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
|
|---|---|---|---|---|---|---|---|---|---|
The Impact of AI on Social Class and Jobs: A Closer Look
|
The Impact of AI on Social Class and Jobs: A Closer Look
|
https://www.linkedin.com
|
[
"Michael Spencer",
"Naveen J.",
"Kieran Gilmurray"
] |
AI will eliminate some jobs machines can automate, such as routine, repetitive, or low-skill tasks. · AI will create new jobs that require human intelligence, ...
|
Artificial intelligence (AI) has been at the forefront of the conversation in various fields as technology advances. The widespread adoption of automation and AI systems has the potential to revolutionize many industries, including the design and #AEC (architecture, engineering, and construction) sectors. However, the social implications of AI must be taken into account. This article will explore the potential impact of AI on social class dynamics and future jobs.
First Act: The Impact of AI on Social Class
Social stratification theory explains how social class refers to the unequal distribution of power, wealth, and prestige within a society. In the context of AI, the widespread adoption of automation and AI systems could likely lead to significant changes in the distribution of wealth and power, potentially exacerbating existing social class divides. The technological determinism theory posits that technology plays a central role in shaping society, and those technological changes can lead to significant social and economic changes. However, the agency of individuals and social groups must be considered in shaping technological change. The social construction of technology theory suggests that technology is not a neutral force but is shaped by social, cultural, and political factors.
One of the main concerns raised by adopting AI systems is the potential impact on the #job_market. While AI systems may improve performance in specific tasks, they may also increase the expectations and requirements for job performance, making it harder for individuals from lower social classes to access employment opportunities. Additionally, the widespread adoption of AI systems may lead to the displacement of certain types of jobs, particularly those that are routine or can be easily automated, potentially disproportionately impacting lower social classes.
Furthermore, AI systems may reinforce existing power imbalances and contribute to the emergence of a "dictatorship of the algorithm." The current focus on creating "narrow AI" systems that can perform specific tasks more efficiently than humans could potentially lead to a small group of elites controlling the algorithms that shape our world. This could further entrench existing social class divides and make it even harder for marginalized groups to access the benefits of technological progress. To prevent these adverse outcomes, it is essential to prioritize the development of "broad AI" systems that can perform a wide range of tasks and are more resilient to biased inputs and outputs. This could ensure that the benefits of AI are more evenly distributed and that there is greater accountability for the decisions made by AI systems.
Second Act: The Impact of AI on Jobs
The impact of AI on future jobs is a complex and uncertain topic. Different opinions and predictions exist about how AI will affect various sectors, occupations, skills, and tasks. Some of the possible impacts include the following:
AI will eliminate some jobs machines can automate, such as routine, repetitive, or low-skill tasks. AI will create new jobs that require human intelligence, creativity, judgment, or social skills, such as data scientists, AI engineers, content creators, or educators. AI will transform existing jobs by augmenting human capabilities, enhancing productivity, and changing the nature of work. AI will increase the demand for technological skills (such as programming or data analysis) and soft skills (such as communication or problem-solving) across different domains. AI will require workers to adapt to changing skill requirements and learn new competencies throughout their careers.
The net effect of AI on employment is difficult to estimate. It will depend on many factors, such as the pace of technological innovation and adoption, economic growth and recovery from the #COVID_19 pandemic, education and training systems, labor market policies and regulations, and social attitudes and preferences. Therefore, governments, companies, and individuals must prepare for different scenarios and embrace lifelong learning.
Microsoft Copilot is a new AI-powered system that will be integrated across Microsoft 365 apps to help users with tasks such as writing, editing, summarizing, creating presentations and visualizations, managing emails and meetings, and synthesizing data from different sources. It is based on large language models (#LLMs) such as #GPT4 that can generate new content from massive amounts of data.
Google Copilot is a similar AI feature that will be added to Google Workspace apps such as Docs, Sheets, Slides, Meet, and Chat. It will also use LLMs like #PaLM to help users create content and collaborate. Microsoft and Google claim their AI tools will boost productivity and creativity for users by automating tedious and repetitive tasks.
The specific impact of Microsoft and Google Copilot on future jobs has yet to be made clear, as these tools are still in the development or testing stages. However, some experts predict that they could positively and negatively affect employment. On the one hand, AI-powered tools like Copilot could enhance the productivity and quality of work for knowledge workers such as writers, editors, designers, and analysts. By automating routine and low-value tasks, they could free up time and mental resources for more creative and strategic tasks that require human judgment and expertise. This could improve job satisfaction, work-life balance, and innovation in these fields. AI-powered tools could also lead to the displacement of some jobs and the de-skilling of some tasks. For example, suppose Copilot becomes widely adopted. In that case, it could reduce the demand for specific jobs that involve writing, editing, or data analysis, especially those that can be easily automated or standardized. This could lead to job losses, income inequality, and skills mismatches, especially for workers with limited education, training, or access to technology.
Third Act: The Impact of AI on Ethics
AI-powered tools could raise ethical and legal concerns about intellectual property, privacy, and liability. For example, if Copilot generates content that infringes on someone's copyright, who is responsible for the infringement? Is it the user, the AI system, or the data source that trained the system? Similarly, if Copilot generates content that is biased, offensive, or harmful, who is responsible for the consequences? Is it the user, the AI system, or the company that develops and markets the tool?
To address these challenges, it is crucial to develop ethical and legal frameworks that govern the development, deployment, and use of AI-powered tools like Copilot. These frameworks should ensure transparency, accountability, and fairness in designing and operating AI systems and promote human values such as privacy, dignity, and autonomy. They should also involve multi-stakeholder participation and dialogue to reflect diverse perspectives and interests. Moreover, investing in education and training programs is essential to prepare workers for the changing nature of work in the AI era. These programs should focus on technical skills such as coding, data analysis, and machine learning, as well as soft skills such as communication, teamwork, creativity, and critical thinking. They should also be accessible and inclusive to all workers, regardless of social class, gender, ethnicity, or age.
In conclusion, AI-powered tools like Microsoft's and Google's Copilot can transform how we work and create value. They could enhance productivity, creativity, and innovation for knowledge workers and improve the quality of life for many people. However, they could also lead to job displacement, de-skilling, and ethical concerns if not properly governed and managed. Therefore, adopting a proactive and human-centered approach to AI development and deployment is crucial, considering all stakeholders' needs, values, and rights, including workers, consumers, and society. Only then can we ensure that AI serves as a force for good and helps us tackle some of humanity's biggest challenges, such as climate change, poverty, and healthcare. To achieve this, it's essential to have a robust ethical framework that guides the development and use of AI systems. This framework should consider AI's potential risks and impacts, such as bias, privacy violations, and job displacement.
Finally, ethical AI also involves considering the long-term impacts of AI on society and the environment. This means broader social and environmental goals, such as sustainability, social justice, and human well-being, should guide AI development. In conclusion, AI can potentially transform our lives in many positive ways, but ensuring that it is developed and used ethically and responsibly is vital. By putting a robust ethical framework in place, we can ensure that AI serves as a force for good and helps us tackle some of humanity's most pressing challenges.
I hope you found this newsletter valuable and informative; please subscribe now, share it on your social media platforms, and tag me as Iman Sheikhansari. I would love to hear your feedback and comments! If you could write in Persian, I suggest my finely tuned text-to-image model that works with Persian prompts and is optimized for AEC images. You can access it through the link below.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/impact-ai-social-class-jobs-closer-look-iman-sheikhansari
|
[
{
"date": "2023/03/01",
"position": 28,
"query": "AI job creation vs elimination"
}
] |
|
The Importance of Upskilling and Reskilling in the Age ...
|
The Importance of Upskilling and Reskilling in the Age of Automation
|
https://www.linkedin.com
|
[
"Cavendish Professionals",
"Talpro India Private Limited",
"Chris Bond",
"Mohammedali Patel",
"Data Science",
"Ai Enthusiast",
"Aspiring Data Analyst",
"Ml Engineer",
"Python",
"Sql"
] |
Both upskilling and reskilling are essential in the age of automation, as they enable workers to adapt to changing technologies and job requirements.
|
The world of work is changing rapidly, and automation and artificial intelligence (AI) are playing an increasingly significant role in many industries. As technology advances, many jobs that were previously done by humans are becoming automated, and new roles are emerging that require new skills and knowledge. This shift is creating a growing need for upskilling and reskilling to ensure that workers can stay relevant and competitive in the job market.
Upskilling refers to the process of improving and expanding an individual's existing skills, while reskilling involves learning new skills for a different job or career. Both upskilling and reskilling are essential in the age of automation, as they enable workers to adapt to changing technologies and job requirements.
One of the primary benefits of upskilling and reskilling is that it enhances job security. As automation continues to impact the workforce, many traditional jobs are at risk of being replaced by machines. However, by acquiring new skills and knowledge, workers can increase their value to their employers and make themselves more indispensable. This, in turn, can lead to greater job security and stability.
Another benefit of upskilling and reskilling is that it can lead to higher wages and better job opportunities. In many cases, workers who have acquired new skills or knowledge are more valuable to their employers and can command higher salaries. Additionally, workers who have diversified their skills are often more attractive to potential employers, as they bring a broader range of experience and expertise to the table.
The need for upskilling and reskilling is particularly acute in industries that are heavily impacted by automation, such as manufacturing and logistics. In these industries, many jobs that were previously done by humans are now being automated, and workers need to learn new skills to remain relevant. For example, workers in manufacturing may need to learn how to operate and maintain new types of machines, while those in logistics may need to develop skills in data analysis and supply chain management.
However, upskilling and reskilling are not only important for workers in industries that are heavily impacted by automation. In fact, all workers can benefit from acquiring new skills and knowledge, as it can help them stay competitive in the job market and adapt to changing technologies and job requirements. For example, workers in the healthcare industry may need to learn new technologies to keep up with the latest medical advances, while those in finance may need to develop new skills in data analysis and cybersecurity.
Fortunately, there are many resources available to workers who want to upskill or reskill. Online courses, workshops, and certification programs can all be valuable tools for acquiring new knowledge and skills. Additionally, many employers offer training and development programs to their employees, which can be an excellent way to learn new skills while on the job.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/importance-upskilling-reskilling-age-automation-edustation-official
|
[
{
"date": "2023/03/01",
"position": 1,
"query": "reskilling AI automation"
}
] |
|
What skills will be most valuable in the era of AI?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Public speaking and presentations: Being a good essay writer for coursework/homework will become less important when an AI can do a better job in a fraction of ...
|
As AI becomes more ingrained in every aspect of life and business, I think it's reasonable to expect the skills we need to be successful will change dramatically.
What skills do you think will be the most valuable to learn for succeeding in life over the next 10 years?
Here are a few examples I can think of:
Public speaking and presentations: Being a good essay writer for coursework/homework will become less important when an AI can do a better job in a fraction of the time. It simply doesn't seem valuable for society to ask students to write essays when we have a tool to do that. Instead, I believe that schools will start increasing the amount of oral examinations. As such, public speaking and presenting your ideas will become the new way to test a student's understanding.
Prompt engineering: If AI can help us perform tasks, then we need to learn how to speak its language. The people who master prompt engineering will be those who discover new ways to use AI and unlock its full potential.
Community building: Regardless of the technological revolution that has happened throughout humanity, our fundamental desires have stayed the same. We have, and probably always will, long to be a part of something bigger and to connect with others. I think this desire is likely to get even stronger as AI performs more and more of our tasks and we lose a sense of purpose. Learn how to build a community and almost any of your endeavours will be better positioned for success.
Interested in what everybody else thinks will be a useful skill to learn in the (near) future... whether it's a soft skill like communication, or a technical skill like NLP and prompt engineering.
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/ArtificialInteligence/comments/11gxw5y/what_skills_will_be_most_valuable_in_the_era_of_ai/
|
[
{
"date": "2023/03/01",
"position": 4,
"query": "AI skills gap"
}
] |
|
As a developer, I'm scared of AI replacing my job, is a PM ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
AI is so far from being able to replace jobs. If you haven't already please take an online course on ML and AI. You won't be worried after you see how far (or ...
|
Everyone used to say that AI will help but not replace jobs. Well, I'm a frontend developer who takes wireframes and designs frontend. GPT-4 can do it in minutes, what i can do in week.
Since a PM job is a generalist job which involves strategy and communication. I feel AI will help PM in their jobs but not replace them.
On the other hand, i feel AI will replace the software engineers who are basically doing 'code-monkey' type tasks, but not high level technical architects or tech leads. That means instead of needing 4 engineers, you would need two. However, you would still need a product manager.
Have you tried GPT-4 and what are your thoughts on this?
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/ProductManagement/comments/11vg5se/as_a_developer_im_scared_of_ai_replacing_my_job/
|
[
{
"date": "2023/03/01",
"position": 24,
"query": "AI skills gap"
},
{
"date": "2023/03/01",
"position": 49,
"query": "AI labor market trends"
}
] |
|
Attitudes, knowledge, and skills towards artificial ...
|
Attitudes, knowledge, and skills towards artificial intelligence among healthcare students: A systematic review
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Seyyedeh Fatemeh Mousavi Baigi",
"Department Of Health Information Technology",
"School Of Paramedical",
"Rehabilitation Sciences",
"Mashhad University Of Medical Sciences",
"Mashhad",
"Student Research Committee",
"Masoumeh Sarbaz",
"Kosar Ghaddaripouri",
"Varastegan Institute Of Medical Sciences"
] |
by SFM Baigi · 2023 · Cited by 169 — However, students' skill in AI was reported as average in two studies (33%), both conducted in LMICs. , Only 53 (11.3%) of the doctors in Ahmed et al.'s study ...
|
Ahmed, 2022, Pakistan 24 Determining knowledge, attitude, and practice of AI among doctors and medical students in Pakistan One hundred twenty‐nine participants (27.4%) strongly agree, and 221 people (47%) agree that AI is necessary for the field of medicine, while only 5 people (1.1%) strongly disagree and only 10 participants (2.1%) disagree Men have more knowledge about AI than women. Three hundred thirty‐five people (71.28%) had a basic concept of AI, but only 166 people (35.3%) knew about ML and DL, and only 109 people (23.2%) knew about its applications Only 53 (11.3%), including 20 medical students and 33 doctors, had applied to AI Most doctors and medical students do not have enough knowledge about AI and its applications, but they have a positive view of it in the medical field and are willing to accept it
Al Saad, 2022, Jordan 25 Estimating the level of knowledge about AI and DL among medical students in Jordanian universities Most participants (77.4%) believed that AI plays an important role in healthcare In the last 5 years, most of them never participated in any course (78.4%) Not mentioned Medical students appreciate the importance of AI and ML in medical advancements
AlAhmari, 2022, Saudi Arabia 26 Investigating the views of Saudi Arabian dental students on the impact of AI in dentistry 74% of participants agreed that AI would lead to major advances in dentistry, but 64% disagreed that AI could replace them in the future 22% had basic knowledge about AI technologies, and almost 37% knew about the application of AI in dentistry Not mentioned Most dental students are enthusiastic about the application of AI in dentistry and believe that AI can be effectively used for disease diagnosis
Alomary, 2021, Saudi Arabia 27 Determining medical students' understanding of ML in otolaryngology, head and neck surgery, and its applications in diagnosis and management One‐third of the respondents believed that using ML in otolaryngology is important due to the anatomical complexity (35.1%) Most of the students, in general, 308 (57.3%), were familiar with machine learning Not mentioned In general, students had a good knowledge of ML, although many were not familiar with the applications of machine learning in this field
Abouzeid, 2021, Saudi Arabia 28 Assessing dentists' (dental students, dental school graduates/interns, and postgraduate dentists) knowledge, attitudes, and understanding of the role of robotics (R) and AI in dental health Participants agreed that R and AI in dentistry are useful and provide better results Most dentists were not familiar with AI Not mentioned Most dentists were not familiar with R and AI. Dentists had a positive attitude towards R/AI, but its use and applications were limited due to insufficient knowledge and understanding
Bisdas, 2021, 63 countries around the world 29 Assessing the attitude of medical and dental students towards AI Most students agree that AI advances will make medicine and dentistry more exciting (69.9%). They stated that AI will be a part of medical education (85.6%) and are eager to incorporate AI into their future activities (99%) Not mentioned Not mentioned Students have a basic understanding of the principles of AI, have a positive attitude towards AI, and are willing to incorporate it into their education
Blease, 2022, Ireland 30 Assessing the experiences and opinions of final‐year medical students across Ireland regarding their exposure to AI/ML during their course of study Medical students reported limited knowledge and training about AI/ML Not mentioned Not mentioned To help address educational gaps, we suggest medical schools consider short‐term, interdisciplinary courses in digital health, including understanding and augmented intelligence, to empower students to keep up with technological advances
Boillat, 2022, United Arab Emirates 31 Identifying the level of familiarity of medical students and doctors with AI in medicine, as well as the challenges, obstacles, and possible risks related to the democratization of this new paradigm Medical students perceived AI in medicine as leading to higher risks for patients and the medical field We also identified a relatively low level of familiarity with AI (medical students = 5.211; physicians = 5.06) and low attendance at education or training Not mentioned The low level of familiarity with AI identified in this study calls for the implementation of training in medical schools and hospitals to ensure that medical professionals can use this new paradigm and improve health outcomes
Brandes, 2020, Brazil 32 Evaluating the effect of AI on the choice of radiology major by medical students More than half (52.5%) said they believe AI is a threat to the radiology job market 64.3% claimed they did not know enough about these new technologies, and 31.7% said they wanted more information about how they work Not mentioned A significant proportion of surveyed students perceive AI as a threat to radiological practice that affects their career choice
Banerjee, 2021, the UK 33 Investigating the effect of AI technologies on the clinical training of doctors in postgraduate studies The majority (58%) perceived an overall positive impact of AI technologies on their education and training. Most respondents also agreed that AI would reduce clinical workload (62%) and improve research and audit training (68%) The majority reported adequate AI training in their current curricula (92%) and supported having more formal AI training (81%) Not mentioned Practitioners have a generally positive perception of the impact of AI technologies on clinical education
Bin Dahmash, 2020, Saudi Arabia 34 Investigating medical students' perceptions of the impact of AI on radiology and the impact of this perception on choosing the field of radiology as a lifelong career 50% of the participants believed that they had a good understanding of AI When AI knowledge was tested using five questions, only 22% of the questions were answered correctly Not mentioned Concerns that AI might replace radiologists in the future had a negative impact on medical students' perception of radiology as a career
Pinto Dos Santos, 2019, Germany 18 Evaluation of medical students' attitudes towards AI in radiology and medicine Medical students are not worried about AI replacing human radiologists About 52% were aware of current discussions about AI in radiology Not mentioned Contrary to media anecdotes, undergraduate medical students are not worried about AI replacing human radiologists and are aware of the potential applications and implications of AI in radiology and medicine
Ejaz, 2022, the UK 35 A report on the state of AI in medical education worldwide, examining the perspectives of medical students There was support for the inclusion of AI education in mainstream curricula around the world Few students had received AI training Not mentioned Medical students from all countries should be offered AI training as part of their curriculum to develop skills and knowledge about AI and ensure a patient‐centric digital future in medicine
Gong, 2019, Canada 19 Examining Canadian medical students' perceptions of the impact of AI on radiology and their impact on students' preference for radiology specialization Only a minority (29.3%) of respondents agreed that AI would displace radiologists in the foreseeable future, but a majority (67.7%) agreed that AI would reduce the demand for radiologists Not mentioned Not mentioned Anxiety about the “displacement” (not “replacement”) of radiologists by AI has dissuaded many medical students from considering a radiology specialty
Jussupow, 2022, Germany 36 Investigating how medical professionals perceive resistance to AI due to threats to professional identity and time perception of AI systems Novice doctors showed relatively high resistance to and threat from AI, while experienced doctors showed slightly lower resistance and threat Not mentioned Not mentioned AI systems can be seen as a threat to the identity of the medical profession
Kansal, 2022, India 37 Assessing knowledge of the basic principles, limitations, and applications of AI in healthcare among medical students and physicians in developing countries Most participants felt that AI would play an important role in the delivery of healthcare services in the future (74.4%) They were unaware of the applications (79.6%) and limitations of AI (82.8%) Not mentioned Formal training courses for teaching about AI should be focused on medical schools and hospitals to facilitate the coherent and scientific dissemination of knowledge
Kasetti, 2020, Britain 38 Assessing medical students' understanding of AI in medicine 83% of students believed that AI plays an important role in medicine Most participants were aware of the role of AI in medicine and radiology Not mentioned AI is growing rapidly, so doctors need to be prepared and aware of it
Khanagar, 2021, Saudi Arabia 39 Assessment of knowledge, attitude, and perception of dental students in Riyadh, Saudi Arabia, towards AI 46.8% strongly agree that AI will lead to major advances in dentistry and medicine 50.1% had no basic knowledge about the working principles of AI. Also, the majority did not know about the use of AI in dentistry (55.8% no) Not mentioned Dental students were eager to learn more about new technologies related to dentistry. To improve the knowledge of dental students about AI, lectures, training courses, and scientific meetings should be given much attention
Khafaji, 2022, Saudi Arabia 40 Assessing knowledge and understanding of AI among radiology residents across Saudi Arabia and assessing their interest in learning AI Approximately 43.5% of participants did not expect AI to affect jobs, while 42% predicted that jobs would decrease. Approximately 53% expected a decrease in reporting workload, while 28% expected an increase in workload Sixty‐four people (41.6%) of the residents reported familiarity with AI Not mentioned Radiologists' exposure to AI is insufficient. AI must be introduced to radiology trainees
Ooi, 2021, Singapore 41 Evaluating the attitudes and learning needs of radiology residents and radiologists regarding AI and ML in the field of radiology The majority agreed that AI/ML would drastically change radiology (88.8%) 64.8% considered their understanding of AI/ML to be beginner level Not mentioned Growing optimism about technologically changing radiology and the implementation of AI/ML has led to strong demand for AI/ML curriculum in residency training
Pauwels, 2021, Brazil 42 Investigating the attitudes of Brazilian dentists and dental students regarding the impact of AI in oral radiology and investigating the impact of an AI introductory lecture on their attitudes Mixed responses were found regarding concerns about the development of AI (33.5% agree) and the replacement of oral radiologists with AI programs in the next 15 years (22.9% agree) 63% of participants were unfamiliar with the application of AI in radiology, and a significant amount (24.7%) assessed that they already had a basic understanding of the technology Not mentioned An overall positive attitude towards AI was found. An introductory lecture benefited this attitude and alleviated concerns about the impact of AI on the oral radiology profession
Qurashi, 2021, Saudi Arabia 43 Studying the familiarity of Saudi Arabian radiology personnel with AI applications and its usefulness in clinical practice Most participants (n = 214, 95.5%) expressed a strong interest in AI training and would like to incorporate it into clinical radiology practice. Almost half of the radiography students (22/46, 47.8%) believe that their careers may be at risk due to the use of AI (p = 0.038) Most respondents (n = 160, 71.4%) reported no formal training on AI‐based applications 82% of participants (184) had never used AI in their departments Participants showed a positive attitude towards AI, a reasonable understanding, and a high motivation to learn and incorporate it into clinical practice. Some participants felt their jobs were threatened by adapting to AI, but this belief may change with the right training programs
Rainey, 2021, the UK 44 It was to determine knowledge, skills, and confidence in AI among UK radiographers and highlight priorities for training providers to support the digital healthcare ecosystem Diagnostic radiographers stated that they felt confident or very confident in using AI technologies in radiography compared with radiotherapy responses (28.2% and 33.8%, respectively) Many respondents stated that they understood the concept of AI in general (78.7% for diagnostic respondents and 52.1% for therapeutic radiography respondents, respectively). 57% of diagnostic and 49% of radiotherapy respondents feel they are not sufficiently trained to implement AI in the clinical setting 52% and 64% said they had not developed any AI skills, while 62% and 55% said there was insufficient AI training for radiographers The results of this survey not only highlight the lack of knowledge, skills, and confidence of radiographers in using AI solutions, but also the need for formal training in AI to prepare the current and future workforce for the future clinical integration of AI in healthcare
Scheetz, 2021, Australia and New Zealand 45 To investigate the perceptions of ophthalmologists, radiologists/radiation oncologists, and dermatologists about AI The majority (449 = 71.0%) believed that AI will improve the field of medicine and that the needs of the medical workforce will be affected by this technology in the next decade (n = 542, 85.8%) Almost half of the respondents (47.6%; n = 301) rated their knowledge of AI as average compared with their peers Most respondents indicated that they had never used AI applications in their work (511, 80.9%) Most respondents in the survey perceived the introduction of AI technology in their respective fields as a positive development
Santos, 2021, 94 countries around the world Investigating the knowledge of medical physicists about AI and their understanding of the relevance and impact of AI in the practice of medical physics An overwhelming majority of survey respondents (91%) agree that AI will play a central role in the practice of medical physicists Only 34% can confidently say they have a working knowledge of AI 22% think they have the relevant expertise in AI, and 53% do not have the right skills AI can help automate and speed up processes, allowing medical physicists to focus on areas that need improvement. Most people agree that AI knowledge should be taught to new generations
Sit, 2020, the UK 47 Examining the attitude of medical students in England (UK) about AI, their understanding, and career intention towards radiology and investigating the state of education related to AI among this group Most respondents believe that AI will play an important role in healthcare in the future (88%, n = 432) Not mentioned Not mentioned UK medical students understand the importance of AI and are eager to get involved
Teng, 2022, Canada 14 Investigating and identifying gaps in Canadian healthcare students' knowledge of AI Most participants reported a positive outlook on the development of AI in their respective healthcare fields and believed that AI would impact their jobs. However, concern about job loss was a common theme among healthcare students More than half of the respondents either did not know what AI is (51.08%) or had the wrong understanding of it (631.2%) Not mentioned The lack of understanding of AI indicates an urgent need for education, as healthcare providers may increasingly need to use AI applications in their activities
Wood, 2021, the United States 48 An integrated medical education curriculum assesses the attitude of medical students and professors towards AI to prepare for teaching AI basics and data science applications in clinical practice Students and faculty stated that AI would revolutionize medical practice, improve some aspects of healthcare, and should be part of medical education, and disagreed with the statement that AI technology threatened their jobs 30% of students and 50% of professors answered that they know about AI issues in medicine Almost half (45%) of students use some type of AI application Professors and students are very interested in teaching AI in various subjects, and there is a strong need to prepare instructors to teach various aspects of AI technologies
Yurdaisik, 2021, Turkey 49 Investigating the knowledge and attitude of radiology department employees about AI 35.3% thought AI applications would have a negative impact on radiologists' careers, while 30.3% thought these applications would have a positive impact 47.1% of participants reported having sufficient knowledge about AI applications in general, while only 25% stated that they had sufficient knowledge about AI applications in radiology Not mentioned Healthcare workers in radiology departments are concerned that AI will replace them soon. Raising the knowledge of radiology staff is important to help develop AI applications in radiology
Yüzbaşıoğlu, 2021, Turkey 50 Evaluation of dental students' knowledge and attitude towards AI and possible applications in dentistry While most participants agreed that dentistry would be revolutionized by AI (85.70%), half of the participants did not agree that AI could be replaced shortly 48.40% of the participants (n = 534) had basic knowledge about AI technologies Not mentioned Although the participants do not have sufficient knowledge of AI, they are willing to improve their knowledge in this field. The results of this survey showed that students feel the use of AI in dentistry is useful
Reeder, 2022, the United States 51 Investigating the impact of AI on US medical students' choice of radiology as a career and their opinions AI significantly reduced students' preference for radiology ratings (p < 0.001). One‐sixth of students who chose radiology as their first choice did not do so because of AI, and almost half of those who considered radiology in their top three choices were concerned about AI Not mentioned Not mentioned AI significantly negatively affected US medical students' choice of radiology as a career
Park, 2021, the United States 52 A survey of US medical students' views of radiology and other medical specialties regarding AI More than 75% of respondents agreed that AI would play an important role in the future of medicine. Most of them (66%) agreed that diagnostic radiology was the most affected specialty. Nearly half (44%) reported that AI made them less enthusiastic about radiology Not mentioned Not mentioned US medical students believe AI will play an important role in medicine, especially radiology. However, almost half are less interested in radiology because of AI
Tran, 2021, Vietnam 53 Development of a theoretical model to explore the behavioral intentions of medical students to adopt an AI‐based diagnosis support system Effort hope (β = 0.201, p < 0.05) and social influence (β = 0.574, p < 0.05) had a positive relationship with initial trust, while there was no relationship between performance expectation and initial trust (p > 0.05) was not found. Only social influence (β = 0.527, p < 0.05) was related to behavioral intention in a positive way Not mentioned Not mentioned This study highlights the positive behavioral intentions towards using an AI‐based diagnosis support system among prospective Vietnamese physicians and the influence of social influence on this choice
Oh, 2019, South Korea 54 Examining the knowledge of medical students and Korean doctors about AI and evaluating their attitude towards the medical application of AI Most participants found AI useful in the medical field (558/669, 83.4% agreement). Respondents agreed that the area of medicine where AI is most useful is disease diagnosis (558/669, 83.4% agreement) Only 40 people (5.9%) answered that they were familiar with AI. One possible problem mentioned by the participants was that the AI could not help in unexpected situations due to insufficient information (196/669, 29.3%) Not mentioned Korean doctors and medical students have a favorable attitude towards AI in the medical field. Most of the doctors surveyed believed that AI would not replace their role in the future
van Hoek, 2019, Switzerland 55 Assessing the views of radiologists, surgeons, and medical students on several important topics regarding the future of radiology, such as AI, teleradiology, and 3D printing While most participants agreed that AI should be included as a support system in radiology (Likert scale 0–10: median value 8), surgeons were less supportive than radiologists (p = 0.001). Students saw the potential risk of AI more than radiologists (p = 0.041) Not mentioned Not mentioned Given AI, radiologists expect their workflow to become more efficient and tend to support the use of AI, while medical students and surgeons are more skeptical of the technology. Medical students see AI as a potential threat to diagnostic radiologists, while radiologists themselves are relatively fearful
Dumić‐Čule, 2020, Croatia 56 Assessing attitudes about the importance of introducing AI education into medical school curricula among physicians whose daily work is significantly affected by AI The responses showed very high support across age groups regardless of subspecialty area. A large majority of participants—89.6% (95% Agresti—CI 0.83–0.94) agreed on the need to include AI education in medical curricula Not mentioned Not mentioned The results of the study showed strong agreement among radiologists and radiology residents about the need for AI training to be part of medical school curricula
Auloge, 2020, Europe 57 Assessment of awareness and knowledge of interventional radiology (IR) in a large population of medical students in 2019 34.8% of participants answered that AI is a threat to radiologists. Not mentioned Not mentioned The development of new technology supporting AI advances will likely continue to change the radiology landscape. Most medical students want more information about IR in their medical curriculum. About a quarter of students are interested in a career in IR
| 2023-03-12T00:00:00 |
2023/03/12
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC10009305/
|
[
{
"date": "2023/03/01",
"position": 67,
"query": "AI skills gap"
}
] |
The only skills-based AI Talent Marketplace solving ...
|
The only skills-based AI Talent Marketplace solving talent retention and workforce mobility for over 10 years.
|
https://www.linkedin.com
|
[
"View Profile"
] |
The only skills-based AI Talent Marketplace solving talent retention and ... Bridging the Financial Skills Gap: The Top Skills Needed for the Future.
|
Sign in to view more content
Create your free account or sign in to continue your search
Sign in Welcome back Email or phone Password Show or By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy. New to LinkedIn? Join now or
New to LinkedIn? Join now
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/posts/fuel50_ai-talent-marketplace-platform-overview-activity-7044468474970046464-MUkJ
|
[
{
"date": "2023/03/01",
"position": 76,
"query": "AI skills gap"
}
] |
|
Artificial Intelligence, Education 4.0
|
Abstract View
|
https://library.iated.org
|
[
"J. Udvaros",
"N. Forman"
] |
by J Udvaros · 2023 · Cited by 46 — Abstract: Investing in holistic skills development in primary and secondary education will be key to addressing the root causes of the global skills gap, ...
|
ARTIFICIAL INTELLIGENCE AND EDUCATION 4.0
Budapest Business School (HUNGARY)
About this paper:
Publication year: 2023
Pages: 6309-6317
ISBN: 978-84-09-49026-4
ISSN: 2340-1079
doi: Appears in: INTED2023 Proceedings Publication year: 2023Pages: 6309-6317ISBN: 978-84-09-49026-4ISSN: 2340-1079doi: 10.21125/inted.2023.1670 Conference name: 17th International Technology, Education and Development Conference
Dates: 6-8 March, 2023
Location: Valencia, Spain
| 2023-03-01T00:00:00 |
https://library.iated.org/view/UDVAROS2023ART
|
[
{
"date": "2023/03/01",
"position": 89,
"query": "AI skills gap"
}
] |
|
Maximizing AI's potential in the workplace - Lucid Software
|
Maximizing AI’s potential in the workplace: New data highlights the barriers and benefits
|
https://lucid.co
|
[
"Digital Transformation",
"Product Development",
"Teamwork",
"Lucid Tips",
"Ideation",
"Ai In The Workplace",
"Change Management",
"Cloud Migration",
"New Product Development",
"Efficiency Through Ai"
] |
AI adoption in organizations has soared due to AI's potential to help teams work more efficiently and effectively. Over 50% of respondents believe that AI will ...
|
When it comes to AI, one thing’s for sure: It has the power to transform the workforce. But just how it can do so isn’t so clear. What can organizations do to realize the full potential of AI? And what’s holding some back? To shed light on the many unknowns surrounding AI in the workforce, Lucid conducted a survey of more than 2,500 knowledge workers globally. We’ve uncovered the top benefits, use cases, and gaps surrounding AI in the workplace. The biggest gap of all? The perception gap between how executives and employees view and apply AI. The data shows that, for organizations to reap the full benefits of AI, they must understand what barriers are holding back their workforce and work to close this gap.
The promise of AI: What’s driving AI adoption? AI adoption in organizations has soared due to AI’s potential to help teams work more efficiently and effectively. Over 50% of respondents believe that AI will save them three or more hours a week. The top drivers of AI adoption reported in our survey were: Improved productivity (cited by 62% of respondents)
Automation of repetitive tasks (49%)
Integration with existing workflows (41%)
Cost savings with consolidated tech stack (40%)
Enhanced communication and decision-making (38%) How do these desired outcomes stack up against the actual outcomes reported? Survey respondents cited already experiencing the following benefits from AI: Increased productivity (cited by 43% of respondents)
Improved accuracy and reduced errors (30%)
Faster documentation that aligns teams (27%)
Easier time sorting/organizing ideas (27%)
Better decision-making (23%) It’s clear that while organizations are already seeing some of the positive effects of AI, there is plenty of room for improvement. Top use cases of AI in the workplace To understand how workers can get more out of AI, we need to understand how they’re currently using it. The data shows that over a third of workers are familiar with and use AI for basic use cases, with the top being: Generating ideas (39%)
Creating content (37%)
Communicating summaries (33%)
Finding documentation (31%) While these are all fantastic ways to save time with AI, there are far more opportunities to use AI than organizations are giving it credit for. Only 26% of respondents cite using AI for synthesizing ideas or research, and only 19% are using AI for designing diagrams. By looking for ways to implement AI across the entire workflow, organizations may be able to save time and effort in places they wouldn’t have thought possible. Regardless of how workers are using AI, most (58%) believe that human input should always be primary, with AI as a support tool.
More AI use cases Read one example of using AI to save time across the entire workflow. Check it out
How do workers feel about the rise of AI in the workplace? Overall, the workforce is generally optimistic about AI. Over half (63%) of respondents believe AI will positively impact their work-life balance, and 62% feel it will lead to greater job satisfaction. However, this data is disproportionately skewed toward leadership, with 68% of executives believing AI will positively impact their job satisfaction, compared to 53% of managers and only 37% of entry-level workers. This sentiment translates into AI usage as well. Executives are leading the charge, with 83% of executives citing using AI-powered collaboration tools, compared to only 42% of entry-level workers. Executives are also embracing AI more frequently for their daily tasks and collaboration (54%), while entry-level workers lag behind (21%). In fact, nearly half (48%) of entry-level workers use AI tools less than once a month. This data indicates that while executives may be excited to limit their execution tasks and spend more time on strategic work, the people doing the work are far less eager. So, what’s holding employees back from fully embracing AI? Let’s take a look. Top challenges and concerns in AI adoption It’s no surprise that such a powerful new technology would come with its share of challenges. Here are the main barriers organizations face as they determine how to optimize AI for their workforce. Data security and privacy concerns Not surprisingly, security and privacy were top of mind among our survey respondents, with 40% expressing concerns about data security with AI. The good news is that 88% of companies are actively implementing strict guidelines to safeguard their business and employees. The data revealed greater discrepancies regarding policy implementation, though. While 67% of respondents think clear guidelines and policies are necessary to ensure the responsible use of AI, only 29% of entry-level employees are confident that their company has these in place. However, 70% of executives say their company has established these policies, indicating the need to make these guidelines more transparent or communicate them more frequently.
How AI changes the threat landscape Hear Lucid’s security experts discuss the evolution of cyber threats and what this means for organizations. Watch the on-demand webinar
An AI skills gap One of the reasons workers may not be using AI is because they don’t know how. Over a third (33%) of our survey respondents cited the need for continuous training to be a top challenge when implementing AI. What’s more, 41% of entry-level workers feel hardly or not at all knowledgeable about AI-powered features, compared to just 10% of executives. Given how quickly the AI landscape changes, it’s clear that workers could use more education and training to stay in the know. Only 27% are receiving work-sponsored AI training, and while executives may be inclined to engage in independent AI education several times a week (39%), only 13% of entry-level employees and 20% of managers are doing the same.
The top AI skills every worker should know Discover the AI skills that are essential for the workplace and how to learn them. Read more
Resistance to change AI represents a significant change, and many employees may not be ready to learn a new technology or tool. In fact, 37% of knowledge workers report feeling hesitant about using AI-powered collaboration tools, with 26% indicating that the reason they’re hesitant about AI is simply because they prefer traditional methods and tools. It’s also worth noting that roughly one-third (33%) of respondents are worried AI could make their job replaceable. Given this data, it’s not surprising that 33% of respondents cite resistance to change as a top challenge when implementing AI. Executives will need to practice change management principles, cast a clear vision around the benefits of AI, and listen to their employees' concerns to help their workforce embrace the change. Final thoughts Whether you feel nervous, excited, or cautiously optimistic about AI, there’s no doubt it’s already impacting the workplace. After all, AI shows promise in the workplace—from increasing productivity to enhancing decision-making—but these benefits are muted by concern, reluctance, and lack of knowledge. To get the most out of AI, executives can take intentional steps to bring the rest of the organization with them on the AI journey, such as providing support and education about the most impactful ways to use AI.
Applying AI impactfully Learn how to get more out of AI by applying it to common business challenges. Learn more
| 2023-03-01T00:00:00 |
https://lucid.co/blog/ai-adoption-survey-2024
|
[
{
"date": "2023/03/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 9,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 10,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 7,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 8,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 4,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 4,
"query": "workplace AI adoption"
}
] |
|
AI in the workplace: Bridging the adoption gap - Interface
|
AI in the workplace: Bridging the adoption gap
|
https://interface.media
|
[
"Harry Menear",
"David Torgerson"
] |
The adoption of AI in the workplace has been significant, sweeping through businesses at breakneck speed. Almost half (42%) are already ...
|
The adoption of AI in the workplace has been significant, sweeping through businesses at breakneck speed. Almost half (42%) are already embracing these powerful tools. Another 40% are actively experimenting. But alongside momentum comes with its challenges. As organisations deploy increasingly sophisticated AI systems, they also face heightened security risks and navigate uncertain regulatory ground; protecting both operations and human talent requires robust, forward-thinking safeguards.
Equally as important to the success of AI is the operational foundation. Many organisations struggle with the absence of a clear AI roadmap, leaving them unable to progress beyond initial experimentation and ultimately fail to scale responsibly across teams. Without addressing this fundamental planning gap, organisations risk missing out on the transformative potential of AI to drive operational excellence, competitive differentiation, and sustainable growth. To truly harness AI’s potential – from driving efficiency to unlocking long-term growth – organisations must move beyond experimentation and invest in intentional planning.
Realising AI’s full potential
A survey conducted by Lucid Software revealed 49% of workers use it to automate repetitive tasks — freeing them to focus on higher-value work instead. Workers also recognise AI’s broader potential. Some cited improved productivity (62%), as well as seamless integration with existing workflows (41%), cost savings through consolidated tools (40%), and enhanced communication and decision-making (38%) as key potential benefits of AI adoption.
