
We welcome feedback on how this roundup and the underlying tracker could be most helpful in your work – please contact Alex Hart and Kennedy Patlan with your thoughts.
| 2023-04-01T00:00:00 |
2023/04/01
|
https://techpolicy.press/march-2023-u-s-tech-policy-roundup
|
[
{
"date": "2023/03/31",
"position": 63,
"query": "government AI workforce policy"
}
] |
2000+ Generative Ai jobs in San Francisco Bay Area (78 ...
|
2,000+ Generative Ai Jobs in San Francisco Bay Area
|
https://www.linkedin.com
|
[] |
2,000+ Generative Ai Jobs in San Francisco Bay Area (78 new) · AI Trainer for Thermodynamics (Freelance, Remote) · AI Trainer for Quantum Mechanics (Freelance, ...
|
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
| 2023-03-31T00:00:00 |
https://www.linkedin.com/jobs/generative-ai-jobs-san-francisco-bay-area
|
[
{
"date": "2023/03/31",
"position": 5,
"query": "generative AI jobs"
},
{
"date": "2023/12/01",
"position": 5,
"query": "generative AI jobs"
},
{
"date": "2024/03/01",
"position": 12,
"query": "generative AI jobs"
},
{
"date": "2025/01/01",
"position": 17,
"query": "generative AI jobs"
},
{
"date": "2025/02/01",
"position": 5,
"query": "generative AI jobs"
}
] |
|
Skills HR Leaders Need to Capitalise on AI
|
Skills HR Leaders Need to Capitalise on AI
|
https://www.myhrfuture.com
|
[
"Jasmine Panayides",
"Adam Mckinnon",
"Martha Curioni"
] |
... machine learning, natural language processing, and predictive analytics. HR data often contains sensitive information about employees, and mishandling it ...
|
''The first is transparency. If you think about when you go and buy a beverage at your favourite coffee shop, you see the nutrition label; you see how many calories it has. What is that about AI? What is the help about AI? You should be able to see it; you should be able to delve into it as a user, not just as a data scientist, but as a user of the AI.
Explainability. Why is the AI giving me this recommendation? When you watch a movie it has some sense of the genre of movies that you like, what other viewers are watching, and why the AI is giving you a certain movie recommendation. The AI in HR should also give you that same sense of the why behind the what. The ultimate decision is yours, of course, but you should be able to understand the why behind the what.
The third pillar is fairness. This is all about bias identification and mitigation. So it is something you want to do upfront as part of the design of the AI.
The fourth, robustness. Having the right guidelines and operational principles.
And the fifth, privacy. This is something we have all been practising for a while, but it becomes even more important in the area of increased regulations in the space. People who have the need to know should know it and not others.''
| 2023-03-31T00:00:00 |
https://www.myhrfuture.com/blog/skills-hr-leaders-need-to-capitalise-on-ai
|
[
{
"date": "2023/03/31",
"position": 92,
"query": "machine learning workforce"
},
{
"date": "2023/03/31",
"position": 63,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/03/31",
"position": 88,
"query": "artificial intelligence hiring"
}
] |
|
Project Overview - BIAS
|
Project Overview
|
https://www.biasproject.eu
|
[] |
Artificial Intelligence (AI) is increasingly deployed in the labour market to recruit, train, and engage employees or monitor for infractions that can lead ...
|
Background
& Mission
Artificial Intelligence (AI) is increasingly deployed in the labour market to recruit, train, and engage employees or monitor for infractions that can lead to disciplinary proceedings. One type of AI is Natural Language Processing (NLP) based tools that can analyse text to make inferences or decisions. However, NLP-based systems face the implicit biases of the models they are based upon that they learn. Such bias can be already encoded in the data used for machine learning training, which contains the stereotypes of our society, and thus be reflected inside the models and the decision-making.
This can lead to partial decisions that run contrary to the goals of the European Pillar of Social Rights in relation to work and employment and the United Nations’ Sustainable Development Goals.
Despite a strong desire in Europe to ensure equality in employment, most studies of European labour markets have concluded that there is discrimination across many factors such as gender, nationality, or sexual orientation. Therefore, addressing how AI used in the labour market either contributes to or can help mitigate this discrimination is of great importance. That is the main concern of the BIAS project.
| 2023-03-31T00:00:00 |
https://www.biasproject.eu/project-overview/
|
[
{
"date": "2023/03/31",
"position": 18,
"query": "AI labor union"
}
] |
|
Types of Unions & Some Popular Union Organizing ...
|
Types of Unions & Some Popular Union Organizing Strategies
|
https://callhub.io
|
[
"Sindhu Prabhu"
] |
AI Smart Insights · Inbound Calling ... Due to their little strength, they often work with labor unions to gain a stronger voice through union strategies.
|
Participation in unions has continuously declined for years. In 1983, unions represented around 1 in 5 workers; now, it’s 1 in 10. To change this trend and improve your membership numbers, you need to adapt some of the best union organizing strategies.
In this article, we discuss some of the most important union organizing strategies. Before we get to that, let’s define union organizing.
What is the union organizing process?
When workers feel they don’t have an individual voice, they feel the need to be a part of a group that can give them one.
The union organizing process involves gathering people from an organization into a group called a union, which acts as a negotiation mediator between the organization and the workers. More often than not, a union requires a voting process to come into existence.
What are the types of unions?
Here are 6 types of unions that are widespread in the US.
1. Labor unions
A labor union is a group of people who work together in a craft or trade. Sometimes, these types of unions also consist of people with the same skills and abilities. Labor unions have been known to end unemployment and help members earn fair wages and benefits.
2. Industrial unions
An industrial union is made up of people who work within the same industry or industry service. Industrial unions actively work on contract negotiations that spread across many employers within an industry.
Industrial unions are one of the strongest unions and are known to reshape the entire industry with better health and working conditions.
3. Public service unions
A public service union is a group of people who work in the public service sector with the same or similar job types. These unions typically operate at a sector, regional, or institutional level. So, any bargaining conditions affect only a certain level and not the entire industry.
4. Federations
A federation is a group of one or more unions. Federations support their members with different services, protections, and benefits.
5. Uplift unions
Uplift unions mainly focus on the social and emotional well-being of their members. They work on improving work conditions, quality of life, morality, etc. These unions welcome workers with all levels of skills, including unskilled laborers.
6. Identity-exclusive unions
An identity-exclusive union is a group of people that share a social, religious, or cultural identity. These types of unions, too, focus on availing fair wages, protection, and benefits to their members. Due to their little strength, they often work with labor unions to gain a stronger voice through union strategies.
You May Also Like: Union Authorization Card 101: All You Must Know Before Asking for Signs
Union organizing strategies
Now, let’s see 7 union organizing strategies organizations have been using for years. They’re pretty straightforward, and you can begin deploying them without spending time on infrastructure.
Card checks
“The card-check procedure almost always results in a union victory because the union controls the entire process.”— Hartford Courant
‘Card check’ is a process by which a union gains recognition after a majority of workers vote in favor of forming a union. It’s a means of getting certification from the National Labor Relations Board (NLRB).
Once a union gains this recognition, an employer is expected to entertain contract negotiations with the union. However, an employer has the right to demand an election and valid proof of the majority’s support.
Read Also: Union Authorization Card 101: All You Must Know Before Asking for Signs
Salting
Salting is one of the famous union organizing strategies that is executed in multiple ways:
Method 1:
The union sends a member (the “salt”) to get a job without revealing their union membership. The ‘salt’, after getting hired, organizes the workforce into joining the union. If the salt is asked to leave the workplace, the union files an unfair labor practice charge with the NLRB.
Method 2:
The union sends the ‘salt’ while making the union membership evident. For example, through the union uniform. If the salt is not hired, the union files an unfair labor practice charge with the NLRB.
Method 3:
One person from the union collects a job application form. The union copies this application form, and all the members apply for the job through these applications. If the applications are rejected, the union files an unfair labor practice charge with the NLRB.
Although this is an unfair tactic, salting is a legal practice that can result in hefty penalties for employers if not dealt with properly.
Striking
When unions go on strike, they walk away from their work, pausing all operations. The strike at Yale University in 2003 is one of the best examples of union organizing strategies.
The strike demanded better pension plans for the non-teaching staff, and thousands of workers went on strike, leaving the students scrambling for food.
Since workers aren’t paid during a strike, unions take care of their financial requirements for that period. However, note that unions consisting of people who affect public interests, such as federal employees and air traffic controllers, are not allowed to strike.
Read Also: Community Organizing: Important strategies to keep in Mind
Collective bargaining
When an employer makes a unilateral decision that affects the workers’ salary and benefits, a union comes into play. The union gathers the members’ demands and sets up a negotiation process. Since employees, individually or in small groups, are in no position to fight such a change, they would want someone with authority to speak on their behalf.
At the same time, an organization’s reputation is a key element in attracting talent. So, employers also are looking to handle things well to protect the organization’s reputation.
So, this is a good time for a union to step in, leverage its authority, and increase its strength to act as its voice to get the benefits the workforce deserves.
Read Also: Your guide on how to increase union memberships in 8 ways
Picketing
You may have seen workers of an organization parading and holding signs in front of their workplace. This is called picketing, and the purpose of picketing is to inform the public about unfair practices within an organization.
In 2001, professors at Hawaii University, with their union’s support, adopted picketing to demand better salaries. The whole movement went on for 13 days. As a result, the university accepted the union’s terms and gave an increase of up to 12% in their salaries.
Boycotting
Boycotting is one of the most famous union organizing strategies that are widely used to date. In boycotting, the union instructs its members to stop using a company’s products and encourages others to do so as well.
In 2003, the Actor’s Equity Association and American Federation of Musicians boycotted AFL-CIO (The American Federation of Labor and Congress of Industrial Organizations), demanding to add a roadshow of the Broadway musical to the list.
Why?
The unions objected to adding non-union performers’ work who worked for low wages and virtual orchestra.
Using technology
Before digital connectivity, unions had to knock on their prospective members’ doors, gather members at union halls, hand out fliers, and put in a lot more physical effort. Now, with technology, unions can connect with their members and prospects through social media, text messaging, phone calls, and a lot more.
Read Also: Use Mass Texting to Improve your Click-through-rate: A Complete Guide for Unions(Use Cases Included)
To support these union organizing strategies, there are even apps and online platforms that let people stay connected and have private access to one another. Unit is one such online platform.
Communication platforms like CallHub help organize a union by helping you reach out to people virtually and get the support you need. Since text messaging takes place on a mobile device, it’s easy to access your contacts anytime.
Also, here are 11 union membership software to help you with increasing membership.
Here are some ways you can use technology to gather support for your union:
Getting signatures on online petitions through text messaging. Publishing social media posts to inform people of the benefits of joining your union. Making persuasive cold phone calls to draw people in. Hosting virtual meetups and promoting them on your website and social media. Creating online communities on platforms like Facebook to gather like-minded supporters. Publishing case studies highlighting your accomplishments as a union on your website or as guest blogs.
The possibilities are endless. Technology offers different ways to put your message out there and gather people.
However, convincing people to join unions has been getting difficult over the years. Employers also have strong tactics in place to prevent their employees from unionizing. Adopting such strong union organizing strategies can help you keep your members motivated and draw in new ones.
You might also like: Union Membership Trends: Who’s to Blame for the Decline
Featured image: Photo by Patrick Perkins on Unsplash
| 2023-03-31T00:00:00 |
2023/03/31
|
https://callhub.io/blog/trade-union/union-organizing-strategies/
|
[
{
"date": "2023/03/31",
"position": 45,
"query": "AI labor union"
}
] |
ILO includes an international convention on platform ...
|
ILO includes an international convention on platform workers on its agenda
|
https://fair.work
|
[
"Posted On"
] |
Fairwork AI · Fairwork Sex Work Project · News · Blog · Podcasts · Press Coverage · Engage · Join the Pledge · Resources & Tools · Unions & Workers' ...
|
110th Session of the International Labour Conference, PC: Crozet / Pouteau / Albouy / ILO
The International Labour Organisation (ILO) Governing Body has announced that it will add to its 2025 Conference an agenda item to discuss standards related to decent work on the platform economy.
This decision is great news for those committed to the assurance of workers’ rights in the platform economy. It means the ILO can move forward in discussing and, hopefully, approving an international convention with guidelines that ensure standards of fair work for the millions of workers who provide services via digital labour platforms.
In addition to the government officials and unions who have been supporting this agenda inside the ILO, more than 300 professors, lecturers, and researchers launched a Global Manifesto for a Fairer Platform Economy last October, in which they advocate for the approval of an international convention ensuring standards of decent work for platform workers.
Read: Global Manifesto
The ILO and platform work
Platform work was a focus of attention at the ILO since last year. In October, a group of experts with representatives from unions, platforms, and academic institutions gathered to discuss the main challenges of platform work and decide on the role that the ILO could take in facing those challenges. Unfortunately, platform representatives and some government officials refused to go on towards a consensus on the need for an international convention.
The decision to reopen this discussion at the 2025 ILO conference comes from the Board’s members’ analysis of the document “A normative gap analysis on decent work in the platform economy”, drawing from the Expert group debate. The document lists gaps in the application of international labour standards and challenges in the platform economy that are not properly addressed in current international labour standards. The text lists gaps in topics such as employment relationships, freedom of association and collective bargaining, forced labour, elimination of child labour, equality and opportunity of treatment, labour inspection, employment policy, employment security, wages, working time, health and safety, social security, migrant workers, specific categories, and protection of workers’ data.
Next steps
With this decision, the Governing Body confirmed that the organisation will move forward with elaborating international guidelines to address these problems. The next step will therefore consist in defining the primary problems faced by platform workers and adequate solutions to solve them.
The Global Manifesto for a Fairer Platform Economy and the Fairwork Principles provide a good start for this by listing challenges and guidelines to be considered for a future international convention. The Manifesto:
Highlights the problems caused by gaps in the misclassification of workers. Most platform workers are currently misclassified by platforms as self-employed and are therefore denied many basic employment rights and protections. Stresses the need to ensure basic standards of payment, with measures to ensure minimum and, preferably, living wages. Many platform workers work on a piece-rate and are not paid for their total hours spent working. Argues for implementing health and safety measures to avoid and mitigate risks arising from work and provide a safety net, as well as reduce unpaid work and overwork. Calls for better data protection policies. In many countries, platforms are able to extract and use data from workers without their consent and without adequate privacy protections. Points out that contracts must be accessible and not contain unfair clauses. Platform workers often do not have access to their contracts, nor the contracts’ terms and conditions, and find it difficult to seek legal redress as the applicable law is that of a foreign country. Supports the relevance of due process and appealing systems to avoid unjust disciplinary actions. In most cases, workers can be ‘deactivated’ without the option to appeal the platform’s decision. States that platforms need to adopt anti-discrimination policies. Both algorithms and customers have been found to discriminate against workers on the basis of religion, ethnicity, gender and sexuality, and workers are generally left unprotected against these forms of discrimination. Emphasizes the crucial right to fair representation and collective bargaining. Many workers often work in isolation and find it difficult to build collective power. Moreover, in many countries, due to their self-employed status, they are often prevented from forming a union or engaging in collective bargaining.
The road to 2025 opens an opportunity to deepen the scrutiny on this topic and present solutions which will be a landmark for the platform economy. An international convention can be a powerful regulatory tool to establish limits to abuses and unfair practices in digital labour platforms. In addition, it can set the example for countries to approve of and implement national legislation to improve the standards of platform work and to legitimise the requests of different actors fighting for better and fairer working conditions.
Sign: Global Manifesto
| 2023-03-31T00:00:00 |
https://fair.work/en/fw/blog/ilo-international-convention-platform-workers-agenda/
|
[
{
"date": "2023/03/31",
"position": 60,
"query": "AI labor union"
}
] |
|
AI Advice for creating artwork - lingo help
|
AI Advice for creating artwork - lingo help
|
https://www.graphicdesignforum.com
|
[] |
Ok, so I have seen amazing AI artwork from people in this community. I use DALL-E and have credits there but if you think there is a better platform to use, ...
|
Ok, so I have seen amazing AI artwork from people in this community. I use DALL-E and have credits there but if you think there is a better platform to use, let me know!
If anyone could help me with the lingo to achieve the best images, I’d greatly appreciate it!
I am creating artwork for a friend that will be placed on a coffee mug (and possibly other items). The artwork involves masking a sentence about grief (it’s a conversation starter and something very personal to her). The concept I am working with is masking letters over abstract imagery of a sad girl. I’ve come up with some images that are great but would need me to tweak in Photoshop for more legibility. But I feel like I can do better with Ai and just don’t have the experience yet of the best way to word what I’m looking for.
For my next image, the keywords I would use are the following: sad girl, shades of blue & green, feels like the ocean, sad eyes, abstract art, “not very busy”, no more than 6 colors?? – see I’m already struggling to figure out how to word all of this. Help!
Here are some images that I am currently working with but they are a little busy and need tweaking in photoshop. Otherwise, the feeling is right - it could just be better. The images should feel they carry grief but also be vibrant, have some complexity to them but also be simple enough to show clearly when masked. The complexity and layers in the concept is symbolic for the complexity and layers in what grief means.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://www.graphicdesignforum.com/t/ai-advice-for-creating-artwork-lingo-help/25983
|
[
{
"date": "2023/03/31",
"position": 9,
"query": "AI graphic design"
}
] |
Generative AI for Enterprises
|
Generative AI for Enterprises
|
https://www.deloitte.com
|
[] |
Deloitte offers a method for selecting Generative AI use cases, as well as some next steps for business leaders in the Age of With™. Generative AI has captured ...
|
Let’s take a moment to cut through the hype
Generative AI is all the rage
The AI field took a turn with the release of powerful Generative Artificial Intelligence (AI) models, and as a result, the world is seeing the automation of some skills around creativity and imagination sooner than many expected. For some organizations, Generative AI holds valuable potential for higher order opportunities, like new services and business models. Deloitte offers a method for selecting Generative AI use cases, as well as some next steps for business leaders in the Age of With™.
Generative AI has captured attention in global media and the public square, prompting questions and discussions around this transformative technology.
Businesses, research organizations, and even lay users are experimenting with Generative AI, and given the excitement and interest, it is important to look more closely at the potential capabilities and implications for business.
In this article, we examine the potential benefits and limitations of Generative AI, introduce a method to qualify if, where and how these cognitive tools could be used, and offer important factors for business leaders to weigh when adopting Generative AI.
| 2023-03-31T00:00:00 |
https://www.deloitte.com/us/en/what-we-do/capabilities/applied-artificial-intelligence/articles/generative-ai-for-enterprises.html
|
[
{
"date": "2023/03/31",
"position": 33,
"query": "artificial intelligence business leaders"
}
] |
|
Data Analytics Archives
|
Business Leaders Review: Best Business Magazine and News Online
|
https://businessleadersreview.com
|
[] |
DBT Labs Acquires SDF Labs to Boost Data Transformation · Tableau's AI assistant tackles efficiency and deep analysis · Global Data Analytics Market Expected to ...
|
Business Leaders Review is a global print and digital monthly and yearly magazine, which provides a platform to showcase business/tech leaders and their company’s profile from various sectors. Our aim is to publish the c-suite leaders stories.
We are helping the leaders & readers to showcase their ideas and innovations to the business and tech world in this current market situation along with their awards and achievements. Doing so we hope to leverage thousands of businesses and personnel around the globe.
| 2023-03-31T00:00:00 |
https://businessleadersreview.com/category/technology/data-analytics/
|
[
{
"date": "2023/03/31",
"position": 70,
"query": "artificial intelligence business leaders"
}
] |
|
About the AI in Education category
|
About the AI in Education category
|
https://forum.code.org
|
[] |
This space is designed for educators of all subject areas to engage in thought-provoking discussions on the impact of artificial intelligence in the classroom.
|
This space is designed for educators of all subject areas to engage in thought-provoking discussions on the impact of artificial intelligence in the classroom, to stay informed about the latest advancements in AI, and to understand how to harness its potential for educational purposes.
Let’s explore best practices, address challenges, and collaborate on innovative solutions to revolutionize teaching and learning experiences.
| 2023-03-31T00:00:00 |
2023/03/31
|
https://forum.code.org/t/about-the-ai-in-education-category/37835
|
[
{
"date": "2023/03/31",
"position": 43,
"query": "artificial intelligence education"
},
{
"date": "2023/03/31",
"position": 65,
"query": "artificial intelligence education"
}
] |
EDUO 9326: Understanding and Applying Artificial ...
|
EDUO 9326: Understanding and Applying Artificial Intelligence in Education
|
https://dominicancaonline.com
|
[] |
Artificial Intelligence is rapidly transforming education. Students at all grade levels will increasingly engage in advancing AI usage. Leverage AI to ...
|
B.S., M.A. in Educational Technology
K-8 General Ed; K-12 Technology 30+ years.
Site and District Tech Coordinator; Technology Program Planner; Conference Presenter; Author.
"My current educational goal is to aid in the development of effective and responsible technology use by all students and innovative technology implementation by teachers."
Joe’s personal interests include: Music (guitar/drums), his classic VW bus and helping with local animal rescues.
| 2023-03-31T00:00:00 |
https://dominicancaonline.com/courses/eduo-9326-understanding-and-applying-artificial-intelligence-in-education/
|
[
{
"date": "2023/03/31",
"position": 52,
"query": "artificial intelligence education"
}
] |
|
23+ Artificial Intelligence And Job Loss Statistics [2023] - Zippia
|
23+ Artificial Intelligence And Job Loss Statistics [2023]: How Job Automation Impacts the Workforce
|
https://www.zippia.com
|
[
"Chris Kolmar",
"Jun.",
"Fact Checked",
"Cite This Webpage"
] |
By 2030, 45 million Americans could lose their jobs to AI automation, representing about one-quarter of the workforce. This is an increase from ...
|
AI job loss research summary. Artificial intelligence and job loss statistics indicate that the worldwide economy could lose hundreds of millions of positions to AI over the coming decades, especially in industries where soft skills aren’t a meaningful part of the job description.
After extensive research, our data analysis team concluded:
It’s not all bad news: artificial intelligence could create 97 million jobs and generate $15.7 trillion for the economy by 2030 while eliminating mundane tasks and helping workers enjoy more creativity.
These transitions could be as challenging as the U.S. shifts out of agriculture and manufacturing.
Newer, better-paying jobs likely won’t replace those lost, so without widespread retraining and reskilling , ordinary people will have significant difficulty finding new work.
While there’s no agreed-upon research methodology or expected economic impacts, AI could take the jobs of as many as one billion people globally and make 375 million jobs obsolete over the next decade.
About half of all companies currently utilize AI in some fashion.
For further analysis, we broke down the data in the following ways:
Types of Jobs Affected | Worker Attitudes
AI affects job loss in many different ways. In general, there are positive and negative affects that can come from job automation. Here are some general facts about how AI is affecting jobs:
Elon Musk predicts that “computers, intelligent machines, and robots seem like the workforce of the future.” “And as more and more jobs are replaced by technology,” he says, “people will have less work to do and ultimately will be sustained by payments from the government.” This means the U.S. would need to strengthen the adequacy and duration of its social safety net, such as Medicaid, Supplemental Nutrition Assistance Program, and so forth.
Currently, half of companies have AI embedded into their business on some level. This is perhaps why 27% of employees have anxiety over the possibility of new innovations, robots, or artificial intelligence making their jobs obsolete in the next five years. Or, why 49% believe people have lost their jobs to AI as organizations look to technology for budget cuts and staff reduction.
Automation and AI will lift productivity and economic growth, but millions of people worldwide may need to switch occupations or upgrade skills. Between 400 million and 800 million individuals could be displaced by automation and need to find new jobs by 2030 around the world. And as many as 375 million may need to switch occupational categories — some of which have not existed before — and learn new skills. If displaced workers are reemployed within one year, it could lift the overall economy. However, if it takes workers years to find work, unemployment could rise, and the economy could dip. Either way, some predict that these transitions will be as challenging as the U.S.’s shifts out of agriculture and manufacturing.
The U.S. is predicted to have a lower proportion of the workforce impacted significantly by technological advances over the coming decades than many European Union countries. In the U.S., about 47% of total employment is at risk of computerization, and workers have a high probability of seeing their jobs automated over the next 20 years. EU numbers are as follows: Austria: 54.10%
Bulgaria: 56.56%
Croatia: 57.91%
Czech Republic: 53.65%
Estonia: 53.94%
Finland: 51.13%
France: 49.54%
Greece: 56.47%
Hungary: 55.34%
Ireland: 48.51%
Italy: 56.18%
Latvia: 51.08%
Lithuania: 51.85%
Poland: 56.29%
Portugal: 58.94%
Romania: 61.93%
Slovakia: 54.70%
Spain: 55.32%
Sweden: 46.69%
United Kingdom: 47.17%
By 2030, 45 million Americans could lose their jobs to AI automation, representing about one-quarter of the workforce. This is an increase from a 2017 estimate that signaled 39 million Americans would be automated out of their work. Worldwide, a billion people could lose their jobs over the next ten years due to AI, and 375 million jobs are at risk of obsolescence from AI automation. With this said, it’s important to emphasize there is no shared agreement on the expected impacts on the workforce or economy. For example, depending on variations in research methodology (e.g., the entire occupation is automated or just a specific task), anywhere between 9% and 47% of jobs will be displaced by artificial intelligence.
Outside of potential job loss, artificial intelligence could deliver several crucial benefits. 19% of workers agree that AI can help alleviate the drudgery of their jobs, and nine out of ten tech executives agree that AI-powered machines will handle mundane tasks, thereby freeing up workers to enjoy more creative work. Furthermore, AI can help eliminate work-related tedium and allow humans to explore careers that deliver a greater sense of meaning and well-being. Economy-wise, as it becomes more widely used, AI is predicted to create 97 million jobs, and by 2030, it’s forecast to positively impact the economy to the tune of $15.7 trillion.
In the past, technological change has eliminated specific jobs, but it has always created more in the process. Companies deploying automation and AI say the technology allows them to create new jobs. However, the number of new jobs is often minuscule compared with the number of jobs lost.
Because of AI’s impact on jobs, more than 120 million workers around the globe will need retraining and up-skilling in the next three years. Businesses must determine the skills their employees need and then provide relevant training. School systems should also support STEM curricula that help students learn diverse skills they’ll need to thrive.
| 2023-06-11T00:00:00 |
2023/06/11
|
https://www.zippia.com/advice/ai-job-loss-statistics/
|
[
{
"date": "2023/06/11",
"position": 54,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 53,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 43,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 54,
"query": "job automation statistics"
},
{
"date": "2023/04/01",
"position": 47,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 54,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 53,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 43,
"query": "AI impact jobs"
},
{
"date": "2023/06/11",
"position": 25,
"query": "AI job creation vs elimination"
},
{
"date": "2023/06/11",
"position": 5,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 41,
"query": "artificial intelligence employment"
},
{
"date": "2023/06/11",
"position": 71,
"query": "artificial intelligence workers"
},
{
"date": "2023/06/11",
"position": 39,
"query": "automation job displacement"
},
{
"date": "2023/06/11",
"position": 62,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 37,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 53,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 61,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 37,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 66,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 53,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 36,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 35,
"query": "AI unemployment rate"
},
{
"date": "2023/06/11",
"position": 53,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 54,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 65,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 58,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 57,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 69,
"query": "job automation statistics"
},
{
"date": "2023/06/11",
"position": 68,
"query": "job automation statistics"
}
] |
Can someone explain how if a country strictly regulated AI ... - Reddit
|
The heart of the internet
|
https://www.reddit.com
|
[] |
But let's say you have two nations, 1.) where they let AI run unfettered replacing 80% of jobs or 2.) they put strict regulation and taxes ...
|
I’ve been thinking about this quite a bit. Speaking strictly hypothetical, the big fear is that there will be a mass of unemployed people. However, as the saying goes “you can’t stop progress.”
But let’s say you have two nations, 1.) where they let AI run unfettered replacing 80% of jobs or 2.) they put strict regulation and taxes disincentivizing use of AI for job replacement.
Can someone logically explain how number two falls behind? If everyone is unemployed this isn’t going to lead to any type of progress for #1. Capitalism is all about what is best, and maybe it’s best to not allow this technology to just replace jobs without their being an adequate replacement. It’s not the normal situation where if a nation doesn’t accept the change it falls behind.
Edit: I should have never posted this, as I forgot that this sub was just "anti-work" crossed with StarTrek.
| 2023-04-01T00:00:00 |
https://www.reddit.com/r/singularity/comments/12hwi4n/can_someone_explain_how_if_a_country_strictly/
|
[
{
"date": "2023/04/10",
"position": 36,
"query": "AI regulation employment"
},
{
"date": "2023/04/01",
"position": 9,
"query": "AI regulation employment"
},
{
"date": "2023/04/10",
"position": 53,
"query": "AI regulation employment"
},
{
"date": "2023/04/10",
"position": 34,
"query": "AI regulation employment"
}
] |
|
AI Employment Law Attorney & Lawyer in Washington, DC ...
|
AI Employment Law Attorney & Lawyer in Washington, DC, Maryland & Virginia
|
https://potomaclegalgroup.com
|
[] |
Artificial Intelligence in employment decisions is the fastest changing and most complex area of employment law.
|
Artificial Intelligence (AI) in Employment Law
Artificial Intelligence in employment decisions is the fastest changing and most complex area of employment law.
AI has already changed the way most employers make employment decisions. As AI in employment decision making develops, regulators and lawmakers are seeking to understand the technology and protect workers. AI developments, however, are increasing at an exponential rate, and lawmakers are struggling to keep up.
Potomac Legal Group is closely following the developments in regulations and enforcement of AI use in the workplace. We represent employees who have faced unlawful actions from employers who rely on traditional human decision making, as well as employers using AI services in employment decisions.
Employers Responsible for Decisions
Fortunately, employees do not have to wait for laws to change or adapt. Regardless of who or what makes an employment decision, the employer is ultimately responsible for its own actions. Current law already addresses unlawful employment actions.