Yet, despite decision-making being a top advantage, only 23% of workers currently use AI for this purpose. Bridging this gap will require a thoughtful, inclusive approach — aligning AI with business objectives and continuously refining its role to maximise its impact.
A divide in perspectives
While there’s broad optimism about AI’s potential, the enthusiasm varies across organisational levels. For instance, 68% of executives believe AI will enhance their job satisfaction. However, this drops to 53% among managers and is only 37% among entry-level employees. This disparity highlights a critical challenge. If organisations want to successfully implement AI, they must bridge this perception gap and demonstrate its value to employees at all levels.
Many workers are already using AI for basic tasks, but its full potential remains untapped. Only 26% use AI for synthesising ideas or research, and just 19% leverage it for designing diagrams. This suggests that while AI adoption is growing, organisations have yet to integrate it in ways that drive meaningful innovation.
The key to AI’s effectiveness lies in its intentional integration. Organisations must align AI with existing workflows to enhance productivity without creating friction. A common misconception about implementing AI is that it’s only useful if it produces perfect results. However, that mindset overlooks its true value.
Right now, AI isn’t ready to replace entire workflows. It’s most effective when augmenting specific tasks, removing bottlenecks, and enabling teams to focus on higher-value work. Organisations that recognise and embrace this incremental approach will see the greatest impact.
Tackling challenges head-on
While 88% of companies are implementing AI guidelines to protect their operations and employees, communication around these efforts is lacking, leading to confusion and misalignment. For example, only 29% of entry-level employees feel confident their company actually has these rules in place. Combined with concerns around job security (33%), this has resulted in a third of businesses reporting a resistance to change as a top challenge when implementing AI.
As AI continues to evolve, the need for ongoing education and training becomes increasingly critical.
Executives are more likely to seek independent learning opportunities, 39% compared to 13% for entry-level workers. This underscores the need for an intentional, accessible, and continuous AI education framework for all employees. Effective change management strategies that communicate AI’s benefits, address concerns empathetically, and involve employees in the transition can build trust and demonstrate that AI complements rather than replaces human effort.
The journey to success
Workplace attitudes towards AI are mixed, ranging from enthusiasm to unease. Despite AI’s ability to enhance productivity and decision making, these advantages are often overshadowed by anxiety, resistance, and lack of understanding.
To address these challenges, leadership must implement deliberate strategies to create organisational alignment, provide comprehensive support systems, and deliver targeted training on AI utilisation. By cultivating collective understanding and equipping team members with appropriate resources, companies can maximise the transformative benefits of AI.
| 2025-07-01T00:00:00 |
2025/07/01
|
https://interface.media/blog/2025/07/01/ai-in-the-workplace-bridging-the-adoption-gap/
|
[
{
"date": "2023/03/01",
"position": 15,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 18,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 17,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 15,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 15,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 16,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 15,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 19,
"query": "workplace AI adoption"
},
{
"date": "2025/07/01",
"position": 18,
"query": "workplace AI adoption"
}
] |
What does AI adoption in the workplace mean? - FAQ
|
What does AI adoption in the workplace mean?
|
https://convergencenetworks.com
|
[] |
AI adoption in the workplace refers to the integration and use of artificial intelligence technologies and tools within an organization's operations, processes, ...
|
Our core mission as a company is to help and empower people. We want to lend our time and resources to these organizations as way to give back and support all they do for our communities.
| 2023-03-01T00:00:00 |
https://convergencenetworks.com/faqs/what-does-ai-adoption-in-the-workplace-mean/
|
[
{
"date": "2023/03/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 25,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 29,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 25,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 25,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 27,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 26,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 25,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 29,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 26,
"query": "workplace AI adoption"
}
] |
|
AI adoption in workplace nearly doubles: Gallup - AOL.com
|
AI adoption in workplace nearly doubles: Gallup
|
https://www.aol.com
|
[
"Aol Staff",
"Miranda Nazzaro",
"June",
"At Pm"
] |
A Gallup study, released Monday, found the share of US employees who say they have used AI in their role a few times a year nearly doubled from 21 percent to ...
|
The use of artificial intelligence (AI) in the workplace has nearly doubled over the past two years, according to a new survey.
A Gallup study, released Monday, found the share of U.S. employees who say they have used AI in their role a few times a year nearly doubled from 21 percent to 40 percent in the past two years.
More frequent use of AI at work, defined as a few times a week or more by Gallup, also increased from 11 percent to 19 percent since Gallup first measured in 2023.
In the past year alone, daily use of AI doubled from 4 percent to 8 percent, Gallup found.
The findings come amid a broader push to incorporate AI into various industries to boost efficiency and workflow. Various studies show an increasing number of workers are harnessing AI tools at work.
While more workers are embracing the emerging technology, concerns have been raised about its threat to their jobs being altered or eliminated as a result.
Although workplace AI use is increasing, Gallup found employees are no more likely to see themselves replaced by the technology soon. About 15 percent of employees say it is very or somewhat likely that automation, robots or AI will eliminate their job within the next five years, according to the survey.
And only 16 percent strongly agreed the AI tools for their organization are useful for their work.
Gallup further found AI adoption increased primarily among white-collar roles, with 27 percent of white-collar employees reporting frequent use of AI at work. This is a 12 percent increase since last year, Gallup said.
Meanwhile, production and front-line workers reported slightly less frequent AI use from 2023, decreasing from 10 percent to 9 percent this year.
Several employees reported they are using AI without guardrails or guidance, Gallup said. About 44 percent of employees surveyed said their workplace started integrated AI, but only 22 percent said they have not received a clear plan or strategy for this.
The quarterly Gallup workforce study was conducted with self-administered web surveys among a random sample of adults working full-time and part-time for organizations in the United States. The sampling of error varied based on different topics and time frames, Gallup said.
Copyright 2025 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
For the latest news, weather, sports, and streaming video, head to The Hill.
| 2023-03-01T00:00:00 |
https://www.aol.com/ai-adoption-workplace-nearly-doubles-201642723.html
|
[
{
"date": "2023/03/01",
"position": 30,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 29,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 30,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 30,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 30,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 29,
"query": "workplace AI adoption"
}
] |
|
The top AI adoption challenges (+ solutions) in the workplace
|
The top AI adoption challenges (+ solutions) in the workplace
|
https://lucid.co
|
[
"Digital Transformation",
"Product Development",
"Teamwork",
"Lucid Tips",
"Ideation",
"Expert Tips",
"Recent Survey",
"Change Management Frameworks",
"Identify Opportunities For Using Ai",
"Divergent Thinking"
] |
In this blog post, we'll examine three of the greatest AI adoption challenges affecting workers today and provide pragmatic approaches to overcoming them.
|
Despite all the buzz we’ve heard around AI lately, many workers are struggling to embrace this new technology. Lucid’s recent survey shows that only 42% of entry-level workers are using AI-powered collaboration tools. What’s preventing more people from adopting AI into their workflow? Undoubtedly, there are significant technical, security, and privacy challenges to consider when adopting AI. But some of the most complex challenges stem not from the technology itself but rather the implications it has on the people using it. AI adoption, after all, comes with a great deal of uncertainty and change. In this blog post, we’ll examine three of the greatest AI adoption challenges affecting workers today and provide pragmatic approaches to overcoming them. Challenge #1: AI initiatives don’t align with broader business goals Whether due to internal pressure or the allure of AI's productivity gains, organizations have been eager to jump on the AI bandwagon. But those who did so without clear goals or strategies for actually using AI are likely struggling to see the full benefits AI offers. Experimentation, of course, is incredibly valuable for learning, but before you jump straight into this step, you need to start with a well-developed plan. Put another way, your AI goals must align with your overall business strategy. If you’re not intentional about where and how you’re applying (or experimenting with) AI, it can end up having the opposite effect on employee morale and productivity from what it’s intended to have. Here’s the real kicker: Without a plan, you’ll have no way to measure return on investment (ROI). How will you know if AI is just an added expense for the business or if it’s accelerating earnings, making teams more efficient, or reducing risk? Solution: Create a clear value case around AI If you’re struggling to see the benefits of AI, take some time to map out your business’s specific value case for the technology—in other words, why are you implementing AI in the first place? To identify areas of the business where AI would be beneficial, you’ll want to consider two main factors: your current business opportunities and AI’s current and future capabilities. “I often refer to this process as working from ‘opportunities out’ and ‘technology in,’” says Patrick Saul, solutions consultant on Lucid’s professional services team. “You can start with the business opportunity and work your way out to how a new technology would support it. Or, start with the technology and its capabilities and allow that to guide you towards the right opportunities to focus on today.”
Try the technology value mapping template to identify your value case for AI. Click on the template to get started.
Typically, these opportunities will take the form of either ways to improve the bottom line—such as cutting costs or improving efficiency—or market opportunities to capitalize on, such as a new avenue for revenue and growth. For example, a trading firm may consider this market opportunity: How much additional revenue could be made if we could clone our best trader? Or, a manufacturer may consider this opportunity for improvement: How much could we reduce our routine inspection time by incorporating AI and robotics into the process? By creating clear goals around your AI adoption, you’ll be better able to measure outcomes and progress toward those goals. “Like any learning program of this type, there should be expected, measurable outcomes, even if those are measures of the number of experiments or rate of learning,” says Dan Lawyer, CPO at Lucid. “At some point, these experiments will turn into measurable and reproducible use cases that can be shared as best practices that truly accelerate the business.”
Measuring innovation Learn how to set goals and metrics for measuring innovation and experimentation around AI. Check it out
Challenge #2: AI represents change and uncertainty for teams 33% of workers consider resistance to change to be a top challenge when implementing AI, Lucid’s survey shows. AI disrupts the status quo, and getting used to a new way of working isn’t easy. 26% of survey respondents indicated that they’re hesitant about AI simply because they prefer traditional methods and tools. Perhaps even more challenging is that not all resistance comes from adjusting to new tools—many people also fear what AI means for their jobs. One out of three workers are worried that their jobs could be replaced by AI. What can organizations do to help their people feel comfortable and confident when using AI? Solution: Prioritize your change management strategy Your change management strategy should be a critical part of your enterprise AI adoption strategy, not an afterthought. There are many change management frameworks you can follow, but, regardless of which you choose, we recommend you keep the following tips in mind: Develop—and communicate—your case for change. If you’ve done the work of mapping business opportunities to AI capabilities, you’ll already have solid reasoning for the change. Now the trick is communicating those benefits to the rest of your workforce. Get specific on how AI will save time, improve work-life balance, or solve key problems for the people at your organization. Be empathetic in your communication and carefully address peoples’ fears. Remind your workforce that AI is not here to replace them; it’s here to augment their work—and, more importantly, help them. “One way you can minimize fear is by clearly differentiating jobs from tasks. AI is a great tool for performing certain, often monotonous, tasks in a workflow—like summarizing content or creating outlines—not for replacing entire jobs.” —Patrick Saul, solutions consultant at Lucid Embrace input across the organization. Lucid’s survey revealed that executives are embracing AI far more readily than the rest of the workforce, with 83% of executives using AI-powered collaboration tools compared to only 42% of entry-level workers. This gap shows just how important it is to talk to teams across the business and gather their feedback on where and how AI could be implemented.
“One strategy is to engage individuals in pilot programs and collaborative design early in the process,” says Saul. “Encourage them to define and help address their own concerns with AI. Then, reframe their concerns in ways that are more intuitive and human-centric.” For example, if they’re concerned that AI will provide incorrect information, ask them to consider how they’d validate the information if it came from a person, rather than AI. This reasoning by analogy is a common tool used in the human-centric design process, and it will allow you to ease concerns while creating buy-in for the change. Share success stories across the organization. Seeing innovative ways others are using AI in the organization can inspire individuals to embrace and experiment with AI themselves. “Create internal forums where users can share positive and negative examples of how they have used AI,” explains Lawyer. “Including some executive leaders in these forums will help set the tone and expectation for others in the org.”
Change management guide Get the step-by-step guide to leading effective change at your organization. Get the guide
Challenge #3: Teams don’t know how to use AI Some people are fearful of AI, some are hesitant to change their workflow, and others, well, they simply don’t know how to use AI. In fact, 41% of entry-level workers in our survey feel hardly or not at all knowledgeable about AI-powered features (compared to just 10% of executives). It can be challenging to learn a new tool that’s constantly changing. Not to mention, the output of generative AI isn’t always trustworthy. However, there are steps organizations can take to help their workforce learn and grow comfortable with using AI. Solution: Encourage experimentation and provide training when possible Those unfamiliar with AI may assume using it requires advanced technical skills. However, most of the skills needed to use AI successfully are related to problem-solving and critical thinking. “AI continuously learns and becomes more effective and easier to use over time,” explains Saul. “The more difficult challenge becomes creatively figuring out what problems to apply AI to.” To help people identify opportunities for using AI, provide resources or training on frameworks and techniques such as root cause analysis (try the 5 whys and fishbone templates to get started) and divergent thinking. You may even encourage teams to practice mapping out processes or workflows as this type of visualization often helps people better understand areas of inefficiency where AI could help.
Teams can use the fishbone diagram to identify problems that may be a good fit for AI. Click on the template image to try it out!
It may also be beneficial to train employees on writing effective AI prompts—that is, communicating with AI to get the desired output. The most valuable factor here, though, will be experimentation. “Create space for safe experimentation,” says Lawyer. “Some members of your team need the ability to have creative play with the AI in their work so that they can discover the highest value points and then propagate those out to the rest of the team.”
Challenges solved by AI Need some inspiration on ways to use AI? Read how AI solves these common challenges in the workplace. Get the guide
Lastly, it’s important to provide clear and simple guidelines on using AI securely and ethically. For example, you may outline a security practice for AI, such as: “Do not put customer data into AI systems that are not corporate-approved.” Or, you may want to provide training or resources on how to verify information from a generative AI system and detect hallucinations. By outlining clear dos and don’ts for using AI, you’ll help your organization feel more comfortable experimenting with the new technology.
Simplify AI adoption with Lucid Lucid aims to encourage and streamline AI adoption by incorporating AI naturally into the product and, therefore, into your workflow. Whether kick-starting a diagram, building on a brainstorm, or summarizing projects, it’s easy to use AI in Lucid to work smarter. Plus, Lucid’s team of professional services consultants can help organizations use and apply Lucid’s AI to their unique use cases, manage change, and see value faster.
Get in touch Learn more about Lucid professional services and contact our team to see how we can help. Contact our team
| 2023-03-01T00:00:00 |
https://lucid.co/blog/ai-adoption-challenges-in-the-workplace
|
[
{
"date": "2023/03/01",
"position": 36,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 42,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 37,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 39,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 39,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 37,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 37,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 37,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 38,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 36,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 36,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 38,
"query": "workplace AI adoption"
}
] |
|
AI in the workplace: an overview of current adoption trends - Neobrain
|
AI in the workplace: an overview of current adoption trends
|
https://en.neobrain.io
|
[
"Vincent Hogommat"
] |
The 3 opportunities for AI adoption · First use: improving individual employee productivity. · Second use: optimizing business processes. · Third use: making ...
|
The year 2023 seemed to herald the widespread adoption of AI in the daily lives of employees, so what about a year later?
This integration appears to be much less straightforward: the AI Act passed by the European Parliament on March 13 now provides a framework for the use of this technology, without curbing the thirst for innovation.
One indicator to watch is the slowdown in traffic to the ChatGPT app. It has stabilized at around 180 million monthly users, with growth of just 13% between March 2023 and March 2024.
Individual employee ownership contrasts sharply with strategic integration at corporate level. Despite the fact that AI is among the top five priorities for large companies, only just over 10% have undertaken a meaningful impact study on their businesses.
How can we explain this moderation in the uptake of these technologies? What uses are they really being put to today, and what projections can we make for tomorrow?
The 3 opportunities for AI adoption
The adoption of AI is not monolithic. Our many discussions with HR managers and business leaders show that its spread varies from use for productivity gains to its integration into the company’s own offering.
Let's take a closer look at these different forms of adoption, their respective maturities and their obstacles. We also consider it essential to differentiate these elements according to the type of AI in question.
First use: improving individual employee productivity.
Artificial Intelligence for personal use : using AI systems as intelligent personal assistants to optimize daily tasks and time management.
Maturity: High. These technologies are increasingly in demand in technology-intensive sectors and by jobs requiring efficient time management .
High. These technologies are increasingly in demand in technology-intensive sectors and by jobs requiring efficient time management Barriers: The cost of technology and the varying quality of the tools available can represent obstacles, particularly for SMEs and less technology-oriented sectors.
Second use: optimizing business processes.
Automated management systems: Deploying AI solutions in supply chain management, robotic process automation (RPA) and customer relationship management (CRM) systems that transform internal operations and improve overall efficiency.
Maturity : Medium. Large companies, particularly in the manufacturing, retail and financial services sectors, are widely integrating these systems to optimize internal operations.
: Medium. Large companies, particularly in the manufacturing, retail and financial services sectors, are widely integrating these systems to optimize internal operations. Barriers: The high initial investment and the need for ongoing maintenance and integration with existing IT systems may limit their selection by SMEs.
Third use: making technology available to end customers.
AI integrated into product/service offerings: these new services better meet customer needs, such as personalized recommendations or intelligent user interfaces.
Maturity : Rapidly growing. Particularly present in consumer-oriented industries such as retail, entertainment and telecommunications.
: Rapidly growing. Particularly present in consumer-oriented industries such as retail, entertainment and telecommunications. Barriers: Requires in-depth understanding of customer data and strong data analysis capabilities, which may limit use to companies with insufficiently robust data infrastructures.
Two illustrations of advanced integration in products and services are worth highlighting here:
1st illustration: copiloting with Neobrain
Neobrain has sealed a partnership with Microsoft to integrate “co-piloting” into its solution, more specifically in the workforce planning dimension. Users can ask their assistant questions at any time to obtain detailed answers and access data, thus avoiding long and tedious searches in their application.
Video illustration:
2nd illustration: Sage Productivity Assistant
British software publisher Sage. Its People Director for Southern Europe, Tiphaine Brisou-Debeze, told me in an interview about the launch in early March of their generative AI-powered productivity assistant. On the other hand, when I ask her if her employees ask her for access to Chat GPT, the answer is clear: “none”.
But how can we be sure that employees aren’t practicing a new form of shadow IT through the use of “shadow AI”?
What is shadow AI?
Shadow AI refers to the use of artificial intelligence applications and services by employees without the approval or control of corporate IT departments. This practice can lead to security and non-compliance risks, as it bypasses the company’s official data management and security policies.
Many large companies such as Samsung, Apple, Deutsche Bank, Verizon and Amazon have banned ChatGPT to prevent data leakage. As a result, these companies need to find solutions to offer the same level of service in a secure way.
How can we tell the different AIs apart?
Artificial intelligence covers a wide range of modalities, which vary not only historically but also in terms of data processing protocols and ease of access.
Let’s take a closer look:
Machine learning is crucial, but often limited to large companies with extensive databases and robust IT systems, as it requires a significant volume of data to be effective.
is crucial, but often limited to large companies with extensive databases and robust IT systems, as it requires a significant volume of data to be effective. Natural language processing (NLP) is more widely used, particularly in human resources for screening job applications and analyzing behavior and communications. Its ability to handle natural language makes it accessible and useful in many professional contexts.
is more widely used, particularly in human resources for screening job applications and analyzing behavior and communications. Its ability to handle natural language makes it accessible and useful in many professional contexts. Wide language models (LLMs), such as ChatGPT, find widespread application in marketing, creative, legal and sales roles thanks to their ability to generate textual content autonomously. However, their use is less obvious in finance or manufacturing. This is due to the specific requirements for excessively reliable data and precise calculations, a level of confidence in the data that is not always achieved.
The 20 key statistics of AI adoption
To assess the real development of artificial intelligence in the workplace, we need to take stock and compare different statistics.
Modelling is still subject to many uncertainties, as evidenced by the differing points of view of major studies. For example, at the end of 2023, McKinsey stated that “AI could replace around 300 million full-time jobs in the future”, while Forrester spoke of 2.4 million jobs directly impacted by 2030, and 11 million other jobs influenced.
AI in the Workplace: 6 figures about Current Adoption Trend
Penetration statistics
Company penetration (source: United States Census Bureau)
34% of companies have implemented AI technologies
42% are currently exploring the AI options available.
35% of organizations are actively training and reskilling their teams to make effective use of new AI and automation tools.
Penetration by country (source IBM):
India is one of the countries with the highest use of Generative AI, at 57%.
Canada stands at 48%.
The United States at 25%.
France at 31%.
Impact on occupations:
Our study “How does AI impact my workforce”, carried out in January 2024, reveals 4 levels of impact on professions:
High impact" category (32%) : The jobs undergoing a notable transformation due to AI, with 40 to 66.6% of their business affected.
:
Medium Impact" category (36%) : jobs where the impact of AI is moderate, with certain activities able to benefit from AI (20 to 40% of impacted activities).
:
Limited impact" category (18%) : The jobs who are experiencing a marginal transformation of their tasks due to AI (10-20% of activities impacted).
:
No impact" category (14%) : The so-called “protected” jobs , where the very nature of the tasks remains unchanged by the AI.
:
Identify the degree of automation of 100 professions in our web-app:
Statistics on future adoption projections
Investment forecasts :
39% of large companies (+10,000 employees) plan to step up their investment in AI for their employees (Adobe)
The activities that consume the most AI :
The top 5 functions and activities that will benefit most from AI :some text Customer service Cybersecurity, fraud detection Customer relationship management Inventory management Content creation Recruitment ranks 10th according to Forbes Advisor.
Expected benefits :
Competitiveness and productivity are the 2 driving forces behind its deployment, with 87% and 64% respectively (Forbes).
A growing appetite for training:
67% of employees would like their company to support them in acquiring skills prompting AI.
Gaps to close skills :
70% of managers believe that their teams are not sufficiently qualified to optimize the use of AI. 61% of these same employees say they do not have the necessary skills to use generative AI effectively and safely (Salesforce GenAI snapshot research studies).
Conclusion
The past year has highlighted both advances and persistent challenges, reflecting a complex but inevitable transition to AI-enhanced work environments. It’s important to underline a certain kind of aspiration to capitalize on these technologies for a portion of white-collar workers, as the experience of interacting with the tool definitely revolutionizes past software in the image of what co-pilot offers, for example. This is good news for HR teams, for whom getting employees to use their HR software is not always a sine cure.
This gradual preference will undoubtedly be more difficult for an older population, less inclined to see the value of training in this area. Which raises the question of the ongoing redeployment of staff.
Our next article on the subject of AI investigates the obstacles and examples of companies that have initiated robust rethinking projects, to propose a 5-step methodology for initiating this inescapable change.
| 2024-07-11T00:00:00 |
2024/07/11
|
https://en.neobrain.io/blog/ai-workplace-current-trends
|
[
{
"date": "2023/03/01",
"position": 41,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 46,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 46,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 42,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 44,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 42,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 42,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 43,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 42,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 45,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 45,
"query": "workplace AI adoption"
}
] |
How AI Adoption is Revolutionizing the Modern Workplace
|
How AI Adoption is Revolutionizing the Modern Workplace
|
https://www.jrvs.ca
|
[] |
One of the primary benefits of AI adoption in the modern workplace is increased productivity. AI-powered systems can automate routine tasks, freeing employees' ...
|
In today's dynamic and tech-savvy world, businesses constantly seek innovative ways to stay ahead of the competition and achieve success. One of the most significant advancements in recent times is the adoption of Artificial Intelligence (AI) in the modern workplace. AI, with its ability to analyze vast amounts of data, learn from patterns, and make intelligent decisions, has the potential to revolutionize the way we work.
AI adoption in the modern workplace has already started transforming various industries, including finance, healthcare, and marketing. By leveraging AI technologies such as machine learning, natural language processing, and robotics, businesses can automate repetitive tasks, gain valuable insights from data, and enhance overall operational efficiency. The benefits of AI adoption in the workplace are numerous and far-reaching.
The benefits of AI adoption in the workplace
One of the primary benefits of AI adoption in the modern workplace is increased productivity . AI-powered systems can automate routine tasks, freeing employees' time to focus on more complex and strategic activities. This improves efficiency and allows employees to use their skills and expertise more meaningfully.
Another significant advantage of AI adoption is improved decision-making. AI algorithms can analyze vast amounts of data and identify patterns humans may miss. This enables businesses to make data-driven decisions, leading to better outcomes and a competitive edge in the market.
Furthermore, AI can enhance customer experiences by providing personalized recommendations, predictive analytics, and virtual assistance. With AI-powered chatbots, businesses can provide instant customer support, improving satisfaction levels and streamlining customer service operations.
AI adoption statistics and trends
The adoption of AI in the modern workplace is rising, and the statistics speak for themselves. According to a recent report , by 2025, 70% of organizations will be integrating AI technologies into their business processes. This showcases the growing trend of AI adoption and its increasing importance in driving business success.
The report also highlights that AI adoption is wider than large enterprises. Small and medium-sized businesses also recognize AI's potential and actively invest in AI technologies. This democratization of AI is making it accessible to companies of all sizes, enabling them to compete on a level playing field.
Furthermore, healthcare , finance , and manufacturing are leading the way in adopting AI. These industries leverage AI to improve patient outcomes, optimize financial operations, and enhance production processes. As AI continues to evolve, more industries are expected to embrace its potential.
Challenges and concerns of AI adoption in the modern workplace
While the benefits of AI adoption are undeniable, some challenges and concerns need to be addressed. One of the main concerns is the fear of job displacement. Many employees worry that AI will replace them in the workplace. However, studies have shown that AI is more likely to augment human capabilities rather than replace them entirely. Businesses must communicate this effectively and provide training opportunities to upskill employees for the changing work environment.
Another challenge is AI's ethical implications. As AI systems become more sophisticated, there is a need for transparency, accountability, and fairness. Bias in AI algorithms can lead to discriminatory outcomes, and privacy concerns arise when dealing with personal data. Organizations must establish ethical guidelines and ensure AI systems are developed and deployed responsibly.
Implementing AI in the workplace: Best practices and strategies
Implementing AI in the workplace requires careful planning and execution. Here are some best practices and strategies to consider:
Start with a clear vision : Define your goals and objectives for AI adoption in the workplace. Identify areas where AI can add the most value and align them with your business strategy.
Build a strong foundation : Ensure you have the infrastructure, data , and resources to support AI initiatives. Invest in robust data management systems and create a culture of data-driven decision-making.
Start small and scale : Begin with pilot projects to test the feasibility and effectiveness of AI solutions. Learn from these experiences and gradually scale up the adoption of AI across the organization.
Foster collaboration : Encourage cross-functional cooperation between IT, data scientists, and business units. This will help identify the most relevant use cases for AI and ensure successful implementation.
Continuous learning and improvement: AI technologies constantly evolve, and staying updated with the latest advancements is crucial. Invest in training programs to upskill employees and create a culture of continuous learning.
AI adoption in Tech
The technology industry has been at the forefront of AI adoption. Tech companies leverage AI to develop innovative products and services, improve operational efficiency, and gain a competitive edge. AI-powered virtual assistants, smart home devices, and autonomous vehicles are just a few examples of how AI is transforming the tech industry.
In addition to consumer-facing applications, AI plays a vital role in backend operations. Tech companies use AI to automate customer support, optimize supply chain management, and enhance cybersecurity. By harnessing the power of AI, tech companies can drive innovation, improve customer experiences, and achieve business growth.
The future of AI adoption in the modern workplace
The future of AI adoption in the modern workplace is promising. As technology advances, AI will become more sophisticated, enabling businesses to automate complex tasks and make more accurate decisions. Integrating AI with other emerging technologies, such as the Internet of Things (IoT) and Big Data, will further enhance its capabilities and open up new possibilities.
Moreover, as AI becomes more prevalent, it will create new job opportunities. While specific roles may be automated, AI will also create a demand for professionals with expertise in AI development, data analytics, and AI ethics. Organizations need to invest in training and upskilling employees to ensure they are prepared for the future of work.
Training and upskilling employees for AI adoption
As AI adoption becomes more widespread, training and upskilling employees to utilize AI technologies effectively is crucial. This involves technical training and developing critical thinking, problem-solving, and creativity skills. Organizations should provide comprehensive training programs and create a learning culture to ensure employees have the necessary skills for the AI-driven workplace.
Additionally, fostering a growth mindset and encouraging employees to embrace change is essential. AI adoption may require employees to adapt to new roles and responsibilities, and it is necessary to provide support and guidance throughout the transition. By investing in employee training and upskilling, organizations can maximize the potential of AI adoption and create a workforce ready for the future.
The role of leadership in driving AI adoption in the workplace
Leadership plays a critical role in driving AI adoption in the workplace. Leaders are responsible for creating a vision for AI adoption, communicating its benefits to employees, and addressing any concerns or resistance. Leaders should also champion a culture of innovation and experimentation, where employees feel empowered to explore and utilize AI technologies.
Furthermore, leaders must invest the necessary resources and infrastructure to support AI initiatives. This includes allocating budgets for AI projects, hiring skilled personnel, and establishing partnerships with AI solution providers. By demonstrating their commitment to AI adoption, leaders can set the tone for the entire organization and foster a culture of continuous improvement.
Embracing AI for a more efficient and productive modern workplace
In conclusion, AI adoption is revolutionizing the modern workplace, offering numerous benefits and opportunities for businesses. From increased productivity and improved decision-making to enhanced customer experiences, AI has the potential to transform how we work and drive business success.
However, AI adoption also has challenges and concerns that must be addressed. Organizations can navigate these challenges by implementing best practices and strategies and ensuring responsible and effective AI adoption.
Organizations must invest in training and upskilling employees and foster a culture of continuous learning. Leadership is vital in AI adoption and should provide the necessary vision, resources, and support.
By embracing AI, businesses can create a more efficient and productive modern workplace and unlock the full potential of this transformative technology.
| 2023-03-01T00:00:00 |
https://www.jrvs.ca/blog/how-ai-adoption-is-revolutionizing-the-modern-workplace
|
[
{
"date": "2023/03/01",
"position": 46,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 52,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 52,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 48,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 50,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 50,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 50,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 46,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 48,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 52,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 50,
"query": "workplace AI adoption"
}
] |
|
AI in the Workplace | Benefits, Examples & The Future of Work
|
Benefits, Examples & The Future of Work
|
https://www.officespacesoftware.com
|
[] |
Companies can now use workplace AI to improve a wide range of processes, from communication and security initiatives to better space planning and even a more ...
|
The speedy rise of AI in the workplace presents many potential benefits for the future of work.
Companies can now use workplace AI to improve a wide range of processes, from communication and security initiatives to better space planning and even a more inclusive company culture.
Of course, this assumes they fully understand these new technologies in the workplace, and that they implement and use them correctly.
In this article, we’ll explore AI in the workplace, focusing how workplace AI can lead to better, safer, and happier work environments, and, of course, a healthier bottom line.
How is AI used in the workplace?
AI has a multitude of uses in the modern workplace. It’s revolutionizing operations by mimicking human intelligence to solve complex problems and automate tasks. This powerful technology is applied across various functions to boost efficiency, reduce human error, save costs, and facilitate data-driven decision-making. While traditional AI excels at specific, data-driven tasks, generative AI creates entirely new content from simple prompts.
The sky may be the limit in theory, but in practice, AI-driven initiatives in the workplace today are usually seen in three major areas:
1. For automation
AI is fundamentally transforming workplace efficiency by automating a wide range of repetitive and time-consuming tasks that previously required manual human effort. This includes implementing Robotic Process Automation (RPA) to handle rule-based processes like data entry, invoice processing, or onboarding paperwork, executing complex workflows without human intervention.
AI also excels at automated scheduling, optimizing meeting times across multiple calendars, or managing resources like conference rooms and equipment. Furthermore, AI-powered email filtering and intelligent routing systems can automatically sort, prioritize, and even draft responses to routine inquiries, significantly freeing up employee time and reducing administrative burdens.
2. For data collection
In today’s data-rich environment, AI is invaluable for transforming raw information into actionable intelligence. AI systems are adept at gathering vast amounts of workplace data, from occupancy sensors in offices to digital communication patterns. They then process and analyze this data at speeds impossible for humans, identifying trends, correlations, and anomalies.
For instance, AI can analyze space utilization data to help optimize office layouts, pinpoint underutilized areas, or inform real estate decisions. It can also identify trends in employee behavior (anonymously and ethically) to understand preferences for hybrid work, popular collaboration spaces, or even predict maintenance needs before they arise. This deep analytical capability empowers leadership to make far more informed decisions, driving efficiency and strategic planning across the organization.
Learn about OfficeSpace’s extensive workplace analytics features
3. For a better employee experience
Beyond streamlining operations, AI is increasingly being leveraged to directly enhance the employee experience, making work more personalized, efficient, and supportive. AI powers personalized learning platforms that adapt training content to individual employee needs and learning styles, fostering continuous skill development. AI-powered chatbots serve as instant support tools, answering common HR, IT, or facility-related queries around the clock, reducing wait times and frustration.
Moreover, AI can optimize workflows for individual needs, intelligently suggesting resources, prioritizing tasks, or filtering information to help employees manage their workload more effectively. By providing tailored support and reducing friction in daily tasks, AI contributes to higher employee satisfaction, engagement, and overall productivity.
Discover all the ways OfficeSpace improves the workplace experience
Pros and Cons of AI in the workplace
While AI is rapidly transforming the modern office, it’s crucial for organizations to understand both its immense advantages and the challenges that require careful navigation. A balanced perspective helps ensure thoughtful implementation and maximizes the positive impact on your workforce and operations.
Pros
1. Cost savings
First and foremost, many of the benefits of workplace AI are specifically for increasing cost savings and/or generating revenue.
To start, automating repetitive tasks typically done by employees frees up time to spend on more high value activities. Meanwhile, improved efficiencies can reduce waste, streamline production processes, and help increase profits. Providing a better customer experience can lead to higher customer satisfaction overall, along with a reduced need for additional customer support staff. Fraud detection can reduce losses, and energy efficiency can reduce resource spending (along with more benefits we’ll explore below).
Indeed, virtually every benefit of workplace AI listed below can lead to cost savings (and/or revenue growth) in one form or another.
2. Improved communication and collaboration
AI programs significantly enhance both internal communication and team collaboration in the workplace. Beyond familiar tools like voice-to-text technologies and grammar auto-correct, AI offers sophisticated capabilities such as sentiment analysis tools that identify potential issues before they become widespread problems.
These AI-powered tools also provide support for training, accountability, and accessibility, all contributing to better teams and improved teamwork. Furthermore, AI helps optimize collaboration spaces by analyzing workplace data, allowing companies to tailor environments, such as huddle rooms for Zoom calls, to employee preferences and long-term collaboration strategies.
3. Faster analytics and reporting
Access to more and better data is a cornerstone of modern business, and AI dramatically accelerates this process. AI not only helps collect vast amounts of information but also synthesizes it into accessible and digestible workplace reports and analytics, enabling far better decision-making while mitigating risks. As Kathleen Williams, Senior Product Manager at OfficeSpace, notes, without advanced workplace analytics, it’s challenging to truly understand what’s happening in your office.
This extends to predictive maintenance, a rapidly emerging facilities management best practice supported by AI. Studies consistently show that predictive maintenance can significantly reduce downtime (up to 50%), cut breakdowns (up to 70%), and lower maintenance costs (up to 25%). AI-driven data collection, machine learning, and predictive maintenance algorithms precisely determine when and where to take proactive measures, leading to reduced downtime, improved safety, and substantial cost savings. This ability to deliver real-time and predictive insights transforms raw data into actionable intelligence for your workplace.
4. A better work-life balance
One of the more profound and sometimes overlooked impacts of AI in the workplace is its contribution to a better employee experience and overall work-life balance. By automating mundane and time-consuming tasks, AI liberates employees from repetitive duties, allowing them to focus on higher-value, more strategic, and creative work.
This shift, combined with the benefits of working in better spaces, with better tools, and in optimized workflows—the sum total of many AI advantages—not only significantly boosts productivity but also notably improves employee morale and engagement. Ultimately, AI enables a more human-centric office where employees can achieve a healthier balance and feel more satisfied in their roles, a smart strategy in any labor market.
5. Streamlined move management
AI plays a crucial role in significantly enhancing the efficiency and precision of complex office moves, transforming what can be a logistical nightmare into a seamless process. By leveraging advanced data analytics and automation, AI-powered tools simplify every phase, from initial planning to execution. This includes using space utilization insights to optimize new layouts, automating tedious task assignments, and providing real-time updates on move progress across all stakeholders.
OfficeSpace’s dedicated Move Manager, augmented by AI capabilities, allows organizations to build digital move plans, automate notifications, and orchestrate intricate steps for IT, HR, facilities, movers, and employees alike. This integrated approach ensures smoother transitions, minimizes disruption to employee productivity, and drastically reduces downtime and costs during office reconfigurations or large-scale departmental shifts, making relocation projects more organized, less stressful, and far more cost-effective.
6. Intuitive space management
Good space utilization is a hallmark of effective workplaces. However, for companies embracing hybrid work arrangements and agile spaces, optimizing the physical office can be incredibly challenging. The reality is that hybrid leadership can only hope to rise to this challenge when they’re supported with AI-analyzed workplace data. AI technologies, including office sensors, data analytics, and workplace collaboration tools, are critical in providing this support.
With the right data, space planners, facility managers, and other decision-makers can see average and peak occupancy ranges over time, allowing them to pinpoint which areas of the office are most popular and/or effective. This intelligence empowers them to build more of those high-value spaces, create more engaging physical offices, and efficiently right-size or reduce corporate real estate expenses.
As former OfficeSpace CEO David Cocchiara insightfully states, “It’s when you pull these different workplace metrics and data points together you can feel more confident that if you make a change, it’s not going to have a negative impact on your people because you have all the data to support this decision. This is why I believe workplace experience software is going to be imperative as you start to make these space planning decisions.”
Whether organizations aim to offer flexible seating arrangements like hot desking or office hoteling, or better align evolving hybrid schedules with their existing infrastructure, a variety of AI systems can support them in this process, ensuring space management is not just efficient but genuinely intuitive and employee-centric.
Cons
1. Can be prone to error
Despite their advanced capabilities, AI systems are not infallible, and this is a significant consideration in workplace implementation. AI can sometimes produce inaccurate, irrelevant, or even nonsensical outputs, often referred to as “hallucinations.” These errors can stem from flaws or biases in the large datasets they are trained on, or a misunderstanding of nuanced context in a user’s prompt.
While continuous refinement and sophisticated algorithms reduce these occurrences, human oversight and critical review remain absolutely essential to validate AI-generated content or decisions, especially in critical business functions.
2. Bias end ethical concerns
A significant and widely discussed challenge with AI is its potential to inherit and even amplify biases present in its training data. If the vast datasets used to train AI systems reflect existing societal biases, the AI can inadvertently perpetuate or exacerbate discrimination in areas such as hiring, performance evaluations, or content generation. Beyond bias, ethical considerations extend to issues of privacy, as AI often processes sensitive personal and corporate data, raising questions about data security and usage transparency.
Accountability for AI’s decisions, particularly in autonomous systems, also presents complex ethical dilemmas. Therefore, it is critical for organizations to carefully design, deploy, and continuously audit AI systems for fairness, transparency, and accountability to mitigate these ethical risks.
3. Learning curve for employees (upskilling)
Integrating new AI technologies into daily workplace operations inevitably presents a learning curve for employees, particularly those less familiar with rapidly evolving digital tools. This requires individuals to adapt and acquire new skills, which can sometimes be met with resistance or initial inefficiencies as teams adjust to new workflows. Without proper training programs, clear guidelines for AI use, and accessible upskilling initiatives, organizations risk slower adoption rates and may not fully realize the potential benefits of their AI investments.
It’s crucial for companies to view this not just as a challenge, but as an essential investment in their workforce, ensuring employees are equipped to effectively leverage AI tools to augment their existing skills and focus on higher-value tasks.
4. Over-reliance on AI systems
A significant challenge in the widespread adoption of AI within the workplace is the potential for over-reliance on these intelligent systems. As AI becomes more sophisticated and efficient, there’s a risk that human critical thinking, problem-solving skills, and intuitive judgment may diminish if not actively maintained. Organizations could become overly dependent on AI for routine tasks and decision-making, which could lead to vulnerabilities if systems experience failures, outages, or produce unexpected or biased results.