If you have experienced employment discrimination, unlawful termination, or retaliation due to an employment decision made by AI or a human, contact our attorneys to request a review of your matter to determine the options available to you.
Contact Us Today to Discuss Your Matter
What is AI in Employment?
AI in employment refers to the use of artificial intelligence and machine learning in employment-related decision making and in the hiring, promotion, tracking and management of employees.
Employers may use AI to automate certain aspects of the hiring process, such as resume screening and initial candidate interviews. The use of AI in employment, however, must comply with laws and regulations that prohibit discrimination and harassment while protecting personal data privacy, health information and security.
Unlawful Use of AI in Employment
The use of AI in employment decision-making may result in biased outcomes if the algorithm and training data are not properly designed, selected and tested for bias. Employers must also ensure that their use of AI does not result in a disparate impact for protected groups.
There are multiple federal laws that employers must comply with when using AI in the hiring process. For example, Title VII of the Civil Rights Act of 1964, the Americans with Disabilities Act (ADA), and the Age Discrimination in Employment Act (ADEA) prohibit employment discrimination on the basis of race, color, religion, sex, national origin, disability, and age.
Additionally, employers may have compliance requirements with respect to federal laws related to data privacy and security, as well as an emerging patchwork of laws in state and jurisdictions, including Washington, D.C., Maryland and Virginia.
AI Bias in Employment
An employer is not permitted to use AI that discriminates against individuals based on protected characteristics, such as race, gender, religion, age, and disability. Employers are also prohibited from using AI to make employment decisions that have a disparate impact on protected groups. Employers must comply with laws related to data privacy and security when using AI in the workplace.
Employers using AI should take steps mitigate the risk of negative or unintended outcomes, such as by testing the algorithm for bias and ensuring that it is fair and non-discriminatory.
AI Employment Discrimination
Discrimination of employees and applicants by artificial intelligence and other algorithms is unlawful. An AI program need not be openly discriminatory toward individuals in a protected class to be in violation of federal law.
An AI program may be discriminatory when it selects against characteristics or aspects statistically correlated to a certain class. This may include your hairstyle, your clothing, the college you attended, the types of activities you enjoy or your performance on an AI administered test.
Determining AI discrimination in employment matters is complex, and the specific facts of your employment are relevant in determining whether an employer has violated your rights.
AI in Hiring & Resume Screening
AI can be used in the hiring process to assist with tasks such as resume screening, candidate matching, and interview scheduling. By automating these tasks, AI can help reduce bias and increase efficiency in the hiring process if the AI system is properly trained and validated to minimize the risk of bias and discrimination.
If the model is trained on data that has been collected from a biased or discriminatory system, it can perpetuate those biases in its predictions. This can lead to unfair decisions in hiring, promotion, or other employment-related actions.
Recruitment
Employers may not recruit and hire based on the actions of a discriminatory AI. Problems may arise when programmers overuse data coming from certain classes and characteristics. For example, an employer may have to shut down an AI recruiting tool that shows bias against women because the data it judged resumes against came predominantly from men. Job search and employee selection systems that repeatedly reject a candidate may be discriminatory and require further investigation.
AI in Employee Monitoring & Tracking
AI can be used to track employees in various ways, such as monitoring their work hours, location, computer usage, and productivity. Many systems offer keylogging and screen recording features with triggers that alert an employer when an employee is less than normally productive or accesses unapproved websites, social media accounts or personal documents on their work device.
The use of AI in tracking employees, however, raises several legal and ethical concerns.
One of the main legal concerns is the issue of employee privacy. Employers may need to comply with state laws related to data privacy and security when collecting, storing, and using employee data. These laws require employers to obtain employee consent for the collection, use, and storage of personal data. They also require employers to implement appropriate security measures to protect employee data.
The use of AI in employee tracking may also raise concerns about discrimination, especially in regard to physical and mobility concerns. Employers must ensure that their use of AI in tracking employees does not result in a disparate impact on protected groups.
Another concern with AI in tracking employees is that it may create a negative work environment, where employees feel under constant surveillance and pressure to perform at a high level. This can lead to stress, burnout, and a decrease in employee morale and productivity.
Overall, employers must weigh the potential benefits of using AI in tracking employees against the legal and ethical concerns. They should consider seeking legal and ethical advice, and also communicate and consult with employees, before implementing AI tracking systems.
State Law: Employee Monitoring
Currently, Washington, D.C., Maryland nor Virginia have specific laws address that address the use of employee monitoring and tracking software. Maryland and Washington, D.C., are addressing technologies that may be incorporated in monitoring systems.
In Maryland, an employer may not use facial recognition for the purpose of creating a pattern of an applicant’s face without the permission of the employee.
Washington, D.C., does not have specific privacy laws for employees. The city council, however, has proposed the D.C. Stop Discrimination by Algorithms Act of 2023, which likely would govern algorithms used in monitoring systems.
Virginia has no specific privacy laws for employees. Virginia’s corporate data privacy law specifically exempts employees.
Criminal Background Checks
In Maryland and Washington, D.C., employers often are prohibited from requiring applicants to disclose whether they have a criminal record or have had criminal allegations brought against them. These restrictions also extend to AI technologies. Vendors providing AI services may not use this criminal background data in training their algorithms.
Federal Regulation of AI in the Workplace
Federal agencies and Congress are exploring possible regulations for AI in employment.
The U.S. Equal Employment Opportunity Commission (EEOC) is holding hearings to examine the impact of AI and automated systems on employment decisions. The EEOC is concerned about tools including resume screening, video-interviewing software evaluating facial expressions and speech and software that assesses “job fit” based on personality, aptitude, or skills.
The EEOC recognizes that these AI systems can have a negative impact on protected groups and “particularly vulnerable workers,” including immigrants, individuals with disabilities, those with criminal records, LGBTQI+ individuals, older workers, and those with limited literacy or English proficiency.
Proposed Legislation in Washington, D.C., Maryland & Virginia
D.C. Stop Discrimination by Algorithms Act of 2023
Under this proposed act, employers would be required to conduct an annual discrimination audit, which must be conducted by a third party and reported to the city. Employers would also have a poster requirement informing employees about the law, as well as a required pop-up notice on certain systems.
The council included a wide definition of protected data that an algorithm might use. The bill addresses the use of IP addresses, equipment identification or MAC addresses, history of consumer purchases, geolocation data, education records, certain automobile records and more.
While employees already have protections from workplace discrimination, the purpose of this bill is to provide them new protections in relation to the data that algorithmic-based systems would use in making decisions to hire, promote or terminate an employee.
Maryland Proposes Committee on AI in Employment Decisions
A proposed bill in the Maryland House of Delegates would form a committee charged with studying and making recommendations toward the proper use of AI technology in a number of different sectors. The committee would especially be concerned with the use of AI in employment decisions and recommend regulations to the Maryland legislature that would assist in preventing systemic AI bias and keeping AI usage equitable, accountable, sustainable and responsible with respect to public resources.
Potomac Legal Group is currently monitoring for any activity in the Virginia related to the regulation of AI in employment.
Contact Us
Contact Potomac Legal Group to discuss any matter related to your employment, including any employment decision you believe was made by AI or is discriminatory.
Contact Us Today to Discuss Your Matter
| 2023-03-31T00:00:00 |
2023/03/31
|
https://potomaclegalgroup.com/ai-employment-law-attorney-lawyer-in-washington-dc-maryland-virginia/
|
[
{
"date": "2023/04/01",
"position": 37,
"query": "artificial intelligence employment"
},
{
"date": "2023/04/01",
"position": 7,
"query": "AI regulation employment"
},
{
"date": "2023/04/01",
"position": 88,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 61,
"query": "artificial intelligence hiring"
},
{
"date": "2023/04/01",
"position": 10,
"query": "AI regulation employment"
},
{
"date": "2023/04/01",
"position": 20,
"query": "artificial intelligence employers"
},
{
"date": "2023/04/01",
"position": 86,
"query": "artificial intelligence hiring"
}
] |
🐙 After AI, where will the jobs come from?
|
🐙 After AI, where will the jobs come from?
|
https://www.exponentialview.co
|
[
"Azeem Azhar"
] |
The researchers propose that jobs with 50% or more of their tasks automated are at risk, while those with 10-49% automation will see AI complement human ...
|
In my commentary this week, I look at the insightful research note from Goldman Sachs, titled “The Potentially Large Effect of Artificial Intelligence on Economic Growth”, in which the authors explore the labour market's future.
The study posits that global productivity could see an impressive uptick, ultimately boosting global GDP by 7%. In the U.S., economic growth could leap from the anaemic range of 1% to 1.5% to a more robust 2.5% to 3%, reminiscent of the booming 1950s and 60s.
The research highlights that AI automation affects two-thirds of U.S. occupations to varying degrees. A significant portion of these jobs could see substantial replacement due to automation. The researchers propose that jobs with 50% or more of their tasks automated are at risk, while those with 10-49% automation will see AI complement human efforts.
Historical evidence suggests that companies adopting new technologies tend to expand their workforce while others lag behind. Firms investing in AI are poised for better performance, but the landscape will inevitably include both winners and losers. Moreover, widespread downward wage pressure is anticipated as workers become more efficient and the demand for human labour diminishes.
The temptation
I wondered about how organisations might respond to this.
Here is one hunch, when thinking about medium and larger firms. Middle-tier employees—well-compensated but not part of top leadership—may find themselves in the crosshairs of cost-cutting measures. Enough of this tier would be retained to guard the tacit knowledge, the accumulated social learning, of how the firm actually works. AI-enabled junior workers could collaborate with this leaner group of seasoned senior professionals to bridge the gap.
I suspect this might be quite a tempting path for top management.
Where’s the new?
The projected 7% productivity growth would fuel a faster-growing economy. This economy will have new demands. We’ve seen this picture before. Over the past 80 years, a striking 85% of U.S. employment emerged in jobs that didn't exist in 1940. Innovation works!
It’s always worth bearing Schloss’ Lump of Labour Fallacy in mind. According to GPT4’s output, the fallacy is
the mistaken belief that there is a fixed amount of work available in an economy, and that creating more jobs for one group of people will necessarily take away jobs from others. This fallacy ignores the fact that economies can grow, creating more jobs, and that increased productivity can lead to higher demand for goods and services, generating even more employment opportunities.
However, the swift deployment of AI technologies could lead to job losses outpacing the creation of new roles.
Addressing the challenges of reskilling workers and ensuring the emergence of new jobs in suitable locations requires nuanced and effective policy interventions. Both private and public sector solutions must be devised and implemented at scale in the coming years.
I would love to hear your thoughts: what kind of private or public sector interventions could speed up the creation of new types of work? Where are there good examples which are already having the right effect? Share your ideas in the comments below.
| 2023-04-01T00:00:00 |
https://www.exponentialview.co/p/after-ai-where-will-the-jobs-come-from
|
[
{
"date": "2023/04/01",
"position": 53,
"query": "artificial intelligence employment"
},
{
"date": "2023/04/01",
"position": 76,
"query": "artificial intelligence workers"
},
{
"date": "2023/04/01",
"position": 81,
"query": "AI impact jobs"
}
] |
|
Who does it best—humans or computers?
|
Who does it best—humans or computers?
|
https://saifr.ai
|
[
"Vall Herard"
] |
We keep hearing about the coming of artificial intelligence (AI). Will computers start with vacuuming our houses, then driving our cars, and ultimately taking ...
|
We keep hearing about the coming of artificial intelligence (AI). Will computers start with vacuuming our houses, then driving our cars, and ultimately taking all our jobs? The answers are yes, probably, and no. The majority of AI applications won’t be all-encompassing like self-driving cars. Instead, computers using AI will likely augment aspects of what we currently do to help make a lot of our jobs easier.
Humans and computers have different capabilities. Each boast advantages and limitations when it comes to solving problems, yet they can be complementary. Let’s explore a few ideas.
Computer strengths
Computers using AI can be invaluable tools in problem solving since they can quickly and accurately process large amounts of data from a variety of sources. Because of their data acuity and AI algorithms, they can help to:
identify patterns and trends that may not be apparent to the human eye
identify solutions that might not have been considered otherwise
bring a personal experience to scale, such as for shopping and customer service
provide humans the data to back gut-based decisions
Computers are also excellent at small, structured, repetitive tasks that require a high degree of precision and accuracy, such as calculations, data analysis, and some specific mechanical operations. They can help eliminate human error and make one part of the process more efficient and accurate. However, computers are not so great at entire jobs or processes because they are often limited by their training set and may not be flexible enough to do all the various tasks in a process.
Human strengths
Yes, humans can also do the things mentioned above, but not always as quickly nor as accurately. And, the structured, repetitive, mundane tasks are not our strength, and can be quite boring. Our strengths are often things that computers just can’t do.
One of the biggest advantages humans have over computers is our ability to handle uncertainty and edge conditions. We can think abstractly, come up with creative solutions to novel and intricate problems, and adapt to changing conditions quickly. This allows us to make decisions in complex and dynamic environments, where computers struggle.
Humans uniquely possess “softer,” intuitive skills. We excel at tasks that require empathy, such as communicating with others, reading body language, and understanding social cues. Humans can also easily understand context. For example, if you are in a clothing store and tell the fashion advisor that you need a great dress for a summer wedding that your ex will be attending, they can understand all that your scenario implies and provide options that can likely do the trick. And only humans can develop relationships with one another.
Additionally, humans are great at complex, multi-staged tasks that require flexible motor skills, such as driving, playing sports, and operating complex machinery. This is especially true when the task encompasses many different movements and requires adaptability or some on-the-fly judgement.
Better together
Humans and computers are different. Humans are incredibly adept at dealing with ambiguity and uncertainty, while computers excel at “understanding” vast amounts of data. The successful organizations will find ways to combine the best of both worlds. They will build systems that combine computers and humans in ways that help us to better understand the world, make more accurate decisions faster, and tackle complex problems in ways that haven’t been possible until now.
1079911.1.0
| 2023-04-01T00:00:00 |
https://saifr.ai/blog/who-does-it-best-humans-or-computers
|
[
{
"date": "2023/04/01",
"position": 58,
"query": "AI job creation vs elimination"
}
] |
|
AI Rewrites Coding - Communications of the ACM
|
AI Rewrites Coding – Communications of the ACM
|
https://cacm.acm.org
|
[
"Samuel Greengard",
"R. Colin Johnson",
"About The Authors",
"Anusha Musunuri"
] |
Although it is unlikely AI will eliminate jobs for developers anytime soon, it is poised to revolutionize the way software is created. For instance, OpenAI ...
|
Computer code intersects with almost every aspect of modern life. It runs factories, controls transportation networks, and defines the way we interact with personal devices. It is estimated that somewhere in the neighborhood of 2.8 trillion lines of code have been written over the last two decades alone.a
Yet it is easy to overlook a basic fact: people have to write software—and that is often a long, tedious, and error-prone process. Although low-code and no-code environments have simplified things—and even allowed non-data scientists to build software through drag-and-drop interfaces—they still require considerable time and effort.
Enter artificial intelligence (AI). Over the last several years, various systems and frameworks have appeared that can automate code generation. For example, Amazon has developed CodeWhisperer, a coding assistant tool that automates coding in Python, Java, and JavaScript. GitHub’s Copilot autogenerates code through natural language, and IBM’s Project Wisdom is focused on building a framework that allows computers to program computers.
“As software becomes more complex and moves into the realm of non-developers and non-data scientists, there’s a need for systems that can simplify and automate coding tasks,” says Ruben Martins, an assistant research professor at Carnegie Mellon University. Adds Abraham Parangi, co-founder and CEO of Akkio, a firm that offers AI-assisted coding tools, “People have been working on these tools for many years. Suddenly, the trajectory is going vertical.”
Although it is unlikely AI will eliminate jobs for developers anytime soon, it is poised to revolutionize the way software is created. For instance, OpenAI has introduced DALL-E 2, a tool that generates photorealistic images and art through natural language. In addition, the OpenAI Codex builds software in more than a dozen programming languages, including Python, Perl, Ruby, and PHP.
Observes Ruchir Puri, chief scientist for IBM Research, “The ability for computers to write code—and even program other computers—has the potential to fundamentally reshape the way we work and live.”
Back to Top
Abstracting the Code
The idea of automating coding tasks is not new or particularly revolutionary. From punch cards to today’s vast open source code libraries, the need to construct software from scratch has steadily declined. In recent years, low-code and no-code environments—which typically allow a person to drag-and-drop elements that represent pre-established tasks or functions—have greatly simplified software development, while expanding who can produce software.
Yet the emerging crop of AI tools turbocharge the concept. In some cases, these platforms anticipate tasks and suggest blocks of code—similar to the way applications now autopredict words and phrases in email and other documents. In other cases, they actually generate images, functions, and entire websites based on natural language input, or they suggest coding actions based on what the AI believes should happen next.
For example, Akkio’s platform allows humans to build machine learning and other AI models for things like forecasting, text classification, and lead scoring, without ever interacting with code. It is a simple drag-and-drop proposition en route to a tool or app. “This makes it possible for people who have no knowledge of coding to accomplish all sorts of reasonably complicated tasks—and produce code without the formidable barriers of the past,” Parangi explains.
Amazon’s CodeWhisperer also is designed to serve as a machine learning-powered coding companion for software developers. It analyzes existing code structure, as well as standard written comments residing in an integrated development environment (IDE), and generates up to 15 lines of code at one time. These include entire functions and logical blocks.
GitHub’s Copilot automates code generation through IDE platforms such as Visual Studio Code, Visual Studio, Neovim, and JetBrains. It makes suggestions across dozens of programming languages.
Then there is IBM’s Project Wisdom, which aims to leap beyond 10 or 15 lines of autogenerated code and build an AI framework that can produce entire components, services, and applications within hours, rather than days or weeks. It automatically generates YAML code on the Red Hat Ansible platform through a natural-language interface. The goal, Puri says, is to “move beyond structured rules and mechanical processes and develop an AI framework that’s capable of understanding machine language.”
Back to Top
Maintaining an Image
The splashiest examples of AI-generated code come from OpenAI, however. Type a few words into the DALL-E application—anything from “photorealistic chateau next to a river in France” to “woman sitting at a beach Picasso style painting”—and the application spits out images that look as though they were produced by a talented human artist or photographer. The platform deftly combines concepts, attributes, and styles to create the images.
The OpenAI Codex also is pushing the boundaries of conventional software development. It can build simple apps from natural language commands. For example, a software designer might instruct the system in plain English to write an app that can process a product return and issue a label. After providing basic parameters and a description of the graphics, menus, and buttons needed, the OpenAI Codex can generate the code. Although the system is not perfect, a human can typically review the results and apply minor fixes where needed.
The goal, Puri says, is to “develop an AI framework that’s capable of understanding machine language.”
Meanwhile, various other companies, including the likes of Microsoft, Diffblue, and DeepMind (acquired by Google in 2014), continue to explore and develop AI coding as part of their platforms or as discrete AI engines. In Microsoft’s case, it has its own tool called Power Platform, but it also has helped fund GitHub’s Copilot, along with the private initiative OpenAI. “The enormous amount of data that we can feed into neural nets has changed the playing field. We’re seeing platforms that can generate code from scratch—through natural language models,” Martins explains.
The resulting unsupervised deep learning frameworks fuel this revolution. For example, Amazon trained CodeWhisperer on a large language model (LLM) of both open source and Amazon-supplied data. The OpenAI Codex is derived from more than 700 gigabytes of data collected from the Web and other sources. IBM initially plugged in about a third of a gigabyte of Ansible information technology-centric data, as well as its own GitHub and Yammer data; the total size of the data sources is approximately 10 gigabytes.
Still, AI coding is not without its challenges and controversies. While no one is particularly concerned that developers, website designers, and others will join the unemployment line anytime soon—these platforms serve as assistive tools for now—it is not outside the realm of possibility that within a decade or two, they will begin to replace humans at many tasks. Machines are gaining an increasingly impressive grasp of natural language, and the semantics and logical sequences that produce software.
Back to Top
AI Coding Is Not Picture Perfect
A bigger concern revolves around the quality of the code these systems generate—and an inability to peer into many of these AI models and fully understand how they are built. It is one thing to use predictive tools to suggest code to developers; it is entirely another thing to fully hand off the task to a computer. In many situations, such as software that controls an airplane, medical device, or an autonomous vehicle, coding errors could prove dangerous or even deadly. In banking or healthcare systems, automated coding errors could result in major disruptions.
Yet, because AI does not truly grasp the meaning of things—it can generate natural language text and even computer code that appears to make sense, but contains logic, syntax, and other errors—the lack of close human review ratchets up the risks. As Stuart M. Shieber, James O. Welch, Jr. and Virginia B. Welch Professor of Computer Science at Harvard University, puts it, “There is no consciousness or sentience. It’s simply a machine making highly probable predictions.” Indeed, AI can lead to mistakes in binding, operational variables, and consistency. What’s more, there’s no certainty that a program will produce the same code over time—even with the same input or request. As a result, for the foreseeable future, many of these systems are not completely trustworthy, if not risky, to deploy in critical situations.
In fact, enthusiasm about the technology notwithstanding, “AI coding still has a lot of limitations and a long ways to go,” Martins says. “It still makes many mistakes—including critical errors.” One of the trickiest errors is spotting syntactic anomalies that are not easily detected by humans. Just as a person or AI system might ignore the use of “threw” for “through” or “witch” for “which,” the computer can incorporate errors into code, with sometimes serious consequences.
As a result, Martins has focused his research on developing a framework that can spot and fix problems through a technique called program synthesis. It relies on advanced validation tools that incorporate structural elements and semantic patterns.b “The validation process occurs using formal methods and mathematics,” Martins explains. Although the method works well on both human and AI-generated code—and it shows a great deal of promise for building a repair framework—it is currently limited to reviewing fewer than 100 lines of code at a time.
“There’s no consciousness or sentience. It’s simply a machine making highly probably predictions.”
Another issue is the blurry legal and ethical line that AI coding systems introduce. Because these deep learning systems often are built from numerous sources of data containing both publicly available and copyrighted content, problems can ensue. For instance, the DALL-E system’s ability to generate artificial images in the style of the creator has attracted the wrath of contemporary artists who say their works and portfolios—which can take years to create—are diminished in an instant as a result of copycat images.c
Back to Top
Blurred Lines
Things become even more complicated when copyrighted material—including publicly available source code scraped from the Internet—is fed into a deep learning model that builds actual software applications. For instance, in October 2022, software developer and designer Matthew Butterick accused GitHub of improperly training Copilot with his intellectual property and other people’s copyrighted works. He subsequently threatened to file a lawsuit.d The accusation also ensnarled Microsoft, which partly funded the project and promotes the tool.e
To be sure, many questions remain unanswered, including whether it is possible to reach a point where programming languages simply are not necessary. In the meantime, it is clear automated AI coding will play an increasingly prominent role in the way developers, data scientists, and ordinary people create software and other content. “AI coding is destined to become even more powerful—and influential,” says Akkio’s Parangi. “We’re already building very powerful and capable AI code-generation models that are making a clear impact.”
Further Reading
Sarkar, A., Gordon, A.D., Negreanu, C., Poelitz, C., Ragavan, S.S., and Zorn, B.
What is it like to program with artificial intelligence? Proceedings of the 33rd Annual Conference of the Psychology of Programming Interest Group (PPIG 2022), August 12, 2022. https://arxiv.org/abs/2208.06213
Chen, M. et al.
Evaluating Large Language Models Trained on Code, July 7, 2021. Cornell University. https://arxiv.org/abs/2107.03374
Li, Yi et al.
Competition-Level Code Generation with AlphaCode. March 16, 2022. DeepMind. https://arxiv.org/pdf/2203.07814.pdf
Feng, Y., Martins, R., Bastani, O., and Dillig, I.
Program synthesis using conflict-driven learning, ACM SIGPLAN Notices, Vol. 53, Issue 4, April 2018, pp 420–435. https://dl.acm.org/doi/abs/10.1145/3296979.3192382
Vasconcelos, H., Gansal, G., Fourney, A., Liao, Q.V., and Vaughan, J.W.
Generation Probabilities are Not Enough: Improving Error Highlighting for AI Code Suggestions, 2022. https://helenavasc.com/static/HCAI_NeurIPS_2022.pdf
| 2023-04-01T00:00:00 |
https://cacm.acm.org/news/ai-rewrites-coding/
|
[
{
"date": "2023/04/01",
"position": 89,
"query": "AI job creation vs elimination"
}
] |
|
Workforce Skills Gap Analysis
|
Workforce Skills Gap Analysis:
|
https://www.talentguard.com
|
[] |
The same applies to technology—a domain where skills gaps are especially common. Without a clear understanding of your workforce's capabilities, you may be ...
|
A skills gap analysis is the process of identifying the skills your organization needs and comparing them to the skills your employees currently possess. This method is essential for understanding workforce strengths and uncovering areas for improvement. Addressing skill gaps not only enhances operational efficiency but also ensures your business remains competitive in an ever-evolving market. In this post, we’ll define skill gap analysis, explore its benefits, and outline actionable methods to help you close those gaps effectively.
What Is a Skills Gap?
A skills gap occurs when an organization requires certain skills that its employees lack. For example, imagine your business experiences a surge in growth, and you want to launch a marketing campaign. However, none of your current employees possess marketing expertise. This gap forces you to seek external assistance, often at a higher cost than training or reskilling existing employees. Learn more about skills management.
The same applies to technology—a domain where skills gaps are especially common. Without a clear understanding of your workforce’s capabilities, you may be unaware of existing gaps, leaving your business vulnerable to inefficiencies or missed opportunities.
Why Conduct a Skills Analysis?
A analysis offers several benefits to align skills:
Improved Workforce Planning: Helps you understand the skills your team needs now and in the future.
Helps you understand the skills your team needs now and in the future. Cost Efficiency: Reskilling employees can be more affordable than hiring new talent.
Reskilling employees can be more affordable than hiring new talent. Enhanced Productivity: Employees equipped with the right skills perform tasks more effectively.
Employees equipped with the right skills perform tasks more effectively. Future-Proofing: Prepares your organization for technological advancements and market shifts.
Methods for Conducting a Gap Analysis
Performing a skills gap analysis doesn’t have to be overwhelming. Here’s a step-by-step guide to get started:
Identify Current and Future Skills Needs
Begin by listing the skills required to achieve your business goals. Consider both present needs and anticipated future demands driven by technology or market trends. Assess Employee Skills
Use tools such as surveys, self-assessments, or performance evaluations to gather data on your workforce’s existing skills. Compare and Identify Gaps
Match the skills your employees possess with the skills needed for current and future roles. Highlight areas where deficiencies exist. Create an Action Plan
Develop a strategy to bridge the gaps through upskilling, reskilling, hiring, or leveraging external expertise. Ensure the plan aligns with your overall business objectives.
A Simplified Approach
Skill gap analysis doesn’t need to be overly complex. By taking the above steps, every organization can gain insights into their workforce and address areas for improvement. Here’s a quick example: If your company plans to adopt a new software system, assess whether your employees have the technical skills to use it effectively. If not, schedule training sessions to ensure a smooth transition.
The Bottom Line
A skills gap analysis is a critical tool for maintaining a competitive edge. By identifying and addressing skills gaps, organizations can operate more efficiently, enhance employee productivity, and prepare for the future. The process may require effort, but the payoff is invaluable.
Don’t let skills gaps hold your business back—start your skills gap analysis today and position your organization for long-term success. Use a skills inventory tool to simplify the process of a gap analysis.
To learn more about skills, check out the Brandon Hall Group
| 2023-04-01T00:00:00 |
https://www.talentguard.com/skills-gap-analysis-definition-benefits-methods
|
[
{
"date": "2023/04/01",
"position": 45,
"query": "AI skills gap"
}
] |
|
AI Recruitment Tools: How AI is Changing the Hiring Process
|
How AI is Changing the Hiring Process
|
https://www.recruitbpm.com
|
[] |
... job and industry. Predictive Analytics. Predictive analytics tools analyze data from past recruitment processes to identify patterns and trends. The tools use ...
|
In recent years, the use of Artificial Intelligence (AI) in the recruitment process has become more common. Recruiters and HR professionals use AI recruitment tools to streamline and make the hiring process more efficient. This article will discuss the benefits of using AI recruitment tools and how they are changing the recruitment process.
AI recruitment tools are becoming increasingly popular in today’s fast-paced job market. These software applications use artificial intelligence algorithms to automate various aspects of the recruitment process, such as sourcing candidates, screening resumes, and conducting initial interviews.
One of the key benefits of AI recruitment tools is their ability to manage large volumes of job applications. Machine learning algorithms in AI recruitment tools quickly sort through resumes and identify the best matches for the job. This saves recruiters and HR professionals time, allowing them to focus on more strategic tasks.
AI recruitment tools also have the ability to identify suitable candidates based on a variety of criteria. For example, some tools can analyze resumes and social media profiles to determine a candidate’s skills, experience, and even personality traits. This can help recruiters to more accurately assess a candidate’s fit for a particular role, increasing the likelihood of a successful hire.
In addition to resume screening, AI recruitment tools can also conduct initial screening interviews. Automated interviews can be conducted using NLP tools through chatbots or voice assistants. These tools ask predetermined questions and evaluate candidate responses. This helps reduce workload for recruiters and provides valuable insights into a candidate’s qualifications and potential fit for the role.
Another important benefit of AI recruitment tools is their ability to reduce bias in the hiring process. By removing human biases and relying on objective criteria, these tools can help to ensure that all candidates are evaluated fairly and on the basis of their qualifications alone. This can help to promote diversity and inclusion within the workplace, which has been shown to improve organizational performance.
Overall, AI recruitment tools are a valuable addition to the modern recruiting landscape. By automating various aspects of the recruitment process and providing valuable insights into candidate qualifications, these tools can help recruiters and HR professionals to make more informed hiring decisions and build stronger, more diverse teams.