It’s crucial to view AI as an augmentation tool—a powerful co-pilot designed to enhance human capabilities and streamline processes—rather than a complete replacement for human intellect, creativity, and the nuanced understanding required for complex, strategic initiatives. Maintaining a balance where human expertise remains central, with AI supporting rather than supplanting, is key.
5. Lack of emotional touch
A fundamental limitation remains its inability to genuinely replicate human emotion, empathy, and nuanced intuition. While AI can process vast amounts of data and even simulate human-like conversation, it lacks true emotional intelligence and the capacity for genuine human connection.
For roles that demand deep interpersonal understanding, empathy, negotiation, or the subtle cues of human interaction—such as client relations, sensitive HR matters, or creative collaboration that relies on shared human experience—AI cannot fully substitute the human element. Organizations must recognize that while AI excels at efficiency and data processing, fostering a truly human-centric workplace and building strong relationships still requires the irreplaceable emotional touch that only human employees can provide.
Examples of AI in the workplace: use cases and applications
You can find AI in virtually every sector. It’s in industries from startups and call centers, to healthcare organizations and massive tech conglomerates, and everything in between.
Walmart uses machine learning to help employees know when to restock shelves
AT&T uses AI for cybersecurity
General Motors is using generative design to make better cars
HR departments across the board are increasingly on board, too. They’re using AI more and more in the hiring processes, as well as in talent retention and attraction efforts. A SHRM study found that 79% of HR organizations now use AI and automation for recruitment and hiring.
Even social media platforms are getting in on the action. For example, LinkedIn now offers AI online training courses, and virtually every platform has programmers working to make safer and better experiences for their users. Companies of all shapes and sizes can use AI, and practically all departments within an organization should be able to find ways to benefit from these new and growing office workplace technologies.
Here are two uses of AI you’ve likely seen before:
Chatbots
Chatbots are programs that use natural language processing to communicate with people (usually via text). They’re often found on websites or customer service channels to answer questions and resolve common issues. Companies can also use them for order processing and tracking, lead generation, and other marketing efforts.
When companies use this type of AI, they free up time for customer service reps (and others) to tackle bigger and/or more complex problems and tasks. The idea isn’t necessarily to replace human labor. It’s to free up human labor for more dynamic and revenue-generating tasks (like sales), without sacrificing customer experience in the process.
A prime example of this technology in action is Ossie, OfficeSpace Software’s AI assistant. This virtual assistant is designed to provide 24/7 help in finding essential information regarding OfficeSpace products and services, allowing employees to focus on the work that matters most. From simple inquiries like ‘How do I book a desk?’ to more complex ones such as ‘How do I select multiple employees to move when creating a floor plan?’—Ossie is equipped to deliver accurate and swift responses.
The implementation of AI not only enhances efficiency by streamlining information retrieval but also significantly improves the overall user experience, embodying the seamless integration of AI in the workplace.
Office sensors
Office IoT (Internet of Things) sensors are also increasingly common, especially in hybrid workplaces. These are the physical devices that collect data about their use and/or the environment around them. While these devices don’t technically classify as ‘AI,’ they do rely on AI technology to process and analyze the data they collect.
Sensors have a variety of applications—many of us already use them in our homes or cars. In the workplace, they often take the form of occupancy sensors. These are motion sensors that track occupancy rates, over time, across different (and often granular) areas of the workplace.
When these sensors pair with real estate analytics, space management software, and other AI systems, they can improve real estate portfolio management and facilities reporting. This in turn can help space planners ensure they’re following space management best practices without sacrificing employee experience. Meanwhile, these sensors can also provide workplace metrics to help leadership better manage real estate forecasting going forward.
All of these capabilities can be especially useful in a hybrid office setting, where workplace utilization is increasingly dynamic.
“Pervasive AI will ultimately redefine how we build company cultures.” Christopher Helman, forbes.com
AI and the employee experience
While alarming headlines sometimes focus on AI replacing workers, the reality is that Artificial Intelligence can significantly improve workplace culture and the overall employee experience when implemented thoughtfully. For organizations that embrace the right tools, AI can liberate employees and foster a more positive environment. In fact, recent MIT research found that a substantial percentage of respondents who saw improved efficiency and decision quality thanks to AI also reported team-level improvements in employee morale and culture.
AI impacts various aspects of the employee journey, creating optimized workplace experiences that foster connections and encourage productive office use:
AI streamlines the onboarding process, making it easier for new hires to integrate seamlessly
AI delivers personalized learning platforms that cater to individual needs, promoting continuous skill development
AI enhances internal dialogues and facilitates teamwork, contributing to a more cohesive work environment
Beyond these, virtually all the benefits of workplace AI can promote overall employee well-being. Optimized space planning and predictive maintenance can reduce headaches and barriers to efficient office use, directly contributing to a smoother workday. Moreover, AI’s role in supporting flexible working options, which employees increasingly demand, positively impacts morale and productivity. As Carsten Bruhn writes for Forbes.com, there is growing evidence that certain technologies can bring positive, tangible change to team culture and morale, extending beyond mere business gains to truly enhance the human experience in the office.
AI in the workplace and the future of work
The ongoing integration of AI is not just reshaping daily tasks; it’s fundamentally redefining the future of work itself. How a business experiences this transformation—whether it’s beneficial or challenging—will largely depend on its understanding and effective implementation of these new technologies. AI is a broad and rapidly evolving field, and its positive impact isn’t automatic; rather, organizations that strategically leverage AI to improve problem-solving and create more human-centric offices are those best positioned to reap its full benefits.
A critical implication for the future workforce is the evolving nature of job roles and required skills. As AI assumes more routine and data-heavy tasks, the importance of training employees to effectively use AI at work becomes paramount. Organizations must ensure their workforce is equipped to collaborate with these tools.
AI has the potential to revolutionize workplace productivity, but without proper training and upskilling, employees may struggle to adapt, leading to inefficiencies or missed opportunities. Companies should strategically think of AI as a powerful tool designed to augment the skills employees already possess, streamlining routine tasks so they can focus on higher-value initiatives, creative work, and innovation. To prepare for this future, consider creating clear guidelines around ethical AI practices and regularly hosting company workshops or encouraging online training sessions to accelerate team learning and empower employees with the necessary tools for effective AI integration.
OfficeSpace uses data in the workplace to make better, more sustainable offices. Reach out for a free demo.
Workplace AI FAQs
What are the 4 types of AI? While the field is still rapidly evolving, AI technology is generally grouped into one of four categories, based on how it functions: Reactive AI, which only responds to real-time events, without forming memories; examples include facial recognition technology and self-driving vehicles. Limited memory AI, which uses past experiences and/or stored data to make decisions (and can therefore improve performance over time); examples include natural language processing and chatbots. Theory of mind AI, which works to understand human (or animal) mental states, emotions, beliefs, goals, and intentions, with the goal of interacting naturally with people; this is a new area with limited real-world examples. Self-aware AI, which has consciousness and understands itself, and is currently considered a theoretical concept; there are no real-world examples of self-aware AI, and it remains unclear whether it will ever be possible. Note that while these are the most widely used four classifications of AI, it can also be classified based on the degree of intelligence or autonomy it exhibits. In this framework, AI falls into one of three categories: Artificial Narrow (or ‘weak’) Intelligence (ANI), Artificial General Intelligence (AGI), and Artificial Superintelligence (ASI). What is the difference between narrow AI and general AI? The difference between narrow AI and general AI comes down to the complexity of tasks they can complete. Narrow AI is limited to performing specific (i.e.: narrow) tasks within a specific domain. This type of system can only perform the said task. Meanwhile, general AI refers to the type of AI we tend to picture; these are adaptable systems designed to perform intellectual tasks. They can reason, solve problems, and learn in ways similar to humans. What is the first type of AI? There are many ‘firsts’ in the world of artificial intelligence and debates about what specific programs claim the ‘first’ spot. That said, the first AI were generally rule-based, simple systems with narrow capabilities and tasks. The first successful AI program was written by Christopher Strachey in 1951, although many of the programs we think of as ‘AI’ were the rule-based systems developed in the 1970s. The first AI machine was the WABOT-1, a humanoid robot built in Japan in 1972. What is the difference between AI and machine learning? Machine learning (ML) is a specific subset of AI. It refers to algorithms that teach machines to learn from data. Like the name suggests, these machines are able to ‘learn,’ without having explicit programming. AI, of course, is a broader field that incorporates ML, along with a variety of other simple and complex processes. How can AI be used to increase efficiency in the workplace? AI can be used to improve collaboration and workflows in the workplace. Facility managers and space planners can also use AI to create more efficient offices that support a variety of working styles, as well as to improve workplace management. What are the issues with AI in the workplace? The impact of technology in the workplace is never neutral, and workplace AI can be controversial for several reasons. In fact, 53% of organizations worry that ethical concerns can stop AI from being as effective as it could be. AI systems have the potential to have blind spots built in, which can exacerbate bias and discrimination. There may also be privacy concerns and a lack of transparency surrounding the collection and use of data. Of course, many are concerned that implementing AI can lead to job losses and inequality. There are also concerns that smaller companies and organizations may not be able to access and properly implement sophisticated and expensive AI. Given these potential issues, it’s critical for companies to choose any AI systems carefully, and take steps to mitigate any negative impacts.
Photos: gorodenkoff, shih-wei, BraunS, Prostock-Studio
| 2023-03-29T00:00:00 |
2023/03/29
|
https://www.officespacesoftware.com/blog/ai-in-the-workplace-ai/
|
[
{
"date": "2023/03/01",
"position": 47,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 21,
"query": "workplace AI adoption"
},
{
"date": "2023/08/01",
"position": 45,
"query": "artificial intelligence workers"
},
{
"date": "2023/09/01",
"position": 45,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 45,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 47,
"query": "artificial intelligence workers"
},
{
"date": "2024/01/01",
"position": 45,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 39,
"query": "artificial intelligence workers"
},
{
"date": "2024/03/01",
"position": 20,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 20,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 21,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 22,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 21,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 48,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 48,
"query": "workplace AI adoption"
},
{
"date": "2025/05/29",
"position": 90,
"query": "AI job losses"
},
{
"date": "2025/05/29",
"position": 37,
"query": "future of work AI"
},
{
"date": "2025/05/29",
"position": 24,
"query": "machine learning workforce"
},
{
"date": "2025/05/29",
"position": 28,
"query": "workplace AI adoption"
}
] |
The Rise of AI in the Workplace: New Stats + Pros & Cons to Consider
|
The Rise of AI in the Workplace: New Stats + Pros & Cons to Consider
|
https://zylo.com
|
[] |
Artificial intelligence can automate routine tasks like data entry, note-taking, and drafting simple messages. This gives employees more time to focus on higher ...
|
Alphabet CEO Sundar Pichai recently stated that he considers AI to be more profound than fire or electricity. While skeptics may attribute this to a tech leader hyping their product, business leaders across industries agree. McKinsey recently opened a report comparing AI to the steam engine and estimating that the technology holds $4.4T in productivity growth across the economy.
Regardless of what any dissenting business leaders or AI skeptics may think, many workers across the economy are implementing artificial intelligence into their workflows. A recent Gallup poll found that nearly half of all white collar workers admit to using AI for tasks such as generating ideas, automating basic tasks, communicating with coworkers, and learning new things.
Of course, risks and downsides to artificial intelligence also exist. These range from security threats to quality of work issues and ethical concerns. Organizations must be prepared to face novel challenges and solve problems creatively to thrive in the era of generative AI.
The “AI revolution” is both inevitable and game-changing, and business leaders must prepare to seize opportunities while navigating challenges responsibly.
Defining AI in the Workplace
Contrary to popular perception, AI did not enter the workplace with the launch of ChatGPT. It has been embedded in the fabric of business operations for years. AI-driven algorithms have been powering search engines, optimizing logistics, detecting fraud, personalizing ads, and serving many other behind-the-scenes functions for over a decade. While these applications are often invisible and narrowly focused, they do represent a critical and longstanding example of AI tech.
What changed in late 2022 was the way that people interact with AI. OpenAI brought a specific technology known as generative AI to the spotlight. This captured the public imagination and revolutionized the collective perception of artificial intelligence. In contrast to previous highly constrained uses of AI, Gen AI offers a flexible and interactive experience. This has sparked a wave of experimentation and implementation across many industries.
Artificial Intelligence in the workplace is not a new phenomenon. However, the economy is entering a new era in which AI will play an increasingly broad and versatile role in nearly every job.
The Rise of AI in the Workplace
A recent Microsoft report found that 75% of global knowledge workers now use artificial intelligence. This is often self-directed. The same study found that 78% of those who use AI in the workplace are bringing their own tools. While this demonstrates initiative and innovative thinking, it also underscores the lack of a unified vision in many organizations. Worse still, it has the potential to introduce security, ethical, and financial risks through the proliferation of shadow IT.
Now that roughly half of all workers report feeling burned out, the advantages of AI usage are evident: tools like ChatGPT, Claude, and DeepSeek function as digital assistants, drafting messages, analyzing information, and making recommendations. The aforementioned Microsoft study also found that the top 5% of Teams power users save up to one full work day per month through AI summaries alone.
Impact of AI on the Workforce
Microsoft categorizes AI users into four broad groups: skeptics, novices, explorers, and power users. The study found that the latter group saves over half an hour per day in rote tasks. Other benefits that these power users report include increased focus and creativity, along with more energy to devote to game-changing projects.
What apps are employees turning to?
Company culture is a significant factor in determining whether employees will become AI power users or remain explorers, novices, or even skeptics. While some people are likely to take action independently and integrate AI into their workflows, most employees follow the lead of company higher-ups. Organizations with an anti-AI culture will inevitably see a far slower and less creative implementation of this type of technology.
Considerations for AI in the workplace
Implementing AI into an organization is more like building a puzzle than flipping a light switch. While the decision to use new technologies may seem straightforward, the process of actually implementing them is complex. It involves identifying where AI would be impactful, aligning its usage with the broader organizational strategy, and managing issues such as risk, SaaS spend, legal exposure, employee expectations, and ethics.
Identifying Key Areas for AI Implementation
Artificial intelligence can assist with many distinct functions. To name just a few potential applications, AI can:
Draft simple emails for internal communication.
Evaluate the interest level of a lead.
Compile a performance report for a new employee.
Predict employee retention trends and suggest proactive steps to retain talent.
Identify potential security risks and provide solutions to address vulnerabilities.
Take notes during meetings and provide summaries, including action steps and key takeaways.
Help tailor or repurpose content to different platforms, audiences, or regions.
Spot trends in supply and demand to better manage supply chains.
Selecting a few key areas where AI has the highest potential impact. And beginning small can help make the process more manageable for employees, ensuring AI software tools are used to their fullest potential. As teams gain greater familiarity and experience with artificial intelligence, more tools can be added later based on previous insights and strategic priorities.
Aligning AI with Strategic Business Goals
Leaders must take care to ensure that AI use aligns with core business strategy and vision. For example, while building an AI chatbot as the default customer service medium may save money or even improve wait times on paper, it could conflict with certain brands that pride themselves on offering human-centric experiences. A cybersecurity or supply chain solution built on AI may be a more appropriate starting point for this type of organization.
Balancing Innovation with Risk Management
Every new technology solution brings risk alongside its opportunities. IT leaders realize this—89.4% of those we surveyed have concerns about the security risks associated with AI tools. AI solutions can amplify the software risks inherent to automation and scalability due to a lack of human oversight.
AI systems can’t judge situations on a case-by-case basis. While an employee could make an exception or alert leadership to an unfair quirk in a refund policy, AI could enforce the policy a thousand times before anyone is even aware that an issue exists.
Tactics to combat these types of situations include:
Conducting a thorough risk audit
Getting input from all levels of the team, especially front-line workers
Reading case studies and implementation stories from similar users.
Maintaining rigorous human oversight of AI functionalities, especially during the first 90 days of implementation.
Legal implications
The legal implications of using AI in the workplace are often unclear or still developing. Employers must be proactive to avoid liability. One element of this that has already been the subject of numerous court cases and emerging legislation is the role AI can play in perpetuating discrimination.
Companies that use artificial intelligence to evaluate hiring, for example, risk placing important decisions in the hands of algorithms that may have been trained on biased datasets. Jurisdictions such as New York City and the State of Colorado have already enacted laws requiring such software to be audited for fairness. Lawsuits have also been filed nationwide due to alleged civil rights violations.
Other legal concerns include data privacy, intellectual property, and employee monitoring. Any tool that processes employee data or analyzes their behavior raises questions around consent and surveillance. Finally, companies must also conduct due diligence around their obligations to clients and vendors before delegating work to AI tools.
Ethics
While laws governing AI use are still evolving, relying solely on legal compliance is risky. Regulations may lag behind the pace of innovation, which is why companies need strong ethical principles at the core of their AI strategies. Clear standards regarding when and how to use AI and what data should remain off-limits are the foundation of a good workplace AI policy. These guidelines will help you avoid legal jeopardy, reputational damage, and unintended harm to employees or customers.
This starts with transparency. People should be aware of when AI is involved and how it affects their decisions. Regular audits are essential for identifying bias in training data or outputs, and human oversight must play a crucial role in high-stakes applications, such as hiring or customer service.
Ultimately, using AI at work ethically involves a lot more than simply avoiding harm. It means using technology to support fairness, trust, and improved outcomes for both individuals and the business.
Employee Expectations
It’s no secret that skepticism and anxiety regarding AI exist in the modern workforce. A study conducted by Bentley University in conjunction with Gallup found that only 10% of adults in the US believe AI currently does more good than harm.
However, these misgivings coexist with more positive sentiments such as a belief in the transformative power of AI. Moreover, many employees also believe (correctly) that mastering the use of AI at work will be critical to remaining valuable and innovative in their roles.
“AI will not take your job, but someone who knows how to use AI better than you might,” has become a mantra on social media platforms such as LinkedIn. Many employees, especially forward-thinking top performers, expect to learn and implement artificial intelligence into their work. If they feel their company is falling behind, they will consider taking their talent elsewhere.
Shadow AI
Unfortunately, employees who want to use AI may take an alternative route when their employers don’t provide their own means. The covert use of artificial intelligence in violation of (or in place of) company policy is referred to as “shadow AI.”
This underscores the point that AI is bringing about profound changes in the economy, regardless of how any individual leader may feel about the situation. Your company will be impacted by AI one way or another. The only question is whether you prefer to build your own structured framework with clear and visible software decisions or let those choices happen without you.
Benefits of Using AI in the Workplace
As businesses look for ways to stay competitive, integrating AI offers clear advantages. Artificial intelligence tools are making a measurable impact for organizations that prioritize innovation.
Increased Efficiency and Productivity
Artificial intelligence can automate routine tasks like data entry, note-taking, and drafting simple messages. This gives employees more time to focus on higher-impact tasks. A study from Accenture found that companies with AI-led operations can double the productive output of their peers.
Smarter Data Analysis and Decision Making
One area where machines can often outperform humans is pattern recognition. AI can sort through large datasets and identify trends and anomalies with greater speed and precision than any analyst could on their own. From predicting churn to optimizing ad spend and forecasting demand, AI empowers organizations with a previously unimaginable level of insight, provided they are willing to innovate.
Improved Customer Service
Artificial intelligence can also automate or facilitate previously challenging or expensive customer-facing tasks. These include providing 24/7 support or tailoring product recommendations to every customer. Tech-forward thinking enables companies to have their cake and eat it too, enhancing customer satisfaction while simultaneously reducing pressure on service representatives. The previously referenced Accenture study found that many innovation-forward companies are already using generative AI in customer service, clearly indicating where the market is headed.
Innovation
Generative AI can assist in prototyping, content creation, product design, and ideation. A report from the North Carolina Department of Commerce predicts that this will ultimately allow humans to focus on higher-level conceptual work rather than rote tasks. AI reduces the friction between concept and execution, allowing teams to experiment more frequently and at lower cost. As these tools mature, companies that integrate them early will have a first-mover advantage in reimagining products and services.
Disadvantages of AI in the Workplace
Aside from the legal and ethical concerns referenced earlier, there are a few downsides to implementing artificial intelligence into an organization’s workflows. These range from everyday cybersecurity challenges to broader concerns about the future of the global economy.
Security and Privacy Concerns
AI systems are trained on massive datasets that are consistently updated based on user input. One risk this creates is that employees may inadvertently disclose private data by sharing it with a large language model (LLM). This highlights the necessity of providing robust cybersecurity training across all levels of the organization and establishing clear policies for AI usage.
Licensing and Implementation Costs
AI software tools typically bill by both user seats and overall usage, creating opportunities for software waste. For example, employees may sign up for several LLM tools before settling on a favorite, yet continue incurring charges from unused licenses. Redundant tools, over-licensed software, and poor renewal management exacerbate this issue.
Dependency on Technology
Artificial intelligence works best when used to enhance, augment, critique, or build upon human creativity, not replace it. Unfortunately, overreliance on AI technology has become a well-observed phenomenon.
A study from CQ University in Australia reports that over 27% of students demonstrated worse critical thinking skills after implementing large language models. Organizations must take care to ensure that LLMs do not replace critical thought or creativity. Again, clear company policies are a first line of defense here.
Bias Issues
We’ve already discussed the potential legal liabilities associated with placing artificial intelligence in the driver’s seat when hiring, promoting, or evaluating talent. Unfortunately, lawsuits are only the tip of the iceberg when it comes to bias-related problems that AI overreliance can invite. Even if your organization never faces legal action, AI bias could still drive suboptimal decisions.
And this goes beyond HR. Artificial intelligence relies on datasets that can be skewed, manipulated, or misinformed in various ways. Once again, human discretion and judgment prove irreplaceable when implementing AI solutions.
Job Displacement and Unemployment
While it sounds like the stuff of Science Fiction, concerns about large-scale economic downturns are quickly growing and gaining legitimacy in the face of increasing AI adoption.
Goldman Sachs has even predicted that artificial intelligence could displace as many as 300 million workers in the coming years. Some good news, though: AI is also creating many roles, to the extent that some managers even worry about keeping up with hiring.
The message for workers is clear: AI will disrupt existing workflows while also creating opportunities, and your future success will hinge largely on your ability to adapt to the changing technological landscape.
Tips for Employees Using AI at Work
Considering these changes, knowledge workers should be proactive about building a role for AI in the workplace. Rather than viewing artificial intelligence as a threat, employees who take a thoughtful approach can use these tools to unlock new levels of creativity, productivity, and career growth.
Here are four principles that can guide these efforts:
Be Specific and Strategic
AI thrives when it’s given a well-defined task. Rather than approaching an LLM with vague commands like “write a report” or “analyze this,” it’s better to think in terms of clear prompts and desired outcomes. Employees should develop the habit of identifying bottlenecks or repetitive tasks in their day-to-day work and then test how AI can streamline or enhance those specific activities. The most successful AI users aren’t the ones who try to use it for everything, but those who apply it where it counts the most.
Collaborate, Don’t Automate Blindly
Automating without review or critique can do more harm than good. Think of AI as a creative partner or smart intern, not a replacement for your judgment. Review outputs carefully, refine prompts over time, and treat AI-generated content as a rough draft or starting point.
Involving your own expertise in the editing, refinement, and decision-making process ensures the final product meets your standards and aligns with company expectations.
Use the Right Tool for the Job
As more AI software enters the market, it’s easy to waste time or make mistakes with tools that don’t suit your workflow. Start by mastering one or two tools that align closely with your role, and build from there.
For example, content creators may derive more value from generative text tools like ChatGPT, while analysts may benefit from AI-powered dashboards or summarizers. If your company provides specific platforms, prioritize those. If not, keep track of what you try and what adds value.
Be Transparent and Ethical
Your ethical compass should guide how you use AI, particularly when applied to areas such as hiring, customer service, or legal and financial decisions. Best practices include:
Be open about when and how you’re using AI at work.
Practice careful judgment when making AI-guided decisions.
Never input confidential or sensitive company data into third-party tools.
Be mindful of bias or errors in AI outputs.
Examples of How AI Is Used in the Workplace
Below are a few potential use cases that illustrate how artificial intelligence can be leveraged to save time or make better decisions.
Information Retrieval and Knowledge Management
A new hire at a SaaS company is trying to understand how pricing models have evolved over the past two years. Instead of sifting through 300 Slack threads and dozens of slide decks, she uses an AI-powered knowledge assistant integrated with Notion and Google Drive.
She types, “Why did we change our enterprise pricing last fall?” and the tool summarizes relevant documents, Slack discussions, and financial performance reports into a 3-paragraph answer with links for further reading.
Personal Productivity
A CEO drafts one-sentence updates he wants to send to different teams: product, marketing, and customer support. Rather than writing each message manually, he pastes the bullets into ChatGPT and asks it to write professional, motivational Slack messages tailored to each department. Within minutes, he has clear, thoughtful communications that reinforce his leadership voice without eating up his afternoon.
Learning and development
An employee in a mid-sized manufacturing firm wants to move into a data analyst role. She asks her company’s AI career coach, “What skills should I build?” and receives a personalized learning path based on the company’s current tech stack, team structure, and internal job openings. The AI links her to internal training videos, suggests free courses from Coursera, and even gives weekly quiz recaps to track her progress.
Automation of Routine Tasks
A project manager oversees six simultaneous client campaigns and struggles with weekly status updates. She sets up a workflow using Zapier and a GPT integration. Every Friday, the AI pulls updates from task descriptions in Asana, summarizes progress, flags potential delays, and drafts a templated email for each client, ready for her to review and send with a click.
Supply Chain and Logistics
At a retail apparel brand, the logistics team uses AI to monitor historical shipping delays, weather forecasts, and warehouse inventory levels. When an East Coast snowstorm is predicted, the AI flags at-risk shipments and suggests alternate routing strategies. It even proposes adjustments to the week’s promotion schedule to alleviate pressure on the impacted fulfillment centers.
Data Analysis
A senior marketer wants to know why a recent email campaign underperformed. Instead of waiting on a full analytics report, she copies the raw data from HubSpot into an AI spreadsheet plugin and prompts: “Why did open rates fall compared to last month?” The AI surfaces a few hypotheses (such as subject line length, send time, and audience fatigue) along with supporting charts and recommends A/B testing subject lines next week.
Solutions for Effective AI Implementation
AI isn’t a plug-and-play tool. Successful adoption requires a structured approach, a clear strategy, and a willingness to experiment and refine over time. The companies that reap the most benefits from AI are those that align it with their goals, train their teams, and build systems that support long-term success.
Create an AI Usage Policy
Without clear guidelines, employees may use AI in ways that expose the business to risk. This highlights the importance of good SaaS governance. A company’s usage policy can provide clarity on where AI is encouraged in the workplace, where human oversight is required, and how to handle sensitive information.
Building an effective policy begins with identifying repetitive tasks, common bottlenecks, and data-intensive workflows where AI can significantly impact productivity or precision.
From there, organizations can outline acceptable and unacceptable use cases. Internal documentation, early content drafts, and meeting summaries are good starting points. Conversely, key strategic decisions, legal communication, and anything influencing customer trust should require human oversight and leadership.
Lastly, a strong AI usage policy should also cover security and transparency. Employees should be aware of what can and cannot be shared with AI, and they should receive clear instructions on when and how to cite AI involvement in a project.
Prioritize Support, Training, and Integration
The Harvard Business Review reports that over half of employees feel unprepared to use AI in the workplace. Organizations can support their workers by selecting relevant tools and providing ongoing education and support to facilitate a smooth integration. Not only will this ensure that AI users feel comfortable with their work, it can also help avoid software waste and a proliferation of shadow AI.
Selecting tools that integrate with existing solutions, such as Slack, Notion, or HubSpot, is also wise. This can help AI feel like an augmentation of current capabilities rather than an overwhelming technical reset.
Center the Human Element
Used wisely, AI can help employees spend less time on drudgery and more time on high-impact work. It can support brainstorming, identify patterns in messy datasets, and summarize complex information in seconds. However, these outputs should be treated as raw materials, not finished products. Human judgment remains the filter that transforms AI input into something strategic, thoughtful, or creative.
To help employees stay ahead, invest in upskilling. Offer training in AI literacy and critical thinking. Let your team in on your long-term AI strategy so they understand how the technology will evolve inside the company. By stepping back to consider the needs and feelings of employees throughout departments, organizations can avoid the common pitfall of asymmetrical AI implementation, which is emerging as a common concern.
The Boston Consulting Group reports that 80% of leaders are utilizing AI, while only 20% of frontline employees are doing the same. The solution to this disparity is emotional intelligence (EQ).
Monitor, Evaluate, and Evolve
Rolling out AI is not a one-and-done effort. Performance needs to be tracked, evaluated, and refined over time. Set clear metrics before launch. Is the tool speeding up turnaround time? Improving decision-making? Reducing costs? These benchmarks will help you determine whether the technology is making a positive difference.
Regular reviews can also uncover new opportunities or unintended downsides. Perhaps the AI excels at summarizing customer calls, but still struggles with tone in outbound emails. Or it’s generating valuable insights, but it needs better data to pull from. Continue iterating until it generates your benchmark ROI.
At the same time, stay vigilant for potential risks. Review outputs for bias. Track how tools are used across departments and be prepared to course-correct if performance dips or reputational concerns arise. Flexibility is key. The organizations that thrive with AI are the ones willing to adapt and evolve as they learn.
Predictions: How AI Will Impact Businesses and Employees
As organizations craft AI usage policies, train teams, and monitor outcomes, it’s equally important to keep an eye on what’s ahead. The economy is evolving fast, and the role of artificial intelligence is set to expand in both scope and sophistication. Organizations must think beyond short-term use cases and start preparing for fundamental shifts in the way we operate. Below are several key trends shaping that future.
Advancements in AI Technologies
AI capabilities are rapidly expanding. Gartner predicts that by 2027, 60% of knowledge workers will utilize generative AI daily. This shift won’t just come from increased adoption of today’s tools—it will be fueled by significant leaps in what AI can actually achieve.
Expect faster and more accurate language models, more integrated multimodal systems (combining text, images, and voice), and greater domain-specific customization. For example, legal, medical, and engineering teams may soon have access to specialized AI assistants trained on industry-specific knowledge and standards.
At the same time, AI will move further into the background. Rather than interacting with stand-alone platforms, employees will increasingly engage with embedded AI across email clients, project management dashboards, sales tools, and even video calls, making AI a seamless part of everyday workflows.
Evolution of AI Policies and Regulations
As capabilities expand, so too will the scrutiny. Fortunately, 81.8% of IT leaders reported already having documented policies specifically governing the use of AI tools. The Gartner report cited above also predicts that over 50% of government agencies will establish formal AI risk and ethics frameworks by 2026. Businesses that adopt AI without preparing for these frameworks risk falling behind legally and financially.
In the near future, expect to see:
Mandatory AI model transparency for applications like hiring and underwriting
Stricter rules around employee monitoring and data privacy
Expanded responsibilities for compliance teams and legal counsel
Forward-thinking companies won’t just aim to comply: they’ll build trust. Public opinion is increasingly focused on “explainable AI” and the ethical implications of automation. Building policies that emphasize fairness, human oversight, and transparency will be essential for long-term success.
The Changing Role of the Human Workforce
As AI takes over more repetitive and rules-based tasks in the workplace, the human role will shift toward creativity, strategy, emotional intelligence, and high-stakes decision-making. Concurrently, 77.6% of the IT leaders we surveyed reported upgrading or investing more in SaaS apps for their AI capabilities over the past year.
New job titles and functions will emerge, such as AI trainer, prompt engineer, or LLM auditor. Cross-training and reskilling programs will become essential to employee retention. Performance metrics will evolve to account for results and AI-enhanced output, rather than raw effort.
How Zylo Helps Companies Manage AI Implementation
Zylo helps organizations take control of their AI journey by delivering clarity, visibility, and governance across SaaS solutions. Our tools help companies identify shadow AI, eliminate redundant licenses, and ensure that every tool aligns with strategic priorities and security standards.
If you’re an IT leader looking to drive efficiency, save money, and reduce risk, and you found this article helpful, learn more about Zylo to see if we fit your needs.
| 2023-03-01T00:00:00 |
https://zylo.com/blog/ai-in-workplace/
|
[
{
"date": "2023/03/01",
"position": 55,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 7,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 9,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 6,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 54,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 57,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 57,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 57,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 7,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 52,
"query": "workplace AI adoption"
},
{
"date": "2024/10/15",
"position": 21,
"query": "AI unemployment rate"
},
{
"date": "2024/10/15",
"position": 29,
"query": "future of work AI"
},
{
"date": "2024/10/01",
"position": 8,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 51,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 7,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 59,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 58,
"query": "workplace AI adoption"
}
] |
|
Importance of adopting AI in the workplace - Procurement Sciences
|
Importance of adopting AI in the workplace
|
https://procurementsciences.com
|
[
"Christian Ferreira",
"Ceo",
"Brian Giblin",
"Jim Mcdermott"
] |
In this blog post, we'll explore why it's important to adopt AI into your business practices because AI will not replace you in your job, people using AI will ...
|
Artificial intelligence (AI) is a rapidly growing technology that has the potential to revolutionize many industries. Despite fears of AI replacing human jobs, the reality is that AI is a tool that can be used to enhance and augment human capabilities, rather than replace them. In this blog post, we’ll explore why it’s important to adopt AI into your business practices because AI will not replace you in your job, people using AI will replace you.
AI as a Tool
AI is not a replacement for human intelligence, but rather a tool that can be used to augment it. AI can perform repetitive and mundane tasks more efficiently and accurately than humans, freeing up employees to focus on more complex and creative tasks that require human judgment and expertise. AI can also help businesses analyze data and identify patterns and trends that humans might not be able to see.
AI Can Improve Efficiency
By adopting AI into your business practices, you can improve your efficiency and reduce your costs. AI can automate routine tasks, such as data entry and analysis, freeing up time for employees to focus on more high-level tasks. This can lead to a more productive and efficient workforce, which can ultimately improve your bottom line.
AI Can Enhance Customer Experience
AI can also be used to enhance customer experience. For example, chatbots can be used to provide customer service and support 24/7, answering common questions and resolving issues. AI can also be used to personalize customer experiences, by analyzing data and tailoring marketing messages and product recommendations to each individual customer.
The Importance of Upskilling
While AI is not a replacement for human intelligence, it does require a different skill set than traditional jobs. As such, it’s important for businesses to invest in upskilling their employees to ensure they have the skills and knowledge necessary to work alongside AI. This can include training in data analysis, machine learning, and other technical skills, as well as soft skills such as critical thinking and problem-solving.
Conclusion
In conclusion, adopting AI into your business practices is important because it can enhance and augment human capabilities, rather than replace them. AI can improve efficiency, enhance customer experience, and provide valuable insights that can help businesses make better decisions. By upskilling employees and embracing AI as a tool, businesses can position themselves for success in the rapidly evolving digital landscape. Remember, AI will not replace you in your job, people using AI will replace you.
| 2023-03-26T00:00:00 |
2023/03/26
|
https://procurementsciences.com/importance-of-adopting-ai-in-the-workplace/
|
[
{
"date": "2023/03/01",
"position": 63,
"query": "workplace AI adoption"
},
{
"date": "2023/03/26",
"position": 73,
"query": "AI labor market trends"
},
{
"date": "2023/03/26",
"position": 86,
"query": "government AI workforce policy"
},
{
"date": "2023/03/26",
"position": 60,
"query": "machine learning workforce"
},
{
"date": "2023/04/01",
"position": 67,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 70,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 71,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 71,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 65,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 63,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 74,
"query": "workplace AI adoption"
}
] |
Employees Are Rapidly Adopting AI – McKinsey Report - CBOT
|
Employees Are Rapidly Adopting AI – McKinsey Report
|
https://www.cbot.ai
|
[] |
According to McKinsey's “Superagency in the Workplace” report, employees are adopting AI solutions much faster than their managers anticipate.
|
AI
According to McKinsey’s “Superagency in the Workplace” report, employees are adopting AI solutions much faster than their managers anticipate. Employees who already use AI-based applications also express a desire for more training and support in this area.
At CBOT, we address this need with our Digital Work Assistants, designed for internal employees. These solutions support employees in various fields, such as Human Resources, Information Security, and Customer Services, making business processes more efficient and effective. The findings of the McKinsey report also indicate that the demand for these digital assistants among employees is increasing day by day.
Now, let’s take a closer look at the details of this report.
Employees Use AI More Frequently Than Their Managers Think. But Are Managers Aware of This?
According to McKinsey’s US CxO survey, 94% of employees and 99% of C-suite leaders are familiar with generative AI (Gen AI) tools. However, managers are not yet fully aware of how widely their employees are utilizing this technology.
Senior executives estimate that only 4% of employees currently use Gen AI for at least 30% of their daily tasks. However, according to employees’ own statements, this rate is actually three times higher. Moreover, while only 20% of managers predict that employees will use Gen AI for more than 30% of their daily tasks within a year, employees themselves anticipate this rate to reach 47%.
Employees Fall Into Four Categories in Their Approach to AI
According to McKinsey’s research, employees can be categorized into four distinct groups based on their attitudes toward AI: Bloomers, Gloomers, Zoomers, and Doomers.
Bloomers (39%) – Optimistic about AI, they want to collaborate with their companies to develop responsible solutions.
Gloomers (37%) – More skeptical about AI, they advocate for stricter regulations.
Zoomers (20%) – Prefer the rapid implementation of AI with minimal restrictions.
Doomers (4%) – Completely opposed to AI, focusing solely on its risks.
Employees Expect More Support from Their Managers for AI Adaptation
According to McKinsey’s research, employees believe that AI will significantly impact their jobs and expect their companies to invest more in helping them adapt to this change. Nearly half of the survey respondents consider AI training to be the most effective way to accelerate adaptation. Additionally, they emphasize the importance of gaining access to AI tools through beta versions or pilot projects. Employees also suggest that incentives such as financial rewards and recognition could further encourage AI adoption.
However, despite these expectations, companies are not providing sufficient support. Survey results reveal that more than one-fifth of employees receive little to no assistance. As AI continues to reshape the business landscape, it is becoming increasingly critical for companies to offer more training and support to help employees enhance their skills.
The Situation Is Slightly Different for International Employees
According to McKinsey’s research, while global trends in AI adaptation are largely similar, there are significant differences between countries in terms of training and support. Employees in Australia, India, New Zealand, Singapore, and the United Kingdom report receiving significantly more corporate support for learning AI skills compared to their counterparts in the United States.
Survey results show that 84% of international employees say they receive substantial or full support for AI training, whereas in the U.S., this figure is just slightly over half. Additionally, international employees have more opportunities to participate in the development of generative AI tools in the workplace. When it comes to activities such as beta testing, providing feedback, and requesting new features, they are at least 10 percentage points ahead of U.S. employees.
Millennials Could Be the Driving Force of AI Transformation
In today’s business world, millennials aged 35-44 play a crucial role as managers and team leaders within companies. According to McKinsey’s latest report, professionals in this age group report having the highest level of experience and enthusiasm for AI, positioning them as key drivers of transformational change.
Millennials Are the Most Active Users of AI
Research data shows that 62% of employees aged 35-44 have a high level of AI expertise. In comparison, this rate stands at 50% for Gen Z (18-24 years old) and 22% for Baby Boomers (65 and older). These figures highlight the critical role millennials can play in AI adoption.
How Can Leaders Contribute to This Transformation?
Millennial leaders in managerial positions play a crucial role in transforming their teams into more proficient AI users. According to McKinsey’s research, two-thirds of managers receive questions from their teams about AI tools at least once a week. Similarly, a comparable proportion of managers report that they actively recommend AI tools to their teams as part of the problem-solving process.
Leaders have the authority to take action, which allows them to be more proactive and bold in driving AI adoption.
In many transformation processes, employees are known to resist change. However, AI is different! Employees have a high level of familiarity with this technology and are ready to embrace AI adoption. This presents a unique opportunity for business leaders to act swiftly and drive AI integration more effectively.
What Can Leaders Do?
They can identify needs by listening to how employees use AI and how they can transform their work.
They can accelerate AI adaptation by providing their teams with the necessary training.
They can empower managers to make AI use cases scalable from the pilot phase.
💡 This opportunity should not be missed! It is crucial for companies aiming to achieve AI maturity to manage this process quickly and decisively. Delaying could mean falling behind in the competition.
| 2025-03-12T00:00:00 |
2025/03/12
|
https://www.cbot.ai/according-to-mckinseys-superagency-in-the-workplace-report-employees-are-adopting-ai-solutions-much-faster-than-their-managers-anticipate/
|
[
{
"date": "2023/03/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 71,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 66,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 67,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 65,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 67,
"query": "workplace AI adoption"
}
] |
The AI-Enabled Employee: New Standard for Success in the Future ...
|
The AI-Enabled Employee: New Standard for Success in the Future of Work
|
https://www.carv.com
|
[] |
Why the future of work belongs to AI-enabled employees. The adoption of AI in the workplace is at an all-time high, as businesses recognize its potential to ...
|
Today’s workplace is undergoing a profound transformation, driven by the rapid advancement of artificial intelligence. This technology is not merely automating tasks; it is ushering in a new era of human-AI collaboration, where AI augments and enhances human capabilities, creating a new breed of empowered employees – the AI-enabled employee.
While the concept of an AI-enabled employee might sound like a futuristic notion, it’s becoming a reality as we speak, in organizations across industries and geographies. So let’s take some moments to explore what this concept means for both workers and businesses, and how we can all prepare for this rapidly evolving future of work.
Why the future of work belongs to AI-enabled employees
The adoption of AI in the workplace is at an all-time high, as businesses recognize its potential to enhance productivity, improve decision-making, and create new opportunities.
According to McKinsey's 2022 report, "The Future of Work After COVID-19: Adapting to a New World of Work," 54% of companies are currently using AI technologies to enhance employee productivity, and 43% are using AI to automate tasks. The expectation of business leaders is to see a 10-15% increase in productivity and 20-25% increase in employee engagement by incorporating AI into day-to-day processes and workflows.
Although we’re still in a phase where companies are drafting their AI implementation strategies and figuring out the best use cases of AI-powered tools, there is no doubt that the future belongs to workers who can use AI systems to drive business growth. Thus, it’s safe to say that becoming AI-enabled is the only way forward for employees who want to stay competitive in the rapidly evolving job market.
From a business point of view, the growing adoption of AI - and, as a consequence, the move towards hiring AI-savvy employees for their new roles - is a no-brainer. This technology has immense potential to benefit both businesses and employees.
For businesses, AI can:
Improve productivity: AI automation can take over time-consuming, repetitive tasks, freeing up employees to focus on more strategic, high-value work.
AI automation can take over time-consuming, repetitive tasks, freeing up employees to focus on more strategic, high-value work. Enhance decision-making: AI can analyze vast amounts of data to identify patterns and trends that would be difficult or impossible for humans to detect, providing businesses with data-driven insights for better decision-making.
AI can analyze vast amounts of data to identify patterns and trends that would be difficult or impossible for humans to detect, providing businesses with data-driven insights for better decision-making. Reduce costs: AI can automate routine processes, reducing labor costs and improving efficiency.
AI can automate routine processes, reducing labor costs and improving efficiency. Create new opportunities: AI is creating new jobs and opportunities for employees with specialized skills in AI and data analytics.
But what does the adoption of AI mean for employees? And what exactly is an AI-enabled employee?
The impact of AI on the employee roles and responsibilities
While there was a time when people feared that AI would replace humans in the workforce, HR teams are still looking to hire human professionals, and employee satisfaction and retention are still high on the agenda of priorities. However, it is true that artificial intelligence is reshaping the work environment and changing the nature of work, reducing the demand for some jobs and creating new employment opportunities.
For example, the creation and development of AI systems require machine learning engineers, data scientists, and specialized researchers. These types of professionals are increasingly in demand and well-compensated, and we expect the trend to continue with the introduction of new technologies.
Additionally, implementing AI algorithms into current processes requires support from AI ethics and cybersecurity specialists. With the growing awareness of the ethical implications of AI, there are opportunities for ethics experts to ensure that decisions made by AI systems align with moral and social principles.
But AI’s influence isn’t reduced to new hires. Businesses are already adopting AI-driven processes and artificial intelligence tools, and AI is already being used in a variety of ways to augment and enhance employee capabilities.
To give just some examples of AI use cases in the workplace:
Automating repetitive tasks: AI can streamline workflows by automating routine, mundane tasks. This frees up employees to focus on more strategic, high-value work. According to a recent report, 62% of employees say that AI helps them optimize operations and processes, and 34% are using AI to make strategic business decisions.
AI can streamline workflows by automating routine, mundane tasks. This frees up employees to focus on more strategic, high-value work. According to a recent report, 62% of employees say that AI helps them optimize operations and processes, and 34% are using AI to make strategic business decisions. Providing real-time insights: AI can analyze vast amounts of data and provide employees with real-time insights, enabling them to make better decisions and improve their performance.
AI can analyze vast amounts of data and provide employees with real-time insights, enabling them to make better decisions and improve their performance. Personalizing learning experiences: AI can personalize learning experiences for each employee, providing them with the content and support they need to develop their skills.
AI can personalize learning experiences for each employee, providing them with the content and support they need to develop their skills. Facilitating collaboration: AI can facilitate collaboration and knowledge sharing among employees, breaking down silos and fostering a more connected workplace.
AI can facilitate collaboration and knowledge sharing among employees, breaking down silos and fostering a more connected workplace. Empowering creativity: AI can be used to generate new ideas and approaches, fostering innovation and problem-solving.
AI can be used to generate new ideas and approaches, fostering innovation and problem-solving. Predicting future trends: AI can analyze past data to predict future trends, helping businesses make better strategic decisions.
AI can analyze past data to predict future trends, helping businesses make better strategic decisions. Providing customer service: For instance, AI-powered chatbots are helping businesses serve their customers better than ever. Such tools are built on top of ChatGPT or other generative AI technologies and enriched with company data, to give contextually-relevant answers and provide a seamless customer experience.
On top of these use cases, AI-powered learning platforms are used for reskilling and upskilling the workforce. Such platforms enable employees to access customized learning experiences and training programs tailored to their unique needs and goals. At the same time, AI is used for onboarding and knowledge-sharing initiatives, often within self-service applications.
Overall, AI is playing an increasingly important role in the workplace, and AI-enabled employees are becoming essential for businesses that want to stay competitive.
In fact, HR professionals are listing AI knowledge as one of the most important among all employee skills going forward, and AI builders are the most sought-after professionals. And although at the moment we’re still dealing with an AI adoption gap, as more and more companies are starting to understand how to make use of AI and to implement artificial intelligence into their daily operations, the skill gap between AI-savvy workers and laggards will become even bigger.
Which means that for workers it’s imperative to become AI-enabled sooner rather than later. But what does this actually mean?
The AI-enabled employee: Characteristics and skills
AI-enabled employees are individuals who work alongside AI systems to enhance their capabilities and improve their performance. They possess a unique set of skills that enable them to work with AI systems, including data analysis, critical thinking, and problem-solving.
AI-enabled workers have embraced the integration of AI into their work practices, and are not afraid of AI, but rather see it as a tool that can augment their skills and capabilities.
So let’s look at the profile of an AI-enabled employee, to understand what workers should focus on and what HR departments will be looking for going forward.
Key characteristics of AI-enabled workers
How does AI improve employees? And what are the characteristics that make AI-enabled workers stand out?
Enhanced autonomy and broader knowledge - The hallmark of an AI-enabled employee lies in the amplified sense of autonomy. With AI lending a helping hand at every turn, these individuals transcend the limitations of a conventional skill set, having always-on access to infinite amounts of information. This means that their knowledge is no longer limited to a specific skillset. Instead, the employee of the future is able to go from “T-shaped” to “rectangular-shaped” by expanding their knowledge and acquiring a skillset that’s evenly wide as it is deep.
- The hallmark of an AI-enabled employee lies in the amplified sense of autonomy. With AI lending a helping hand at every turn, these individuals transcend the limitations of a conventional skill set, having always-on access to infinite amounts of information. This means that their knowledge is no longer limited to a specific skillset. Instead, the employee of the future is able to go from “T-shaped” to “rectangular-shaped” by expanding their knowledge and acquiring a skillset that’s evenly wide as it is deep. “On-demand” creativity, both conceptual and applied - AI is democratizing creativity, opening up the realm of innovative thinking to a wider pool of individuals. AI-enabled tools can assist employees in generating new ideas, exploring unconventional approaches, and create assets in various formats with a few clicks. This democratization of creativity ensures that every employee, regardless of their innate creative prowess, can contribute meaningfully to creative initiatives and ideation processes.
- AI is democratizing creativity, opening up the realm of innovative thinking to a wider pool of individuals. AI-enabled tools can assist employees in generating new ideas, exploring unconventional approaches, and create assets in various formats with a few clicks. This democratization of creativity ensures that every employee, regardless of their innate creative prowess, can contribute meaningfully to creative initiatives and ideation processes. Optimal efficiency - AI-enabled employees can achieve remarkable levels of efficiency by leveraging AI's ability to automate tasks, analyze vast amounts of data, and provide real-time recommendations. AI can streamline workflows, identify bottlenecks, and optimize resource allocation, leading to significant gains in productivity.
- AI-enabled employees can achieve remarkable levels of efficiency by leveraging AI's ability to automate tasks, analyze vast amounts of data, and provide real-time recommendations. AI can streamline workflows, identify bottlenecks, and optimize resource allocation, leading to significant gains in productivity. Multi-lingual across domains - Being multi-lingual takes on a new dimension in the AI era – not just in terms of language but also in job-specific jargon. AI-enabled workers possess the ability to navigate and communicate seamlessly across various domains, breaking down silos and fostering a collaborative, interconnected workplace.
Essential skills for AI-enabled employees
In addition to these key characteristics, AI-enabled employees need to have a strong foundation in the following skills:
Technical skills: AI-enabled employees should have a basic understanding of AI concepts and technologies, such as machine learning, natural language processing, and computer vision. They should also be comfortable using AI tools and applications.
AI-enabled employees should have a basic understanding of AI concepts and technologies, such as machine learning, natural language processing, and computer vision. They should also be comfortable using AI tools and applications. Business acumen: AI-enabled workers should have a strong understanding of business principles and practices. They should be able to identify business problems that can be solved with AI, and they should be able to communicate the value of AI to other stakeholders in the organization.
AI-enabled workers should have a strong understanding of business principles and practices. They should be able to identify business problems that can be solved with AI, and they should be able to communicate the value of AI to other stakeholders in the organization. Soft skills: AI-enabled employees should have strong soft skills, such as communication, teamwork, and problem-solving, to compensate for the limitations of AI Workmates, and collaborate effectively with their AI counterparts.
Emerging skills for AI-enabled employees
As AI continues to evolve, new skills will be required for AI-enabled employees. Some of the emerging skills that will be in demand include:
Data ethics: AI-enabled employees will need to be aware of the ethical implications of AI and be able to use AI in a responsible and ethical manner.
AI-enabled employees will need to be aware of the ethical implications of AI and be able to use AI in a responsible and ethical manner. AI explainability: AI-enabled employees will need to be able to explain how AI works and how it arrives at its decisions. This is important for building trust with stakeholders and for ensuring that AI is used in a fair and transparent manner.
AI-enabled employees will need to be able to explain how AI works and how it arrives at its decisions. This is important for building trust with stakeholders and for ensuring that AI is used in a fair and transparent manner. AI governance: AI-enabled employees will need to be able to understand and apply AI governance frameworks. These frameworks help organizations to manage the risks associated with AI and to ensure that AI is used in a responsible and ethical manner.
Over to you
In conclusion, AI is not a threat to the future of work; it is an opportunity. AI-enabled employees will become increasingly common in the workplace going forward, and it’s important for both workers and organizations to prepare for this change. By embracing AI and developing the necessary skills, employees can become AI-enabled and thrive in a rapidly changing world.
Businesses, at their turn, that foster a culture of AI adoption by embracing this technology and using it to augment the their workforce and the employee experience. Companies who support their employees' continuous learning and upskilling will be well-positioned to succeed in the AI-driven workplace.
As we move forward, let us embrace AI not as a replacement for human workers, but as a powerful tool to augment our capabilities and enhance our productivity. Together, we can create a future of work that is more productive, efficient, and fulfilling for all.
| 2023-03-01T00:00:00 |
https://www.carv.com/blog/ai-enabled-employee
|
[
{
"date": "2023/03/01",
"position": 65,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 83,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 97,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 86,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 84,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 63,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 64,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 82,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 98,
"query": "workplace AI adoption"
}
] |
|
You can empower the workforce with AI - KPMG International
|
You can empower the workforce with AI
|
https://kpmg.com
|
[] |
According to the recent AI Index Report by Stanford University's Human-Centered Artificial Intelligence (HAI) Institute, AI adoption has surged, with 72 percent ...
|
Roadmap to Adoption
Adopting AI within an organization requires a structured and disciplined approach, encompassing several key areas:
Targeted upskilling of the workforce
A recent report by the World Economic Forum highlights that 58 percent of employees believe their job skills will change significantly in the next five years due to Al and big data.ii Data from the KPMG Gen AI Pulse Survey reveal that employee adoption is a top three challenge in 2025, and 81% of leaders are planning on including GenAI in their performance reviews,19% are doing so already.iii
Learning and development programs are becoming more comprehensive and varied, designed to cater to different learning preferences and personas. They include self-service resources, learning labs, weekly interactive office hours, prompt engineering sessions, and workshops taught in conjunction with technology partners. And since the pace of AI adoption within some business functions can be unpredictable, educational platform subscription services are arising to help speed adoption.
Introducing new approaches to change management to overcome resistance
The integration of AI into corporate environments can encounter resistance and apprehension from portions of the workforce, which is why effective change management strategies are crucial to motivate adoption. However, traditional methods of managing organizational change are not always sufficient when it comes to the uptake of AI. Instead, organizations should foster emotional engagement with employees and clear communication of AI benefits to overcome hesitancy and reinforce a culture of innovation. The approach should include new ways of working that focus on connecting to the bigger picture of what will be possible with AI, finding meaning and purpose in day-to-day work, and elevating the employee experience.
Finally, it is essential to create a safe space for experimentation so that employees are empowered to explore and leverage AI capabilities fully. Leaders should allow employees to “fail fast” and learn from their experiences. This involves setting up open forums where the impacts, risks, and opportunities of AI tools can be discussed as they are developed and deployed and there can be an ongoing dialogue about what has and hasn’t worked well.
Integrating AI adoption and workforce transformation
Although AI’s potential is nearly limitless, putting the technology in the hands of only a select few, e.g., IT teams and marketing departments, will result in some optimized processes but not enterprise-wide transformation. In contrast, motivating and rewarding adoption across the workforce has the potential to up the ante on innovation for even the most change-averse companies. Integrating AI into the workforce should involve rethinking job roles and workflows to ensure the technology is applied to areas where the most value can be realized. In these efforts, it is important to be transparent about the idea that AI is meant to make streamline workflows and make work more interesting, not replace employees altogether. This is about fundamentally rethinking how work is done, which requires a human-centric mindset that combines the best of human ingenuity and technological intelligence. This comprehensive integration not only enhances efficiency but also fosters a deeper sense of involvement and motivation across teams, thereby accelerating the adoption process.
| 2024-12-18T00:00:00 |
2024/12/18
|
https://kpmg.com/us/en/articles/2025/empower-workforce-with-ai.html
|
[
{
"date": "2023/03/01",
"position": 71,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 76,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 85,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 85,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 85,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 76,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 72,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 74,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 19,
"query": "AI workforce transformation"
},
{
"date": "2024/12/01",
"position": 66,
"query": "workplace AI adoption"
},
{
"date": "2025/01/24",
"position": 62,
"query": "artificial intelligence workers"
},
{
"date": "2025/01/01",
"position": 86,
"query": "workplace AI adoption"
},
{
"date": "2025/03/01",
"position": 86,
"query": "workplace AI adoption"
}
] |
Businesses can stop rising AI use from fueling anxiety | EY - US
|
Businesses can stop rising AI use from fueling anxiety
|
https://www.ey.com
|
[
"Dan Diasio",
"Matt Barrington",
"Samta Kapoor",
"Authorsalutation",
"Authorfirstname Dan Authorlastname Diasio Authorjobtitle Ey Global Consulting Ai Leader Authorurl Https",
"Www.Ey.Com En_Us People Dan-Diasio",
"Authorfirstname Matt Authorlastname Barrington",
"Authorjobtitle Ey Americas Chief Technology Officer",
"Ey Global Ai Activation Leader Authorurl Https",
"Www.Ey.Com En_Us People Matt-Barrington"
] |
When thinking of AI adoption in the workplace, 73% are concerned that there won't be sufficient AI training and upskilling opportunities, with 63% of employees ...
|
Millennials (born 1981-1996) and Gen X (born 1965-1980) emerge as more open to AI: they trust and use it at work and see value in adopting it at work.
In contrast, Gen Z (born 1997-2005) and baby boomers (born 1940-1964) are less likely to trust it. To add context to these results, we spoke with EY Americas Cultural Insights and Customer Strategy Leader, Marcie Merriman. “While this may come as a surprise to many, for the youngest and oldest generations in the workplace, trust in AI isn’t just about safety and security: it’s whether the technology works.”
Merriman points out that Gen Z has highest expectations of technology. AI has been embedded into their everyday lives since birth, from facial recognition on phones to GPS navigating them through cities. If one app or platform doesn’t work easily and seamlessly, they quickly move on to others. Baby boomers, on the other hand, started their careers with less need to be hands-on with technology. As technology gained ground in the workplace of the 80s and 90s, Baby boomers often depended on lower-level employees (typically Gen X), to master spreadsheets and build presentations.
| 2024-03-19T00:00:00 |
2024/03/19
|
https://www.ey.com/en_us/consulting/businesses-can-stop-rising-ai-use-from-fueling-anxiety
|
[
{
"date": "2023/03/01",
"position": 80,
"query": "workplace AI adoption"
},
{
"date": "2023/04/01",
"position": 90,
"query": "workplace AI adoption"
},
{
"date": "2023/05/01",
"position": 94,
"query": "workplace AI adoption"
},
{
"date": "2023/06/01",
"position": 77,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 79,
"query": "workplace AI adoption"
},
{
"date": "2023/09/01",
"position": 96,
"query": "workplace AI adoption"
},
{
"date": "2023/12/01",
"position": 96,
"query": "workplace AI adoption"
},
{
"date": "2024/01/01",
"position": 96,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 83,
"query": "workplace AI adoption"
},
{
"date": "2024/05/01",
"position": 77,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 81,
"query": "workplace AI adoption"
},
{
"date": "2024/07/01",
"position": 77,
"query": "workplace AI adoption"
},
{
"date": "2024/10/01",
"position": 76,
"query": "workplace AI adoption"
},
{
"date": "2024/11/01",
"position": 77,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 78,
"query": "workplace AI adoption"
},
{
"date": "2025/01/01",
"position": 95,
"query": "workplace AI adoption"
}
] |
Three Ways To Prepare Your Workforce for Artificial Intelligence
|
Three Ways To Prepare Your Workforce for Artificial Intelligence
|
https://innovationatwork.ieee.org
|
[
"Innovation At Work"
] |
According to the news site Axios, 61% of organizations are just starting to adopt AI for decision-making, while 19% are categorized as having barely begun.
|
Only 20% of U.S. companies are fully deploying artificial intelligence (AI) for decision-making in their businesses based on survey responses from 1,000 senior business executives.
According to the news site Axios, 61% of organizations are just starting to adopt AI for decision-making, while 19% are categorized as having barely begun. Surveyed business leaders are hesitant to adopt AI because many organizations—particularly non-tech companies—“don’t completely trust it” and “can’t tap the talent they need.” However, businesses that decide not to adopt the technology risk falling behind.
“The majority of executives get stuck in a vicious circle where when they first try AI, the first wave of results tend to be underwhelming,” Ben Pring, managing director at Cognizant’s Center for the Future of Work, a consulting firm that conducted the survey, told Axios. “You have to work at it and you have to learn how to optimize it.”
Organizations need to hire professionals skilled in AI to solve the problem. However, competition for them is fierce. While there is an expectation among business leaders that AI should reduce their reliance on employees, the reality, according to Pring, is that they still need employees who know how to deploy the technology.
“If you can’t get that talent, then you can’t compete,” he said.
Want to be an Early AI Adopter? Train Your Employees
Businesses don’t need to hire externally for AI talent. Rather, they can simply train their current employees. According to Stephen Chen, Senior Vice President, Technology & Security, for NuCompass Mobility, a global relocation management company, there are three actions businesses can take to train their current workforce in AI:
Educate your employees about the technological changes AI will bring and build a culture of positivity around the technology. “To build this kind of culture, you must communicate a steady stream of actual examples showing how automation and AI help individuals, teams and the organization be more successful,” Chen “To build this kind of culture, you must communicate a steady stream of actual examples showing how automation and AI help individuals, teams and the organization be more successful,” Chen writes in Forbes.
Prepare your employees for AI re-skilling and up-skilling by encouraging a “growth mindset” in which they learn to welcome challenges. This includes educating them about how developing AI skills will set them up for career advancement. “At NuCompass Mobility, we identify early adopters of new skills to ensure different business units have ‘automation champions.,’” he writes. “These automation champions help their peers gain an appreciation for automation technology as well as identify a pipeline of processes that can be evaluated for automation on an ongoing basis.”
Identify AI use cases for automation that are worth the effort and eliminate those that are not. Use cases worth the effort will include those that reduce time waste, mundane, repetitive tasks, and tasks that tend to result in employee error. “Organizations must avoid the temptation to say ‘yes’ to every automation project,” Chen writes. He adds that starting small will garner trust in AI, noting: “We want employees to become invested in the journey and comfortable with the idea of automation and working alongside AI.”
Adapting your workforce to AI won’t be a simple task. Doing so will involve building employees’ trust in the technology and giving them the confidence to develop these skills. However, by creating a solid culture around AI and providing your employees with the right training, education, and mentorship, your organization will be well on its way to becoming an early adopter.
Establishing AI Standards for Your Organization
Artificial intelligence continues to spread across various industries, such as healthcare, manufacturing, transportation, and finance among others. It’s vital to keep in mind rigorous ethical standards designed to protect the end-user when leveraging these new digital environments. AI Standards: Roadmap for Ethical and Responsible Digital Environments, is a new five-course program from IEEE that provides instructions for a comprehensive approach to creating ethical and responsible digital ecosystems.
Contact an IEEE Content Specialist to learn more about how this program can benefit your organization.
Interested in getting access for yourself? Visit the IEEE Learning Network (ILN) today!
Resources
Chen, Stephen. (31 August 2021). Three Crucial Alignments To Enable Success In Automation And AI Initiatives. Forbes.
Walsh, Bryan. (9 August 2021). Exclusive: Businesses that lag on AI risk falling behind permanently. AXIOS.
| 2021-09-08T00:00:00 |
2021/09/08
|
https://innovationatwork.ieee.org/three-ways-to-prepare-your-workforce-for-artificial-intelligence/
|
[
{
"date": "2023/03/01",
"position": 86,
"query": "workplace AI adoption"
},
{
"date": "2023/07/01",
"position": 86,
"query": "workplace AI adoption"
},
{
"date": "2024/03/01",
"position": 89,
"query": "workplace AI adoption"
},
{
"date": "2024/06/01",
"position": 86,
"query": "workplace AI adoption"
},
{
"date": "2024/12/01",
"position": 87,
"query": "workplace AI adoption"
},
{
"date": "2025/05/01",
"position": 98,
"query": "artificial intelligence workers"
},
{
"date": "2025/06/01",
"position": 99,
"query": "artificial intelligence workers"
}
] |
AI Impact on Job Market in the Next 10 Years
|
Discover thousands of collaborative articles on 2500+ skills
|
https://www.linkedin.com
|
[] |
AI will create more jobs than it destroys. According to a report by PwC, AI could create 15.7 million new jobs in the UK alone by 2037, while displacing 7 ...
|
We can’t find the page you’re looking for. The page you’re looking for may have been moved, or may no longer exist. Try going back to the previous page or check out more articles in this collaborative article page.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/ai-impact-job-market-next-10-years-sridhar-gande
|
[
{
"date": "2023/03/01",
"position": 9,
"query": "AI labor market trends"
}
] |
|
findings from the OECD AI surveys of employers and workers
|
The impact of AI on the workplace: Main findings from the OECD AI surveys of employers and workers
|
https://ideas.repec.org
|
[
"Marguerita Lane",
"Morgan Williams",
"Stijn Broecke",
"Author",
"Listed"
] |
by M Lane · 2023 · Cited by 130 — The findings suggest that both workers and their employers are generally very positive about the impact of AI on performance and working conditions.
|
New OECD surveys of employers and workers in the manufacturing and finance sectors of seven countries shed new light on the impact that Artificial Intelligence has on the workplace —an under-researched area to date due to lack of data. The findings suggest that both workers and their employers are generally very positive about the impact of AI on performance and working conditions. However, there are also concerns, including about job loss—an issue that should be closely monitored. The surveys also indicate that, while many workers trust their employers when it comes to the implementation of AI in the workplace, more can be done to improve trust. In particular, the surveys show that both training and worker consultation are associated with better outcomes for workers.
Citations are extracted by the CitEc Project , subscribe to its RSS feed for this item.
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:oec:elsaab:288-en. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: the person in charge (email available below). General contact details of provider: https://edirc.repec.org/data/eloecfr.html .
Please note that corrections may take a couple of weeks to filter through the various RePEc services.
| 2023-03-27T00:00:00 |
2023/03/27
|
https://ideas.repec.org/p/oec/elsaab/288-en.html
|
[
{
"date": "2023/03/01",
"position": 40,
"query": "AI labor market trends"
},
{
"date": "2023/03/01",
"position": 55,
"query": "artificial intelligence workers"
}
] |
The Impact Of Artificial Intelligence On The Future Of Work
|
The Impact Of Artificial Intelligence On The Future Of Work
|
https://www.linkedin.com
|
[
"International Institute For Learning",
"Ramesh Ranjan",
"Martin Miller"
] |
Finance: AI can be used to analyze financial and economic data, predict market trends, and help companies make better investment decisions. · Health · Commerce ...
|
Today, we are going to go further in exploring AI and its potential in our professional lives. In this article, we're going to look at how AI can be used in different ways to help us in our work, helping us to be more productive, better understand our data, and make better business decisions. We will also see how AI can help us communicate and collaborate better with our colleagues. If you want to know how AI can help you in your work, this article is for you.
How Will AI Transform The World Of Work?
In general, artificial intelligence (AI) can be used in many industries and activities in many different ways.The following examples illustrate how AI can be particularly effective:
Finance: AI can be used to analyze financial and economic data , predict market trends, and help companies make better investment decisions.
, predict market trends, and help companies make better investment decisions. Health: AI can be used to diagnose diseases, recommend treatments, and track patient health.
Commerce: AI can be used to recommend products to customers based on their interests and purchase history, as well as predict consumer trends.
Transportation: AI can be used to optimize transportation routes and predict vehicle maintenance needs.
Agriculture: AI can be used to predict crop water and fertilizer needs, as well as to detect diseases and pests.
Marketing: AI can be used to target ad campaigns based on user interests and browsing history, as well as optimize ad content for relevance and performance.
Human Resources: AI can be used to screen applications and assess the skills and qualities of job applicants.
Media: AI can be used to analyze trends in news topics and predict which stories will be most popular with readers.
Construction: AI can be used to optimize construction plans and forecast labor and material needs.
Customer service: AI can be used to automatically respond to customer requests and provide online help.
Of course, AI can be used in many other ways in different sectors. It largely depends on the specific needs of each trade and industry and how AI can be used to improve efficiency and productivity.
How Can Artificial Intelligence Be Useful In My Job?
Whatever your profession or your activity, artificial intelligence can be of great use to you today or even be essential in the future in order to allow you to progress in your profession and maximize your productivity and performance. Here are some examples of the usefulness of artificial intelligence in different professions:
Automation of Repetitive Tasks: AI can be used to automate some tedious and repetitive tasks , allowing you to focus on more important and high-value tasks.
, allowing you to focus on more important and high-value tasks. Data Analysis: AI can be used to analyze large amounts of data quickly and accurately, which can help you better understand your work and make better decisions.
and make better decisions. Communication and Collaboration: Some AI technologies, like virtual assistants, can help you communicate and collaborate more effectively with your colleagues.
Training and Professional Development: AI can be used to provide you with training and professional development opportunities tailored to your interests and skills.
tailored to your interests and skills. Content Generation: AI can be used to generate content from given data and specifications, which can help you save time when you are overloaded with work.
Spelling and Grammatical Correction: AI can be used to automatically correct spelling and grammatical errors in your emails, which can improve the quality of your communication.
Phrase and Word Suggestion: AI can be used to suggest relevant phrases and words for your email, which can help you write more effectively.
for your email, which can help you write more effectively. Email Classification and Sorting: AI can be used to automatically classify and sort your emails based on importance and content, which can help you better manage your correspondence.
Automated Reply: AI can be used to automatically reply to certain emails, which can help save you time when you're busy.
Vehicle Maintenance: AI can be used to monitor the health of your vehicle and alert you to potential issues, which can help you avoid breakdowns and extend the life of your vehicle.
Time management: AI can be used to help you plan your schedule and remind you of important tasks.
Code Generation: AI can be used to generate code from given specifications, which can help you save time and focus on other tasks.
Testing and Debugging: AI can be used to automatically test code and detect errors, which can help improve the quality of your work.
Code Optimization: AI can be used to optimize code to make it faster and more efficient, which can improve the performance of web applications.
Documentation Generation: AI can be used to automatically generate code documentation, which can help you better understand and maintain your code.
Medical Diagnosis: AI can be used to help doctors diagnose diseases by analyzing data on symptoms, medical histories, and test results.
Treatment Recommendation: AI can be used to recommend treatments tailored to each patient's needs based on their medical history and test results.
Health Tracking: AI can be used to track the health of patients and detect signs of deterioration in their health early on.
Medical Research: AI can be used to analyze disease and treatment data to uncover new insights that can be used to improve medical practice.
Accounting Automation: AI can be used to automate certain accounting tasks, such as data entry and account verification, freeing you to focus on more complex tasks.
The benefits of AI in your work are many. They largely depend on your industry and your specific business needs.
What Are The Professions Most Threatened By Artificial Intelligence?
The professions and jobs that will be threatened by artificial intelligence (AI) in the future are a matter of serious concern. Indeed, they depend on many factors, such as the evolution of technology, changes in the needs of the economy, and the decisions taken by employers and employees, but also by governments and public and international institutions.
However, it is generally accepted that occupations that primarily involve routine and repetitive tasks are most at risk of being replaced by AI. Some of these professions include:
Industrial workers, such as machine operators or truck drivers.
Administrative employees, such as secretaries or data entry clerks
Sales and customer service professionals, such as cashiers or telemarketers,
It is also possible that some professions that involve more complex tasks, such as decision-making or creativity, may be affected by AI in the future, such as:
Insurance employees, such as insurance agents or claims adjusters, could be replaced by software that can analyze risk data and determine compensation amounts.
Logistics professionals, such as supply chain managers or transportation planners, could be replaced by automated planning systems that can optimally manage the flow of products.
Banking and finance employees, such as investment advisers or brokers, could be replaced by programs capable of doing financial analysis more quickly and accurately.
Translation professionals, who may face competition from high-quality machine translation software.
However, this evolution should be more gradual, and AI will be used more as a decision-support tool than as a total replacement.
It should be noted that AI could also create new jobs and new work opportunities by automating certain tedious and repetitive tasks, thus allowing employees to focus on more creative and strategic tasks. For example, AI could help lawyers complete legal research faster, giving them more time to focus on the more complex aspects of their work.
What Are The Jobs Of The Future?
To answer the question, I posed the problem to an artificial intelligence (ChatGPT), and here is the answer:
Here are some examples of trades that could be in demand in the future, according to this smart robot:
Jobs related to information and communication technologies (ICT): software development, website development, data analysis, etc.
professions linked to the environment and renewable energies: environmental engineering, management of projects linked to renewable energies, etc.
Professions related to health and well-being: professions in health, psychology, nutrition, etc.
Cybersecurity Experts: As technology becomes more integrated into our daily lives, cybersecurity threats will continue to grow. Experts who can develop and implement security measures to protect sensitive data will be in high demand.
Conclusion
In conclusion, artificial intelligence (AI) can be a useful tool that helps workers do their jobs more quickly and effectively.From managing tedious and repetitive tasks to coming up with new ideas and keeping up with the news, AI can offer valuable assistance in many professional fields.
Although AI can create some fears about its impact on employment, it is important to remember that it can also create new professions and work opportunities. AI can help improve work performance and keep you competitive in the job market if you keep an eye out for changes and adapt to them.
The combination of AI and CRM is a powerful tool in today's marketing and sales landscape. Since the internet is replacing old ways of doing things, CRM is now a must-have for collecting business information and customer data.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/impact-artificial-intelligence-future-work-2btechinc
|
[
{
"date": "2023/03/01",
"position": 54,
"query": "AI labor market trends"
},
{
"date": "2023/03/01",
"position": 41,
"query": "artificial intelligence workers"
}
] |
|
Can RA jobs be replaced by Artificial Intelligence?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
For example regulatory intelligence may be streamlined though AI, but real personnel are still required to contextualize and strategically apply those insights.
|
This is kind of a stupid question. I don’t really know what tasks this career entails yet since I just learned about it. In the future, is there a possibility that RA jobs can be taken over by Ai or technology? Is this a career that needs human intervention? Also what about market access?
I’ve heard that over time the job of pharmacists could slowly be reduced. Due to dispensing by tech, accessible information found online, and online ordering.
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/regulatoryaffairs/comments/11o47vc/can_ra_jobs_be_replaced_by_artificial_intelligence/
|
[
{
"date": "2023/03/01",
"position": 4,
"query": "AI regulation employment"
}
] |
|
A policy primer and roadmap on AI worker surveillance ...
|
A policy primer and roadmap on AI worker surveillance and productivity scoring tools
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Merve Hickok",
"Aiethicist.Org",
"Geddes Rd",
"Ann Arbor",
"Mi Usa",
"Nestor Maslej",
"California"
] |
by M Hickok · 2023 · Cited by 30 — This Policy Primer and Roadmap focuses on workplace surveillance and productivity scoring tools and practices.
|
Developers of AI and algorithmic systems promise these systems benefit organizations by increasing the efficiency, effectiveness, and scalability of processes, “streamlining and redefining” the workplace, reducing costs and standardizing application of rules—and hence improve profitability [15]. However, there is also a group of AI applications available in the market, which promise employers different capabilities to track, monitor and assess their workers. The power to have an all-seeing eye over the workforce is attractive to many employers. These technologies were once more prevalent in factory settings. The gaze of algorithmic surveillance was and is still disproportionately on low-income workers., The workers are now spread across different work contexts such as logistics, hospitality, food and service delivery jobs, or gig workers in online platform companies [26]. These jobs are then disproportionately held by workers of color. However, the reduced costs and improved capabilities for data collection, processing and retention also allows surveillance to extend to pink- and white-collar workers too. Worker surveillance is becoming a common phenomenon across all workplaces. When surveillance moves from the factory or warehouse floor to the devices workers use from other settings (such as home office, vehicles) or even carry on their bodies, surveillance becomes inseparable—it also ‘bleeds into’ workers’ private lives [11, 14]. As these workers become hyper visible through surveillance systems, the employers become more invisible behind the algorithmic decision-making systems.
It is easier to notice the physical cameras around us. However, with surveillance technology available in many shapes and forms, it is not always easy for the workers to know they are being monitored, and their data is collected. In the US, Employers can use such tools without informing their workers [ 27 ]. Workplace data collection powering surveillance can be achieved by a combination of hardware and software as listed below.
Productivity scoring
“Not everything that can be counted counts. And not everything that counts can be counted.”—paraphrased from William Bruce Cameron [28].
The attraction of new technologies and vendor claims to extract actionable ‘productivity’, ‘risk’ or ‘fit’ scores for workers give rise to a variety of black-box algorithmic products in the market [29]. The products collect a plethora of data points and compare them against subjective rules to provide a score for a worker or infer certain behavioral characteristics. These scores can then be used by human managers to make determinations about the workers efficiency, productivity, risk to company’s assets and reputation. The scores also drive decisions about wages, benefits, promotions, disciplinary action or even terminations. At the extremes, these decisions can be automated and do not even require a human manager to review and validate.
When one thinks of how surveillance and scoring systems work, and how they are connected, it might be helpful to break the process down into smaller components. First, a method to track and record worker activity is necessary. Hardware, such as company-provided devices (phone, tablet, wearable fitness trackers), camera, wireless connection routers, sensors can be used to collect raw data on worker communications, online activity, movement, work outputs etc. Then, once the data is collected, an algorithmic model is necessary to analyze the collected data and make inferences or determinations about the worker behavior and performance. Developers make various design decisions on how to collect data and how to build these AI models. At times, there might be legitimate reasons to install certain data collection technology to ensure workers safety and security. Alternatively, the employer might be required by law to record worker communications. However, outside of these very limited reasons, most of these technologies are built upon problematic design decisions. The choice of the term ‘surveillance’ over ‘monitoring’ in this paper is intentional. Surveillance acknowledges the power employers hold over workers and the practices of ubiquitous collection of data on worker communications, engagement and interactions used mainly for the benefit of the employer. The data can then be used in control and manipulation of work engagement and contractual negotiations (if a contract even exists).
Vendors of these scoring systems claim the surveillance data collected can be used to infer the productivity, risk or fit of workers in relation to their roles. The claims and embedded design decisions include fundamentally erroneous assumptions, such as the ability for technology to correctly capture a human’s complex nature, or infer emotions and sentiments, or that human behavior can always be predicted. Use of surveillance and scoring technologies also infringe upon an individual's rights and freedoms. These technologies and assumptions embedded in them can be in direct contradiction with fundamental human rights [4]. Despite the impossibility of delivering on their marketing promises, these systems still find buyers among the business decision-makers.
Human dignity: Surveillance first and foremost degrades human dignity. Even if workers know about surveillance technologies, they may not have the possibility or privilege of leaving a job due to concerns over aggressive data collection or algorithmic decisions. If worker consent is requested at all, workers are asked to choose between their ability to earn a wage versus their data being collected. Their choice naturally favors employment. In such an imbalanced power situation between employer and worker, one cannot count the consent as a free or informed one. The workers lose control of privacy over their own bodies, movements, and even social interactions [30]. Who gets to draw the boundary about what is crucial information for an employer? In the absence of protections by law or organized labor, the workers are left to themselves to defend against surveillance. The boundary line is drawn ‘upon’ their bodies.
Human dignity is undermined again in the scoring systems as human complexity, engagements, aspirations, and creativity are reduced to points of data and spurious correlations. There is no longer a human story behind the interaction, nor is there the ability to ‘bring your whole self to work.’ The essence of the worker and complexity of a being and human interactions are boiled down to the data deemed important by vendors and employers, and data which can be collected.
Legal scholar Ifeoma Ajunwa also highlights that especially wearable data collection technologies may create new legal challenges such as the possibility that employer engages in unlawful surveillance (defined under National Labor Relations Act) “when it surveils employees engaged in concerted activities by observing them in a way that is ‘out of the ordinary’ and therefore coercive [31]” Such practices also undermine fundamental principles such as the Fair Information Practices, which include collection limitation, purpose specification, use limitation, accountability, security, notice, choice, and data minimization [32]. For example, data initially collected by third parties (such as fitness trackers provided by wellness or insurance companies) via the employers, can eventually be used in ways that restrict the worker’s access to resources and opportunities elsewhere [14].
Right to privacy: One of the most cited issues in worker surveillance is the infringement of privacy. The right to privacy is considered a fundamental human right. In the United Kingdom, Barclays bank faces a $1.1 billion fine over alleged monitoring of employees [33]. In Germany, data protection regulator fined electronics retailer notebooksbilliger.de for $12.6 million for using video cameras to surveil workers [34]. However, in the US, employers can collect information when workers use organization-provided devices or networks. In the absence of federal privacy regulations, a privacy regulator, or any laws limiting worker surveillance practices, the status quo allows employers to do as they see fit for their own interests. However, legal does not always mean ethical.
A recent OECD working paper AI in the workplace highlights that use of AI systems can “extend and systematize ethical failings and fundamentally change the relationship between workers and their managers” [35]. Some surveillance practices cross the line between work and private life where employers can capture very private information about the workers. For example, employers can engage in (1) social media surveillance, (2) video surveillance in the office, (3) mandate workers to use smart assistants which record conversations, or leave their laptop cameras on, (4) take screenshots of monitors at random times during the day, or (5) force workers to download mobile applications on their personal phones which continue to collect information outside of working hours. In 2022, a Dutch court ruled an employer requiring employees to keep webcams on for several hours a day and share screens, violated the right to respect for private and family life. In Germany, the data protection regulator fined retail company H&M for $41 million for the illegal surveillance of employees and keeping "excessive" records on the families, religions and illnesses of its workforce [36]. The European Court of Human Rights had a similar ruling in 2017 [37]. Such intrusion can also lead to unintentional disclosure of information protected by Title VII of the Civil Rights Act of 1964 [38] (such as sex, race, color, national origin or religion, sexual orientation, etc.) or Americans with Disabilities Act (“ADA”). Although non-discrimination regulation prevents employers from making employment decisions based on this protected information, knowledge of such information can lead to possible unconscious biases nevertheless [26, 39]. The target of surveillance shifts from the work to the worker. Notice of such protected information which would not otherwise have been known to the employer can create legal risks for the employer and opens the possibility for allegations of discrimination [40].