There are several benefits to using AI recruitment tools. These include:
Increased Efficiency
Recruiting new employees is a time-consuming and resource-intensive process. AI recruitment tools can automate many repetitive recruitment tasks. These include screening CVs, scheduling interviews, and conducting initial candidate outreach. Automating these tasks saves recruiters and HR professionals time. They can then focus on more strategic aspects of recruitment.
AI-powered recruitment tools can simplify the recruitment process. They make it easier to gather and analyze candidate data. Applicant tracking systems (ATS) can store candidate information and track their progress. This ensures that important candidate information is not missed, making the recruitment process more efficient overall.
The candidate experience is an important factor in the recruitment process, as it can impact a candidate’s perception of a company and their decision to accept a job offer. AI recruitment tools can help to provide a more positive candidate experience by making it easier for candidates to interact with recruiters and HR professionals.
For example, AI-powered chatbots can be used to answer candidate questions and provide feedback on the recruitment process, even outside of business hours. This can help to provide candidates with a more personalized and responsive recruitment experience. In addition, AI recruitment tools can help to reduce bias in the recruitment process, as they can analyze job applications objectively and without bias.
Improved Hiring Quality
The ultimate goal of the recruitment process is to identify and hire the most suitable candidate for a role. AI recruitment tools can help to achieve this goal by analyzing job applications and identifying the most relevant candidates based on their qualifications, experience, and other factors.
For example, AI-powered screening tools can analyze CVs and identify the most suitable candidates based on specific keywords and criteria. This can help to reduce the time and resources required to identify and screen potential candidates. In addition, AI recruitment tools can help to reduce bias in the recruitment process by analyzing job applications objectively and without bias.
Overall, AI recruitment tools can help to streamline the recruitment process, improve the candidate experience, and identify the most suitable candidates for a role. By leveraging the power of AI, recruiters and HR professionals can improve the efficiency and effectiveness of their recruitment process, ultimately leading to better hiring outcomes for their organization.
There are several types of AI recruitment tools available. These include:
AI-powered CV screening tools analyze resumes to identify the most qualified candidates based on qualifications and experience. These tools quickly sift through large volumes of resumes and filter out unqualified candidates. They can also identify candidates with certain skills or experiences that are particularly relevant to the position.
Some CV screening tools use natural language processing (NLP) to understand the context and meaning of the text in resumes. This allows them to identify skills and experiences that may be relevant even if they are not explicitly stated in the job description or resume. Additionally, some CV screening tools can integrate with job boards and social media platforms to automatically search for and screen candidates who have applied or shown interest in similar positions.
When using CV screening tools, it’s crucial to ensure that they are designed to avoid bias. AI algorithms may be unintentionally biased against specific demographics or experiences, which could unfairly screen out qualified candidates. It’s important to evaluate and test any CV screening tool carefully to ensure that it is designed to avoid bias and make fair and accurate hiring decisions.
Chatbots
AI-powered chatbots can enhance the candidate experience. They can interact with candidates and provide personalized responses. Chatbots can answer common questions about the job, company, or application process. They can also provide real-time feedback on application status. Chatbots collect and analyze candidate behavior data, providing recruiters with valuable insights into the candidate experience.
Recruiters can integrate chatbots with other AI recruitment tools like CV screening or interviewing tools. They can use a chatbot to pre-screen candidates before inviting them to an interview or to collect feedback from candidates after an interview. This can help streamline the recruitment process and provide a more efficient and effective experience for both candidates and recruiters.
AI recruitment tools use NLP to conduct initial screening interviews and identify suitable candidates. These tools can ask job-specific questions and evaluate responses based on tone, sentiment, and communication skills.
Some interviewing tools also use facial recognition technology to analyze candidates’ expressions and body language during the interview. This can provide additional insights into a candidate’s communication and interpersonal skills, as well as their level of comfort and confidence.
Interviewing tools may not fully replicate human interaction and intuition, which can be crucial in hiring. It’s important to test and evaluate any interviewing tool carefully to ensure its effectiveness and appropriateness for the job and industry.
Predictive Analytics
Predictive analytics tools analyze data from past recruitment processes to identify patterns and trends. The tools use AI to analyze candidate demographics, qualifications, experience, and performance, as well as hiring outcomes and retention rates. Recruiters can use this information to make more informed hiring decisions and improve overall hiring outcomes. The tools help identify factors that are most predictive of successful hires, which can inform future recruitment strategies.
Predictive analytics can detect bias in hiring. Recruiters can use this data to fix the problem. If a certain group is not being represented, recruiters can take action. This will ensure that all qualified candidates have a fair chance.
Predictive analytics can help in hiring, but it’s crucial to use them as just one of many factors. Relying too much on predictive analytics might cause us to miss out on candidates who don’t fit the typical patterns but could still excel in the role.
It’s essential to ensure that the data used to train predictive analytics algorithms is diverse and representative of the overall population. If the data is biased or incomplete, the algorithms may make biased or inaccurate predictions.
While there are many benefits to using AI recruitment tools, there are also some challenges to consider. These include:
Bias
One of the major challenges of AI recruitment tools is the potential for bias. AI algorithms can only learn from the data they are trained on, and if that data is biased, the algorithm will also be biased. This can lead to discrimination against certain candidates, particularly those from underrepresented groups.
For instance, if the dataset predominantly consists of male candidates, training an AI screening tool on it may create bias against female candidates. Similarly, training an AI interviewing tool on a dataset that is predominantly white may create bias against candidates of color. This could unfairly screen out qualified candidates and further perpetuate systemic bias in the hiring process.
To reduce bias in AI recruitment tools, evaluate the training data for diversity and representation. Regularly test and audit algorithms to identify and address any biases.
Cost
Another challenge of AI recruitment tools is the cost of implementation. Developing and implementing AI tools can be expensive, particularly for small businesses that may not have the resources to invest in this technology. Additionally, ongoing maintenance and updates to the AI algorithms can also be costly.
To address the challenge, partner with third-party providers that specialize in AI recruitment tools instead of building and maintaining your own. Evaluate the cost-benefit of implementing AI tools and ensure a sufficient return on investment.
Security
AI recruitment tools may require access to sensitive data, such as candidates’ resumes, contact information, and personal identifiers. This can pose a security risk if not managed properly. If those in charge of the AI algorithms do not secure them properly, they may become vulnerable to hacking or data breaches. These could compromise the personal information of candidates.
To address this challenge, it is important to implement robust security measures, such as encrypting data, restricting access to authorized personnel, and regularly monitoring for potential security threats. Additionally, businesses should ensure that they are in compliance with applicable data privacy laws and regulations.
Recruiters and HR professionals should follow several best practices to ensure the effective use of AI recruitment tools. These include:
Regularly reviewing and updating AI algorithms to ensure that they are free from bias:
One of the major concerns with the use of AI in recruitment is the potential for bias in the algorithms. This bias can lead to discrimination against certain groups of candidates. To avoid this, it is important to regularly review and update AI algorithms to ensure that they are free from bias. Recruiters can analyze the data used to train the algorithms and identify any patterns that may contribute to bias. Once identified, these patterns can be corrected to ensure that the algorithms are fair and impartial.
Being transparent with candidates about the use of AI recruitment tools in the hiring process:
Transparency is key when it comes to the use of AI recruitment tools. Employers should let candidates know that AI tools will be used in the hiring process and clarify the ways in which their data will be utilized. Employers can provide clear and concise information about the tools and offer candidates the chance to opt-out of using AI tools.
Conducting regular security audits to ensure that sensitive data is kept secure:
The use of AI recruitment tools requires the collection and processing of sensitive data, such as personal information and employment history. It is important to ensure that this data is kept secure and confidential. Regular security audits can be conducted to identify any vulnerabilities in the system and to ensure that appropriate security measures are in place to protect against data breaches and cyber attacks.
Ensuring that AI recruitment tools comply with privacy and data protection laws:
The use of AI recruitment tools is subject to various privacy and data protection laws, such as the General Data Protection Regulation (GDPR) in the European Union. To avoid legal consequences, you should review the privacy policies of the tools you are using and make sure they comply with applicable laws.
Training recruiters and HR professionals on the proper use of AI recruitment tools:
Provide training to recruiters and HR professionals on the proper use of AI recruitment tools. This includes interpreting results and combining them with traditional recruitment methods. It can also include training on ethical considerations, such as avoiding bias and protecting candidate privacy.
Conclusion
Staying current with emerging best practices is crucial for effective and ethical use of AI recruitment tools. Improvements in AI technology will likely increase their use in recruitment. However, we must consider potential challenges like bias and privacy. Regular algorithm reviews and security audits can help mitigate concerns and ensure compliance with laws and ethics.
In conclusion, AI recruitment tools improve the hiring process by making it more efficient and effective. To ensure ethical use, companies should review algorithms, be transparent with candidates, conduct security audits, comply with privacy laws, and provide proper training. Therefore, Staying up-to-date with best practices will maximize the benefits of AI technology in recruitment.
FAQs
A1. AI recruitment tools are software that automates hiring tasks such as screening, sourcing, and analyzing resumes. They use machine learning to identify qualified candidates and save time while reducing bias.
Q2. What are some benefits of using AI in recruitment?
A2. Some benefits of using AI in recruitment include:
Improved efficiency: AI recruitment tools can process large volumes of data and screen candidates more quickly than humans, saving time and resources.
Increased accuracy: AI can analyze candidate data objectively and accurately, reducing the risk of bias and error.
Better candidate experience: AI can provide a more personalized and efficient hiring experience for candidates, from initial screening to scheduling interviews and providing feedback.
Cost savings: AI can reduce the need for manual labor and streamline the hiring process, potentially saving companies money on recruiting and onboarding.
A3. While AI recruitment tools can automate many aspects of the hiring process, they cannot completely replace human recruiters. Human recruiters should work alongside AI to improve efficiency and accuracy in candidate evaluation. AI can assist in the initial screening and assessment of candidates. However, human recruiters are still required to make final hiring decisions and assess soft skills.
A4. To ensure fair hiring practices, designers of AI recruitment tools must create them to reduce bias and promote diversity. They should analyze data based on qualifications and skills objectively rather than demographics.
A5. Some popular AI recruitment tools include:
| 2023-03-28T00:00:00 |
2023/03/28
|
https://www.recruitbpm.com/blog/latest-ai-recruitment-tools/
|
[
{
"date": "2023/04/01",
"position": 92,
"query": "AI labor market trends"
},
{
"date": "2023/04/01",
"position": 96,
"query": "AI regulation employment"
},
{
"date": "2023/04/01",
"position": 13,
"query": "artificial intelligence hiring"
},
{
"date": "2023/04/01",
"position": 34,
"query": "artificial intelligence hiring"
}
] |
The Ethics of Artificial Intelligence: Sociopolitical and Legal ...
|
The Ethics of Artificial Intelligence: Sociopolitical and Legal Dimensions
|
https://www.journalisslp.com
|
[
"Jingjing Wang",
"Law School",
"Peking University",
"Pku",
"Peking",
"Wenjie Mao",
"Faculty Of Law",
"Zhejiang University",
"Yuhangtang",
"Hangzhou"
] |
... AI and Employment, Digital Divide, and AI in Governance. The Legal Dimension ... Regulatory Frameworks, AI Ethics and Law Integration, and Human Rights and AI.
|
Abstract
This study aims to explore the ethical dimensions of artificial intelligence (AI), focusing on its sociopolitical and legal implications. It seeks to identify and analyze the primary ethical concerns that arise from the development and deployment of AI technologies, with an emphasis on understanding how these concerns impact society and the legal frameworks that govern AI. Employing a qualitative research design, this study conducted semi-structured interviews with 22 participants from diverse professional backgrounds, including technology ethicists, legal scholars, AI developers, policymakers, and advocacy group representatives. The data collection aimed for theoretical saturation, with the interviews designed to uncover a broad range of perspectives on AI ethics. Thematic analysis was used to identify and categorize the main themes and sub-themes related to the ethical implications of AI. The analysis revealed two main themes: Sociopolitical Dimension and Legal Dimension. The Sociopolitical Dimension includes categories such as Privacy and Data Governance, Bias and Discrimination, AI and Employment, Digital Divide, and AI in Governance. The Legal Dimension encompasses Intellectual Property Rights, Liability and Accountability, Regulatory Frameworks, AI Ethics and Law Integration, and Human Rights and AI. Each category was further explored through specific concepts, highlighting the complexities and challenges inherent in the ethical considerations of AI technologies. The study underscores the intricate relationship between AI technologies and ethical considerations, emphasizing the necessity for comprehensive, multidisciplinary approaches to address the identified sociopolitical and legal challenges. It advocates for the development of inclusive, equitable, and responsive frameworks that not only mitigate risks but also promote the beneficial potential of AI, ensuring that technological advancements align with societal values and legal norms.
| 2023-04-01T00:00:00 |
https://www.journalisslp.com/index.php/isslp/article/view/27
|
[
{
"date": "2023/04/01",
"position": 71,
"query": "AI regulation employment"
}
] |
|
Resolution on the EU Artificial intelligence Act for ...
|
Resolution on the EU Artificial intelligence Act for the inclusion of persons with disabilities
|
https://www.edf-feph.org
|
[
"Andre Felix"
] |
Welcoming the decision of the European Commission to propose an EU law – the AI Act – to regulate the use of AI in three risk categories.
|
adopted by the Board of Directors of the European Disability Forum on the 1st of April 2023
Highlighting that Artificial intelligence (AI) is an emerging technology that has made its way into various areas of our lives, such as personalised recommendations online, virtual personal assistants, chatbots, speech-to-text technologies and computer vision applications, and AI based applications are also used by public and private services, including in the areas of social policies, healthcare, insurance, banking, education and employment.
Recalling that emerging technologies such as AI can further support the social participation and inclusion of persons with disabilities if they are developed with a Design for All approach, and used in a way that respects the right to non-discrimination, equality and privacy.
Concerned that persons with disabilities are at increased risk of becoming victims of fraud or misinformation through misuse of generative AI[1], and limitation of their self-determination.
Stressing that AI solutions that are not designed taking human diversity into consideration can increase the exclusion and discrimination against already disadvantaged groups, such as persons with disabilities, but also women, racialised persons and ethnic minorities, older persons and other discriminated people. Such discrimination can occur without the person noticing it.
Recalling that the United Nations Convention on the Rights of Persons with Disabilities (CRPD) has been the first international human rights instrument that recognises the need to promote equal access to technology as a fundamental right for persons with disabilities (article 9) and to ensure equality and non-discrimination in all areas of life (article 5).
Underlining that the United Nations Special Rapporteur on the Rights of Persons with Disabilities recognised that the negative impacts of AI on the rights of persons with disabilities must be openly acknowledged and addressed through cooperation between states, companies, national human rights institutions, civil society, and organisations for persons with disabilities.[2]
Stressing that a lack of accessibility in the design and use of AI can endanger the lives and well-being of persons with disabilities.
Noting that the EU Strategy for the rights of persons with disabilities 2021-2030 recognises that accelerated digital transformation and the green transition offer opportunities, using information and communication technology (ICT), artificial intelligence and robotics to design on-site and remote services tailored to the needs of persons with disabilities; but that the effective use of these technologies requires the removal of accessibility barriers for persons with disabilities and investing in their digital skills.