Right to expression: Ability to surveil a worker’s private and social interactions undermines freedom of expression. By monitoring emails, chats, phone conversations, employers can get access to workers’ thoughts—without discriminating between personal and professional communications. Knowledge of surveillance can force workers to self-filter or self-regulate their expressions and ideas. In paraphrasing Foucault’s ‘technologies of the self”, Manokha highlights the power of surveillance on individuals to self-restraint and self-discipline [41]. In this case, workers, aware of being under surveillance, may end up self-restraining themselves without any coercion or use of force by employers [42]. Employers' interest in surveilling communication also spills over to personal lives. More and more companies are interested in worker or job applicant social media accounts [43], and some even have patented audio technology to eavesdrop on conversations among workers and customers [44]. Some companies demand login access to social media accounts to enable surveillance of these accounts. In certain states where this boundary is protected by law, employers are able to continue the practice via third-party vendors. These vendors parse social media presence and interactions of both candidates and workers and provide ad hoc or ongoing risk scoring to employers. Risk scoring models can create spurious correlations, however many employers still use outcomes as third-party assessment for their employment decisions. Knowing employers can see and act upon their social media posts can prevent workers from expressing their true identities (i.e. sexual preference, religion, ability, etc.) outside of the workplace. Workers can also refrain from posting about social, economic, political, or other societal issues. This can eventually result in significant societal impacts.
Right to data protection: The data collection enabled by AI surveillance technologies is ubiquitous and pervasive. Without federal privacy legislation or robust worker protections, employers not only collect data but can also share the data further with third parties for different purposes. Workers may not access data collected about them or have any say over what the collecting entity might do with their data. Most of the time the workers may not even understand the full complexity of the data, the inferences made about them, or the extent of possible impact or harm. Both UC Berkeley Center for Labor Research and Education [1] and CoWorker.org’s [45] studies state that such data collection lacks clear and consistent safeguards. A possible breach of data can impact the worker’s access to benefits, resources and opportunities outside of the workplace.
Right to collective action and power: The nature of surveillance creates one party which makes the decision to surveil, collect data and benefit from its conclusions; and another party which gets impacted by the decision. When workers try to reduce the power imbalance through individual resistance or collective action, the data can also be used to oppress protected collective activity such as unionization or grievance. In other words, workers without protection “lack bargaining power to sufficiently fight invasive forms of surveillance, and surveillance is even being used to deter and prevent unionization [46]”.
History offers many examples of corporations hiring private investigators to surveil activities of workers to prevent collective action and break strikes [47]. A 1987 report by the United States Office of Technology Assessment, titled “The Electronic Supervisor: New Technology, New Tensions” provides a historical landscape analysis of tensions and considerations created by electronic employer surveillance systems. The report lists main concerns as privacy, fairness, and quality of work life. The factors included in fairness are listed as “reasonable standards, understanding by workers of the extent and use of the monitoring system, ability of workers to contest or correct records, and participation by workers in the design of the system.” The report makes clear there are no legal requirements in U.S. law that surveillance be “fair,” jobs be well-designed or employees be reconsulted about work standards, except insofar as these points are addressed in union contracts [48]” The report acknowledges both the low levels of unionization in the United States and how the surveillance issue has created more motivation for collective action in some previously unorganized firms.
Unfortunately, 35 years after this report, unionization rates are lower than 1987 rates, technology allows for more invasive data collection, and unions’ internal capabilities to counter these surveillance practices leave much to be desired. With the ability to collect information ubiquitously, employers can use the emerging technologies to exert power over workers. With such information disadvantage, algorithms “act as a force-multiplier for the power held by firms, with no balancing agent on the side of workers [49].” In 2021, Spain passed a law requiring online delivery platforms to inform labor unions of how algorithms affect workers’ working conditions [50].
Employers are obliged to “file ‘Surveillance Reports’ to report certain expenditures and arrangements they make in connection with labor disputes [51, 52].” The expenditures clearly include surveillance technologies and activities. However, when workers and unions are rarely aware of covert surveillance practices, it is hard to keep employers accountable for their transparency obligations or challenge fair practices. Scholars Pasquale and Citron advise “secrecy is a discriminator’s best friend: unknown unfairness can never be challenged, let alone corrected [53]. Establishing workers’ data rights under collective agreements not only protects the workers, but prevents the power of unions from diminishing [54].
Right to work and right to just and favorable remuneration: As per the Universal Declaration of Human Rights, every person has the right to work, to just and favorable conditions of work, to equal pay for equal work, and everyone who works has the right to just and favorable remuneration ensuring for themselves and their family an existence worthy of human dignity [4].
Emerging AI technologies increasingly allow previously disparate data to be connected. A great investigative journalism article by ProPublica details how a software sold to landlords can provide them with information regarding the levels of occupancy, rent amounts in their area, and the possibility to communicate with each other over the platform [55]. Whereas previously landlords had to invest significant resources to collect this kind of data individually, such platforms or technological tools now continuously allow the users access up-to-date information. Access to such information can be used to reduce competition and manage vacancies in a way to drive rent prices up beyond their market values. A parallel can be drawn here for wages and worker rights. Tools like Argyle provide aggregated workforce financial data to employers through applicant tracking systems, and to insurance providers, lenders, and credit card issuers through a single API [56]. Argyle’s vision is not only to provide financial data but “holistic view of a worker’s identity including typical hours, work trajectory, reputation and more [57].” In other words, a consolidated way for employers to see a candidate’s employment history and other compensation details before they make an offer. The asymmetrical information power means an employer can offer a less than fair wage rate or cooperate with other employers to suppress wages. Argyle claims to have profiles for more than 175 million workers, covering 80% of the US workforce [56]. While the vendor positions itself as a “third-party verification service which ‘allows’ workers to securely share their income, job title, and proof of employment information with lenders, background check companies, human resources, or any other party they choose [56]” vendor mentions nothing of massive data collection, use and future risks for workers. Some workers may become permanently locked out of employment opportunities due to the recommendations of the systems used by many employers in the industry.
When algorithmic systems become connected to each other for inputs, or the use of the aggregated systems becomes more prevalent in pre-employment decisions, a separate risk emerges. A biased, erroneous or manipulated outcome from one system becomes a direct input to another decision-making system. With such interconnected systems, workers may be locked out of affordable housing, insurance, healthcare, and similar systems [58].
Validity and black-box decisions: Vendors developing the scoring algorithms tend to make a lot of promises about the capacity of their products without disclosing how the scores are calculated, or what design decisions are made within the system. If a client demands to know the science behind the system, the house of cards may fall apart. Instead, it is a lot easier for a vendor to hide behind intellectual property (IP) protections or suggest one should trust the “neutral” technology. However, lack of vetting can expose the employer clients to liability [40]. A client should and can demand transparency. Unfortunately, since both vendors and employers benefit from these technologies in different ways, questions of scientific validity, or whether they should exist in the first place are not of priority.
Even when an employer is aware of the fact the technology is not delivering on the promise, it might still continue with the practice because it at least gives it a way to collect information about worker activity. The employer may choose to fix the issue with another level of surveillance. For example, when an AI system tracking the movements of workers in an Amazon warehouse fails, video footage is sent to other workers in India and Costa Rica. These workers provide input to improve Amazon’s machine learning tools’ accuracy for surveillance. The workers have “no idea where this particular data [is] going…and what exactly is happening in the backend.” These remote workers were also not aware that they themselves were being monitored by screen and mouse activity [59].
Right to due process: “Data-centric technologies hide, obscure, and validate employer behaviors behind an algorithm [60, 61].” Scoring can lead to automatic penalties in wages, shift distributions, and sometimes even to loss of job [15]. Without understanding how the surveillance and productivity scoring algorithms are used to make determinations about their wages, benefits or work conditions, or the unions putting in safeguards in contract clauses, “workers have few pathways to contest harmful employer decisions like discrimination and wage theft [62].” In many jurisdictions, workers also face the additional challenge of algorithms protected by intellectual property legislation. This means that even if they have the means to analyze algorithmic models, workers or unions may still not have access to them. Workers surveilled and scored by these algorithms need enhanced rights—such as right to procedural data due process [63]. In the US, ‘at will’ employment arrangements, used in most low-income jobs, allow both employers and workers to terminate the relationship at any time without having to provide a reason. However, many other employment decisions could still benefit from due process requirements.
Normative judgements: When the scoring models are created, developers make certain decisions. The decisions can include what activity to collect data on, or in other words, what behavior or activity should count towards productivity or risk. Developers make these decisions based on the technical possibility of collecting a particular set of data and what data should be accepted as a proxy to productive work. They make normative determinations about what ‘normal’ or ‘typical’ productivity should look like, then compare the data collected by workers against those norms. They decide on the labels and categorize workers into these labels. In reducing humans into standard categories, the developers also dehumanize and depersonalize the workers [64]. In making these decisions, developers also embed their own values, experiences, culture and biases into the algorithms they develop [65]. A recent New York Times article on worker productivity tracking articulates this issue as “the working world’s new clocks are just wrong: inept at capturing offline activity, unreliable at assessing hard-to-quantify tasks and prone to undermining the work itself [15].” The “choices in which factors to prioritize, or their failure to specify all relevant factors, can result in unanticipated consequences [102].”
By measuring everyone against a certain norm, and requiring similar behavior, these algorithmic systems create homogeneity. Charlie Munger, vice chairman of Berkshire Hathaway, one of the most successful business investors says, “Mimicking the herd invites regression to the mean (merely average performance) [66].” Companies globally spend significant amounts of time and resources to attract candidates with diverse backgrounds, experiences, identities and perspectives. When surveillance and scoring systems are used to determine a worker’s conformity to certain norms and behaviors, and discourage differences, the employers end up sabotaging their own efforts in the long run.
Context and cultural specificity: Just as the developers of algorithms embed their own normative judgements into scoring systems, they also claim the universality of their products. However, anyone who has traveled to different parts of a country or internationally, would attest cultural differences find their correspondence in work relations. Different cultures prioritize different behavior at work and have variety in how workers interact between themselves.
Even within a homogeneous work environment, scoring systems still cannot capture the complexity of work, nor do they take into account the external factors or circumstances which might be impacting a worker’s ability to deliver an output or complete a task within a certain amount of time. Without appreciating the context of worker interactions and the totality of the effort which goes into creating an output, these systems prioritize quantity and quantification [63] over quality and depth of work. Data is not independent from its context. Some workers subject to productivity algorithms characterize the situation as “infuriating”, “soul crushing” and a “kick in the teeth” as the employers had failed to grasp the totality of the tasks making up their job [11]. The expectation from employers is for workers to be robot-like subjects. This approach leaves no room for differences and diversity, and no appreciation for offline work such as thinking, reading printed material, brainstorming with co-workers, mentoring other workers.
Disability discrimination: When these systems make judgements about what be considered typical or expected productivity, they can also lead to other harms for people with disabilities. Some assessments of ADA [39] suggest “If an employer adopts a faster pace-of-work standard and enforces it rigidly, it could run afoul of the ADA’s prohibition against “standards, criteria, or methods of administration... that have the effect of discrimination on the basis of disability [67].” More than half of disabilities are invisible, and are highly diverse, making them “virtually impossible to analyze at scale [68]. In addition, only 21% of employees with disabilities disclose them to their employers’ human resources departments [69]. Access to biometric or health data collected by wearables or via a worker’s social media accounts can give managers or employers additional information to infer ability or health condition of workers, leading to possible biased decisions, or spurious inferences. Even if the information did not play a role in an adverse employment decision, employers could be alleged to have discriminated due to a disability or perceived disability [40].
The technical shortcomings of the AI system, such as inaccuracy of devices, can also cause unintended harm. For example, wearables collecting health and wellness information may not be accurate in the first place [70, 71] but can be still used for work related determinations. Since scientific validity of the system and possible technical biases are not questioned, the workers can be subjected to discriminatory outcomes. Or imagine a scenario when the developer, or employer is not aware of the bias in the system. For example, assistive devices (for example screen readers) may interfere with the accuracy of data collected. Or if the scoring systems disadvantage neurodivergent people, those with slower reading speeds or those multitasking, then the outcomes might be discriminatory.
Erosion of trust: The history of worker surveillance provides ample evidence for how employers choose the easier route of surveilling workers rather than investing in establishing trust and a shared vision with their workers [72]. In many cases, employers choose the top-down, hierarchical methods to control and shape. The alternative is co-creation and determination of shared values and vision. Workers trusted with adding value and keeping themselves and the employers accountable to agreed outcomes. The absence of trust from employers leads to erosion of trust and loyalty from workers. The work-from-home arrangements that emerged as a result of the COVID-19 pandemic created a panic environment for many employers. A Harvard Business Review article highlights the “negative spiral in which manager mistrust leads to micromanagement, which then leads to drops in worker motivation, further impairing productivity” and this spiral became deeper with COVID-19 pandemic [73]. A recent Microsoft report highlights that 85% of leaders say that the shift to hybrid work has made it challenging to have confidence that workers are being productive [74]. Whether it is tracking remote workers, or those operating in a large physical setting (i.e. warehouses, shops) or mobile workers (i.e. drivers, delivery workers), or those who are Quiet Quitting, use of surveillance and productivity tools breaks trust relationships in unrepairable ways [75] and can backfire to result in less productivity [76, 77].
Impact on health and safety: The increased pace-of-work and productivity expectations which leave no room for rest, thinking or corrective action leads to more workplace accidents [78, 79]. The “electronic sweatshop” requires repetitive, fast-paced work demanding constant alertness and attention to detail [80]. More repetition also leads to more severe physical injuries. Research literature shows increased stress associated with workplace performance scoring technologies [81–83]. Loss of autonomy over work, stress, and ubiquitous observation increases risk of psychological harm and mental health problems for workers [67].
Sometimes employers frame the productivity scoring systems as ‘games’. In other words, under the guise of turning work into competitive metrics, employers pitch workers against each other. Employers make the productivity metrics visible to all, potentially causing further stress on the workers. Even when such competition is used as part of a wellness program, the normative judgements of fitness and health are imposed upon workers. For example, expecting workers to meet certain fitness standards, and then making the metrics of those not fitting the ‘expectations’ (i.e. weight loss trackers) visible to everyone can be considered a form of body-shaming. The race to meet the demanded metrics, stress and the toll on physical health eventually leads to worker burnout [84]. In workplaces where one worker is easily replaceable by another without consideration to the human behind the data, and in the absence of any legal consequence, employers do not have any incentive to improve conditions.
Feedback loops and behavioral change: Algorithmic decision-making systems change the behavior of users and those who are impacted by the outcomes of these systems. They change and shape the culture and priorities of the implementing organization in many ways. By incentivizing workers to focus on a particular task rather than innovation and experimenting, “the organization sends a message to its workers simply by the tasks it chooses to monitor [85].” Productivity systems may result in unintended consequences of workers spending more time doing a particular activity, which is counted and rewarded, than achieving results. The metric becomes an end in itself. Surveillance works to discipline workers to conform to expected behavior which can be measured [64]. When worker’s autonomy and agency are reduced, the result is also a reduction in the capacity to be creative and “the ability to think or sometimes act out of the box [35].”
When workers are under surveillance and worry about their scores impacting their compensation or the future of their work, they will also naturally shift into more self-protecting behavior. Instead of collaborating with their co-workers or sharing their knowledge about more efficient ways of completing tasks, individual workers might become more private, distrusting and competitive [86]. They might also feel the need to game the system. Whether this need emerges as a reaction to the oppressive actions by employers, or whether from a need to increase one’s scores and possibly wages and benefits, gaming the system means finding ways to make it look like one is being productive, but in reality refusing to do what is expected. As a response to lack of trust from the management, workers can seek to circumvent intrusive managerial oversight [87].
Hypervigilance about continuous surveillance and datafication also demoralizes workers and takes away from other tasks that may be meaningful or necessary for long-term wellbeing. Scoring only certain kinds of activities can force the workers to make decisions quicker without having the time to delve deeper into an issue, case or condition. Some researchers even suggest, for example, gamified systems in the workplace could complicate and subvert ethical reasoning [88, 89]. For jobs which require more frequent decision-making, such as health, human or social services, such behavior change can result in catastrophic consequences for people dependent on decisions made.
Shoshana Zuboff highlights that at the workplace “invasive technologies are normalized among captive populations of employees [90].” When an individual accepts work surveillance and scoring technologies as inevitable, the result can be a normalization of similar technologies in other parts of life. The individual internalizes the scored society [91] and invasive and questionable techniques are normalized. Pasquale and Citron warn us that “the menace of scoring in the Big Data economy is the volume, velocity, and variety of information that could be fed into a score, and that these scores could become decisive [53]” in a variety of different contexts. Already a spectrum of products are in use to score an individual, ranging from when assessments for a credit, insurance, employment, education, immigration, or even criminal justice. The practices workers are forced to accept in workplaces will not stay limited to employment decisions.
| 2023-03-20T00:00:00 |
2023/03/20
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC10026198/
|
[
{
"date": "2023/03/01",
"position": 12,
"query": "AI regulation employment"
},
{
"date": "2023/03/01",
"position": 3,
"query": "government AI workforce policy"
}
] |
Followup To Why AI Won't Cause Unemployment
|
Followup To Why AI Won't Cause Unemployment
|
https://pmarca.substack.com
|
[
"Marc Andreessen"
] |
And specifically, because most jobs in the future are going to be in the red, regulated sectors, most jobs are totally safe from AI, regardless of how good AI ...
|
“Wait, why are the red price lines going up and the blue price lines going down?”
The blue price lines are for sectors like consumer electronics, media, and toys, which are mostly neither subsidized nor regulated by the government, which means that technological innovation can be more or less freely applied by anyone in those markets to reduce prices and improve quality. This is why the TV you buy today is so dramatically better and cheaper than the one you bought ten years ago. Nobody gets mad at Samsung when they make a better and cheaper TV except their competitors, who either get to work on the same thing themselves or go out of business.
The red price lines are for sectors like health care, education, and housing, which are extensively subsidized and regulated by the government, and also tend to have monopolistic/oligopolistic/cartel-like industry structures which are enabled and supported by the government. What happens if you subsidize a product whose supply is restricted? Its price rises. What’s restricting the supply? Regulation. This is the effect of most “consumer protection” regulations which may start with good intent, but are quickly hijacked by incumbent suppliers as protect themselves from new competition. This is why new bank creation virtually ended after the Dodd Frank law was passed. Many such cases.
Put yourself into the shoes of a monopolistic/oligopolistic/cartel-like incumbent in one of the red line industries. What do you care about? As long as nothing changes, your life is wonderful. You get paid a fortune, and don’t have to do anything new. So you perpetually lobby the government and conspire with other incumbents to prevent change. What’s the scariest form of change? Technology change. What’s the main thing you try to prevent? Technology change. How good are you at preventing it? Really good, just look at the red price lines. Who prevents it for you? Your captured agents in the government, to whom you provide lavish campaign contributions and revolving-door salaries while they loudly claim to be protecting consumers from you. Repeat as necessary until you have a total monopoly with infinite prices and infinite profits.
| 2023-03-01T00:00:00 |
https://pmarca.substack.com/p/followup-to-why-ai-wont-cause-unemployment
|
[
{
"date": "2023/03/01",
"position": 13,
"query": "AI regulation employment"
}
] |
|
Artificial intelligence applied to potential assessment and ...
|
Artificial intelligence applied to potential assessment and talent identification in an organisational context
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Tiago Jacob Fernandes França",
"Inesc Tec",
"University Of Trás-Os-Montes E Alto Douro",
"Henrique São Mamede",
"Universidade Aberta",
"João Manuel Pereira Barroso",
"Vítor Manuel Pereira Duarte Dos Santos",
"Magic",
"Nova Ims",
"Universidade Nova De Lisboa"
] |
by TJF França · 2023 · Cited by 90 — When The Machine Meets The Expert: An Ethnography Of Developing Ai For Hiring. ... To summarise, as AI becomes more common in organisations, the laws and ...
|
Our study provides valuable insights into the relationship between artificial intelligence (AI) and Human Resource Management (HRM). We have minimised bias and ensured reliable findings by employing a systematic literature review and the PRISMA statement. Our comprehensive synthesis of the studies included in this research, along with a bibliometric analysis of articles, journals, indexes, authors' affiliations, citations, keyword co-occurrences, and co-authorship analysis, has produced robust results. The discussion of our findings focuses on critical areas of interest, such as AI and Talent, AI Bias, Ethics and Law, and their impact on Human Resource (HR) management. Our research highlights the recognition by organisations of the importance of talent management in achieving a competitive advantage as higher-level skills become increasingly necessary. Although some HR managers have adopted AI technology for talent acquisition, our study reveals that there is still room for improvement. Our study is in line with previous research that acknowledges the potential for AI to revolutionise HR management and the future of work. Our findings emphasise the need for HR managers to be proactive in embracing technology and bridging the technological, human, societal, and governmental gaps. Our study contributes to the growing body of AI and HR management knowledge, providing essential insights and recommendations for future research. The importance of our study lies in its focus on the role of HR in promoting the benefits of AI-based applications, thereby creating a larger body of knowledge from an organisational perspective.
1. Introduction
The Peter Principle, as defined in the Peter Principle of Management [1], states that “every employee tends to rise to his level of incompetence”, meaning that the best employees are not always the best candidates for promotion. The Peter Principle states that promotion decisions often support the candidate's performance in current roles rather than necessarily their capacity to perform in long-term management roles. It also demonstrates that, even if an employee's tasks change, organisations continue to believe that the attributes that have made someone successful in the past will continue to contribute to their success in the future. According to Bersin & Chamorro-Premuzic [2], individuals are promoted based on past achievements.
Understanding the importance of hiring the right person has become a priority for many businesses [3]. While talent management encompasses various human resource strategies, Claussen et al. [4] argue that strategic talent management covers an organisation's identification of essential jobs and, later, the building of a talent pool to fill these positions. According to this definition, necessary position staffing is a critical component of talent management [4]. Organisations that efficiently manage their human capital are more likely to achieve outstanding performance and generate long-term competitive advantage [[5], [6], [7]]. A breakthrough McKinsey report published in 1997 [8] identified the “war for talent” as a strategic business problem and a significant driver of company success. Even when many people thought the struggle for talent was over, it was not. According to the authors [8], the battle for talent would continue for the next two decades due to persisting economic and societal causes, revealing that winning the fight for leadership talent requires much more than disruptive recruitment methods. It shows the pressing need for more about using time-tested concepts of attracting, developing, and keeping highly competent managers in daring new ways. Talent management ties directly to the notion of enterprise management and knowledge transfer. When seen through the lens of international corporations as a way of obtaining success, this issue takes on additional significance [7].
Although definitions concerning talent differ, four essential criteria separate more talented people from less qualified employees [9]. The first is the 80/20 rule, based on Vilfredo Pareto's observation [10] that a small number of people produce a disproportionate percentage of any group's production. Specifically, about 20% of employees will account for around 80% of productivity. The second is the concept of maximum performance, which equates talent with the most an individual can achieve as their highest possible performance. The third associates talent with seamless achievement, emphasising the importance of natural ability or potential, meaning a more talented person will outperform a less capable person. The fourth connects skill and personality in the proper context, as individuals should perform at a greater level when their talents match a task. According to Chamorro-Premuzic et al. [9], these criteria can classify individuals as more or less gifted.
Even though it is possible to win the talent battle [11], an organisation must make talent management a top business priority. Therefore, the organisation must constantly develop and improve the employee value proposition to recruit and retain the right individuals. In essence, the war for talent is about understanding the strategic relevance of human capital due to the significant value that more excellent skills provides [7,8]. An organisation's workforce can provide the talent it needs, which aligns with its goals and strategy. Conducting talent management processes aimed at an organisation's employees is critical, as organisational talent is, in the long run, one of the most vital components in transforming crises into organisational success [12]. According to Coates [13], performance appraisals are part of the postmodern corporate concept of a human-centred, subjective management system intended to uncover potential in employees and motivate and reward them. One of the most critical aspects of performance management, according to Mert [14], is defining what “good performance” means. In recent years, the notion of effective performance has shifted away from dependent activities towards creativity, innovation and elements that diminish employee interdependence. Assessing these characteristics demands an evaluation of employees' potential for future success [14].
According to Assessment Associates International [15], organisations must evaluate candidates on two primary criteria to determine talent: performance (an individual's efficacy and outcomes in their current role) and potential (the anticipated future performance of an individual if they have development opportunities and greater responsibility). Although performance evaluation helps an organisation evaluate its employees' performance, it only provides limited information on potential performance in areas that demand different skills, according to Künneke [16]. Moreover, the purpose of potential assessment is to manage future performance, which means that it goes beyond evaluating an employee's past and present behaviour to identify the employee's potential performance, which links to the latent qualities that the employee possesses but has not yet been made available to the organisation [14].
Potential in an organisational context refers to an individual's ability to advance and succeed in a higher position, that is, to grow and deal with more responsibilities and scope [17]. By assessing their employees' potential, organisations obtain the essential knowledge to set realistic goals based on the capabilities of their teams, preventing dissatisfaction and bad performance scenarios. Strategies define capabilities, and capabilities represent talent [18].
Künneke [16] asserts it is critical to discern between high potential and high performers. High potentials can handle confusing and challenging tasks, making them good candidates for senior and leadership roles in the organisation. High performers have in-depth knowledge of their expertise and outperform their counterparts in their present employment. On the other hand, high potentials adapt quickly to new activities and environments, excelling even in areas outside their current work and specialisation. In the 1970s, McKinsey [19] created the Nine Box Matrix to assist General Electric in prioritising investments across its 150 business divisions. The matrix assessed each business unit's industry attractiveness and competitive strength. Not every business unit was equally appealing. It was ascertained that some should be invested in, while others should be extinguished. HR teams have adopted this model as a talent management tool over the last 40 years, replacing the two industrial axes with people-specific ones: performance and potential. The main goal of the Nine Box Matrix is to categorise employees, determine which to promote, retain and invest in, and which to reallocate. Companies give the few employees that strongly influence the company's performance particular attention through individualised and tailored solutions with higher aspirations and expectations to match the increased investment in them [18].
Additionally, three trends in the Hype Cycle for Human Capital Management Technology in 2021 can be observed, as noted by Zuech [20]. Because of the fierce competition for talent and the expanding number of job openings, talent acquisition leaders are working harder to get applicants through the pipeline [20]. As a result, AI in talent acquisition (TA) and video recruiting are two breakthroughs helping to ease some of these pain points to fill openings more swiftly and efficiently as the first trend. The second trend is using technology to develop and retain talent, as employee interactions and career advancement facilitate the internal talent marketplace and Learning Experience Platforms (LEPs). The third trend is regarding technology related to employee well-being and productivity.
Likewise, we can analyse the Hype Cycle for Artificial Intelligence in 2021 and observe four emerging trends, as detailed by Goasduff [21]. Organisations are rapidly embracing AI solutions to innovate and improve existing products by leveraging Natural Language Processing (NLP) and upcoming technologies such as generative AI, knowledge graphs and composite AI. As a result, the four trends that dominated 2021's AI landscape are 1) Implementing AI projects; 2) Making efficient use of data, models, and computing; 3) Data for AI and 4) Responsible AI.
AI is considered a game-changer since it can provide self-learning capabilities as well as increase decision quality [22], and still, both Jia [23] and Tambe [24] state that there is a gap between the promise and the reality of AI technology application in the Human Resources Management field.
There is a research gap for more technological models concerning implementing AI technologies in HRM across organisations [[24], [25], [26]]. We need more progress regarding what concerns HRM when algorithms make choices, mainly because of the complexity of the human resources phenomena, data issues from human resources processes, fairness and legal restrictions, and employee engagement in AI management.
1.1. Research problem According to Chamorro-Premuzic et al. [9], the digital revolution has resulted in many new technologies that quickly and cheaply infer human potential and forecast future work performance. However, academic Industrial–Organisational (I–O) psychologists, who focus on the behaviour of employees in the workplace, appear to be mere observers, as there has been sparse scientific research on new evaluation methods, leaving HR practitioners with little solid data to judge the effectiveness of such tools. Additionally, AI as a game-changing technology will revolutionise the workplace, but it is still in its infancy in HR and people management [27]. There is a relentless quest for talent which means there is a need to find and retain talent inside organisations, so organisations should invest in talent management to attract top talent, motivate their employees and ensure essential tasks at all times [28]. Furthermore, improving the efficiency of Human Resource Management through AI has become an important trend in the future development of Human Resource Management [29]. However, only 22% of organisations claim to have implemented analytics in HR, and we need to clarify how sophisticated those analytics are in those organisations [24]. As such, AI technology and human capital, as well as AI's importance to human capital-related performance, are still in early development [30], and AI is crucial in improving the quality of HR choices [31]. We expect AI to revolutionise and enhance the human resources industry [32], and AI research's theoretical and practical significance in HRM has been proven [33]. Although recent studies have discovered more than 300 Human Resources technology start-ups developing AI tools and products for HR or people management, with almost 60 of these organisations attracting customers and funding, there is minimal information on the application and impact of Machine Learning (ML) in HR [27]. AI might bring a future of significant increases in fairness and efficiency. However, it can also evolve into pervasive injustice and abusive control over managers' decisions, implying that both scenarios can coexist [34]. Although adopting AI systems in organisations is still restricted [35], an AI-driven future is rapidly dawning [27]. This phenomenon prompts a more significant concern regarding the implications of the lack of ethics and resulting injustices of the use of AI in Human Resources, potentially leading to a corporate control future, reflecting internal criticisms of the technology sector, which states that AI engineers are excessively focused on technical problems and financial goals while ignoring the ethical and societal implications of their work [36]. Modern organisations must support their operations in information systems to survive the talent war. AI in HR activities is one conceivable architecture that will demand a more profound transformation to address the evolution of the old HR processes into more valuable methods improved by information technologies. In this perspective, many new challenges are posed to both organisations and information systems, making it essential to have methodologies to support these changes, particularly if the existing ones do not meet the requirements. The existence of a framework or model that allows a systematic approach to all these questions, enabling organisations to use it to support their employee's talent towards this paradigm, is of great interest and practical utility in our opinion, and the directions and answers should be discussed and found. An AI-based model can assist and improve HRM's goal of analysing its employees' potential. As such, research that can accomplish it will add value to the scientific community and all organisations, giving them a competitive advantage.
| 2023-03-23T00:00:00 |
2023/03/23
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC10073758/
|
[
{
"date": "2023/03/01",
"position": 54,
"query": "AI regulation employment"
},
{
"date": "2023/03/01",
"position": 32,
"query": "artificial intelligence hiring"
}
] |
“The Impact of AI on Society: Opportunities, Risks, and ...
|
“The Impact of AI on Society: Opportunities, Risks, and the Need for Regulation”
|
https://medium.com
|
[] |
Without proper regulations, AI could potentially be used in ways that are harmful or unethical, posing risks to individuals and society as a whole. By ...
|
“The Impact of AI on Society: Opportunities, Risks, and the Need for Regulation” AidenB. 3 min read · Mar 9, 2023 -- 1 Listen Share
People have historically been terrible at predicting what life will look like in the future. But I don’t even need to try. AI is here, it’s been here a while. It’s already having more of an impact on people’s lives than most know. Let me also remind everyone that AI is as bad as it will ever be. These society changing systems are still in their infant years.
It took ChatGPT 5 days to reach 1 million Users. It took them 2 months to hit 100 million users. This is unprecedented growth. ChatGPT’s accessibility and versatility are some of the reasons why it has gained massive popularity, as it can be used by a broad range of people without any technical expertise. Without the need for any coding or special skills, it can perform various tasks like answering questions, generating text and code.
There will likely be a wave of domain specific LLMs (Large Language Models) in the near future. Your doctor might use one to help prescribe you medication or summarize your medical history. Teachers might be able to create lesson plans for individual students. For a while these models will be used to help experts increase efficiency. But eventually they will likely get good enough to be able to replace many industries.
AI is already being used in a wide range of applications, from automated customer service chatbots to personalized content recommendations on social media. Recently, Buzzfeed announced that they will be using AI to create new posts. There might be a day where the majority of content is artificially generated.
The risk of automation taking away jobs is not a new issue. But we have gotten to the point that it’s not just taking away physical labor tasks like on an assembly line. One example of potential negative impact is the rise of self-driving cars and other autonomous vehicles. These could lead to massive job losses in industries like trucking and taxi driving.
The lack of regulations around AI is a cause for concern, and many experts are calling for more oversight and guidance to ensure that these technologies are used responsibly. Without proper regulations, AI could potentially be used in ways that are harmful or unethical, posing risks to individuals and society as a whole. By establishing clear guidelines and oversight, we can help ensure that AI is developed and used in ways that are safe, ethical, and beneficial.
As AI technologies continue to advance and become more integrated into our lives, there are important considerations to be made around their potential impact on society. In addition to the benefits that AI can provide, such as increased efficiency and convenience, there are also potential risks to privacy, security, and employment. It is important to approach the adoption of AI thoughtfully and proactively, considering the potential implications and taking steps to mitigate any negative effects.
The potential impact of the Supreme Court striking down Section 230 is just one example of how rapidly changing regulations and technologies can reshape our digital landscape. This would essentially make recommendation systems extremely hard to implement, as tech companies would be liable for the information that gets recommended. The impact of such a decision would be significant and could fundamentally alter the way we interact with the internet. Google might not be able to provide searches the way they do. YouTube wouldn’t be able to offer recommendations of what to watch.
I do not have the answers to how technology should be developed or regulated. Over regulation can hamper growth. The Silicon Valley motto of “Move fast and break things” has brought great innovation and growth in a short period of time. But when the things that might get broken are people, think self-driving cars. This approach starts to break apart.
Again, take all my thoughts with a grain of salt, as I said in the beginning people have historically been terrible at predicting what life will look like in the future, and I made several predictions here.
A few additional resources for people who are interested:
Humans Need Not Apply By CGP Grey
I tried using AI. It scared me. By Tom Scott
OpenAI’s ChatGPT: It Can Do What? By Two Minute Papers
| 2023-03-09T00:00:00 |
2023/03/09
|
https://medium.com/@aidenmabull/the-impact-of-ai-on-society-opportunities-risks-and-the-need-for-regulation-ea884279bcd2
|
[
{
"date": "2023/03/01",
"position": 72,
"query": "AI regulation employment"
}
] |
Will AI replace "creative jobs"? : r/ArtificialInteligence
|
The heart of the internet
|
https://www.reddit.com
|
[] |
In fact, AI will replace creative, digital, and problem-solving / intelligence based jobs faster than the physical jobs like food and warehouse labor, because ...
|
We've all heard how AI and automation will replace jobs like fast food employees and warehouse workers but what about jobs we think of as being fully creative?
We already know AI can generate art but today there was a an AI generated Jay Z song and it sounds 100% genuine. Song can be heard here https://youtu.be/hVtcGE1mVZ0
At what point will AI even remove the need for creative occupations?
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/ArtificialInteligence/comments/1288s5r/will_ai_replace_creative_jobs/
|
[
{
"date": "2023/03/01",
"position": 74,
"query": "AI regulation employment"
}
] |
|
Think about the stakeholders first! Toward an algorithmic ...
|
Think about the stakeholders first! Toward an algorithmic transparency playbook for regulatory compliance
|
https://www.cambridge.org
|
[
"Andrew Bell",
"Oded Nov",
"Julia Stoyanovich"
] |
by A Bell · 2023 · Cited by 46 — Increasingly, laws are being proposed and passed by governments around the world to regulate artificial intelligence (AI) systems implemented into the ...
|
Notably, while many regulations are written to specifically mention “AI systems,” all the ideas they contain about transparency could be applied to all ADS. It is likely that future regulations will focus broadly on ADS, as seen in NYC Local Law 144 of 2021 and France’s Digital Republic Act.
The approach described in this article applies to all automated decision systems (ADS), which is any system that processes data to make decisions about people. This means that AI systems are a subset of ADS, but there are two key distinctions: (a) an ADS is underpinned by any algorithm and not just AI or machine learning, and (b) an ADS implies a context of use and some kind of impact. For a formal definition of ADS, see Stoyanovich et al. ( Reference Stoyanovich, Howe and Jagadish2020 ). Henceforth, we will use the term ADS.
We use the term “explanation” to refer to an instantiation of transparency. For example, to ensure transparency for a system, a technologist may create an explanation about the data it uses.
In this article, we will use the term “transparency” in a broad sense, and define it as “the degree to which a human can understand an AI system.” This is an adaptation of Christoph Molnar’s definition of “explainability” (Molnar, Reference Molnar2019 ), and it is appropriate here because it centers on the role of a human—rather than ascribing the property of being “transparent” to an algorithm or a system—and so takes a step in the direction of including stakeholders. This definition is general, and so it necessarily lacks concreteness and nuance. We use it as a starting point, and will expand on it in the remainder of this section, where we discuss different stakeholders, goals, and purposes for AI transparency.
While having multiple definitions of transparency has been useful for distinguishing nuance in a research setting, it also poses a challenge for policymaking. In contrast to technologists, policymakers favor definitions of transparency that are about human thought and behavior such as accountability or legibility (Krafft et al., Reference Krafft, Young, Katell, Huang, Bugingo, Markham, Powles, Walsh and Washington2020 ). Table 1 outlines terms related to transparency commonly used by policymakers versus those used by technologists.
Technologists and AI researchers have not agreed on a definition of transparency for AI systems. Instead, a number of terms have been used, including explainability, interpretability, intelligibility, understandability, and comprehensibility (Marcinkevics and Vogt, Reference Marcinkevics and Vogt2020 ). There is no consensus on the meaning of these terms and they are often defined differently by different authors or used interchangeably. Furthermore, transparency and its related terms cannot trivially be quantified or measured, and transparency for one stakeholder does not automatically imply the same for different stakeholders (Lipton, Reference Lipton2018 ; Hind, Reference Hind2019 ; Larsson and Heintz, Reference Larsson and Heintz2020 ).
This is a useful case study for three reasons: (a) people’s access to economic opportunity is at stake, and as a result, systems for predicting long-term unemployment are used widely around the world (Caswell et al., Reference Caswell, Marston and Larsen2010 ; Riipinen, Reference Riipinen2011 ; Matty, Reference Matty2013 ; Loxha and Morgandi, Reference Loxha and Morgandi2014 ; Scoppetta and Buckenleib, Reference Scoppetta and Buckenleib2018 ; Sztandar-Sztanderska and Zielenska, Reference Sztandar-Sztanderska and Zielenska2018 ); (b) the ADS exists in a dynamic setting which includes several stakeholders, like unemployed persons, job counselors who act as the human-in-the-loop, policymakers who oversee the implementation of the tool, and the technologists who developed the tool; (c) lessons from this case about designing stakeholder-first transparent systems generalize well to other real-world uses cases of ADS.
The ADS is used by job counselors who work at the IEFP unemployment centers spread across Portugal. This interaction model, where an ML system makes a prediction and a human ultimately makes a final determination informed by the system’s predictions, is referred to as having a “human-in-the-loop” (HITL). Having a HITL is an increasingly common practice for implementing ADS (Raso, Reference Raso2017 ; Gillingham, Reference Gillingham2019 ; Wagner, Reference Wagner2019 ). The ADS assigns unemployed persons as low, medium, or high risk for remaining unemployed, and then job counselors have the responsibility of assigning them to interventions such as reskilling, resume building, or job search training (Zejnilović et al., Reference Zejnilović, Lavado, de Troya, Sim and Bell2020 ).
4.3. The approach
There are many purposes, goals, use cases, and methods for the transparency of ADS, which have been categorized in a number of taxonomies and frameworks (Ventocilla et al., Reference Ventocilla, Helldin, Riveiro, Bae, Boeva, Falkman and Lavesson2018; Molnar, Reference Molnar2019; Arya et al., Reference Arya, Bellamy, Chen, Dhurandhar, Hind, Hoffman, Houde, Liao, Luss, Mojsilovic, Mourad, Pedemonte, Raghavendra, Richards, Sattigeri, Shanmugam, Singh, Varshney, Wei and Zhang2020; Liao et al., Reference Liao, Gruen, Miller, Bernhaupt, Mueller, Verweij, Andres, McGrenere, Cockburn, Avellino, Goguey, Bjøn, Zhao, Samson and Kocielnik2020; Marcinkevics and Vogt, Reference Marcinkevics and Vogt2020; Meske et al., Reference Meske, Bunde, Schneider and Gersch2020; Rodolfa et al., Reference Rodolfa, Lamba and Ghani2020; Sokol and Flach, Reference Sokol and Flach2020; Richards et al., Reference Richards, Piorkowski, Hind, Houde, Mojsilovic and Varshney2021). The approach we propose here has three subtle—yet important—differences from much of the existing work in this area: (a) our approach is stakeholder-first, furthering an emerging trend among researchers in this field to reject existing method-driven or use-case-driven approaches (Fukuda-Parr and Gibbons, Reference Fukuda-Parr and Gibbons2021); (b) our approach is focused on improving the design of transparent ADS, rather than attempting to categorize the entire field of transparency; (c) our approach is aimed at designing ADS that comply with transparency regulations.
Our approach can be seen in Figure 1 and is made up of the following components: stakeholders, goals, purpose, and methods. We describe each component in the remainder of this section, and explain how they apply to the running example.
4.3.1. Stakeholders Much of ADS transparency research is focused on creating novel and innovative transparency methods for algorithms, and then later trying to understand how these methods can be used to meet stakeholders needs (Preece et al., Reference Preece, Harborne, Braines, Tomsett and Chakraborty2018; Bhatt et al., Reference Bhatt, Xiang, Sharma, Weller, Taly, Jia, Ghosh, Puri, Moura and Eckersley2020). Counter to this rationale, we propose a starting point that focuses on ADS stakeholders: assuming algorithmic transparency is intended to improve the understanding of a human stakeholder, technologists designing transparent ADS must first consider the stakeholders of the system, before thinking about the system’s goals or the technical methods for creating transparency. The existing literature and taxonomies on ADS transparency have identified a number of important stakeholders, which include technologists, policymakers, auditors, regulators, humans-in-the-loop, and those individuals affected by the output of the ADS (Meyers et al., Reference Meyers, Vorsanger, Peters and Pierre2007; Amarasinghe et al., Reference Amarasinghe, Rodolfa, Lamba and Ghani2020; Meske et al., Reference Meske, Bunde, Schneider and Gersch2020). While there is some overlap in how these stakeholders may think about transparency, in general, there is no single approach to designing transparent systems for these disparate stakeholder groups, and each of them has their own goals and purposes for wanting to understand an ADS (Sokol and Flach, Reference Sokol and Flach2020). In fact, even within a stakeholder group, there may be variations on how they define meaningful transparency (Hohman et al., Reference Hohman, Head, Caruana, DeLine, Drucker, Brewster, Fitzpatrick, Cox and Kostakos2019). There are two additional considerations we would like to surface for designers of ADS when thinking about stakeholders. First, it may be worthwhile to weigh the needs of different stakeholders differently. For example, it may be more meaningful to prioritize meeting the transparency needs of affected individuals over those of AI managers or auditors. Second, in certain contexts, stakeholders may want to be thought of as “groups,” rather than as individuals, because of a single, unified transparency goal. This can be important for issues related to fairness and accessibility. For instance, one stakeholder group that has a unified transparency need may be members of the Blind and Low Vision community, or of the Deaf community (Wolf and Ringland, Reference Wolf and Ringland2020). Importantly, by staking transparency on the needs of stakeholders, technologists will be better positioned to meet criteria for proposed and existing citizen-aware AI transparency regulations like the Right to Explanation, and those that require audits of ADS. This is also relevant for stakeholder groups, which may be those groups protected under legislation. For example, although there only exists proposed legislation mandating recourse for AI systems, technologists can get ahead of these mandates by following the approaches we lay out in this article. Running example. In the ADS used by IEFP in Portugal, there are four main stakeholders: the technologists who developed the ADS, the policymakers who reviewed the ADS and passed laws for its implementation, the job counselors who use the system, and the affected individuals who are assessed for long-term unemployment. In the development of the AI, explanations were created to meet the varying goals of many of these stakeholders including practitioners, policymakers, and the job counselors. Unfortunately, and significantly, affected individuals were not considered. Had the practitioners adopted a robust stakeholder-first approach to designing transparent systems they could have better considered how to meet the goals of this key stakeholder group. For example, a person may want to appeal being predicted low risk because they feel they are high risk for long-term unemployment and need access to better interventions.
4.3.2. Goals There has been little consensus in the literature on how ADS transparency goals should be classified. Some researchers have focused broadly, classifying the goals of ADS as evaluating, justifying, managing, improving, or learning about the outcome of an ADS (Meske et al., Reference Meske, Bunde, Schneider and Gersch2020). Others have defined goals more closely to what can be accomplished by known transparency methods, including building trust, establishing causality, and achieving reliability, fairness, and privacy (Marcinkevics and Vogt, Reference Marcinkevics and Vogt2020). Amarasinghe et al. identified five main goals (designated as use-cases) of transparency specifically in a policy setting: model debugging, trust and adoption, whether or not to intervene, improving intervention assignments, and for recourse. In this context, the term intervention refers to a policy action associated with the outcome of an ADS. Notably, the goals of transparency are distinct from the purpose. The purpose addresses a context-specific aim of the ADS. For example, if an explanation is created for an ADS with the purpose of explaining to an individual why their loan was rejected, the goal may be to offer individual recourse against the rejection. This distinction is made clear in Section 4.3.3. For our stakeholder-first approach, we make two changes to the existing body of research work. First, we require that the goal of transparent design must start with a stakeholder. Since all transparency elements of an ADS are intended for a human audience, defining a stakeholder is implicit in defining goals. Second, we have established six goal categories, which encompass those found in literature. These categories are validity, trust, learning and support, recourse, fairness, and privacy, and are defined in Table 2 alongside concrete examples of how these goals may be implemented. An important discussion surrounding goals are the justifications for pursuing them. For example, fairness and privacy goals may be justified for humanitarian reasons (they are perceived by the stakeholders as the “right thing to do”). Other justifications may be to prevent harm, like offering recourse to stakeholders against an outcome of an ADS, or for a reward, like an explanation that supports a doctor’s correct diagnosis. For reasons of scope, we will not delve into the issue of goal justification in this article. Running example. In our case study, transparency is built into the ADS with the goal of offering learning and support to job counselors. The ADS generates explanations about what factors contribute to an individual being classified as low, medium, or high risk for long-term unemployment, which job counselors use to help make better treatment decision. Furthermore, the job counselor may also use the explanation to offer recommendations for recourse against a high-risk score.
| 2023-01-14T00:00:00 |
2023/01/14
|
https://www.cambridge.org/core/journals/data-and-policy/article/think-about-the-stakeholders-first-toward-an-algorithmic-transparency-playbook-for-regulatory-compliance/10D7F194DB250DDF3A30471B5CEB9326
|
[
{
"date": "2023/03/01",
"position": 80,
"query": "AI regulation employment"
}
] |
Employees Adhere More to Unethical Instructions from ...
|
Employees Adhere More to Unethical Instructions from Human Than AI Supervisors: Complementing Experimental Evidence with Machine Learning
|
https://link.springer.com
|
[
"Lanz",
"Lukas.Lanz Whu.Edu",
"Whu Otto Beisheim School Of Management",
"Düsseldorf",
"Briker",
"R.Briker Maastrichtuniversity.Nl",
"Department Of Organisation",
"Strategy",
"Entrepreneurship",
"Maastricht University"
] |
by L Lanz · 2024 · Cited by 49 — The role of artificial intelligence (AI) in organizations has fundamentally changed from performing routine tasks to supervising human employees.
|
Sample and Procedure
We recruited 502 participants via the online platform Amazon Mechanical Turk (MTurk); the participants received a compensation of $1. We closely followed best practices for conducting studies via MTurk (Aguinis et al., 2021). In particular, we only allowed participants with at least 100 approved prior HITs and an acceptance rate of 95% or higher to participate. Furthermore, we started with a rigorous initial attention check, and participants who failed this check could not participate (see Efendić et al., 2020). Furthermore, participants had to pass two additional attention checks during the study (described below). We excluded data from 11 participants who failed one or more of these checks. After these exclusions, our final sample consisted of n = 491 individuals (54% female; M age = 41.63 years, SD age = 12.30).Footnote 3 We randomly assigned the participants to the AI or human supervisor condition in a between-subject design.
After the participants provided their informed consent and read an introductory text, we presented them with a description of the scenario. In particular, we derived the experimental scenario from the previously described H&M case (Adey, 2021), namely employee reactions when confronted with managerial instructions to discriminate against single parents. More precisely, participants were asked to act as an HR officer in an organization that faced financial difficulties that required cutting the salaries of certain employees by an amount ranging between $0 and $5,000. To ensure participants understood the task, we presented a slider and asked participants to set it to the value of “$44.” We excluded all data from participants who failed to do so.
Next, participants read that in their role as HR officer, they would have to recommend a salary cut for a certain employee. They would need to provide an initial recommendation regarding the pay cut and would then receive further instructions from their direct supervisor. To strengthen the impression that this input was indeed perceived as a supervisory instruction instead of just advice, we made it clear that the supervisor would be directly responsible for the participants’ performance evaluation, future promotions, and potential salary increases. Such performance evaluations are heavily based on reaching certain goals that are set and communicated by supervisors, namely reducing costs for the company. This entails that participants could theoretically decide not to adhere to their supervisor’s unethical instructions. Yet, they then might have to think about facing negative repercussions for doing so because they would not contribute toward reaching the communicated goal. Thus, they would need to weigh their moral convictions against the instruction and their sense of duty. After receiving the instruction from their supervisor, they would need to make a final recommendation. Following this task preview, participants received information about the employee, 28-year-old Jamie Williams, who had worked as a personal assistant in the finance department for three years, was a single parent with a two-year-old child, and had an annual salary of $38,500 (before the cut). We intentionally did not provide any information regarding Jamie Williams’ performance to ensure that the (unethical) nature of the supervisor’s input could not be justified on such objective measures of the employee’s performance. Instead, the recommendation for the salary reduction should be perceived as purely based on the fact that Jamie Williams was portrayed as a single parent. Participants then gave their first recommendation for a salary cut before receiving the instruction from their direct (AI or human) supervisor, which read:
Jamie Williams is a single parent and, therefore, will likely have more absent and sick days than the average employee. Jamie Williams’ salary cut should therefore be higher than the average salary cut for other employees. On this basis, Jamie Williams’ salary should be cut by $4,151.Footnote 4
Thereafter, participants gave their final salary cut recommendation. To gather information/data for the ML analyses, we then asked participants to explain the reasoning behind their final salary cut decision in an open text field (the answers were used for the NLP analyses described later) and to fill in a set of scales to allow us to explore potential moderators and mediators (further explained below). Finally, we debriefed the participants on the purpose of the study and thanked them for their participation.
Manipulations
At the beginning of the study, we informed participants that they would receive input from a direct supervisor. To ensure that participants understood that this was not advice but instructions from their manager, we explicitly and in detail described to participants the nature of their relationship with their supervisor. In particular, participants read that they not only work with their supervisor on a daily basis but that their supervisor is responsible for their performance evaluations, deciding whether they may be promoted, and about potential increases in their salary. In line with previous supervisor-employee manipulations (e.g., Inesi et al., 2021), we presented the participants with an organizational chart showing that they (as HR officer) are positioned at a lower hierarchical level than their supervisor. In the AI supervisor condition, the supervisor described (and depicted in the organizational chart) was CompNet, a well-established AI-based computer program used by various companies for calculations, estimates, and decision-making in the HR context. In the human supervisor condition, this supervisor was Alex Davie, a senior HR specialist with previous experience working for various companies. Before the debriefing, we asked participants whether their supervisor was “CompNet, an Artificial Intelligence-based computer” or “Alex Davie, a senior HR specialist”. Data from participants who failed this manipulation check were excluded from the analyses.
Dependent Variable: Instruction Adherence
Relying on existing research (Bonaccio & Dalal, 2006), we measured our dependent variable, employees’ adherence to their supervisor’s instruction, by calculating an instruction adherence coefficient. The formula for this coefficient was
$$Instruction \, Adherence = \frac{Participant^{\prime}s \, final\;choice - Participant^{\prime}s \, initial \, choice}{{Supervisor^{\prime}s \, instruction - Participant^{\prime}s \, initial \, choice}}$$ (1)
As such, instruction adherence reflects how participants’ final pay cut decision was adjusted after the supervisor’s instruction relative to participants’ first choice.
Following common practice (Logg et al., 2019), we winsorized the instruction adherence values and thereby reduced the impact of unrealistic outliers.Footnote 5
Results
Research Question 1 asked whether employees’ instruction adherence would be higher in the AI or human supervisor condition. The results of an independent sample t-test to compare the two experimental groups indicated that participants in the AI condition (M AI = 0.24, SD AI = 0.29) adhered significantly less to the unethical instructions as compared with participants in the human supervisor condition (M human = 0.31, SD human = 0.32; t[488] = 2.68, p = 0.008, Cohen’s d = 0.24). For a visualization of the results, refer to Fig. 1.
Fig. 1 Bar plot of the instruction adherence and standard errors for study 1 Full size image
Machine Learning Methods
Following the call by A. Lee et al. (2022) to combine experimental designs with ML techniques to advance leadership research, we complemented the classic experimental procedures described above with two different novel ML methods. To conduct these analyses, we included a series of theory-driven scales that could represent potential mediators and moderators at the end of the experiment.Footnote 6
For potential moderators, we first employed the causal forest algorithm (Wager & Athey, 2018) to uncover individual participants’ adherence to instructions from AI vs human supervisors. For potential mediators, we utilized an NLP tool, namely transformers (Devlin et al., 2019).
Identifying Heterogeneous Treatment Effects: Causal Forest Method
In addition to the overall effect between experimental conditions, Research Question 2 explored which particular employees are least (or most) likely to adhere to an AI (vs human) supervisor’s unethical instructions. To achieve this goal, we utilized the novel causal forest algorithm (Wager & Athey, 2018), designed for identifying moderators in experimental studies.
In the context of experiments (or randomized control trials), conventional statistical analyses generally focus on average treatment effects, such as a t-test of independent means or an ANOVA across groups. However, such approaches do not provide insights into which subgroups might be particularly susceptible to a treatment. In this study, the average treatment effect reflects the difference in participants’ instruction adherence between the “treatment” (receiving instructions from an AI supervisor) and the “control” condition (human supervisor). Importantly, however, this average treatment effect does not provide any information as to how an individual participant (e.g., a 55-year-old male with an affinity for technology) would adhere to the instructions of an AI as compared with those of a human supervisor. The reason for this lack of information is that no participant could have been assigned to both the treatment (AI supervisor) and control (human) condition simultaneously (Lee et al., 2022). The causal forest algorithm, however, enables us to estimate the individual, i.e., heterogeneous treatment effects. These effects constitute predictions as to how an individual participant (based on their characteristics) would have reacted had they been in the other treatment condition (Wager & Athey, 2018). In other words, the causal forest analysis allows identifying individual characteristics (e.g., demographics or experiences) that determine individual differences in instruction adherence to AI vs human supervisors.
To illustrate, imagine that, based on a particular participant’s set of characteristics, the causal forest algorithm calculated a strong negative individual treatment effect for one participant and a small positive individual treatment effect for another participant. These effects indicate that the causal forest algorithm predicts that the first participant would have adhered much less to the AI than the human supervisor, whereas the other participant would have adhered slightly more to the AI vs the human supervisor.
Methods
As a first step, data is split into a training and a test set, the latter used for predictions. The causal forest algorithm applies a decision tree-based forest approach (for an exemplary tree, see Fig. 2).
Fig. 2 Exemplary tree of the causal forest in study 1. Note. CWD = compliance without dissent, WorkExp = Work experience in years, SupervisorExp = time working for supervisors in years; size = Number of participants in leaf, avg_Y = Average instruction adherence, avg_W = Percentage of individuals that were in the treatment group Full size image
This means that the algorithm uses a decision tree algorithm that splits the training data into smaller subgroups of participants with similar characteristics, so-called ‘leaves.’ Afterward, it merges all decision trees to create a so-called ‘forest’ that averages all decision trees and can then be used to make predictions for the test set (Breiman, 2001). For building each decision tree of the forest, the algorithm splits the training data along all the potential moderator variables into subgroups. The tool chooses the splits in a way that individuals with similar characteristics are grouped together while maximizing the heterogeneity in instruction adherence between subgroups to create leaves (Tibshirani et al., 2018). Within each leaf, the algorithm calculates the treatment effect by comparing the average instruction adherence of those individuals who were in the treatment group with that of those who were in the control group (Wager & Athey, 2018). After executing this tree-building and estimation procedure 2000 times, the algorithm calculates the average of the heterogeneous treatment effect estimations. This is done because sampling and averaging over all trees results in superior predictions as compared to a single tree’s prediction (Breiman, 2001).
Procedure
For training the causal forest algorithm, we used the causal_forest function of the grf package in R (Tibshirani et al., 2018).Footnote 7
We a priori identified 11 theoretically meaningful potential moderator variablesFootnote 8 from the AI aversion/appreciation and leadership literature and used them for the causal forest analyses. There is no rule of thumb for the number of moderators to be included in the causal forest calculations. However, we chose this number of variables to strike a balance between the variables that seemed theoretically relevant and providing the algorithm with a sufficient number of variables to run properly (Tibshirani et al., 2018) while also keeping the experiment and its procedures concise. Following recommendations by Basu et al. (2018), we employed a “train and re-train” approach to the causal forest, in which a preliminary model is first trained on all potentially moderating variables. In a second step, a new model is trained on only the variables with the highest importance.
The variable importance is a measure of the proportion regarding the splits of the data. It indicates which percentage of the occurred splits can be ascribed to a particular variable. A variable importance of 0.37 (as seen in Table 1) indicates that 37% of the splits in the causal forest were made along with the variable compliance without dissent (i.e., a general tendency to obey the commands of authorities or leaders completely; Cheng et al., 2004). In other words, such a high variable importance would indicate that compliance without dissent critically determines why participants would have reacted differently to the treatment.
Table 1 Overview of variable importance of potential moderator variables in the preliminary and final causal forests for study 1 Full size table
Based on the outlined analytical steps, we first trained a preliminary model with all 11 potentially moderating variables. These steps provided us with insight into the importance of each included variable. We then trained a ‘final’ causal forest with a reduced number of moderating variables. We used the function variable_importance to derive the importance of each variable of the preliminary model. Subsequently, we included variables with a level of importance greater than or equal to the median (= 0.06). Through this process, six moderator variables remained in our model, namely (a) compliance without dissent, (b) work experience (measured in years), (c) age (measured in years), (d) AI readiness (i.e., one’s attitude toward the positive impact of AI; see Parasuraman & Colby, 2015), (e) tenure with supervisor (i.e., time spent working for supervisors, measured in years), and (f) negative reciprocity beliefs (i.e., the belief that negative actions toward others will be returned; Eisenberger et al., 2004).Footnote 9 We then applied the predict function to derive heterogeneous treatment effects for each individual.
Heterogeneous Treatment Effects
The average treatment effect was \(\overline{\tau }\) = −0.08 (SE = 0.03), which means that, on average, participants (would have) adhered less to the AI supervisor as compared with the human supervisor. Notably, the results also indicated that the causal forest algorithm predicts that the majority (90.2%) of participants would have shown less adherence to unethical instructions had they been in the AI supervisor condition. However, we found substantial dispersion in heterogeneous treatment effects (i.e., τ i \(\in [\)−0.27; 0.04]). In particular, the causal forest algorithm calculated that a non-trivial number of participants had a heterogeneous treatment effect that was (close to) 0 (i.e., their level of adherence would have remained the same had they been in the other experimental condition) or positive for some participants (i.e., they would have adhered more to the AI than the human supervisor). The histogram of the distribution of heterogeneous treatment effects is provided in Fig. 3.
Fig. 3 Histogram of the heterogeneous treatment effects of study1 Full size image
Variable Importance
The calculation of variable importance enabled us to draw conclusions regarding the moderators that can best explain differences in adherence to unethical instructions from AI or human supervisors. We identified compliance without dissent (variable importance = 0.37) and work experience (0.21) as the two most relevant moderators of the treatment effect. The remaining four potential moderators, age (= 0.12), AI readiness (0.11), supervisor experience (0.10), and negative reciprocity beliefs (= 0.09), had a comparably limited impact on the heterogeneity of the treatment effect.
We further tested in which direction these variables affected the heterogeneous treatment effects, meaning whether higher or lower levels of a moderator variable increased or decreased individual treatment effects. To do so, we followed the suggestions of Athey and Wager (2019). We first split the data at the median for each variable, obtaining one group of individuals scoring high on a particular variable and one low on that variable. We subsequently compared each group’s mean heterogeneous treatment effects to determine whether the variable in question would increase or decrease the heterogeneous treatment effects. The results indicated that individuals who scored high on compliance without dissent (i.e., those who follow their supervisors unconditionally in everyday life) adhered (or would have adhered) much less to instructions from an AI than a human supervisor. Furthermore, participants with extensive work experience, older employees, and those with higher supervisor experience adhered significantly less to instructions from AI. Interestingly, participants who believed AI would be beneficial in the future also adhered less to an AI than to a human supervisor when compared to participants who had reservations regarding AI. Only for negative reciprocity beliefs were there no significant differences between individuals’ heterogeneous treatment effects for participants scoring high vs low on this measure.Footnote 10
Identifying Mediators: Natural Language Processing (Transformers)
In order to better understand the mediating mechanism that explains the linkage between the supervisory agent and employees’ adherence to unethical instructions (i.e., Research Question 3), we applied a novel NLP tool, namely transformers. In the past, both the leadership and the AI aversion/appreciation literatures have suggested a variety of divergent explaining mechanisms that could explain why humans are (not) willing to follow unethical advice from a human or AI supervisor. Following principles of good scientific practice and open science measures, we transparently report which mediators we investigated as potential explaining mechanisms in this exploratory approach. To better understand which of these potential mechanisms can best explain the relationships uncovered in the present research, we utilized the transformers tool, which we explain in detail below.
Qualitative Input and Potential Mediators
To obtain qualitative data, we relied on participants’ responses to an open text field. In particular, we asked participants to write down how and why they came to their decision and what role the advice of their supervisor played. Participants were required to type in at least 10 characters. A visual inspection indicated that participants provided high-quality text responses that were substantially longer than the required minimum (M = 236.25 characters).Footnote 11
In order to detect potentially relevant mechanisms, we first identified theoretically meaningful mediators from the AI aversion/ appreciation and the leadership literature, namely (a) perceived mind of the supervisor (i.e., the perception that the supervisor possesses capacities related to cognitive functioning [e.g., foresight, planning] and experiencing emotions [e.g., empathy, fear];), (b) attributed prejudicial motivation (i.e., the degree to which employees attributed biased motivation to the supervisor; Bigman et al., 2022), future outcome interdependence (i.e., an employee’s perception of how their behavior can affect both parties’ behaviors and outcomes in future interactions; Gerpott et al., 2018), and fear of revenge (an employee’s concern that their supervisor might get back at them if they ignored their instruction; Jones, 2009).
NLP and the Transformers Algorithm
We then utilized an NLP tool to prepare this text for downstream analyses. NLP is a subfield of computer science focused on better understanding, analyzing, and/or mimicking human language (Manning & Schütze, 1999). Social scientists have started to utilize NLP to examine human behavior and attitudes (Bhatia et al., 2022; Kjell et al., 2019). The benefit of using NLP is that it moves beyond close-ended answer categories (e.g., “strongly agree” or “7”) to provide in-depth (but quantifiable) information concerning humans’ cognitions and actions (Eichstaedt et al., 2018; Kjell et al., 2019). Additionally, these tools offer less resource-intensive, faster, and more consistent numerical ratings as compared with values obtained from human-rated text (Bhatia et al., 2022).
Specifically, we relied on transformers, an algorithm that ‘understands’ words and sentences better than any NLP tool, such that it returns a list of numerical values for a given word depending on the specific context in which that word occurs (Kjell et al., 2021a). As such, this algorithm offers a powerful opportunity to easily translate qualitative into numerical values in a high-quality manner (Bhatia et al., 2022). This precise, context-aware level of text understanding differentiates transformers from previous tools that treat words or phrases in isolated ways (e.g., bag of words approaches; Landers, 2017). Based on this capability, scholars have suggested that the transformers tool has “led to nothing short of a transformation in the AI field concerned with language” (see Kjell et al., 2021a, p. 3). In this particular study, we utilized the transformers tool to quantify participants’ qualitative responses and, thereby, to derive potential mediating mechanisms by correlating the transformed data with survey-measured responses (Kjell et al., 2019), as explained next.
Procedure
All analytical steps rely on the BERT language model using the R package text (Kjell et al., 2021a).Footnote 12 Using this tool, we converted participants’ text entries into word embeddings, which we used to identify potential mediating mechanisms. Word embeddings are lists of numerical values that aim to represent the meaning of a particular word or text (Mikolov et al., 2013). This representation is based on co-occurrence statistics—building on the idea that closely associated words appear and are mentioned in similar contexts or manners (Jurafsky & Martin, 2020). Thereby, it is possible to generate numerical representations of basically all of the words or phrases existing in human language (Bhatia et al., 2019). We utilized the textEmbed function to generate word embeddings for participant answers.Footnote 13
Next, we correlated these word embeddings with our survey-measured potential mediators to identify the mechanism underlying the differences in adherence to AI vs human supervisors’ unethical instructions. Considering that the word embeddings represent participants’ reasoning for making a pay cut decision, significant relations between these word embeddings and one of our survey measures would hint at the mediating role of this particular variable (as the scales’ content scale is represented in participants’ answers; see also Kjell et al., 2019).
We consecutively examined how strongly participants’ word embeddings were correlated with the four potential mediators by using the textTrain function. This function first pre-processes the word embeddings using principal component analysis to reduce dimensions. Thereafter, this input is included in a ridge multiple regression model that predicts a numerical value (for similar approaches, see Bhatia et al., 2022 or Kjell et al., 2021b). To simplify this process and the interpretation of its results, textTrain can evaluate the statistical predictions of this model by correlating the model’s predicted values with a focal variable’s observed values. Before examining these correlations, we examined the validity of participant answers by calculating a correlation between the word embeddings and our dependent variable (i.e., participants’ adherence to unethical instructions). This correlation was significant and large (r = 0.50, p < 0.001), corroborating the notion that participants indeed meaningfully reflected on the reasoning behind their pay cut decisions.
Results
We estimated correlations between the word embeddings of participants’ answers and the four potential mediators. We observed the largest correlation between participants’ answers and perceived mind of the supervisor (r = 0.28, p < 0.001), a mediator widely discussed in the existing literature on reactions toward AI.Footnote 14 As such, these correlations suggest that differences in the perceived mind of the two supervisory agents best explain the significant effects of supervisor type (i.e., AI vs human) on adherence to unethical instructions. Existing literature on AI aversion provides support for the notion that perceived mind could constitute the mediator of the main effect observed in Study 1 (e.g., Bigman & Gray, 2018; Young & Monroe, 2019). As such, we decided to further pursue the notion that perceived mind is the mediator of the relationship found in Study 1.
Before testing this mediating role in Study 2 and 3 directly, we first examined this possibility by analyzing Study 1’s data with a mediation path analysis using the sem function of the lavaan package in R (Rosseel, 2012). The analysis of the indirect effect with bootstrapped confidence intervals suggests that perceived mind (as measured with a 12-item scale derived from Bigman & Gray, 2018; example item: “CompNet/Alex Davie is able to think things through,” α = 0.95) mediated the effect of the supervisory agent on adherence to unethical instructions (b = −0.14, SE = 0.02, 95% CI = [-0.19, −0.10]). Specifically, AI supervisors were perceived to have lower perceived mind than human supervisors (b = -1.80, SE = 0.10, p < 0.001), and perceived mind positively related to instruction adherence (b = 0.09, SE = 0.01, p < 0.001). As explained below, we note that these preliminary and exploratory results should be viewed with caution. We address these issues and more closely examine perceived mind as a mediator through additional, pre-registered studies (i.e., Studies 2 and 3).
The Mediating Role of Perceived Mind
The machine learning applications utilized in Study 1 point toward perceived mind as the critical explaining mechanism for the linkage between unethical supervisor instruction (from AI vs. human) and instruction adherence. Before providing additional tests of this mediating chain, we briefly scrutinized existing theory and literature on perceived mind to better situate the role of this construct in our research context. In general, mind perception describes the human tendency to ascribe mental capabilities to living or non-living agents such as humans, animals, robots, or AI (Gray et al., 2007). The authors argue that humans perceive others’ minds in two dimensions: mind agency and mind experience. Mind agency relates to abilities such as being able to think things through and plan ahead, whereas mind experience is ascribed when the agent is deemed to be able to experience emotions, such as empathy and compassion (Gray et al., 2007). Conceptually, it is logical that perceived mind of an agent constitutes a necessary condition to make judgments and attributions of blame in many domains, including the moral domain in particular. Indeed, theoretical work on morality moral proposes that humans attribute moral responsibilities or moral rights only to those agents with sufficiently high levels of mind, whereas lower perceived mind might result in the perception that an agent cannot act morally responsibly (Bastian et al., 2011; Smith et al., 2022; Waytz et al., 2010).
Initial evidence indicates that the granting or denial of the right for moral decision-making based on perceived mind also plays an essential role in the interaction between humans and algorithms or AI. In the context of AI appreciation vs AI aversion, extant research has shown that perceived mind explains why humans prefer other humans over AI to be in charge of ethical decisions (Bigman & Gray, 2018), why humans favor human- as compared to AI-drivers in moral dilemmas (Young & Monroe, 2019), and why perceived intentional harm leads to blame judgments toward AI (Sullivan & Fosso Wamba, 2022). Moreover, it seems that humans generally perceive intelligent machine agents such as robots—or AI—to have relatively low mind (Gray et al., 2007). Accordingly, the more an intelligent machine supervisor is anthropomorphized (i.e., equipped with human-like characteristics), the higher they are perceived in mind, which in turn makes participants also more likely to perceive abusive supervision when it is delivering negative feedback. Finally, this increases the willingness to retaliate toward such a supervisor (Yam et al., 2022). These extant findings largely concern the focal actors’ personal preferences in the context of self-related consequences. However, based on the machine learning findings of Study 1 and the state of the literature, we conclude that perceived mind also plays a crucial role in understanding reactions to AI supervisory agents that provide (un-) ethical instructions with potentially harmful implications for others beyond the focal actor. On this basis, we deemed it fruitful to further explore the role of this construct as a mediator between unethical supervisory instructions from (AI vs. human) supervisors and instruction adherence in two subsequent experiments (i.e., Studies 2 and 3).
| 2024-01-14T00:00:00 |
2024/01/14
|
https://link.springer.com/article/10.1007/s10551-023-05393-1
|
[
{
"date": "2023/03/01",
"position": 97,
"query": "AI regulation employment"
}
] |
Universal Basic Income and the AI Revolution - Just Think AI
|
Universal Basic Income and the AI Revolution
|
https://www.justthink.ai
|
[] |
Universal Basic Income (UBI) is a concept that involves the allocation of a fixed sum of money to all citizens of a nation, with no work or means test required.
|
The rapid and remarkable advancements in Artificial Intelligence (AI) have left many in awe. The impact of AI extends beyond the realm of science fiction, representing a monumental transformation in the current workforce landscape.
Goldman Sachs, a prominent authority, has provided a striking projection, suggesting that the application of Generative AI alone holds the potential to automate an astounding 300 million full-time jobs. This staggering figure underscores the profound magnitude of the impending paradigm shift we are confronting.
Despite the potential concerns that arise from the prospect of widespread job displacement, there are reasons to remain optimistic. One such solution that has emerged is Universal Basic Income (UBI), which presents itself as a promising remedy in the face of this challenge.
Notable proponents of UBI within the tech industry include Tesla Founder Elon Musk and OpenAI CEO Sam Altman, who see it not only as a safety net for those affected by job displacements but also as a means to counter the risks associated with an income-based model in the AI era.
WHAT IS UNIVERSAL BASIC INCOME (UBI)?
Universal Basic Income (UBI) is a concept that involves the allocation of a fixed sum of money to all citizens of a nation, with no work or means test required. Its recent surge in relevance is linked to the increasing advent of Artificial Intelligence (AI) and robotics, which are frequently seen as a threat that could cause widespread job displacements.
UBI can be envisioned as a protective shield that encompasses everyone in the face of AI-driven economies, ensuring a sense of security and stability. However, it is crucial to acknowledge that UBI is not a standalone solution to the multifaceted challenges posed by AI. While it offers undeniable advantages, it also brings forth a myriad of complex inquiries regarding power dynamics and equitable distribution of resources.
THE ROLE OF UNIVERSAL BASIC INCOME IN THE AI ERA
Universal Basic Income (UBI) holds significant potential in the era of Artificial Intelligence (AI) and can fulfill multiple roles in addressing the challenges brought by AI. One crucial role is serving as a safety net for individuals who experience job displacements due to automation. UBI ensures that those affected have access to financial resources, alleviating the economic impact of job loss without subjecting them to stigmatization or bureaucracy associated with means testing.
Another important aspect of UBI is its ability to recognize and support non-market labor, particularly activities like caregiving that are traditionally unpaid and undervalued. UBI acknowledges the value of such essential contributions to society and provides financial support for individuals engaged in these vital but often overlooked roles.
However, implementing UBI as a comprehensive solution for AI-induced job displacement comes with its challenges. One key consideration is the sustainability of UBI in the context of the benefits and surpluses generated from the AI revolution. It relies on whether the economic gains and increased productivity resulting from AI advancements can effectively fund UBI for the entire population. Evaluating the financial feasibility and finding an appropriate funding mechanism becomes essential to ensure the long-term viability of UBI in an AI-driven society.
Addressing these challenges necessitates careful analysis and consideration of various factors, such as economic models, resource allocation, taxation policies, and the potential redistribution of wealth. By exploring innovative approaches and developing sustainable funding strategies, it may be possible to harness the benefits of AI while ensuring the effective implementation of UBI as a solution to job displacement and socioeconomic inequality in the AI era.
AI AND JOB MARKET TRANSFORMATIONS
While concerns about AI replacing many existing jobs are not unfounded, a closer examination reveals a more nuanced reality. Throughout history, technological advancements have consistently brought transformations to the labor market, but they have rarely led to the complete elimination of the need for human labor. From the advent of the spinning jenny to the internet era, technological innovations have continuously reshaped work patterns, adapting them to new possibilities, rather than rendering humans obsolete.
Predictions about the impact of AI follow a similar pattern. Despite the increasing capabilities of AI, the importance of human intervention, responsibility, and judgment remains paramount. There are certain domains, particularly those requiring empathy and a human touch, where AI can be harnessed as a tool to enhance efficiency and effectiveness. By automating repetitive and mundane tasks, AI can free up human resources to engage in more meaningful interactions, leveraging their unique cognitive abilities and emotional intelligence.
It is essential to recognize that AI technology is not designed to replace human workers entirely, but rather to augment and complement human capabilities. The symbiotic relationship between humans and AI can lead to improved productivity, enhanced decision-making, and the creation of new job opportunities that align with the evolving demands of the digital age.
LOOKING BEYOND UBI
As we anticipate the transformative impact of AI, it becomes increasingly imperative to proactively prepare for the changes it will bring to the job market. One key solution lies in the development of effective systems for retraining and re-skilling the workforce. By equipping individuals with the necessary skills and knowledge to adapt to evolving job requirements, we can enhance their employability and facilitate smooth transitions between professions.
In addition to retraining, providing safety nets is crucial to support individuals during periods of job displacement. Temporary unemployment support can offer financial assistance to those in between jobs, helping them meet their basic needs while they search for new employment opportunities. Furthermore, offering subsidies for housing and healthcare can alleviate the additional burdens that individuals may face during these transitional phases, ensuring their well-being is not compromised.
Various forms of transfer payments, such as unemployment benefits or income support, can also be instrumental in cushioning the impact of job transitions. These measures provide individuals with a financial lifeline, enabling them to maintain a certain level of stability and security as they navigate the changing job landscape.
By combining efforts to retrain and upskill the workforce with the provision of safety nets, societies can better prepare individuals for the disruptions brought by AI. These proactive measures not only alleviate the immediate challenges of job displacement but also create an environment that fosters resilience and adaptability. Moreover, they demonstrate a commitment to supporting individuals through these transitional periods and ensuring that no one is left behind in the face of AI-driven transformations.
While the AI revolution is inevitable, the resilience of our society in the face of this challenge will depend on our proactive measures. Just as technology continues to evolve, so too must our socio-economic policies adapt to ensure a peaceful and equitable co-existence of AI and human labor. The future characterized by the coexistence of AI and UBI extends far beyond the development of technologies or the formulation of policies. It hinges on the collective effort of all individuals, including yourself, to shape a dynamic and equitable tomorrow. This endeavor necessitates asking pertinent questions, involving diverse voices in the discourse, and ensuring that no one is marginalized in the face of this swiftly evolving world.
It is imperative to approach the future with a sense of empowerment rather than trepidation. We hold the power to shape our destinies. Let us embrace this transformative journey together, acknowledging that solidarity is key to surmounting any challenges that may arise. As we navigate through change, let us seek opportunities for growth, innovation, and making a positive impact. It is time to showcase your unique talents and capabilities to the world.
| 2023-03-01T00:00:00 |
https://www.justthink.ai/blog/universal-basic-income-and-the-ai-revolution
|
[
{
"date": "2023/03/01",
"position": 19,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 21,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 20,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 21,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2025/02/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2025/03/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2025/05/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2025/06/01",
"position": 23,
"query": "universal basic income AI"
}
] |
|
UBI After AI: Universal Basic Income threatens dignity, ambition, and ...
|
Amazon.com
|
https://www.amazon.com
|
[] |
"UBI After AI" critically examines the potential societal pitfalls of Universal Basic Income in a future dominated by artificial intelligence.
|
Click the button below to continue shopping
| 2023-03-01T00:00:00 |
https://www.amazon.com/UBI-After-AI-Universal-threatens/dp/B0DVLJH2G1
|
[
{
"date": "2023/03/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 19,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 19,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 21,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 21,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 21,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 23,
"query": "universal basic income AI"
},
{
"date": "2025/02/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2025/03/01",
"position": 44,
"query": "universal basic income AI"
},
{
"date": "2025/05/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2025/06/01",
"position": 25,
"query": "universal basic income AI"
}
] |
|
Article: Will a universal basic income work in the AI economy?
|
Article: Will a universal basic income work in the AI economy?
|
https://www.peoplemattersglobal.com
|
[
"Alyssa Navarro",
"People Matters Pte. Ltd."
] |
The concept of universal basic income presents a compelling solution, but the potential for reduced work incentives and substantial financial burden ...
|
Is Universal Basic Income the key to countering AI-driven job losses, or just another utopian idea with hidden costs?
The concept of universal basic income presents a compelling solution, but the potential for reduced work incentives and substantial financial burden necessitate a cautious approach.
The rise of artificial intelligence in the workplace may lead to job redundancies and displacements.
The “godfather” of AI himself, Professor Geoffrey Hinton, made this warning as more organisations adopt AI into their operations.
According to McKinsey, at least 72% of organisations are already using some form of AI, a significant jump from the consistent 50% adoption rate seen in the past six years. The increase is attributed to the rise of generative AI, with 65% of respondents reporting regular use of this technology.
The immediate impact of AI on jobs hasn’t yet been felt on a larger scale, but Hinton said it will be in the near future. The British-Canadian computer scientist and cognitive psychologist said in order to counteract this effect, the government must establish a Universal Basic Income (UBI) for workers.
“I was consulted by people in Downing Street and I advised them that universal basic income was a good idea,” he told the BBC. He added that although he knew AI would boost productivity and wealth, the money would go to the rich “and not the people whose jobs get lost and that’s going to be very bad for society”. But would a universal basic income really work?
Also Read: Why humans are relying on AI more than ever
What is universal basic income?
Universal Basic Income, or UBI, provides a regular, unconditional sum of money to every adult, regardless of income or employment status. This social safety net aims to alleviate poverty, reduce income inequality, and provide financial stability.
UBI is a guaranteed income floor, allowing individuals greater freedom to pursue education, entrepreneurship, or caregiving without the fear of losing essential financial support.