Welcoming the decision of the European Commission to propose an EU law – the AI Act – to regulate the use of AI in three risk categories, while concerned that the proposal does not sufficiently include and protect the rights of persons with disabilities.
The EDF Board of Directors calls on the European Union institutions to:
Live up to its obligations under the CRPD and ensure that all persons with disabilities can benefit from accessible, affordable, and available AI-technologies that support their socio-economic participation and independent living, and that AI systems put in place in the EU and worldwide respect persons with disabilities’ rights to non-discrimination, equality, self-determination, and privacy. Adopt the proposed EU Regulation on AI ensuring that AI systems, regardless of their level of risk, are subject to mandatory accessibility requirements. This includes AI-related information and user guides, which will need to be in line with existing EU legislation on accessibility, in particular the European Accessibility Act. Recognise the disproportionate risk to the rights of persons with disabilities in the areas identified as high risk in the proposed AI Act, such as biometric identification, access to education, employment, private and public services, law enforcement, migration and border control, and the administration of justice. Enlarge the list of prohibited uses of AI systems to cover, in particular: Biometric identification and categorisation of natural persons.
AI systems that determine the possibilities for individuals to gain access to education and employment.
Access to and use of essential services and benefits, both private and public, including provision of healthcare and emergency services (Except for prioritizing emergency response services – see page 9 in the EDF position paper).
Use of AI by law enforcement (Except for detecting deepfakes – manipulated video, audio or image that looks real but is digitally created – and to evaluate the reliability of evidence – see page 9, in the EDF position paper)
Use in the management of migration, asylum and border control. (Except for evaluating the authenticity of traveling documents and assisting authorities in examining applications and associated complaints – see page 9, in the EDF position paper) Ensure that the Regulation protects the privacy and data protection of all persons with disabilities, including persons with intellectual and psychosocial disabilities and persons subject to substitute decisions, such as guardianship, when their data are processed by AI systems. Put in place effective and accessible measures so that individuals, including persons with disabilities, are informed when their data is being collected and have the opportunity to inquire about and object to the processing of such data. Prohibit public and private entities from using AI to recognise emotions, except for certain well-defined research purposes subject to strict privacy safeguards, including informed consent and the ability of research subjects to object. AI-based emotion recognition assistive technologies should also comply with such safeguards. Ensure the protection of individuals’ fundamental rights in relation to the use of AI, including measures for reporting problems, making complaints to competent authorities (including collective complaints and complaints made by civil society actors on behalf of individuals) and seeking remedies in the event of abuse, and ensure that these measures are accessible to persons with disabilities. Promote the development of AI that involves the meaningful participation of experts with disabilities, accessibility professionals and other rights holders through financial and other incentives (such as EU and national funding for projects led by disability organisations or directly involving accessibility professionals). Adopt measures to support the development of AI for human and societal benefit, taking into account the needs of diverse communities, including persons with disabilities. In accordance with Article 4(3) of the CRPD, to closely consult and actively involve persons with disabilities, through their representative organisations, in the development, implementation and monitoring of European and national AI policies, including in relation to the EU Coordinated Plan on AI and national AI strategies.
Documents
| 2023-04-01T00:00:00 |
2023/04/01
|
https://www.edf-feph.org/publications/resolution-on-the-eu-artificial-intelligence-act-for-the-inclusion-of-persons-with-disabilities/
|
[
{
"date": "2023/04/01",
"position": 93,
"query": "AI regulation employment"
}
] |
A grassroots group took on Amazon and won. Then came ...
|
A grassroots group took on Amazon and won. Then came the hard part
|
https://www.cnn.com
|
[
"Catherine Thorbecke"
] |
The Amazon Labor Union shocked the world last April by successfully forming the first US union in the e-commerce giant's history.
|
CNN —
When the Amazon Labor Union shocked the world last April by successfully forming the first US union in the e-commerce giant’s history, Chris Smalls, the president and face of the organization, celebrated by making champagne rain on the street and thanking Jeff Bezos “for going to space” while workers organized.
Smalls, a worker who was fired by Amazon (AMZN) in the early days of the pandemic and then labeled as “not smart or articulate” by a company lawyer, quickly emerged as an icon for the resurgent US labor movement. He went on a media tour that took him from the red carpet to the White House, often clad in his “Eat the Rich” jacket and Versace sunglasses.
But in the year since the landmark victory, Smalls and ALU appear to have fallen back to earth. Amazon still refuses to recognize the union or come to the bargaining table, dashing the Staten Island workers’ hopes of creating their first contract. The group fell short in its campaigns to organize two other Amazon warehouses in New York, including one across the street from the unionized facility. Meanwhile, Smalls and the union have been grappling with public infighting which, combined with its stalled progress on other fronts, could threaten the union’s future.
The early struggles for ALU highlight the challenges of taking on one of the biggest employers in the world. It has also renewed questions about whether a grassroots organization, rather than a more established union, is best suited for the task, even though no established union has ever made it this far in organizing a US union at Amazon.
“I think that’s a lesson here, that an established union would have helped the local leaders in these internal battles to get worked out, and to help them prepare and structure a bargaining approach and strategy,” said Thomas Kochan, a longtime labor researcher at the MIT Sloan School of Management’s Institute for Work and Employment Research.
But in a recent interview with CNN, Smalls was enthusiastic about the state of his union, noting that “it’s been going great,” while pointing to the realities of being a grassroots group.
Union organizer Christian Smalls (L) celebrates following the April 1, 2022, vote for the unionization of the Amazon Staten Island warehouse in New York. Andrea Renault/AFP/Getty Images
“If anybody could do it better, please be my guest,” Smalls said of running ALU. “This is not an established union that’s been around, this a grassroots movement that’s going to have growing pains, and there’s a lot of uncharted water because it’s never been done before.”
“Our expectations is insane,” he added. “People expect us to be moving like we’re an established union that’s been around for 100 years. That’s not the case, we’re as grassroots as they come.”
Tensions inside a grassroots union
When Heather Goodall and her colleagues started organizing at an Amazon warehouse in Albany, they met with representatives from multiple established unions, including the Teamsters, to discuss the effort. But ultimately, they decided to organize with ALU.
In the grassroots group, Goodall initially saw a fighter. The union, founded by Smalls after he was fired from the Staten Island warehouse following his decision to lead a protest over pandemic working conditions, was the one group to actually “beat the billion-dollar bully,” as she put it to CNN last year. And the decision of the Albany workers to organize with ALU suggested Smalls’ group could extend its influence throughout Amazon’s sprawling network of warehouses.
Instead, ALU lost the fight to unionize in Albany in October and tensions later boiled over between Goodall and Smalls, with the Albany organizer telling CNN she pushed back on Smalls’ pay, travel and leadership.
“I told Christian, ‘We have a problem, you need to stop traveling, you need to focus on the workers,’” Goodall told CNN. “I wanted to protect the integrity of the ALU, so I kept it internal, but some of the challenges that I was arguing with him about started to really shake the foundation of the ALU.”
Heather Goodall and Amazon Labor Union members rallied at the ALB1 Warehouse in Schodack ahead of their labor union election on October 10, 2022. Karla Coté/SOPA Images/Shutterstock
Goodall said the tensions only increased in January, when she said she learned Smalls was earning a salary of $60,000 from the union, and as she questioned how much was being spent by the group to rent office space in New York City.
“I started to realize that Christian had really convinced himself that he is the end-all and that’s not how a union is run,” Goodall said. “That was kind of the beginning of end.”
Goodall said she was told to “get on board” and when she continued to raise concerns about union leadership, she said she was eventually removed from her role as chairperson for the ALB1 Amazon facility, and stopped receiving her $300 weekly paycheck from the union in early February.
Smalls, for his part, did not directly address the claims about her removal when asked. “First of all, there is no infighting because they’re not in,” he said.
Smalls said that “every union president in this country travels” and defended his salary as a fraction of what other union presidents earn. He said he sees his travel as important for getting young people excited and involved in the broader labor movement, saying, “I’m fighting for workers on a greater scale.”
He also said he earns money from some of his public appearances, but added that, “I put my life on the line long enough,” after spending more than 300 days unemployed and at the bus stop across the street from the Staten Island facility trying to unionize it. “My speaking engagements is yeah, for my own personal well-being, I was out of a job from 2020 with no help, I have a lot of bills and a lot of debts that I accumulated that I need to get rid of.”
And despite now rubbing shoulders with celebrities like Zendaya, appearing on Time’s list of the 100 most influential people and gracing the cover of New York magazine, Smalls insists the fame hasn’t changed him. “I’m still a worker who was fired three years ago during the pandemic,” he said. “I’m the same person who I was in 2020, I’ve always done as much as I can, I’m only one person and I can’t be at every place at every given time.”
Chris Smalls in front of the Amazon LDJ5 fulfillment center in the Staten Island borough of New York, on Feb. 7, 2022. Michael Nagle/Bloomberg/Getty Images
Even with her criticisms, Goodall echoed Smalls in calling the infighting at the organization “growing pains” for the budding union and said she is hopeful that ALU will soon make a “comeback.”
“I don’t care about the money, I’m continuing everything that we’ve been doing,” Goodall said.
“This can be a learning experience,” she added. “We are going to elect strong leadership and we are going to make this a historic movement going forward and make it about the workers.”
An uncertain future
The union’s stated goal is to fight for better pay, benefits and working conditions for warehouse staff. For ALU to prove itself now, it ultimately needs to be able to get Amazon to the bargaining table and secure its first contract for workers at the Staten Island facility — and show workers that it can win some negotiations with the e-commerce giant.
“They’re under a lot of pressure,” said Kate Bronfenbrenner, the director of labor education research at Cornell University’s School of Industrial and Labor Relations, “because they went around talking about what a great victory they have. Then everybody says, ‘Okay, what’s next?’”
Bronfenbrenner, who is also the co-director of the Worker Empowerment Research Project, an interdisciplinary network of labor market researchers, added that not having a first contract a year after an election is “not a big deal” for the union, as “only a third of a third of newly-organized workplaces” meet this milestone in that timeframe.
“What’s different about this,” she said, is that Amazon is challenging not just ALU’s win but also the “legitimacy” of the National Labor Relations Board. The company has claimed the independent federal agency tasked with overseeing union elections exerted “inappropriate and undue influence” with the Staten Island effort. (The NLRB has pushed back at that claim.)
An Amazon employee signs a labor union authorization for representation form outside the Amazon LDJ5 fulfillment center in the Staten Island borough of New York, on Monday, Feb. 7, 2022. Michael Nagle/Bloomberg/Getty Images
Amazon, which has long said that it prefers working with employees directly versus through a union, has signaled it’s prepared to take its fight through higher courts. In remarks late last year at the New York Times DealBook conference, Amazon CEO Andy Jassy said, in his opinion, the legal battle with the union was “far from over with.” He added: “I think that it’s going to work its way through the NLRB, it’s probably unlikely the NLRB is going to rule against itself, and that has a real chance to end up in federal courts.”
As Bronfenbrenner put it, “Amazon could stall it forever, and they know that.”
The union was likely caught off-guard by the struggles that come after winning an election, Bronfenbrenner said. “They were very focused on the organizing, and not having had a lot of experience, they didn’t really think about the battle for a first contract.”
Now, the public infighting only risks making it harder for ALU to accomplish its goals.
“They have to resolve those differences, and go to the bargaining table as one united organization,” MIT’s Kochan said. “The longer those internal divisions persist and get publicity, the more emboldened Amazon is going to be to say, ‘See, they can’t even agree among themselves, and we don’t have to do anything, but sit on our hands and this thing is going to fail on its own accord.’”
But ultimately, Kochan said he thinks it’s important to remember that the workers are fighting a system that is rigged against them.
“I think the biggest lesson is our labor laws are so badly broken,” he said, “and it needs fundamental change so that we don’t frustrate workers who want to have a union and recognize the uphill battles they have to fight to get a first contract.”
| 2023-04-01T00:00:00 |
2023/04/01
|
https://www.cnn.com/2023/04/01/tech/amazon-labor-union-one-year-later
|
[
{
"date": "2023/04/01",
"position": 27,
"query": "AI labor union"
}
] |
Generative AI Technology Services
|
Generative AI Technology Services
|
https://www.accenture.com
|
[] |
say at least half their workers have received AI training but only 5% have reached the full workforce ... European Union AI Act. European Union AI Act. Are you ...
|
European Union AI Act
The EU AI Act will be the most comprehensive AI legislation in the world to date. And it will have critical implications for all multinational organizations. The Act’s reach will extend globally. Any organization that develops or deploys AI systems within the EU will need to comply.
| 2023-04-01T00:00:00 |
https://www.accenture.com/us-en/services/data-ai/generative-ai
|
[
{
"date": "2023/04/01",
"position": 61,
"query": "AI labor union"
}
] |
|
Campaigning Platform for Unions
|
Campaigning Platform for Unions
|
https://callhub.io
|
[] |
AI Smart Insights · Inbound Calling ... CallHub is a union software designed to streamline communication between trade or labor unions and their members.
|
CallHub is a comprehensive union campaign management platform with powerful calling, texting, and email automation tools. It’s the only outreach tool you’ll ever need to:
• Grow memberships,
• Mobilize supporters,
• Canvass for candidates,
• Get out the vote and more.
| 2023-03-14T00:00:00 |
2023/03/14
|
https://callhub.io/industries/union/
|
[
{
"date": "2023/04/01",
"position": 63,
"query": "AI labor union"
}
] |
Digital labour – Page 2 - Data Big and Small
|
Digital labour – Page 2 – Data Big and Small
|
https://databigandsmall.com
|
[] |
International Labor Organization (ILO), the Digital Platform Labor ... Worker Engagement and AI Work on Online Labor Markets. Discussant: Simone ...
|
Three to five dollars: that’s the answer. As simple as that. I am talking about the behind-the-curtain market for personal data that sustains machine learning technologies, specifically for the development of face recognition algorithms. To train their models, tech companies routinely buy selfies as well as pictures or videos of ID documents from little-paid micro-workers, mostly from lower-income countries such as Venezuela and the Philippines.
Josephine Lulamae of Algorithm Watch interviewed me for a comprehensive report on the matter. She shows how, in this globalized market, the rights of workers are hardly respected – both in terms of labour rights and of data protection provisions.
I saw many such cases in my research of the last two years, as I interviewed people in Venezuela who do micro-tasks on international digital platforms for a living. Their country is affected by a terrible economic and political crisis, with skyrocketing inflation, scarcity of even basic goods, and high emigration. Under these conditions, international platforms – that pay little, but in hard currency – have seen a massive inflow of Venezuelans since about 2017-18.
Some of the people I interviewed just could not afford to refuse a task paid five dollars – at a moment in which the monthly minimum wage of Venezuela was plummeting to as little as three dollars. They do tasks that workers in richer countries such as Germany and the USA refuse to do, according to Lulamae’s report. Still, even the Venezuelans did not always feel comfortable doing tasks that involved providing personal data such as photos of themselves. One man told me that before, in better conditions, he would not have done such a task. Another interviewee told me that in an online forum, there were discussions about someone who had accepted to upload some selfies and later found his face in an advertisement on some website, and had to fight hard to get it removed. I had no means to fact-check whether this story was true, but the very fact that it circulated among workers is a clear sign that they worry about these matters.