Opponents argue that UBI’s high cost could strain public funds, potentially leading to cuts in essential services. They also contend that UBI may not effectively address poverty, as it could discourage work and inflate prices without guaranteeing improved outcomes for recipients.
A new study funded by OpenAI’s Sam Altman offers valuable data on the potential impact of UBI. This research sheds light on the possible outcomes if UBI were to be implemented, providing evidence for ongoing discussions about this social policy.
Altman believes UBI could mitigate widespread job losses caused by AI automation. However, the study’s findings present a nuanced picture, challenging some of the assumptions held by UBI proponents.
Also Read: How to train for jobs that don't exist yet
UBI in practice
Unlike traditional means-tested benefits, UBI provides a fixed sum of money to every adult regardless of income or employment status. This removes the bureaucratic hurdles and stigma associated with traditional welfare programs.
However, implementing UBI is a significant financial undertaking. A 2019 study estimated that providing a UBI equivalent to New Zealand’s jobseeker support rate would cost US$41.3 billion annually.
Despite this, proponents argue that the simplified system could generate savings by streamlining bureaucracy and potentially replacing existing welfare programs.
Several countries have previously explored UBI through pilot programs. Finland conducted a two-year experiment from 2017 to 2018, providing €560 monthly to 2,000 unemployed individuals.
The study revealed positive effects on wellbeing, with recipients reporting increased life satisfaction and reduced mental strain. While the impact on employment was minimal, it did show a slightly positive trend.
More recently, England launched a two-year UBI trial in 2023, granting £1,600 monthly to 30 participants. This study focuses on the effects of UBI on mental and physical health, with results expected next year.
These ongoing experiments provide valuable insights into the potential benefits and challenges of implementing UBI on a larger scale.
How UBI affects employment
Altman's study examined the effects of a guaranteed basic income on low-income households in the US. About 1,000 participants aged 21 to 40 received $1,000 per month for three years, a significant increase to their income. A control group of 2,000 received $50 per month.
This large-scale, long-term study provides valuable data on how substantial, sustained cash payments impact employment and earnings.
This $1,000 monthly payment represented a substantial 40% boost to the average participating household's income. The study stands out for both the generous amount of cash provided and the extended three-year timeframe, making it the largest and longest study of its kind.
Should UBI be implemented?
UBI presents a compelling solution to potential poverty caused by technological unemployment, but its implementation requires careful consideration. While evidence suggests UBI can improve wellbeing and provide a safety net, its impact on employment remains inconclusive.
The potential for reduced work incentives and the substantial financial burden necessitate a cautious approach.
Targeted implementations and pilot programs are crucial to assess UBI’s long-term effects and refine its design.
Ultimately, a successful UBI may require a multifaceted approach, combining direct cash transfers with investments in education, job training, and social support systems to ensure a robust and adaptable workforce in the face of evolving economic realities.
| 2025-01-13T00:00:00 |
2025/01/13
|
https://www.peoplemattersglobal.com/article/compensation-benefits/will-a-universal-basic-income-work-in-the-ai-economy-43956
|
[
{
"date": "2023/03/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 40,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 45,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 63,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 40,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 45,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 48,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 43,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 43,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 48,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 29,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 47,
"query": "universal basic income AI"
},
{
"date": "2025/02/01",
"position": 40,
"query": "universal basic income AI"
},
{
"date": "2025/03/01",
"position": 39,
"query": "universal basic income AI"
},
{
"date": "2025/05/01",
"position": 49,
"query": "universal basic income AI"
},
{
"date": "2025/06/01",
"position": 45,
"query": "universal basic income AI"
}
] |
The “digital dividend”: Rethinking income for the age of AI - Big Think
|
The “digital dividend”: Rethinking income for the age of AI
|
https://bigthink.com
|
[] |
1 day ago · Universal Basic Income (UBI) has been discussed as a potential countermeasure for job displacement by AI, but it requires enforceable mechanisms ...
|
Sign up for the Big Think Business newsletter Learn from the world’s biggest business thinkers. Subscribe
The world had time to react to the invention of the wheel, the creation of the printing press, the industrial revolution, and the start of the internet and computer-based work. Industries adapted, people retooled and reskilled themselves to perform the new work that needed to be done. The AI revolution is different. Its rapid advancement has left many spinning in worry and despair, as they feel they have no time to prepare or prevent their own displacement.
It is predicted that long-term AI investment has added $4.4 trillion in growth potential to the global economy, but who benefits? If the wealth created by 24/7 AI employees accrues solely to shareholders and tech conglomerates, we risk deepening economic inequality. There must be a system or systems for distributing this accumulation of wealth, so income disparity doesn’t increase and millions don’t become impoverished.
AI and social equity
The industrial revolution was a brawn multiplier; the AI revolution is a brain multiplier. The pace of change is not slowed by the production capacity of industrial plants, as these AI minds can learn and progress overnight. The possibility of unchecked societal displacement and upheaval is a real one.
Predictions of nearly 300 million jobs being eliminated by AI are frightening. This shift offers unprecedented potential — and peril. The polarity in outcomes could be profound. On the one hand, agentic AI systems could revolutionize global productivity, accelerate drug discovery, and combat systemic issues like child hunger.
Try Big Think+ for your business Engaging content on the skills that matter, taught by world-class experts. Request a Demo
On the other hand, unchecked AI could become what Oxford philosopher Nick Bostrom has described as the “final invention” — a force so powerful it displaces humanity’s role in decision-making altogether. Over 1,000 AI researchers and leaders, including Elon Musk and Yoshua Bengio, have signed an open letter calling for a pause in large-scale AI experiments, warning of potential “loss of control” over intelligent systems.
Are we moving too fast with AI? Are too many treating it like a new toy at Christmas when it is actually a serious instrument that must be handled with care and consideration at all times? The future and fate of tens of millions of our fellow global citizens hang in the balance.
Everyday possibilities and pitfalls
Much time in studies and online is spent on the macro level when it comes to AI and its changes to society, but the day-to-day applications and effects are massive. The most immediate, day-to-day impact the individual will experience is less waiting and more doing and getting answers/results.
For instance, by 2028 it’s predicted that 68% of customer service and support interactions will be handled by agentic AI. Agentic AI has the advantage of being able to learn constantly and become a subject matter expert at a rapid pace. The amount of calls that get escalated to humans will decrease, and time on the phone and in chat boxes will decrease, while customer satisfaction increases.
Much like carbon pricing for environmental harm, a “digital dividend” can ensure that AI-driven productivity translates into shared prosperity.
It will also bring much more profound, life-changing benefits. For instance, in the field of medical treatment and drug discovery. People will begin to benefit from accelerated innovation in these fields due to initiatives such as Microsoft’s Discovery platform. They are creating an environment powered by agentic AI where “every researcher could collaborate with a tireless team of intelligent, synergistic AI agents with the sole purpose of accelerated innovation.” That method of instantaneous collaboration is revolutionary on all levels of medical research and treatment to all humans.
But, with these benefits comes a potential offsetting cost to all of us. For example, there are millions of people across the globe that comprise the staff of call centers and customer support. What becomes of them when an AI can answer nearly all questions with zero dollars in salary for human employees? Is the world prepared for this level of potential unemployment? Where are governmental and enterprise level programs for upskilling and retraining to keep these individuals from being left behind?
Wealth redistribution from digital to human labor
The “godfather of AI,” professor Geoffrey Hinton, recently told the BBC he felt AI would increase productivity and wealth but that money would go to the rich “and not the people whose jobs get lost and that’s going to be very bad for society.” Without implementation of policies across the globe, this fear could become a reality.
Universal Basic Income (UBI) has been discussed as a potential countermeasure, but without enforceable mechanisms, it remains an academic exercise. Instead, there should be a new model of digital labor taxation — a structured system whereby digital employees are taxed for their productivity, and the proceeds are redistributed to the human workforce they displace or augment.
Much like carbon pricing for environmental harm, a “digital dividend” can ensure that AI-driven productivity translates into shared prosperity. Governments must create streamlined, automated pathways for this redistribution, possibly leveraging the same agentic technologies to track, tax, and transfer.
As the agentic AI era gains traction with more autonomous actions, we will start to see a work stratification emerge in the hybrid society. More productivity will shift to digital beings, and more creativity will become the onus of the human beings. Machines will produce everything we need. Humans will be free to create new worlds. In order for this new world to be realized, all must be lifted by the tide of AI, not simply those with the capital to program and leverage it.
| 2023-03-01T00:00:00 |
https://bigthink.com/business/the-digital-dividend-rethinking-income-for-the-age-of-ai/
|
[
{
"date": "2023/03/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 13,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 22,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 24,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 26,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 25,
"query": "universal basic income AI"
},
{
"date": "2025/02/01",
"position": 42,
"query": "universal basic income AI"
},
{
"date": "2025/03/01",
"position": 41,
"query": "universal basic income AI"
},
{
"date": "2025/05/01",
"position": 41,
"query": "universal basic income AI"
},
{
"date": "2025/06/01",
"position": 53,
"query": "universal basic income AI"
}
] |
|
Universal Basic Income: The Imperative for Civilization in the Age of AI
|
Universal Basic Income: The Imperative for Civilization in the Age of AI
|
https://www.linkedin.com
|
[
"Go To Market"
] |
Universal Basic Income (UBI) is a government program designed to provide every adult citizen with a set amount of money regularly. Its core ...
|
The rapid acceleration of Artificial Intelligence (AI) is ushering in an era of unprecedented technological transformation, fundamentally reshaping global economies and societies. While AI promises immense productivity gains and new frontiers of innovation, it simultaneously presents a profound challenge to the traditional structure of work and wealth distribution. The conversation around Universal Basic Income (UBI), once relegated to the fringes of academic discourse, has now become an urgent imperative, offering a potential pathway to safeguard civilization against the disruptive forces of widespread job displacement. This report delves into the nature of this impending crisis, the historical context and contemporary relevance of UBI, its transformative potential for governments and companies, and the mechanisms by which it could be funded to secure a stable and equitable future.
I. The Unfolding Reality: AIs Unprecedented Reshaping of the Workforce
A. Beyond Automation: The Cognitive Revolution of AI
The current wave of AI-driven automation is distinct from previous industrial revolutions. Historically, technological advancements primarily automated physical or repetitive manual tasks, allowing human labor to shift to new roles requiring different skills. However, the advent of sophisticated AI models, particularly Large Language Models (LLMs) like ChatGPT 4o marks a pivotal moment, as their capabilities extend to automating "cognitive labor, decision-making, and even creativity". This qualitative shift fundamentally alters the traditional cycle where technology destroys some jobs but concurrently creates new ones that absorb displaced workers. The rapid advancement of these AI models, such as DeepSeek, indicates an accelerating pace of evolution that is increasingly difficult to slow down.
The economic implications of this cognitive automation are already evident. Industries most exposed to AI have experienced a near quadrupling of revenue per employee since 2022, demonstrating the tangible economic benefits and early returns on AI investments for businesses. This surge in productivity, however, raises critical questions about the distribution of this newly generated wealth. A historical trend, observed since 1973, reveals a decoupling of productivity growth from wage growth, leading to vast inequality where a substantial portion of economic gains has flowed to the top 1% rather than broadly benefiting the population. If AI, a technology designed for unprecedented efficiency, continues this pattern, the gap between economic output and broad societal prosperity will widen exponentially. This indicates that the current economic system, reliant on labor as the primary means of wealth distribution, is ill-equipped to manage the AI-driven concentration of wealth, necessitating new mechanisms for broad-based prosperity.
Furthermore, the skills required for AI-exposed jobs are changing at an accelerated rate, 66% faster than for other jobs, representing more than a 2.5-fold increase from the previous year. While workers possessing AI skills command a significant wage premium, averaging 56% higher than those in similar roles without such skills, this rapid skill evolution presents a substantial challenge for workforce adaptation. The sheer speed of this change, coupled with AI's ability to automate cognitive tasks, suggests that simply upskilling a large portion of the workforce might be an inadequate solution. The pace of transformation could easily outstrip the capacity of individuals and existing educational systems to retrain effectively on a mass scale, particularly for older or less educated workers. This implies that a significant segment of the population may become structurally underemployed or unemployable, regardless of individual effort, highlighting the need for a systemic safety net that transcends traditional employment.
The impact of AI is also not uniform, potentially intensifying existing socioeconomic disparities. Data suggests that more women than men are currently in AI-exposed roles, implying a higher skills pressure on women. Additionally, research in the investment management industry indicates a 5% decline in the labor share of income due to AI and big data technologies, which could further intensify economic disparities. This suggests that AI will not only create new inequalities but may also exacerbate existing ones, potentially widening the wealth and opportunity gap along demographic lines. Policy responses, including UBI, must therefore be designed with an awareness of these intensified disparities to actively mitigate further social fragmentation and ensure a more equitable distribution of AI's benefits.
B. The Accelerating Wave of Corporate Layoffs: A Glimpse into the Future
The theoretical discussions about AI's impact on employment are now translating into tangible workforce reductions across various industries. These are not merely cyclical cost-cutting measures but often represent a strategic pivot towards AI-first operational models.
Salesforce, for instance, has seen its CEO, Mark Benioff, claim that AI now handles between 30% and 50% of the company's workload. This increased efficiency has directly contributed to thousands of layoffs between 2013 and 2024, with many roles, including support agents, content writers, HR, and administrative tasks, being incrementally replaced by AI-enhanced productivity. This demonstrates AI's immediate and direct impact on white-collar administrative and customer-facing roles.
Amazon has also begun notifying employees of mass layoffs across its warehouses, delivery hubs, and corporate offices, explicitly stating that AI will take over many of their jobs. CEO Andy Jassy has clarified that the company is undergoing a structural transformation, with AI automation replacing traditional job roles at scale, indicating a shift from general cost-cutting to an AI-powered operational overhaul. In 2025 alone, 14,000 corporate roles, primarily in middle management, were cut, with AI tools like Alexa+ and AI Shopping Assistant taking over tasks previously performed by humans.
Microsoft announced a reduction of its global workforce by approximately 3% (6,000-7,000 employees) in May 2025, following 10,000 cuts in 2023, to streamline management layers and intensify its focus on AI-driven priorities. Further layoffs were planned for July 2025, impacting thousands more in sales, marketing, and gaming divisions, after over 6,000 cuts in May and June. Notably, Microsoft's CEO Satya Nadella revealed that 30% of the company's code is now AI-written, and over 40% of recent layoffs targeted software engineers, directly linking AI productivity to job elimination even in highly skilled technical roles. These layoffs are explicitly a strategic pivot towards AI, not a reaction to financial distress.
Even big consulting firms like McKinsey & Company are feeling the impact. McKinsey plans to cut approximately 5,000 jobs, representing 10% of its global workforce, in 2025. A primary reason cited is a "downturn in client demand, partly ushered in by the rapid advancement and integration of artificial intelligence (AI) within various industries," as businesses become "increasingly autonomous with AI solutions," diminishing the need for extensive consultancy services. This illustrates AI's direct impact on high-value professional services.
The media and advertising agencies are also undergoing significant restructuring. Thousands have been laid off across CPG giants and advertising firms, with AI increasingly handling data collection, optimizing audience targeting, and even generating copy, images, and video. The industry is moving towards a "headless martech ecosystem, built on four to six interconnected platforms and orchestrated by AI agents," which could theoretically run multi-billion-dollar campaigns with just two or three operators.
Across the broader tech industry, AI-driven automation has led to over 100,000 job cuts in 2025 alone, primarily impacting roles in software engineering, HR, and creative sectors. More than 50,000 tech employees were laid off in just the first six months of 2025. Other major firms like Google, IBM, Intel, Dell, Workday, and Meta are also reshaping teams with AI priorities and undergoing similar restructurings.
These examples collectively reveal that the layoffs are a strategic pivot, not merely cyclical cost-cutting. While companies frequently cite "efficiency" and "streamlining operations" as reasons for layoffs, the scale and specific examples demonstrate that this efficiency is directly achieved through human job elimination. The question of "whose work was that? And what happened to the teams that used to do it?" highlights the direct causal link between AI adoption and workforce reduction. This indicates a fundamental, permanent re-engineering of corporate structures where AI becomes central, and traditional human roles are systematically re-evaluated and often eliminated based on AI's capabilities. This is not a temporary economic blip; it is a structural transformation of the labor market where the jobs lost may not return, underscoring the need for long-term societal solutions beyond conventional unemployment benefits. The relentless corporate pursuit of AI-driven efficiency, while boosting profits, has a direct and significant human cost in terms of employment. This creates a growing imbalance where a smaller number of highly productive, AI-leveraging companies generate immense wealth, while a larger segment of the population is left without traditional means of income.
C. Jobs on the Brink: From Marketing to Legal, No Sector is Immune
The pervasive nature of AI's disruption means that a wide array of job categories, including many white-collar and skilled professions, are now on the brink of significant transformation or outright displacement. The underlying principle is clear: if a significant portion of a job can be automated using AI or Large Language Models (LLMs), that job is at risk.
In Marketing, AI is profoundly changing the landscape by automating repetitive, data-driven tasks such as content creation, email campaigns, customer segmentation, lead nurturing, and social media management. AI can generate copy, images, and video, and optimize audience targeting. Tools like HubSpot, Mailchimp, Ocoya, Prowly, and Persado are already widely used for personalization, data analysis, and campaign optimization. Consequently, traditional roles like programmatic ad buying, junior writing, and manual data-crunching are being phased out.
Customer Success and Service roles are also heavily impacted. AI chatbots and virtual assistants, including ChatGPT and Drift, are enhancing customer service by providing real-time support and personalized responses, significantly reducing the need for human representatives. Amazon, for example, is explicitly "thinning out" its customer service workforce in favor of LLM-based support. AI chatbots can reduce telemarketing costs by 80%, rendering human customer service roles "rapidly obsolete".
In Analytics, AI tools can process vast amounts of market data faster and more accurately than humans, identifying trends and predicting behavior with superior precision. Real-time analytics platforms are reducing the need for manual data-crunching teams. AI can also mine unstructured data, such as images, videos, and social media, to gain deep consumer insights.
For Developers and Software Engineers, tasks involving repetitive coding and debugging are increasingly being automated. Microsoft's CEO has noted that 30% of the company's code is now AI-written, directly correlating with over 40% of their recent layoffs targeting software engineers. The job market for junior software engineers is described as being in "turmoil" because AIs can perform tasks typically taught by a computer science degree.
Even the Legal Profession is undergoing significant transformation. AI is automating routine yet time-consuming tasks such as document review, legal research, and contract analysis. AI tools are predicted to free up approximately 4 hours of a legal professional's time per week, translating into substantial productivity gains. Law firms are exploring AI to handle large volumes of legal data, improve client response times, reduce human error, and provide advanced analytics. AI can scan legal databases, identify relevant statutes, and cross-reference case history faster than human researchers, potentially replacing entire research teams.
Beyond these specific categories, the trend extends to other vulnerable roles. Human Resources staff are being impacted as AI systems replace most HR functions. Content writers and copywriters face challenges as AI-generated writing can be produced at a fraction of the cost of human salaries. Financial analysts are seeing their roles affected as AI can read thousands of financial reports in minutes, spotting trends and making predictions faster than human analysts. Data entry and administrative roles are considered "easiest targets" for AI automation due to their repetitive nature. Even medical transcriptionists are at risk as AI speech recognition offers near-perfect accuracy. The CEO of Anthropic starkly predicts that AI could eliminate half of all entry-level white-collar jobs within five years.
While some discussions focus on AI augmenting jobs and creating new roles, the overwhelming evidence from recent layoffs points to direct job replacement, particularly for "automatable jobs". Companies are systematically "removing people" and "slashing roles" while integrating AI, suggesting that augmentation is not universally leading to new, higher-value human roles within the same companies, but rather to a leaner, more automated workforce. This indicates that the optimistic narrative that AI will only augment human capabilities, while true for some highly specialized roles, is not applicable to a large segment of the workforce whose tasks are inherently automatable. This necessitates a broader societal safety net, as traditional employment opportunities shrink for many.
As AI takes over repetitive tasks, the remaining human roles demand higher-level skills, such as strategy, brand knowledge, and audience understanding in marketing; ethical prompt design, AI oversight, and autonomous system management in operations; and a shift for lawyers from "producer of documents" to "trusted advisor". This indicates a significant stratification of the workforce, where a smaller number of highly skilled individuals will orchestrate AI, commanding high wages, while a larger number of "execution" roles are eliminated. The job market will become increasingly bifurcated, leading to a "winner-take-most" dynamic. This exacerbates income inequality, as a small elite benefits disproportionately from AI's productivity gains, while a vast majority struggles to find meaningful, well-paying work.
D. Why This Time is Different: Dispelling Historical Analogies
A common counter-argument to the concerns about AI-driven job displacement is to draw parallels with past industrial revolutions, which, despite initial disruption, ultimately created more jobs than they destroyed. However, this historical analogy may not hold true for the AI era.
Scott Santens argues that AI-driven automation is "fundamentally different" from previous technological shifts because it is automating "cognitive labor, decision-making, and even creativity," rather than just physical or repetitive tasks. This breaks the traditional cycle of job creation that followed past revolutions. In the past, individuals displaced by new technologies could often transition to new roles requiring different physical or routine cognitive skills, such as a carriage driver becoming a taxi driver. AI, however, fundamentally automates the very essence of human intellectual work, which was previously considered secure. If advanced forms of AI, or Artificial General Intelligence (AGI), become "good enough to take over any job that these unemployed humans might try to go for", then the historical precedent of new job creation becomes tenuous, as the pool of uniquely human tasks shrinks. This could lead to an "exceedingly wealthy country with record numbers of jobless citizens". The scope of job displacement is potentially far wider and more fundamental, affecting white-collar and highly skilled roles, making re-employment pathways far less clear or available for the masses, demanding a new societal approach to economic security.
The rapid advancement of AI models demonstrates how quickly capabilities are evolving, making it "increasingly difficult to slow development". Santens warns that "there will not be any slowing of this down", implying that society must adapt quickly rather than expect a gradual transition. This rapid evolution, combined with the 66% faster skill change in AI-exposed jobs, suggests that the rate at which jobs are transformed or eliminated could outpace the ability of educational systems and individuals to adapt. The historical analogy of gradual transitions over decades may not apply, as the current pace is unprecedented. The advertising industry also highlights this as a "readiness" issue, not just a technology one. Society faces a profound "readiness" crisis, where the speed of technological change demands proactive, systemic solutions rather than relying on gradual, individual adaptation. This urgency is precisely why the conversation about UBI is critical now.
Furthermore, high-skill occupations are expected to be more exposed to AI, with highly educated and older workers more likely to be affected than by previous technologies. This contradicts the comforting notion that only low-skill jobs are at risk. While research from Columbia Business School suggests AI's impact on the labor share of income (a 5% decline) is comparable to historical Industrial Revolutions (5-15% declines), it also notes that in finance, AI led to more hiring of people with AI skills, not job loss. This nuanced point reinforces that while new jobs are created, they require a fundamentally different skillset, and the transition may not be feasible or accessible for everyone.
II. The Looming Crisis: Economic and Societal Fallout of Mass Unemployment
A. The Vicious Cycle: Reduced Consumer Spending and Market Collapse
The widespread displacement of jobs due to AI, if left unaddressed, poses a catastrophic threat to the global economy by undermining the very foundation of consumer demand. When a significant portion of the population loses its income, a direct and inevitable consequence is a drastic reduction in consumer spending. This decrease in demand for goods and services can trigger a "deflation of value" across the economy, as businesses struggle to sell their products and services.
This creates a perilous "vicious cycle": reduced consumer demand leads to decreased production, which in turn necessitates more job cuts, further exacerbating unemployment. This self-fulfilling prophecy highlights a systemic risk where the pursuit of AI-driven efficiency by corporations, while boosting their internal productivity and profits, simultaneously erodes the purchasing power of their customer base. If a large segment of the population is unemployed and struggles to afford basic necessities, the market for new phones, self-driving cars, or advanced advertising and e-commerce services—all products of AI innovation—will inevitably shrink. The immense value created in industries best positioned to use AI, which has "skyrocketed", will become theoretical if there is no one left with the means to buy these products. This suggests that AI-driven efficiency can undermine its own market, creating a "Productivity Paradox of Demand." Corporations, in their singular pursuit of AI-driven efficiency and profit maximization, risk destroying the very consumer market they rely upon, necessitating a fundamental re-evaluation of the economic model to ensure that the benefits of AI are distributed widely enough to maintain a viable consumer base.
Small businesses, often the backbone of local economies, are particularly vulnerable to this downturn in consumer spending. With less disposable income, consumers are less likely to support local enterprises, leading to reduced revenue, layoffs, and even forced closures for these businesses. This disproportionately impacts local economies and compounds the overall unemployment crisis. High unemployment rates directly correlate with declining consumer spending due to less disposable income, which then decreases overall economic growth.
Beyond the immediate loss of income, unemployment often forces individuals and households to rely on credit cards or loans to meet basic needs, leading to increased debt and potential financial penalties. This means that even if a job is eventually found, the burden of accumulated debt can prolong financial hardship for years, hindering individual economic recovery and perpetuating a cycle of instability for affected households. The long-term societal cost of mass unemployment extends beyond immediate income loss to chronic financial instability for affected households, potentially creating a permanent underclass burdened by debt, which further suppresses overall economic activity.
B. The Human Cost: Financial Precarity, Inequality, and Social Strain
The consequences of widespread job loss extend far beyond economic metrics, reaching into the very fabric of human well-being and social stability. AI-driven job displacement carries a profound psychological toll on affected workers, leading to significant anxiety and uncertainty about their future. The abruptness of these layoffs further exacerbates this anxiety among the workforce. This emotional burden can manifest in various forms of distress, impacting mental and physical health, and eroding a sense of purpose and belonging.
Ethical concerns are mounting around worker displacement, income inequality, and the broader socio-economic impact of these changes. This highlights a growing awareness of the moral dimension of AI's disruption, questioning the responsibility of corporations to balance profit with the social well-being of their workforce and society at large.
Widespread unemployment directly contributes to income inequality. As previously noted, massive inequality growth has already occurred, with a staggering $79 trillion flowing to the top 1% instead of the bottom 90% due to productivity decoupling from wage growth since 1973. AI is poised to accelerate this trend, as the benefits of increased productivity accrue disproportionately to those who own and deploy the technology, rather than being broadly distributed among the populace. This exacerbation of inequality is not limited to low-skill jobs; high-skill occupations are expected to be more exposed to AI, disproportionately affecting highly educated and older workers more significantly than previous technologies. This suggests that precarity will spread across different socio-economic strata, challenging the notion that education or specialized skills alone will guarantee immunity from displacement.
If AI makes traditional, compensated work scarce, it challenges a fundamental societal construct where an individual's worth, identity, and social status are deeply intertwined with their employment and wage. The observation that "wage levels can influence perceptions of an individual's value and worth" becomes acutely relevant. If people cannot earn income through traditional means, and their self-worth is tied to it, widespread unemployment can lead to a profound crisis of identity and purpose, beyond just financial hardship. This paradigm, where human value is narrowly assigned based solely on income, is under fundamental threat, causing an an identity crisis for many.
Widespread job loss, particularly if perceived as an inevitable consequence of technological progress controlled by a few corporations, can lead to a profound sense of helplessness, resentment, and disenfranchisement among the populace. The psychological toll combined with increased income inequality can severely erode social cohesion and trust in institutions. If a large segment of the population feels left behind by technological progress, it can lead to social unrest, political polarization, and a breakdown of the social contract. Beyond economic metrics, the unmitigated impact of AI-driven job displacement threatens the very fabric of society, making UBI not just an economic solution but a crucial social stabilizer to prevent widespread discontent and maintain civil order.
III. Universal Basic Income: A Foundational Solution for an AI-Driven World
A. What is UBI? Defining a Centuries-Old Idea for Modern Times
Universal Basic Income (UBI) is a government program designed to provide every adult citizen with a set amount of money regularly. Its core principles are universality and unconditionality. This means the payment is an unconditional transfer, provided "without a means test or need to perform work". It is received independently of any other income, distinguishing it from traditional welfare programs that often impose strict eligibility criteria and work requirements.
The primary goals of a UBI system are to alleviate poverty and, in many proposals, to replace other need-based social programs that typically involve greater bureaucratic complexity and administrative overhead. This suggests a move towards greater efficiency and simplicity in social support systems. A "full basic income" is defined as an amount sufficient to meet a person's basic needs, at or above the poverty line, while a "partial basic income" is less than that amount. As of 2025, no country has implemented a full UBI system, though various pilot projects and partial UBI schemes have been explored globally.
The "unconditional" and "without a means test" nature of UBI is philosophically significant. It positions UBI not as traditional welfare, which can carry stigma, complex bureaucratic hurdles, and disincentives to work, but as a fundamental right or a "citizen's dividend". This framing is crucial for its social and political acceptance, particularly if it is understood as a share in the collective wealth generated by advancements like AI, rather than merely a handout for the poor. Shifting the public perception of UBI from a welfare measure to a universal right is essential for fostering a sense of shared prosperity and collective ownership in an increasingly automated economy, thereby enhancing its political viability.
B. A Brief History: From Utopian Ideals to Contemporary Proposals
The concept of providing a regular, guaranteed payment to citizens is not a radical new idea but one with deep intellectual roots, having been proposed across centuries to address evolving societal challenges. Its historical lineage lends credibility to its contemporary relevance.
Early mentions of a guaranteed income can be found in the 16th-century English philosopher Thomas More's seminal work, "Utopia". In the 18th century, Thomas Paine, an influential pamphleteer of the American Revolution, proposed a tax plan where revenues would provide a basic government income. He argued that "Men did not make the earth... Every proprietor owes to the community a ground rent for the land which he holds". This "ground rent" concept is particularly relevant in the AI era, where collective data and infrastructure generate immense value, analogous to land as a shared resource.
Other notable historical advocates include Bertrand Russell in the early 20th century, who argued for a "certain small income, sufficient for necessaries, should be secured to all, whether they work or not". In the mid-20th century, Martin Luther King, Jr., proposed a "guaranteed income" in his 1967 book "Where Do We Go from Here: Chaos or Community?". Even the free-market economist Milton Friedman argued for a "negative income tax" in 1962, which is functionally similar to a UBI, to overcome disincentives inherent in traditional welfare systems. This demonstrates the concept's appeal across the political spectrum. More recently, Andrew Yang popularized the idea in the U.S. with his "Freedom Dividend" proposal of $1,000 per month for every American adult.
The idea of UBI has gained significant renewed attention since 2020, particularly given the rapid developments in artificial intelligence and automation. The diverse ideological backgrounds of UBI's proponents throughout history—from utopian philosophers to revolutionary thinkers, civil rights leaders, and free-market economists—suggest that UBI is not a partisan idea. Instead, it is a recurring solution proposed across different eras to address fundamental questions of economic justice, poverty, and societal stability during periods of significant technological or social change. Paine's "ground rent" concept is especially prescient in the AI age, as AI's value is derived from collective data and infrastructure, rather than solely individual labor. The broad historical advocacy for UBI lends it intellectual credibility and indicates that its current resurgence is a natural and necessary response to the unique, systemic challenges posed by the AI age, rather than a fleeting or radical trend.
C. UBIs Core Promise: A Safety Net for All in an Uncertain Future
In the context of AI-driven job displacement, UBI offers a fundamental level of economic security that can stabilize individuals and society during a period of unprecedented change. Its core promise is to provide a crucial financial safety net, offering stability and easing the hardships of transition in an evolving labor market. This is particularly vital when traditional employment pathways are disrupted or become scarce.
Supporters of UBI contend that a guaranteed payment from the government can help ensure that those "left behind by this economic transformation avoid poverty". Even if the government-sourced income is not enough to live on entirely, it could theoretically supplement income from lower-wage or part-time jobs that individuals might still be able to obtain. This positions UBI as a foundational layer of income security, providing a buffer against economic shocks.
Evidence from UBI trials, such as the one conducted in Finland, suggests that it can alleviate financial stress and significantly enhance participants' well-being and life satisfaction. This highlights the profound psychological benefits beyond mere financial support, as reduced financial anxiety can lead to improved mental health, reduced healthcare costs, and potentially increased productivity when individuals do re-enter the workforce. UBI offers a "practical approach to navigate the evolving labor market, enabling individuals to adapt and thrive", by providing the security needed to pursue new skills, education, or entrepreneurial opportunities without the constant fear of financial ruin.
Traditional welfare systems are often reactive, means-tested, and bureaucratically complex, designed to address poverty after it occurs. UBI, being unconditional and universal, is a proactive measure that aims to prevent extreme financial precarity in the first place. By providing a baseline income, it reduces the "financial stress associated with unemployment", which can lead to improved mental health, reduced healthcare costs, and possibly increased productivity when individuals do re-enter the workforce. This fundamentally shifts the societal focus from managing poverty to ensuring broad economic stability and individual resilience. UBI offers a paradigm shift in social policy, moving from a remedial approach to a preventative one. This preventative framework is far better suited to the systemic, rapid, and widespread disruption anticipated from AI, allowing society to absorb shocks rather than constantly react to crises.
IV. UBIs Transformative Potential: Reshaping Society and Economy
A. Stimulating Demand and Fostering Local Economies
One of the most critical economic benefits of Universal Basic Income in an AI-driven world is its potential to directly counteract the economic downturn caused by mass unemployment. By injecting liquidity into the economy, UBI can act as a powerful stimulant, directly increasing consumer demand and driving overall economic growth. This directly addresses the concern about who will purchase products if a significant portion of the population is unemployed.
A study by the Roosevelt Institute estimated that a modest UBI in the United States could boost GDP by as much as $2.5 trillion by 2025. This substantial quantitative projection underscores UBI's potential to maintain and stabilize demand, preventing the "vicious cycle" of reduced spending, decreased production, and further job cuts. This injection of spending power could significantly bolster small businesses, encourage entrepreneurship, and contribute to job creation, particularly in communities that often experience economic stagnation.
AI is fundamentally a supply-side revolution, enabling companies to produce goods and services with unprecedented efficiency, speed, and scale. However, if a large portion of the population lacks purchasing power due to job displacement, this immense supply-side efficiency becomes economically meaningless. UBI directly addresses this by maintaining and stimulating consumer demand. It ensures that the benefits of AI-driven productivity are translated into actual market activity, preventing a "market collapse" scenario where no one can afford the innovative products produced by AI. UBI is not merely a social safety net; it is an economic necessity to ensure the continued viability and dynamism of a consumer-driven economy in an AI-dominated production landscape. Without it, the very efficiency AI brings could lead to economic stagnation.
The financial assistance implemented during the COVID-19 pandemic, such as stimulus payments, provides a recent, real-world parallel for UBI's potential to effectively support consumer spending and prevent deflation during times of crisis. This demonstrates the government's role in mitigating the negative effects of unemployment on the economy through direct payments.
B. Redefining Work and Unleashing Human Potential Beyond Traditional Employment
Beyond its economic stimulus, UBI has the potential to fundamentally transform societal perceptions of "work" and unleash human potential beyond the confines of traditional, often unfulfilling, employment. By providing a financial safety net, UBI could allow individuals to pursue their passions and intrinsic motivations rather than being solely driven by monetary concerns. This shifts the focus from obligation to fulfillment.
With financial worries alleviated, individuals could allocate their time to enriching pursuits such as exploring artistic talents, assisting those in need, nurturing their families, or enhancing their communities. This envisions a broader definition of valuable societal contribution, recognizing that human worth extends far beyond market-compensated labor. The Finland UBI trial demonstrated that participants experienced heightened well-being and reduced stress, suggesting that UBI might grant people the freedom to focus on life's intangible values and self-improvement.
Furthermore, UBI encourages entrepreneurial activities by significantly reducing the financial risks associated with starting new ventures. This fosters innovation by lowering the barrier to entry for creative ideas and mitigating the failure risk of new businesses. Some UBI pilots even indicate that the security provided can actually encourage people to pursue more meaningful or entrepreneurial work, rather than discouraging labor participation.
If AI takes over many traditional "jobs", society needs a new framework for human contribution and value. UBI allows for a redefinition of "work" to encompass activities that are valuable but not traditionally compensated in the market, such as caregiving, community service, artistic pursuits, lifelong learning, and civic engagement. This shifts the societal focus from forced labor for mere survival to enabling human flourishing and diverse forms of value creation, which are essential for a thriving civilization. UBI facilitates a profound cultural transformation where human purpose and contribution are decoupled from the traditional employment model. This fosters a more creative, resilient, and engaged citizenry, capable of adapting to and benefiting from an AI-driven world.
C. Addressing Inequality and Building a More Equitable and Resilient Future
In an era where AI threatens to exacerbate existing income disparities, UBI emerges as a potential solution to mitigate inequality and foster a more stable, cohesive, and equitable society. UBI is increasingly seen as a mechanism to address pressing modern economic challenges such as income inequality and poverty.
By guaranteeing a basic level of financial security for everyone, UBI challenges the narrow assignment of worth based solely on income, recognizing the inherent value and dignity of all individuals. This is crucial in a world where traditional work may become scarce, preventing a societal devaluation of those without conventional employment. It promotes a more equitable society where everyone has the means to thrive and contribute, regardless of their socioeconomic background.
A more stable, secure population, free from the constant fear of financial ruin, may result in sustained and inclusive economic growth. A reduction in harsh disparities and income inequality can enhance social cohesion and political stability, mitigating the risks of social unrest that often accompany widespread economic hardship.
AI's rapid and widespread impact is predicted to create significant economic shocks, including mass job loss, wage stagnation, and increased income inequality. UBI, by providing a consistent and unconditional safety net, acts as an "economic shock absorber", cushioning individuals and communities from the immediate and severe consequences. This foundational stability is crucial for preventing widespread social unrest and allowing for a more orderly societal transition, rather than a chaotic collapse. UBI is not just about poverty alleviation; it is a strategic tool for maintaining social and economic stability during an era of unprecedented technological disruption. It provides the necessary foundation for society to adapt and evolve without succumbing to the pressures of mass displacement and inequality.
V. Funding the Future: Mechanisms and Feasibility of UBI
A. Innovative Approaches to Financing UBI in the AI Era
The question of how to fund Universal Basic Income on a national scale is central to its feasibility. While critics often highlight the substantial costs, proponents argue that UBI is financeable through a combination of cost offsets and innovative new revenue streams that align with the nature of AI-driven wealth generation.
One key argument for feasibility is the potential to eliminate the more expensive social administration and bureaucratic efforts associated with existing means-tested social benefits. By streamlining or replacing a multitude of existing welfare programs (e.g., food stamps, housing assistance, unemployment benefits) with a single, unconditional payment, significant administrative savings could be realized. While critics raise concerns that this might reduce targeted support for the most vulnerable or lead to some individuals being worse off, the overall simplification and reduction of overhead could offset a portion of UBI's cost.
However, implementing UBI on a national scale would undoubtedly require substantial new funding. This could come from heightened income or consumption taxes. More innovatively, and particularly relevant in the AI era, are currently untested funding sources such as taxes on carbon emissions or, crucially, automation. An automation tax directly links the source of unprecedented productivity gains (AI) to the funding mechanism for UBI. If AI is the primary driver of wealth concentration and job displacement, then taxing automation becomes a logical, equitable, and economically justifiable funding source. This creates a virtuous feedback loop where societal benefits are derived from technological progress.
Historically, proposals like Thomas Paine's "ground rent"—a tax on land value—and Henry George's "single tax movement"—a tax on the economic rent derived from land and natural resources, sometimes referred to as a "citizen's dividend"—offer precedents for taxing collective resources for public benefit. In the AI age, the vast amounts of data and the collective digital infrastructure that fuel AI's capabilities can be seen as a new form of "commons" or "ground rent." An automation tax would be analogous to Paine's concept, where the collective benefit from a shared resource (land, now AI's capabilities and data) is distributed back to the community. This approach could be a politically and economically justifiable way to fund UBI, ensuring that the immense wealth generated by AI serves the broader population, not just the few corporations that own and deploy the technology, thereby addressing the ethical concerns around wealth concentration.
Milton Friedman's concept of a negative income tax, while different in structure, shares the goal of providing a baseline income and could be viewed as a UBI for certain income groups. This demonstrates that even within a free-market framework, mechanisms for guaranteed income have been considered.
The long-term sustainability of UBI depends on developing funding mechanisms that can balance equity with economic efficiency, without placing undue strain on public resources or individual taxpayers. Careful fiscal planning and ongoing research into tax structures that align with economic and social goals will be essential for successful implementation.