On these platforms that operate globally, personal data protection does not work very well. This does not mean that clients openly violate the law: for example, workers told me they had to sign consent forms, as prescribed in the European General Data Protection Regulation (GDPR). However, people who live outside of Europe are less familiar with this legislation (and sometimes, with data protection principles more generally), and some of my interviewees did not well understand consent forms. More importantly, they have few means to contact clients, who typically avoid revealing their full identity on micro-working platforms – and therefore, can hardly exert their rights under GDPR (right to access, to rectification, to erasure etc.).
The rights granted by GDPR are comprehensive, but do not include property rights. The European legislator did not create a framework in which personal data to be sold and bought, and rather opted for guaranteeing inalienable rights to each and every citizen. However, this market exists and is flourishing, to the extent that it is serving the development of state-of-the-art technologies. Its existence is problematic, like the ‘repugnant’ markets for, say, human organs or babies for adoption, where moral arguments effectively counter economic interest. It is a market that thrives on global inequalities, and reminds of the high price to pay for today’s technical progress.
See the full report here.
| 2023-04-01T00:00:00 |
https://databigandsmall.com/tag/digital-labour/page/2/
|
[
{
"date": "2023/04/01",
"position": 100,
"query": "AI labor union"
}
] |
|
Top Tampa, FL AI Companies 2025
|
Top Tampa, FL AI Companies 2025
|
https://builtin.com
|
[] |
Top Tampa, FL AI Companies (14) · PwC · Maxar Technologies · Rapid7 · CDW · Pfizer · Big Fish · Rysun Labs · Five TMS AI. Artificial Intelligence • Logistics • ...
|
Artificial Intelligence • Logistics • Productivity • Software • Transportation
Tampa, Florida, USA 15 Employees
Five TMS AI is a full-service transportation management and procurement platform that provides complete logistics operation management to help you run a more streamlined and digitized transportation department. Five TMS offers more than just software, with complete compliance carrier on-boarding and insurance verification, as well as a digital marketplace to provide you a competitive advantage in freight rates with a cloud optimized RFP to eliminate your excessive excel sheets. Five TMS organizes your workflows while tracking data and leveraging AI for efficiency. With hard break and ETA recognition, our new Track Five App now offers live GPS tracking on your freight, tracking each driver, and optimizing your dock scheduling. Established in the latter part of 2022, Five TMS AI is led by skilled veterans who have developed cutting-edge logistics technology and are now applying their expertise to the supply chain from a fresh perspective. Five TMS AI Launches on 1st April 2023
| 2023-04-01T00:00:00 |
https://builtin.com/companies/location/tampa-bay/type/artificial-intelligence-companies
|
[
{
"date": "2023/04/01",
"position": 6,
"query": "artificial intelligence employers"
}
] |
|
BabsonX: AI for Leaders - edX
|
BabsonX: AI for Leaders
|
https://www.edx.org
|
[] |
However, most leaders, executives and board members lack the necessary AI education, skills, strategies and tactics to create AI-powered business models with ...
|
Level up your career — Get 15% off select programs until July 30. Use the code LEVELUPEDX25. Learn more.
Close site banner.
| 2023-04-01T00:00:00 |
https://www.edx.org/learn/artificial-intelligence/babson-college-ai-for-leaders
|
[
{
"date": "2023/04/01",
"position": 64,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2023/05/01",
"position": 66,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/06/01",
"position": 59,
"query": "AI business leaders"
},
{
"date": "2023/06/01",
"position": 67,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/08/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2023/11/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2023/11/01",
"position": 66,
"query": "artificial intelligence business leaders"
},
{
"date": "2023/12/01",
"position": 66,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/01/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2024/01/01",
"position": 65,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/02/01",
"position": 63,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/05/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/07/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2024/07/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/09/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/10/01",
"position": 65,
"query": "AI business leaders"
},
{
"date": "2024/10/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/11/01",
"position": 69,
"query": "AI business leaders"
},
{
"date": "2024/11/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2024/12/01",
"position": 63,
"query": "AI business leaders"
},
{
"date": "2025/01/01",
"position": 70,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/02/01",
"position": 43,
"query": "AI business leaders"
},
{
"date": "2025/02/01",
"position": 62,
"query": "artificial intelligence business leaders"
},
{
"date": "2025/06/01",
"position": 41,
"query": "AI business leaders"
},
{
"date": "2025/06/01",
"position": 62,
"query": "artificial intelligence business leaders"
}
] |
|
Episode 129 - AI & Economic Disruption with Avi Goldfarb
|
AI & Economic Disruption with Avi Goldfarb
|
https://www.wealthability.com
|
[] |
AI & Economic Disruption: Avi Goldfarb joins Tom to discuss how AI offers value to any business by decoupling prediction from decision-making.
|
Announcer:
This is The WealthAbility® Show with Tom Wheelwright. Way more money, way less taxes.
Tom Wheelwright:
Welcome to The WealthAbility Show, where we’re always discovering how to make way more money and pay way less tax. Hi, I’m Tom Wheelwright, your host, founder, and CEO of WealthAbility.
So what if you could actually predict your revenue, your workflow, the needs that you have for additional workers, and even how a worker, and whether they would fit well within your company, how would that change your life as a business owner? Today we’re going to learn how AI can actually do that, that it can give us the predictability that we’ve been wanting without all of the headache and guesswork that comes from it, but not take away our judgment. And today I have a very special guest with me, Avi Goldfarb from the University of Toronto, he is an expert in this area, and it’s great to have you with us Avi, welcome.
Avi Goldfarb:
It’s fantastic to be here, thanks Tom.
Tom Wheelwright:
And so Avi, if you would, just give us a little bit of your background.
Avi Goldfarb:
Sure. I am a professor at the University of Toronto, the Rotman School of Management, I’m in the marketing department. I am trained as an economist, so way back in the 1990s there was this new technology called the internet, and when I was doing my PhD I decided this was something nobody knew anything about, and so it was the kind of thing that was worth studying and trying to get my head around. And so I spent the first 15 years of my career trying to understand the economic impact of the internet, focused on things like understanding online advertising, understanding online market power, and the challenges with respect to privacy.
Then about 10 years ago, we started this program at the University of Toronto for science-based startups called the Creative Destruction Lab. And in our lab in the very first year we saw this company called Atomwise, it was way back in 2012, that said they were using artificial intelligence for drug discovery. Put yourself back 10 years ago, that just seemed crazy. This idea that you’re going to use artificial intelligence for anything wasn’t on most people’s radar, and for drug discovery, that just seemed like science fiction. And what they were actually doing was using a new emerging technology called deep learning, which is a branch of computational statistics, but they call it artificial intelligence, to try to predict which molecules bind with which proteins to figure out which drugs are going to work.
Tom Wheelwright:
Interesting.
Avi Goldfarb:
And then the next year we had a handful more, and the next year we had this flood of AI companies coming through our lab. And my co-authors and I, who were running a lab at the time, decided this was worth getting our heads around, and so we moved on from studying the impact of the internet to try to understand this new technology. So that’s why I’m here, since 2012, and especially since about 2015, I’ve been focused on trying to understand the impact of AI on the economy and on business, and that led to our first book, Prediction Machines, and our new book, Power and Prediction.
Tom Wheelwright:
I love it. We did a podcast on AI just a few years ago, and I know it has just changed drastically since then. I’ve long been a believer that AI combined with blockchain technology was actually going to change the business world, frankly, and that one is predicting it and the other one is actually auditing it, effectively, and making sure it’s accurate. So let’s talk about AI, if you would, drill down a little bit, make sure everybody understands, what are we talking about when we say AI? Because I don’t think we’re talking about robots here, I think we’re talking about something different.
Avi Goldfarb:
Yeah, the reason we’re talking about artificial intelligence in 2022, and it wasn’t really on anybody’s radar 10 or 20 years ago, it’s because a very particular branch of computer science called machine learning has gotten much better. And machine learning is prediction technology. So it’s not artificial general intelligence, it’s not like the robots you’re going to see in science fiction, it is the ability to take data you have and to fill in missing information.
But it turns out prediction is a really big deal in all sorts of businesses, because anytime you’re trying to fill in missing information, that’s prediction. So if you’re trying to fill in forms, that’s prediction, if you’re trying to diagnose in medicine, that’s prediction. If you’re trying to assess what the right decision is, a key component of that is situational awareness, knowing what’s going on, and that’s fundamentally prediction. The key point though is that prediction’s not everything, so if you have a prediction you still don’t know what to do. You need the prediction, to decide you actually need some judgment, you need to know what matters, what do you value in order to make a decision. And so we can think about that in all sorts of ways.
There’s this old movie I, Robot. I don’t know if you remember.
Tom Wheelwright:
I remember it well, Will Smith.
Avi Goldfarb:
Okay. So it’s a classic science fiction movie based on a classic science fiction novel, and the protagonist of the movie, Detective Spooner, he hates robots. Why does he hate robots? And there’s this flashback scene where he and this little girl are in a car accident, and their cars are both sinking into a river, and it’s pretty clear that both of them are about to drown. And then a robot comes along and saves Detective Spooner, saves the adult, and not the girl, and that’s why he hates robots. And he says, “Well…” Oh, because it was a robot, and actually this is really important in terms of, you said, auditing with blockchain, well it’s also true with auditing with AI, because it was a machine he could audit it he could say, well, why did the robot save me and not the girl? And the robot predicted that he had a 45% chance of survival, and the girl had an 11% [inaudible 00:06:01], but it’s actually very meaningful in the context of understanding today’s AI.
So those predictions, 45 versus 11, actually didn’t tell the robot what to do. Someone programmed the robot to say, well 45 is more than 11, so save the adults and not the child. And then the protagonist, the detective goes on to say, well 11% was more than enough and a human being would’ve known that, the robot should have saved the girl. Well, that’s a different statement, that’s about judgment, that’s about what do you do with a prediction, and it turns out these tools are amazing at prediction, but the judgment of what do you do with those predictions, that remains inherently human. And so all over the place, when we’re thinking about using artificial intelligence and business, the AI’s just giving you those numbers, it’s giving you the predictions, but you have to decide, what do you do with them?
Tom Wheelwright:
So let me give you an example, and lets explore this, because I’m a business owner, most of our listeners are business owners, and we’re looking at, boy, if we could predict revenue, if we could predict customer behavior, if we could predict workflow, it would have a huge impact because then we could make decisions, like you say, judgment, as to when to hire somebody, who to hire, at what time do we hire them, we can make judgments as to how do we expand? Because obviously if we can predict our current revenue we can say, okay, well if we did this, what would happen? And then if it could give us a predictable result and we say, well, okay, well if I spend $5 in this aspect of marketing, I do $5 on a Facebook ad, what will that get me? And it predicts that, well, it’ll get you $20. Well okay, what if I put in $500,000, will it get me 2 million? So the same type of a thing, is that the type of prediction we’re talking about here?
Avi Goldfarb:
So yes to some and no to others. So the investment predictions, that’s less so because ultimately if you’re using a prediction tool to try to figure out how to invest, and so is everybody else, it’s all going to wash out the way the market works out. But for something like what’s demand going to be, what’s customer demand going to look like next period? Giving consumers coming to my website, or to my business, what are their interests? What do they want? That kind of filling in information, that kind of prediction, is very much in the AI’s wheelhouse, today’s AI’s wheelhouse. So you can do things like predicting inventories, predicting demand, predicting whether a new applicant is going to be a good fit in the organization, things like that.
Tom Wheelwright:
So let me give you a… Oh, I like that last one, that’s a tough one, right? So let me give you an example. So in my business, I’m a CPA, and what we’re always trying to do is predict workflow throughout the year. We kind of know what customers have done in the past, but presumably with AI we could absolutely know and it could predict, okay, well we’re going to get this much work in June, this much work in March, and this much work in October, and this is how we need to staff up.
Avi Goldfarb:
Absolutely. So to the extent that those things are predictable year in, year out, or at least they’re based on factors that you can anticipate, then absolutely. So you have a sense maybe in April it’s busy, but exactly how busy, and you could do those predictions at the customer level. So what’s the likelihood that given my set of customers, each one is going to be, how many hours is each one going to require every month? And using your historic data, and historic data from other CPAs that maybe a vendor could provide, you could then predict the demands customer by customer and then you can aggregate it and figure out how to allocate your time and when you need to bring extra people on, et cetera.
Tom Wheelwright:
I like it. So one of my big questions though, for the smaller business, we understand that in our industry, for example, Ernst & Young, yeah they’re probably using AI, they’ve probably been using AI for years now. But what about the smaller business? How does a smaller business actually find, I mean, even figure out how to use that information, where do they even go for that?
Avi Goldfarb:
So for most smaller businesses you’re not going to be developing in-house, you’re going to be going to a vendor.
Tom Wheelwright:
Exactly.
Avi Goldfarb:
But a lot of your software vendors, for lack of, will have some AI built in, you just have to look for it and think about the relevant ones. So if it’s an e-commerce business, Amazon and Shopify will both have AI related tools that can support what you’re doing already, and if you’re, you can think about other dimensions, the tax software will have some AI in it already. So there’s lots of opportunities to use it, but I don’t want to exaggerate the payoff, so I just want to be a little bit cautious here.
So if you have your existing workflow, this is the theme of our new book Power and Prediction, which is if you have your existing workflow and all you’re doing is taking an AI to improve your existing workflow, but not really changing anything else, so oh, you know what? This is a costly human process, it takes lots and lots of hours, let’s use an AI tool, a machine learning tool to make that a little bit better, the upside is necessarily going to be limited. And so you might save 5, 10, 15% on that particular process, maybe even a little more, it’s not going to have any transformative impact in the business. So you got to decide, for 5, 10, 15%, is it worth it to invest your time to learn the new tool, and all that.
Where the real potential lies is once you can figure out what are the major bottlenecks in my business in order to deliver valued my customers, are any of those bottlenecks driven by a lack of prediction, you don’t have good information. And if that’s the case, maybe you can build an entirely new kind of business, or entirely new business line, is maybe the best way to put it, where you take advantage of that better information in order to better serve your customers. My favorite example of this is the airport, which is those airports that are rated the best airports in the world, like Singapore and Seoul Incheon, and there are fewer in the United States and Canada, but there’s some.
Tom Wheelwright:
That’s true.
Avi Goldfarb:
But if you think about these great airports, what makes them so great? They have restaurants and they have shopping and they have museums and art galleries and theater, and all this. What do you actually want to do at the airport? Well, now let’s look at what the super rich do. The private jet terminals don’t look anything like those spectacular airports.
Tom Wheelwright:
That’s right.
Avi Goldfarb:
I’ve been told they’re effectively sheds, right?
Tom Wheelwright:
They are.
Avi Goldfarb:
Because no one wants to spend time at the airport, you only spend time at the airport because of a product fail on the part of the airlines.
Tom Wheelwright:
Hey, if you like financial education the way I do, you’re going to love Buck Joffrey’s podcast. Buck’s a friend of mine, he’s a client of mine, he’s a former board certified surgeon, and he’s turned into a real estate professional. So he has this podcast that is geared towards high paid professionals, that’s who it’s geared towards. So if you’re a high paid professional and you’re going, look, I’d like to do something different with my money than what I’m doing, I’d like to get financially educated, I’d like to take control of my money and my life and my taxes, I would love to recommend Buck Joffrey’s podcast, which is called Wealth Formula Podcast with Buck Joffrey. I hope you join Buck on this adventure of a lifetime, exactly.
Avi Goldfarb:
Your goal is to actually just get out. And so imagine if you had a great prediction about how long it would take to get to the airport and through security, then you don’t need shops, you don’t need restaurants, you don’t need any of that stuff, and the airport and the airlines would actually be delivering much better customer service. And so in your own business, just think through this, where are the constraints? I’m spending all this time, I have all this architecture, I had all these rules and standard operating procedures, not to serve my customers, but to actually compensate for the fact that I’m not serving them as well as I could.
Tom Wheelwright:
Interesting. And I do get to travel private from time to time, because I have buddies with airplanes, and seriously, you park close to the terminal, so the parking is an important part, and you walk in and get on the plane, and that’s it. I mean, there’s actually no security at a private airport, there’s no security at all because you’re getting on a private plane, so we’re not worried about that, we know everybody who’s going to be on that plane. But if you could literally go through security in five minutes and get on the plane five minutes later, that would be amazing. But we know you can’t do that because you got to queue up in line, you got to queue up for getting through the security, then you got to queue up again to get into the seats, and then you got to find out, am I on standby? And all these kinds of things. So you’re suggesting that boy, you could actually use AI to predict all that and actually solve for that if you used good judgment and figured out how to solve for it.
Avi Goldfarb:
Absolutely. And so the process is thinking through what are those things, like the shops and restaurants at airports, in your business that you’re providing to your customers basically because you can’t really deliver excellent customer service, because there’s some constraint that makes it impossible.
Tom Wheelwright:
Yeah, it’d be like the TV’s in the doctor’s office. Why there TV’s in the doctor’s office? Because you’re waiting for 45 minutes to see the doctor. That’s a fail.
Avi Goldfarb:
Exactly, exactly, exactly. And almost every business has examples of those kinds of fails, some smaller scale like TV, some big scale, like the entire multi-billion dollar architecture of an airport. You see it in insurance, you see it in accounting too, you have these constraints and you make your customers wait, and do all sorts of things, just because it takes time to fill in those forms and do things, that fundamentally are predictable in prediction tools.
Tom Wheelwright:
Exactly, exactly. But you distinguish the judgment from the prediction. So I always tell people that the job of a CPA, for example, is analysis, which is to help you make a judgment, right?
Avi Goldfarb:
Right.
Tom Wheelwright:
So how does that differ? I mean, you mentioned the I, Robot movie, but in practical terms, and in typical business terms, how do you combine that judgment with that prediction?
Avi Goldfarb:
There’s all sorts of places, so it depends on a particular context. My favorite example, I’m going to use a sports example, what is the business, it’s the business of sports. Michael Jordan in his first season, this was a long time ago, and he was injured, and he wanted to play, but the doctor said, “There’s a 10% chance that you’ll never play again if you play.” And so the owner of the team went to him and said, “Michael, why do you want to play so much? Imagine that you had a headache and you could take a pill that might cure you, but there’s a one in 10 chance it would kill you. Would you take the pill?” And his response was, “It depends how bad the headache is.” That’s the essence of judgment.
So you think about these risks, it’s a risk reward trade off often in many businesses, which is you have the prediction, and then you have to decide what matters, what do you value? So are you willing to take, in that context, Michael Jordan wanted to take a 90% bet that he’d be able to play in the playoffs, willing to take the 10% risk, the one in 10 risk that his career would be over, the owner of the team was not willing to make that bet, and pretty much didn’t, and basketball history ended up being made as a consequence. But maybe basketball history would’ve started a year earlier, with the Bulls winning the playoffs in his very first season. Who knows. And there’s every single decision you’re going to make.
So a restaurant, you have to decide whether to set up your patio on a given day or not. There’s a prediction on rain. Well, how bad is it if you set up the patio and it rains, versus if you don’t set up the patio and you forego all that money. There’s predictions on, in any business, on how much demand you’re going to have, how many customers are going to come in to your store, or how many clients are going to come in to your business this week or this month. And then you have to make hiring decisions. So the prediction just tells you how many people are going to be there, the judgment is what’s the consequence of hiring too many people, and having to pay a little extra, versus you’re not hiring enough and having to turn customers away.
In every business, frankly even by industry, every business owner is going to think of those costs differently. That’s the essence of the judgment. So the prediction can just tell you, oh, you know what? On Friday you’re going to have 20 extra people in the store. And the judgment is, well what do we do about that? Do we hire more? Do we turn people away? How do we think about those risks?
Tom Wheelwright:
That’s really interesting. So one of the things that every business owner thinks about is what’s the value of my business? Not just what’s the income currently to the business, but what’s the value of the business? And when you look at AI and predictability, do you see AI actually being, in the future, being able to predict, here’s the value of this business based on what’s going on now, and if you change certain parameters, here’s the value of the business if you made these changes?
Avi Goldfarb:
That’s going mad, I’ll put my economist hat on and say it depends, which is for the path that you’re on, if you don’t anticipate very major changes, then you can say yes. If the past is like the future you can use AI to fill in missing information and provide some value to the business. Once you’re starting to think about, well if I do something different, what’s going to happen? Well now we’re actually no longer in the world of prediction, it’s a different AI tool called causal analysis, that hasn’t had the major advances that we’ve seen in prediction tools.
And the reason it’s so hard is… So look, I’m a professor, I come in and I say, “Look, I’m going to teach you all about AI,” and my students come in, they’re like, “Wow, we learned about AI.” And I say, “Well imagine that because you’ve learned about AI from me and you’ve read my books, imagine your future where you’re spectacularly successful professionally and personally in every way you can imagine, and you can connect it to your knowledge of AI. Can you then say it was the right call to read my books and show up to my class?” And the students are like, “Of course.”
And I’m like, “Well actually, unfortunately, as much as I’d love that to be true, the answer is no, because you don’t know what would’ve happened to you had you not read my books and not taken the course. It’s possible you took them because you were interested in AI in the first place, and all of that success would’ve happened anyway.” And because of that we don’t know what happens in the counterfactual, so we don’t know what would happen if you did something different, so it means we don’t have data on it, which means the AI won’t work there. So trying to think about what would happen if is challenging, unless you think you have a business that you can simulate, and you can design a simulated framework for understanding those different opportunities.
Tom Wheelwright:
Interesting. So the AI, when it comes to predictability, is really taking the information that we have and it’s just assembling that information, well, based on the information we have, this is what’s going to happen, but we always know that past performance is not a predictor of future results, right?
Avi Goldfarb:
So it’s not just… The prediction should be fine in terms of past performance predicting future results as long as you don’t change your strategy. But once you change your strategy, we don’t have data on that, we don’t know what will happen if you change your strategy. And so that’s where it’s going to break down. And of course it can tell you in many contexts if we stay along the same path what will happen, but what you want to know is, uh-oh, okay, I see if I stay along the same path what will happen, I want to know what happens if we do something different, and that, at least for now, in most contexts, is not an AI problem, so there we need to remain [inaudible 00:24:00].
Tom Wheelwright:
So not taking over humans anytime soon.
Avi Goldfarb:
Not taking over humans anytime soon at all, no, not at all.
Tom Wheelwright:
Well, that’s good news for most people. Now you’ve said that you think that AI will actually make business better, be more successful, that you think that this will have a powerful impact on business, and really could completely disrupt certain industries. Can you just take a few minutes, go into that a little bit for us?
Avi Goldfarb:
Sure. So it’s a version of the airport example I just gave you, but those happen in all sorts of business. So many businesses have SOPs, standard operating procedures, and for the most part those standard operating procedures are rules that are there to accommodate the fact that sometimes you can’t make the perfect decision every time, and so instead what you go for is reliability, and to become dependable both to your customers and your suppliers, but also to the other people in your company, so person A and person B, the two people, their decisions are coordinated. So bring in AI, and the first way we’ve seen that so far is, okay, let’s add it to our workflow, and it’s had some impact, but it hasn’t, as I said, it hasn’t had that extraordinary impact. To have the extraordinary impact you want to break your SOPs, you want to change your standard operating procedures to think through, how can I deliver value in a way that I hadn’t before?
When I talked about the airport you had think about insurance, you can do the same thing. So we’ll start with, imagine going to your doctor, and your doctor looks over your symptoms, looks at your blood work and says, “There’s a 5% chance that you’re going to have something catastrophic happen to you over the next year.” If that happens we’ll give you $100,000, see you next year. That’s not what, the doctor’s supposed to give you some treatments, right?
Tom Wheelwright:
Right.
Avi Goldfarb:
Think about what your insurance company does, they don’t give you treatments, they say, oh you know what, there’s a 5% chance, they price the risk. So basically they’re saying there’s a 5% chance that something catastrophic is going to happen to your house next year, and if that happens we’ll give you some money. And they claim that they’re giving you peace of mind against catastrophic loss. That’s not really peace of mind, peace of mind would say, you know what? There’s a good chance that something disastrous is going to happen to your house, we think it’s going to be because of an electrical fire, for example, and we can then help you reduce the risk from electrical fire. So not just compensate you if something goes bad, but actually use better prediction in order to reduce the risk and deliver a much better product to customers.
10 years ago that was impossible, the insurance industry’s predictions just weren’t good enough, so they couldn’t do that. But now they’re getting there, the predictions are good enough that it’s not just at the aggregate level, at the sub parallel level they can say no electrical fire, or leaky pipes, or whatever else, and they can help you reduce that risk. And there’s all sorts of industries like that where the fundamental nature of the way you serve customers is related to your standard operating, and the way you build your standard operating procedures is because you don’t really know how to deliver value, and with better prediction, you can deliver value better, you can-
Tom Wheelwright:
Interesting.
Avi Goldfarb:
And I think there’s a real opportunity, there’s a real risk for disruption because if you don’t do it your competitors might, but there’s also a real opportunity.
Tom Wheelwright:
So from a practical standpoint, I remember, well, back in the 1990s when the internet was new, and you spent $15,000 to develop a website, and that was a basic website, and now you have plug and play and it takes 15 seconds to do that. Do you see that coming with AI, do you see where the AI tools will be such where an average business owner can say, okay, CPA, for example, here’s this AI tool that we can use, and let’s sit down and do an analysis because we’ve got this plug and play predictive tool.
Avi Goldfarb:
Yes, I think there’s two ways that small businesses can think about the opportunity. So way number one is we’re moving toward plug and play. We are for various applications, and that plug and play, that you’ll purchase through vendors, will make your businesses more productive in various ways. It’s not going to make a huge difference to the bottom line, but it’s going to be part of the standard improvements that you make every year. There’s various ways that you invest and improve the way your business operates, and one of them will be to use AI, use machine learning tools for a particular context, as purchased from a vendor. And I would [inaudible 00:28:53] percent or more of small businesses are going to be in that category.
But a handful of them are going to see much bigger opportunity, and say, you know what, if I can get these predictions right, then I can actually create a new way, a new type of value for my customers, or even capture a whole customer segment that I was never able to capture before. And those are the ones that are really going to make the headlines and transform the way we operate, but also be the ones that think about AI as central to their business. So there’s going to be most, and I imagine most of your listeners are going to be in the category of this is useful, just figuring out a new way to save on electricity costs, energy costs is useful. And then a handful are going to say, well now that I can do everything differently, I can develop a new product, and that new product is going to be central to the business going forward.
Tom Wheelwright:
Got it. So at the beginning of this discussion I suggested that it was AI combined with blockchain. Have you looked at that as to that combination of AI and blockchain and how they work together?
Avi Goldfarb:
A little bit. So I think there’s, to the extent that we can think about blockchain as verification technology, so that’s the essence of it. Now it’s online verification technology, we know very well that you also need to check things offline, because the internet, cyberspace isn’t a real place, you still need to verify that everything’s really happening. But there are opportunities to take the online verification tool that’s in blockchain and combine it with prediction technologies to develop some better services, particularly in financial services, there’s opportunities there. But in both of those contexts the opportunity relies on you remembering that we still need to do verification in the real world, and we have to recognize that just because we can track the transactions across the blockchain, that doesn’t mean that those transactions themselves are legitimate in terms of what’s happening offline.
Tom Wheelwright:
Awesome, thank you. So to sum up, what would you say are maybe two or three things that a business owner or investor ought to be looking at over the next year or two when it comes to AI?
Avi Goldfarb:
Okay, the first thing is when you hear AI, don’t think the robots from science fiction, think prediction technology. It’s software that gives you predictions, and predictions are useful because they help you make better decisions. So that’s the central point. In terms of, then number two is for most businesses, particularly most small businesses, the gains will be useful but incremental. Now if you’re thinking about, especially if you’re thinking about investment opportunities, what you want to be looking at are, if you’re focused on AI, are opportunities where the prediction allows you to overcome a bottleneck and generate a new way of creating value to some set of customers. And so where the predictions allow you to change your workflow, do things differently, and do things much, much better. There’s going to be lots of opportunities like that, but they’re harder to find. It’s easier to look for the easy wins, but there are big wins out there for rejigging the organization and thinking about disruption. And that last point is the theme of our new book, Power and Prediction: The Disruptive Economics of Artificial Intelligence.
Tom Wheelwright:
Awesome. So thank you so much, Avi Goldfarb from the University of Toronto, really appreciate you being here. If they want more information besides reading your book Power and Prediction, where else could they go for more information?
Avi Goldfarb:
My website is avigoldfarb.com, I’ve got all my work on AI up there.
Tom Wheelwright:
Awesome, thank you so much for being with us. And remember, when we look at these disruptive technologies, it’s either an opportunity, or it’s a challenge, because either you’re going to embrace it or you’re going to get left behind, and if you embrace it, and this is why we do this in The WealthAbility Show, you’re going to end up making way more money, and as we get to using AI and blockchain in the tax world, pay way less tax. Thanks everyone, see you next time.
Announcer:
You’ve been listening to the WealthAbility Show with Tom Wheelwright. Way more money. Way less taxes. To learn more, go to wealthability.com.
| 2022-12-23T00:00:00 |
2022/12/23
|
https://www.wealthability.com/podcast/episode-129-ai-economic-disruption-with-avi-goldfarb/
|
[
{
"date": "2023/04/01",
"position": 53,
"query": "AI economic disruption"
},
{
"date": "2023/07/01",
"position": 53,
"query": "AI economic disruption"
},
{
"date": "2023/09/01",
"position": 49,
"query": "AI economic disruption"
},
{
"date": "2023/11/01",
"position": 47,
"query": "AI economic disruption"
},
{
"date": "2024/01/01",
"position": 49,
"query": "AI economic disruption"
},
{
"date": "2025/01/01",
"position": 49,
"query": "AI economic disruption"
},
{
"date": "2025/03/01",
"position": 45,
"query": "AI economic disruption"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.