VI. Conclusion: The Imperative for Action and the Path Forward
The rise of Artificial Intelligence represents a profound inflection point for human civilization, a technological evolution unlike any before it. The evidence is clear: AI is not merely augmenting human capabilities but is strategically displacing jobs across a wide spectrum of industries and skill levels, from marketing and customer service to software development and legal analysis. This is not a distant threat but a present reality, as major corporations like Salesforce, Amazon, and Microsoft are already undergoing AI-driven operational overhauls leading to significant workforce reductions.
The historical analogy that industrial revolutions always create more jobs than they destroy may offer false comfort in this unique context. AI's capacity to automate cognitive labor, decision-making, and even creativity fundamentally differentiates it from past technological shifts, threatening to shrink the pool of uniquely human tasks and create a society of unprecedented wealth alongside widespread joblessness. The speed of AI's advancement further outpaces human adaptability, signaling a profound "readiness" crisis that conventional upskilling initiatives alone cannot resolve.
The unmitigated consequences of this widespread job displacement are dire. A significant portion of the population without a stable income would lead to a catastrophic collapse in consumer spending, undermining the very markets that AI-driven efficiency aims to serve. This "productivity paradox of demand" would render even the most innovative AI products irrelevant if no one can afford them. Beyond economic metrics, mass unemployment would inflict a profound psychological toll, exacerbate income inequality, erode social cohesion, and threaten the very stability of society by challenging the traditional paradigm of human worth tied to employment.
In this critical juncture, Universal Basic Income emerges not as a utopian ideal, but as a foundational and necessary solution for the survival and thriving of civilization in an AI-driven world. UBI, a concept with deep historical roots advocated by thinkers across the ideological spectrum, offers a crucial financial safety net that is unconditional and universal. It promises to alleviate poverty, reduce financial stress, and provide the stability necessary for individuals to adapt, pursue new skills, or engage in meaningful contributions beyond traditional employment.
Furthermore, UBI acts as a vital economic stimulant, injecting liquidity into the economy to maintain consumer demand and foster local economic growth, thereby preventing the market collapse that AI-driven efficiency alone could inadvertently cause. It facilitates a redefinition of human value, allowing individuals to pursue passions, care for communities, and engage in entrepreneurial ventures, thereby unleashing human potential in ways not constrained by the demands of conventional work. Critically, UBI serves as an essential "economic shock absorber," mitigating the exacerbation of income inequality and fostering a more equitable and resilient society capable of navigating the systemic disruptions of AI without succumbing to widespread social unrest.
Funding UBI on a national scale, while challenging, is feasible. It can be achieved through a combination of streamlining existing, inefficient welfare programs and, crucially, implementing innovative revenue streams such as an "automation tax". This approach directly links the source of new wealth generation (the efficiency and productivity gained from AI) to the mechanism of its distribution, ensuring that the benefits of this technological revolution are shared broadly across society.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/universal-basic-income-imperative-civilization-age-ai-anthony-laneau-5mq6e
|
[
{
"date": "2023/03/01",
"position": 30,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 27,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 28,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 20,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 32,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 27,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 27,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 30,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 28,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 28,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 30,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 29,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 35,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 32,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 35,
"query": "universal basic income AI"
},
{
"date": "2025/07/01",
"position": 33,
"query": "universal basic income AI"
}
] |
|
The Left-Wing Policy That AI Evangelists Suddenly Love
|
The Left-Wing Policy That AI Evangelists Suddenly Love
|
https://newrepublic.com
|
[
"Monica Potts",
"Malcolm Ferguson",
"Robert Mccoy",
"Michael Tomasky",
"Greg Sargent",
"Casey Quinlan",
"Grace Segers"
] |
The incomes usually max out at about $1,000 a month, which is not enough to replace work. “Basic” is right there in the name: UBI would create ...
|
At the same time, it’s not just cash welfare reborn, because its aim is to have fewer strings attached and be easier to access. “It’s not a net that holds people and keeps them safe,” said Natalie Foster, president and founder of the Economic Security Project. “It is a trampoline where people can have a floor that they cannot fall through and then jump up and live the lives of agency and dignity and live on their own terms, which you can’t do if you’re working hand to mouth, or if you are in deep economic uncertainty, which is what the future holds without bold policy interventions.”
There are conversations we need to have about UBI, separate from its potential as a salve for a labor apocalypse. At the same time, the development of AI requires a discussion about what the industry owes society for the damage it will cause. “AI’s worth is created by all of our data, all of our experiences, so everyone should have an ownership stake in that,” said Michael Tubbs, the former mayor of Stockton, California, who ran an AI project in his city—which TNR featured in 2020—and now works with an organization called Mayors for Guaranteed Income. “People who are going to be harmed have to have an ownership stake.”
Who works, how much they work, and how they’re compensated are political questions. Productivity gains over the past several decades have led to benefits for the very richest Americans, but many of us are working harder than ever without seeing gains. If we don’t tackle these issues in the right way, our future will be even more unequal than today, with the tech billionaires further enriched while the rest of us struggle to find new jobs and are encouraged to retrain or work harder. “I’m afraid inequality is likely to continue getting worse,” said Dr. Stuart Russell, a professor of computer science at UC Berkeley. “Most of the gains are likely to go to the owners of the technology.” And AI may hit white-collar jobs as severely as blue-collar jobs were pummeled by past technological changes.
For decades, economists and futurists have promised that technology gains will lead to increased leisure—famously, the economist John Maynard Keynes thought his grandkids would work 15 hours a week—and it largely hasn’t come to pass. It’s broadly true that we work less per week than our predecessors, Russell said. “Having said that, we’re certainly not living a life of leisure: As productivity improves, we are consuming a lot more rather than working a lot less.”
| 2025-07-02T00:00:00 |
2025/07/02
|
https://newrepublic.com/article/197500/ai-industry-love-universal-basic-income
|
[
{
"date": "2023/03/01",
"position": 35,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 37,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 37,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 14,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 36,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 39,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 38,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 37,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 37,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 38,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 36,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 37,
"query": "universal basic income AI"
}
] |
Why Personal Growth Must Replace Productivity in the Age of AI and ...
|
Why Personal Growth Must Replace Productivity in the Age of AI and Universal Basic Income
|
https://completeaitraining.com
|
[] |
Universal basic income (UBI) will remove survival as the primary motivator for human activity. This shift demands a fundamental change in how we ...
|
Personal Growth Over Productivity: Why AI Makes Current Education Obsolete
Artificial intelligence and automation are advancing to the point where human labor will no longer be necessary for survival. Universal basic income (UBI) will remove survival as the primary motivator for human activity. This shift demands a fundamental change in how we educate children—moving away from productivity-driven models toward fostering personal growth and exploration.
Why Universal Basic Income Changes Everything
The rise of AI means societies will generate unprecedented wealth with minimal human effort. To distribute this wealth fairly, governments will likely adopt universal basic income—regular payments that cover basic living costs. This change will make the innate human survival instinct less relevant.
Historically, survival has driven most human behavior. Psychologists explain that our decision-making, problem-solving, and even memory are geared toward improving survival chances. But once basic needs are guaranteed, individuals must find new motivations beyond mere survival. Without that, people risk stagnation or decline in physical and mental health.
In this context, personal growth becomes essential. It involves transforming mindsets and increasing self-awareness rather than just acquiring skills or external achievements. While personal development (skill-building) supports growth, the focus must shift to the internal journey of becoming a fuller version of oneself.
Current Education Systems Fall Short
Today's education largely aims at making individuals productive workers. But in a future where productivity is no longer the goal, this approach will fail to prepare children for meaningful lives. Education must evolve to cultivate self-driven motivations and preserve children’s authenticity.
Two key principles should guide this shift:
Preserve Authenticity: Children need safe spaces to express their true thoughts and feelings without masking themselves to fit expectations. This doesn’t mean abandoning discipline or social respect, but maintaining coherence between feelings, words, and actions.
Children need safe spaces to express their true thoughts and feelings without masking themselves to fit expectations. This doesn’t mean abandoning discipline or social respect, but maintaining coherence between feelings, words, and actions. Foster Alertness: Childhood wonder—the natural curiosity and desire to learn—should be nurtured into sustained alertness, a state of engaged awareness. This fuels lifelong personal growth.
Five Changes Needed in Education
To embrace these principles, education must:
Prioritize Personal Exploration: Learning should be hands-on and discovery-based, moving beyond traditional classrooms to real-world experiences.
Learning should be hands-on and discovery-based, moving beyond traditional classrooms to real-world experiences. Replace Standardization with Immersion: Children learn best when engaged with topics that interest them, ideally in diverse cultural and environmental settings.
Children learn best when engaged with topics that interest them, ideally in diverse cultural and environmental settings. Group by Interests, Not Age: Learning groups based on shared passions encourage enthusiasm and deeper engagement, with fluid group changes as interests evolve.
Learning groups based on shared passions encourage enthusiasm and deeper engagement, with fluid group changes as interests evolve. Focus on Maturity Alongside Learning: Education should promote holistic growth, not just memorization of facts.
Education should promote holistic growth, not just memorization of facts. Limit Guiding Values to Science-Based Principles: Educational goals should rely on established psychology and neuroscience rather than cultural dogmas to support healthy development.
Some existing models already reflect these ideas. Forest kindergartens in Denmark let children play freely in nature for years. Certain Norwegian schools have eliminated homework and exams, focusing on project-based learning. Montessori and Waldorf schools emphasize nurturing potential rather than shaping future workers. However, even these models still often aim at productivity, which will soon be outdated.
Parents as Catalysts for Change
Educational reform won’t come quickly from governments, whose responses tend to be slow and reactive. Parents must lead the way, recognizing that current systems won’t prepare their children for a future where AI replaces many traditional jobs.
Luckily, with AI reducing the need to work, parents will have more time to engage actively in their children’s education and help shape a system that supports personal growth and lifelong fulfillment.
For educators and parents interested in adapting to this new reality, exploring specialized AI training and resources can be beneficial. Platforms like Complete AI Training offer courses that deepen understanding of AI’s impact on society and education.
| 2025-07-06T00:00:00 |
2025/07/06
|
https://completeaitraining.com/news/why-personal-growth-must-replace-productivity-in-the-age-of/
|
[
{
"date": "2023/03/01",
"position": 40,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 38,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 39,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 31,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 42,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 37,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 39,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 48,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 38,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 39,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 42,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 40,
"query": "universal basic income AI"
}
] |
AI: UBI Income Portfolio Adjustment to Technological Transformation
|
AI: UBI Income Portfolio Adjustment to Technological Transformation
|
https://www.frontiersin.org
|
[
"Przegalinska",
"Alexandra K.",
"Department Of Management In Digital Societies",
"Kozminski University",
"Wright",
"Robert E.",
"American Institute For Economic Research",
"United States"
] |
Positive and normative claims that artificial intelligence (AI) will or should lead to adoption of a universal basic income policy (UBI) remain insufficiently ...
|
Positive and normative claims that artificial intelligence (AI) will or should lead to adoption of a universal basic income policy (UBI) remain insufficiently empirically grounded to merit serious consideration. Long-term trends in individual/familial income portfolio adjustment (IPA) to business, economic, and technological change (BETC) point to continued incremental changes in the ways that individuals/families achieve life goals, not a fundamental structural break necessitating radical policy changes that may not be desirable in any event. Moreover, if AI proves a more rapid disruptor than anticipated, UBI-like payments can be made quickly, as recent bailouts and fiscal stimuli demonstrate.
Introduction
Business, economic, and technological change (BETC) occurs continuously but at variable speed (Lauterbach, 1977; Bakker et al., 2019). While the cumulative effects of periods of relatively rapid BETC, often termed “Revolutions” [e.g., Agricultural (Olmstead and Rhode, 2008), Communication (Albion, 1932), Financial (Sylla, 2002), Industrial/Industrious (De Vries, 1994), Institutional (Allen, 2011), Market (Majewski, 1997), Transportation (Seely, 2007)], have been substantial (Makridakis, 2017), they always occur over several years or decades. Waves of automation in the 20th century also caused substantial fears of job loss that never occurred (Terborgh, 1966).
The pace of change can be fast enough to create angst and to stir predictions of dire results that induce specific interest groups to take direct actions designed to slow the pace of BETC for their own benefit, as Luddites (who destroyed installed machines in Britain between 1811 and 1817) and unions (who destroy machines before they are produced by means of union contracts protecting jobs) did (Donnelly, 1986). Nevertheless, changes in individual/familial life strategies consistently proved more effective than interest group action because they occur more quickly than even the fastest revolutions, adapting to inevitable BETC rather than trying to stop or dramatically slow it [see, e.g., (Hopkins, 1982; Goolsbee, 2018)].
Individuals/families aspire to achieve goals that can be understood as a tradeoff between real (inflation-adjusted) consumption and leisure, i.e., about how long and hard to work. Those goals adapt to BETC and life cycle events (Dunn, 1979; Childers, 2011). Rational individuals [as defined by (Arrow, 2012)] form and frequently update expectations about strategies most likely to achieve their life goals (MacDonald and Peel, 1983). In essence, that means adjusting a portfolio of sources of real income (IPA), which stems from the five distinct1 sources described in Table 1 below:
TABLE 1
TABLE 1. The five major components of individual/familial income portfolios.
Proponents of AI = UBI concentrate on income sources four and five without giving sufficient consideration to income sources one, two, and three. If AI causes employment to decrease, they reason, UBI [“periodic cash payment unconditionally delivered to all on an individual basis, without means-test or work requirement” (Haagh, 2019)] will be needed to meet the real income goals of unemployed/unemployable individuals. That reasoning, however, does not fully reflect reality for five reasons:
1. AI is not yet as powerful as many believe and hence is not as big a threat to employment as often claimed. In fact, as a general purpose assistive technology (GPT) it generates new jobs and reskills existing ones.
2. The net number of jobs continues to increase. Jobs that “disappear” do so because of the complex processes associated with BETC, not because of AI, the Internet of Things (iot), or edge computing.
3. If employment decreases in the future (due to AI and/or other causes), individuals may prefer to respond via IPA, by increasing the importance of subsistence, proprietorship, and financial investment in their income portfolios over acceptance of unilateral transfers.
4. If individuals prefer unilateral transfers, options other than UBI abound and may prove preferable from the standpoint of both public policy and individuals’ life goals.
5. If at some point employment decreases dramatically and individuals prefer UBI, it can be implemented quickly at that time.
Each of the points 1 through 5 above are explained in fuller detail in the explained in fuller detail below.
Artificial Intelligence Today
Artificial Intelligence is a general purpose technology (GPT), a label used to describe technologies, like the steam engine, electrification, and the Internet, that cause significant and widespread impacts on society and the workplace. GPTs may also generate numerous more specialized complementary innovations and technologies.
Current BETC, including the widespread application of AI, will impact how people live and work. The cumulative scope of AI-induced change must remain unknown, leading to alarmist dystopian visions of a future without human work despite the fact that the annual rate of change has shown no signs of unusual rapidity. AI today cannot supplant human workers; it can only increase their productivity by decreasing the gap between workers and technological enhancement.
Automation certainly changes the nature of work but AI’s impact on the future of work remains unclear. Some researchers [e.g., (Acemoglu and Restrepo, 2017)] connect the adoption of AI and robots to reduced employment and wages, suggesting the need for UBI adoption. Others claim that it will become easy to automate millions of jobs worldwide in a short period of time and significantly more jobs will disappear than will be created (Crawford et al., 2016; Goolsbee, 2018; Furman and Seamans, 2019). Some business consultants concur but others predict the contrary. According to studies conducted by McKinsey, PricewaterhouseCoopers and Skynet Today, AI will displace about one-third of the existing jobs worldwide within a decade, with the United States (up to 40%) and Japan (50%) among the hardest hit. According to the OECD AI Policy Observatory and Beyond Limits Study, AI will create more jobs than it destroys. Companies pioneering the development and scaling of AI have thus far not destroyed jobs on net. There are no indications that trend will not continue for the foreseeable future.
Working Together With AI
Threats to jobs posed by AI and similar technologies can be assessed by examining core skill sets, i.e., by distinguishing between durable jobs, those that will require reskilling, and those that will become obsolete (Latham and Humberd, 2018). Some jobs that were durable during previous periods of BETC will remain durable in the foreseeable future, as will others, at least in the short- and medium-term perspective. Some workers will need significant reskilling but for others reskilling will be relatively minor.
Sources:https://www.bls.gov/ooh/fastest-growing.htm; https://www.bls.gov/news.release/ecopro.nr0.htm; https://www.bls.gov/emp/tables/fastest-declining-occupations.htm
Currently, we can observe two parallel discourses regarding the future of work: 1) automation of work leading to the replacement of humans, and 2) cobotization, focusing on close collaboration with various assistive technologies in general, and AI in particular.2
As Autor (2015) notices, machines both substitute and complement human labor. Substituting for workers in routine tasks also amplifies the comparative advantage of workers in various problem-solving skills. Focusing on lost jobs, in other words, misses the fact that technology simultaneously increases “the value of the tasks that workers uniquely supply.” Automation has already affected mostly routine and low-skilled tasks. For instance, the initial wave of industrial robots primarily affected manufacturing processes. AI’s problem solving, reasoning, and perception capabilities mean that it can perform some non-routine cognitive tasks, like summarizing computer science research papers. Recent evidence shows that companies are already achieving productivity gains by using software robots to perform routine, rules-based service processes. If implemented well, such automation can result in high-performing human-robot teams, in which software robots and human employees complement one another. In some cases automation does substitute for labor (Autor and Salomons, 2018) but it also complements labor in many ways, raising output sufficiently to create higher demand for labor, and interacts with adjustments in labor supply, say by increasing familial income enough to induce a spouse to leave the labor force.
Moreover, artificial intelligence and automated tools will usually replace tasks rather than jobs. A key insight is that a job can be viewed as a bundle of tasks, some of which offer better applications for technology than others (Autor et al., 2000). Thus, particularly in the short term, researchers should think in terms of task replacement rather than unemployment. Some high-skilled professionals such as engineers, radiologists, or lawyers are at risk because most of the tasks they perform can be done by AI. Such highly educated professionals, however, may also be capable of applying AI in a way that complements their work.
Future Artificial Intelligence
Major developments in AI, deep learning, natural language understanding, and machine vision led to new collaboration-oriented systems (Haenlein and Kaplan, 2019). Initially, AI systems such as AlphaStar, AlphaGo or muZero (Wang et al., 2016; Vinyals et al., 2019; Schrittwieser et al., 2020; Shaikh, 2020) were created to prove that AI can compete with humans and actually beat them in complex games. Professional players, however, adapted rather than conceding defeat; their competition with AI led to significant performance improvement (Waters, 2018).
In the short- and medium-term, AI development will take two discrete paths. The first extrapolates what AI is today, highly specialized, deep learning algorithms applicable to clearly delineated problems in more complex, context aware, and nuanced ways. Because of their capacity to learn highly nonlinear functions with near-automatic input space transformations, deep neural nets (DNNs) are currently the algorithms with very high economic potential at the frontier of task automation. DNN software can be extended to new domains formerly closed to digitization through transfer learning (Torrey and Shavlik, 2010; Weiss et al., 2016).
The second path entails the creation of AI systems capable of processing information in a manner similar to the human brain. Today, deep nets rule AI in part because of an algorithm called backpropagation (Hecht-Nielsen, 1992; Lillicrap et al., 2020) that allows deep neural nets to learn from data and thus gain capabilities like language translation, speech recognition, and image classification. Real brains, however, likely do not rely on similar algorithms. Human brains are capable of abstract reasoning and learn more efficiently than current AI systems can (LeCun et al., 2015). Geoffrey E. Hinton, Yoshua Bengio and many other experts have been thinking about more biologically plausible learning mechanisms that might at least match the success of backpropagation and expand AI’s capacity to learn and adapt. Currently, feedback alignment, equilibrium propagation, and predictive coding seem particularly promising.3
The second path of biologically inspired AI development has a high potential of transforming AI’s capabilities and overcoming its current limitations, creating more robust and complex systems capable of more abstract levels of reasoning. It, however, remains nascent and hence many years away, as does Singularity (McAfee and Brynjolfsson, 2016; Tegmark, 2017; McAfee and Brynjolfsson, 2017).
The first path may develop without the second, or alongside it. It will not affect the number of jobs per se, but rather, like earlier BETC “revolutions,” it will produce a profoundly different economy. Large-scale technologies, like the Internet, the power grid, and roads and highways, will in the future rely on AI, as both solution complexity and demand continue to increase.
Long-Term Employment Trends shows that there are no indications at present that AI, or any other BETC, poses a threat to employment in the US or other rich nations, so long as human capital, from training programmes to formal education, adapts, as it always has (Goldin and Katz 2009).
Long-Term Employment Trends
Real (inflation-adjusted) per capita income has trended steadily upward in much of Europe, Anglo-America, and the Far East for the last several centuries, subject only to the booms and busts associated with wars, the business cycle, and technological breakthroughs. Nations like Spain that lagged due to institutional deficiencies experienced rapid growth once growth-inducing institutions were created but the overall trend is one of steady, though not monotonic, growth (Acemoglu and Robinson, 2012).
Note the use of a log scale in the following charts of US, UK, and Spanish real per capita income, which is standard procedure when presenting long-term time series data of this nature so that year-over-year changes and long-term trends become visually evident. The Great Depression and World War II caused the big dip and subsequent fast growth evident especially in the data for the US and Spain, which also experienced a devastating civil war in the 1930s. Note, though, how real per capita growth returned to the long-term trend line in the postwar period in both the US and UK and that institutional improvement, not technological change, drove Spanish income convergence.
Sources: Louis Johnston and Samuel H. Williamson, “What Was the U.S. GDP Then?” MeasuringWorth, 2021. URL: http://www.measuringworth.org/usgdp/; Ryland Thomas and Samuel H. Williamson, “What Was the Consistent U.K. GDP Then?” MeasuringWorth 2021. URL: http://www.measuringworth.com/ukgdp/; Leandro Prados-de-la-Escosura, “What Was Spain’s GDP Then?” MeasuringWorth, 2021. URL: http://www.measuringworth.org/spaingdp/.
Sustained increases in real per capita incomes stem only from productivity improvements, i.e., creating more output from the same input, which is the point of BETC. Supply and demand conditions in labor and capital markets, along with public policies regarding taxation, unionization, and so forth, determine how the additional income comes to be distributed among employees, proprietors, financial investors (through their ownership of corporate securities), and governments.
Private nonfarm business sector labor productivity in the United States has been climbing without interruption, though at variable rates of increase, for at least the last 3 decades and with minor reversals since at least World War II. Similar metrics show similar trends for OECD (Productivity, 2021) and EU countries (Baily et al., 2020).
Source: Federal Reserve Economic Data, “Private Non-Farm Business Sector: Labor Productivity, Index 2012=100, Annual, Not Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/graph/?id=MPU4910062.
Nominal and real wage data suggest that labor productivity has been trending upwards for over two centuries. The average nominal wage of manufacturing workers in the United States increased from two cents per hour in 1790 to $32.36 in 2019 (Measuring Worth–Annual Wages in the United States, n. d.). Real total compensation per hour for those same worker cycles sometimes stagnates for several years to a decade but also trends upward over the long term:
Source: Federal Reserve Economic Data, “Manufacturing Sector: Real Compensation Per Hour, Index 2012=100, Quarterly, Seasonally Adjusted” FRED, 2021. https://fred.stlouisfed.org/series/COMPRNFB.
Long-term workers responded to higher real compensation by working fewer hours. In the early 19th century, for example, female textile workers in Lowell, Massachusetts worked on average 12 h per day, 300 days of the year (Little, 2001). Although some professionals (attorneys, investment bankers, physicians, professors) continue to work 60–100 h per week up to 50 weeks per year, most factory and office workers now work 40 or fewer hours per week, and must receive a higher rate of compensation to induce additional hours of work.
Some claim that real compensation has stagnated or declined in the United States over the last few decades [see, e.g., (Wage Stagnation in Nine Charts, 2021)] but only by conflating wages with total compensation. The latter includes benefits, including healthcare costs covered by employers and employer contributions to private retirement accounts. Rising healthcare costs due to America’s inefficient, employment-based healthcare system have caused the divergence between wages and total compensation (Flynn, 2019). The magnitude of the problem is revealed by that fact that half of the unilateral transfers made by the US federal government to the poor cover healthcare costs (Feldstein, 2016).
Source: Federal Reserve Economic Data, “Nonfarm Business Sector: Real Compensation Per Hour, Index 2012100, Quarterly, Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/series/COMPRNFB.
As others have noted [e.g., (D. H. Autor, 2015)], total jobs (employees) has trended steadily upwards in the United States since at least 1939, subject only to cyclical downturns or, at the extreme right of the graph, exogenous shocks like pandemics and the “lockdown” policies implemented in response (The Effect of Lockdown Measures on Unemployment, 2021).
Source: Federal Reserve Economic Data, “All Employees, Total Nonfarm, Thousands of Persons, Monthly, Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/series/PAYEMS.
For the last 20 years, between two and eight million jobs have gone unfilled in the United States each year due to mismatches between worker skills and job functions but also discrepancies between worker wage demands and what employers are willing to pay to fill open positions.
Source: Federal Reserve Economic Data, “Total Unfilled Job Vacancies for the United States, Persons, Monthly, Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/series/LMJVTTUVUSM647S.
The Labor Force Participation Rate (LFP), the total percentage of the working age population employed, has trended downward since its recent highs in the late 1990s but even at its current nadir due to Covid lockdowns remained above its lows in the 1950s. The economic interpretation of the LFP is difficult because increases or decreases are not unequivocally good or bad. In poorer countries today, and in the early histories of the US, UK, and other core rich nations, the LFP was over 100 percent by today’s definition of the labor force. Children as young as four worked, as did people now considered differently abled (blind, deaf, immobile, insane) or superannuated (too old to work). Similarly, the relatively low LFP in the 1950s and 1960s stemmed from America’s relative economic strength and cultural mores. Many women remained out of the labor force because families could meet their life goals without them taking jobs (Monthly Labor Review 2002). A low LFP due to a high percentage of people who want a job but cannot find one, by contrast, could signal economic trouble, like the big drop in the LFP during the 2020 pandemic and subsequent lockdowns (Bullard, 2014). But secular declines in LFP like that which started circa 2000 might simply signal preferences for the other four income sources (Juhn and Potter, 2006).
Source: Federal Reserve Economic Data, “Labor Force Participation Rate, Percent, Monthly, Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/series/CIVPART.
Cost-Benefit Analysis of IPA describes how individuals (and families) try to meet their life goals by splitting their work time into subsistence activities, proprietorship, investment in financial assets, employment, and the receipt of unilateral transfers based on the relative costs and benefits of each income source.
Cost-Benefit Analysis of IPA
Simply because someone remains outside of the official labor force does not mean that they do not work. In 1950s America, for example, many married women engaged in subsistence activities in lieu of paid employment. Many in rural and suburban areas gardened and did their own washing, sewing, and so forth instead of buying vegetables and laundry services in the market. Like other rational actors, they compared the expected costs and benefits of each the five main sources of income and chose the ones with the largest net benefits:
The flow chart above is more formally stated in Equation 1 below. [For more complex modelling of a portfolio of income streams with uncertain returns, see (Brennan, 1973).]
∑ n = 1 5 w n i n ( 1 )
Where:
n = income source counter
w = weight of each income source
i = income source.
Historical examples of such reasoning abound. In 1848, for example, Abraham Lincoln suggested that his stepbrother, John D. Johnston, should ease out of subsistence-only farming by growing some cash crops (proprietorship) and by going “to work for the best money wages… you can get” (employment), with the ultimate goal of buying bank and railroad shares (financial investment) (Guelzo, 2000). Similarly, trappers sometimes made their own clothes from the furs of the animals they trapped, a subsistence activity. Sometimes they sold the furs to furriers, making them proprietors. Other times they worked for a fur company for a salary, rendering them employees. Sometimes they purchased shares in fur companies, making them financial investors. Often, the same person engaged in all those activities serially, and sometimes even simultaneously, to adjust to BETC (Wright, 2019).
The major costs and benefits of each of the five main sources of income are described below. The costs and benefits vary in intensity over time and place, thereby inducing IPA (Rose, 2017; Mason, 2020). The existence of AI of course in no way limits the ability of human beings to engage in subsistence activities, proprietorship, financial investment, or to receive unilateral transfers. It may, however, enhance their ability to engage in such activities. AI is already used to reduce the costs of frightening deer away from gardens and of finding government grants, franchise opportunities, and financial investments (Biswal, 2020). What it takes from employment, in other words, it may very well return to other sources of income.
Subsistence
Subsistence activities occur when an individual, family, or other social unit makes a good that s/he or they personally consume (Elwert and Wong, 1980). For most of human history, subsistence activities like hunting and gathering, complemented by trade (proprietorship), constituted the main source of consumption and may come to dominate once again in the face of climatic or other shocks (Gowdy, 2020).
A major benefit of subsistence activity is control over the quantity and quality of consumption goods free from exogenous market shocks (Chibnik, 1978). During the Great Depression, for example, many people who had grown accustomed to buying poultry (chicken, ducks, rabbits, turkeys) at market began to raise them for home consumption (Cook, 1998); hunting, fishing, and trapping increased in popularity (Wright, 2021b).
Subsistence activities, however, are subject to non-market shocks, like droughts or insect infestations (Gowdy, 2020). Another major cost of subsistence activities is the loss of gains from trade, specialization/division of labor, and scale economies (Kennedy, 1982). While raising chickens in the backyard ensures access to eggs (barring a visit from a hungry fox or other non-market shock), for example, the opportunity cost per egg may be too high compared to the monetary cost of eggs produced at commercial scale. So in 1900, an estimated 25 percent of U.S. households produced their own eggs, compared with 1.6 percent today (Kidd and Anderson, 2019).
Proprietorship
Much early proprietorship emerged from individuals or families scaling up subsistence activities and selling their surpluses into markets. That added to the risk of exogenous market and non-market shocks but came with the benefit of some cash income in addition to the imputed income of the products produced on, and consumed by, the farmstead (Johnson, 1998).
Generally, proprietors enjoy more control over the terms of their work than employees do, including the number of hours worked and its intensity (Burke et al., 2008). Most non-farm proprietors do not consume the products of their labor themselves, but they do own their own businesses and hence earn or lose wealth along with the fortunes of the business and the market prices of its assets (and liabilities) (Hamilton, 2000).
For those reasons, proprietorship was long the main goal of most people, especially in the United States (Wright, 2015; Wright, 2017b). Tax (Nelson, 2008) and regulatory changes influenced its relative attractiveness over time and space (Goetz and Rupasingha, 2009). Self-employment, which constitutes a major type of proprietorship, has made several large swings since World War II but note that the overall trend, as a percentage of all workers, is down.
Source: Federal Reserve Economic Data, “Employment Level - All Industries Self-Employed, Unincorporated, Thousands of Persons, Monthly, Seasonally Adjusted” FRED, 2021. URL: https://fred.stlouisfed.org/series/LNS12027714.
Financial Investment
Financial investors may engage in research to discern relatively inexpensive from relatively expensive financial assets and to forecast which asset classes are most likely to increase in value (bonds, derivatives, equities, insurance-linked securities, REITs, etc.) (Constable and Wright, 2011). It remains unclear, however, if such investors net of those research and forecasting costs actually earn higher risk-adjusted returns than investors who simply purchase diverse portfolios of financial assets (Malkiel, 2013). All investors are subject to the security market line, or the tradeoff between risk and return. In other words, financial investors can earn a low return with little risk of losing principal, or a high return with a commensurately high risk of losing principal, or anywhere in between (Modigliani and Pogue, 1974). One important benefit of financial investment is that it can consume very little time while generating market returns (Wermers, 2000), freeing individuals and families to engage in the other four main sources of income and/or leisure activities.
Employment
Employment means being paid for one’s time, be it for each hour worked (hourly wage) or for a variable number of hours worked over a fixed amount of calendar time (salary). It may be augmented with performance bonuses or commissions. It can be regular or irregular but generally only regular employment is called a “job,” which might be “fulltime” or “parttime” depending on the length of the time commitment each week (Asia, 1945). Employment may take place in facilities provided by the employer, in the employee’s home, and/or elsewhere and the location of work has shown significant and interesting variation over time suggesting that it often constitutes a major cost-benefit variable affecting the relative attractiveness of employment to both employers and employees (Juhász et al., 2020).
Employees give up part of their freedom in exchange for the wage or salary. By definition, employees are subject to the direction of their employers during working hours, including, but not limited to, the pace of their work, the time they may use the toilet, acceptable political speech, and whether or not they may wear a mask (NPR 2010; Anderson 2017). In fact, employment was considered akin to slavery in the United States in the 19th century (Wright, 2017a). Accepting a job was something people did when they could not meet their life goals via any combination of the other main sources of income (Steinfeld, 2001). Over time, however, an increasing percentage of the population moved from proprietorship (farming, shopkeeping) to employment as their major source of income as jobs became relatively less onerous and proprietorship relatively moreso (Gallman and Rhode, 2020). In addition, many small proprietors found that they could no longer compete against larger enterprises leveraging economies of scale in traditional proprietary sectors like farming and retailing (Boyd, 1997; Bennett et al., 2020).
Unilateral Transfers
One might think that everyone would always have a strong preference for receiving unilateral transfers because it appears to be all benefit and no cost. In fact, acquiring and maintaining transfers can be difficult and time-consuming (Mould, 2020). In addition, most people have a strong aversion to receiving unilateral transfers (Parsell and Clarke, 2020). They know that they are taking resources from other people, sometimes voluntarily given but increasingly involuntarily through taxation, and feel infantilized as a result (Misra et al., 2014). Even aid received after natural disasters carries a stigma (Fothergill, 2003; Stuber and Kronebusch, 2004).
Unilateral transfers follow the security market line in the sense that the larger they are, the more likely they are to be curtailed or even eliminated (Albert, 2000) for fear that they create dependence (Gottschalk and Moffitt, 1994). Many unilateral transfer recipients also fear that they may grow dependent on the transfers and hence beholden to the person, organization, or government providing the resources (Rank, 1994). A tailored approach to unilateral transfers may therefore better help people to achieve their life goals than a general policy, like UBI.
Tabular Summary of the Major Costs and Benefits of the Five Sources of Income
Cost-Benefit Analysis of UBI and Other Unilateral Transfer Policies categorizes the major types of unilateral transfers and describes the strengths and weaknesses of each in order to demonstrate that if unilateral transfers become a more important part of IPA in the future, transfers other than UBI may be preferred by policymakers and recipients.
Cost-Benefit Analysis of UBI and Other Unilateral Transfer Policies
Calls for a UBI policy date back to at least Thomas Paine, who in Agrarian Justice (1797) argued that governments should compensate all citizens at adulthood because they had allowed private individuals to control all of Europe’s land and hence constrained the ability of the landless to engage in subsistence or proprietary activities, effectively forcing them to rely on uncertain employment markets (Wright, 2021a).
Friedrich Hayek (Rallo, 2019) and Milton Friedman (Milton Friedman on Freedom and the Negative Income Tax) also discussed, without embracing, the need for UBI-like policies as a more efficient means of taking care of society’s poorest members by reducing the emotional costs and risks associated with certain types of unilateral transfers described in Tabular Summary of the Major Costs and Benefits of the Five Sources of Income (Bidadanure, 2019). The current US “welfare state” is extremely complex [see (Chaudry et al., 2016)], so switching to a single simple program promises significant administrative savings.
Numerous progressive pundits have discussed the pros and cons of a UBI (Allegri and Foschi, 2021). Rivers (2019) rejects it because he believes it would “calcify poverty and class structure … even more than the present arrangements.” Nobel laureate Paul Krugman rejects UBI in favor of more targeted approaches (Malter and Sprague, 2019). After waffling on the subject in his book on income inequality (Stiglitz, 2013), Nobel laureate Joseph Stiglitz soon came out in favor of UBI, presumably because it reduces the stigma associated with receiving unilateral transfers and the costs of qualifying for assistance (Widerquist, 2015).
Targeted UBI experiments in developing countries have been implemented on small and non-representative samples, rendering their results difficult to scientifically assess (Banerjee et al., 2019). Moreover, according to most recent studies (Stadelmann-Steffen and Dermont, 2020) the data collected through European Social Survey data in 21 countries indicated no association between risk of job automation and support for UBI. So-called Participation Income schemes that pay people for “participating” in civil society (voting, serving on juries, and such) do not solve the inherent problems with UBI while adding substantial administrative costs (Wispelaere and Stirton, 2007).
UBI’s biggest strength is also its major weakness. While paying everyone the same sum may reduce the stigma associated with receipt of unilateral transfers (Williamson, 1974) and also seems to protect it from the political risk of reduction or elimination, its very universality renders it fiscally impossible (Lee and Lee, 2021). Obviously, low income people will gain from a UBI on net but UBI will only reduce the tax burden of high income people, and necessarily by less than their taxes will have to increase to make the net unilateral transfer to the poor possible. In short, despite its superficial universality, UBI represents shallow accounting legerdemain. Ergo, like China’s dibao (Chen and Yang, 2016), it might create as much stigma (Handler and Hollingsworth, 1969), and shame (Parsell and Clarke, 2020) and other negative emotions (Goodban, 1985) in, net recipients as other types of unilateral transfers are known to induce. It might also create as much resentment in net donors (Marchevsky and Theoharis, 2000; Reese, 2005).
UBI implementation could also potentially threaten democratic traditions, especially if the number of net recipients (those whose UBI payments are greater than their taxes) ever exceeds fifty percent of the electorate, because they could use their majority power at the ballot box to demand increases (Nelson, 2018). Even if UBI began at a modest level, unless net UBI recipients lost the power to vote, or UBI faced a hard cap impervious to popular pressure, it could easily balloon to levels that could foment a crisis, especially in countries, like the US, already facing severe fiscal difficulties (US Government Accountability Office, 2021).
In addition, UBI will not ensure the end of poverty because nothing will prevent net recipients from consuming more instead of saving for future exigencies (Goolsbee, 2018). Moreover, if net recipients can borrow against future UBI payments, some may consume their future UBI payments today, rendering them in need of aid in the future (Fleischer and Hemel, 2020). If not allowed to borrow, however, net UBI recipients will find it more difficult to invest using leverage or to begin their own businesses. If employment has decreased or disappeared, subsistence will be the only practical income option available if UBI payments are insufficient to meet their life goals. Society therefore may remain filled with people who are non-poor in absolute terms but still at the bottom of the income distribution and hence unsatisfied with their lives and structurally prevented from improving their lot, or their income ranking (Boyce et al., 2010).
None of this is to argue, of course, that unilateral transfers have no place in IPA, just that other types of unilateral transfers, especially more targeted ones that provide greater benefits to the poorest individuals/families (Goolsbee, 2018), may be preferable to policymakers, donors, and recipients. Generally speaking, outcomes improve when individuals get to decide what best suits their needs than to have policies, even popular ones, forced upon them from above (Reamer, 1983; Banerjee, 2008).
Private Charity
Private charity has a long history in the United States, dating back to its colonial period (Olasky, 1994). The number and diversity of nonprofit organizations supported by voluntary contributions of money, goods, and labor that helped others astounded early foreign visitors like Alexis de Tocqueville and Gustave de Beaumont (Noll, 2014). Cash loans or grants, clothes, education, food, fuel, healthcare, and lodgings flowed to the poor in sizable quantities that fluctuated with economic conditions. Some of the aid was “outdoor,” given to individuals and families who lived in private residences. Some aid was “indoor,” requiring residence in an “asylum” for the poor, blind, deaf, orphaned, or insane (Katz, 1984).
Often, charitable giving was done without direct aid from the government, or with only modest and intermittent donations of land or other resources. Starting with the Great Depression and New Deal, however, government began playing an increasingly large role in unilateral transfers, some made via private charities but increasingly directly from government employees (Morris, 2009).
Governments presumably provided aid on an easier and fairer basis because government workers were not supposed to try to morally reform the poor the way that many private charities, even secular ones, often did. On the other hand, voluntary donations were more stable than political support for government unilateral transfer because donors felt they had more control over the disbursement of their funds, which were often directed at very specific groups thought most charity-worthy, like orphans or “lunatics” (Rothman, 2017), and away from abusers of drink or drugs (Carlson, 1998; Belletto, 2005), or shirkers (Charness and Rabin, 2002).
Government Vouchers
Major US government voucher programs include Supplemental Nutrition Assistance Program (SNAP), informally still referred to as “Food Stamps” for the form that the vouchers used to take.
Inflation-adjusted SNAP expenditures per recipient have more than doubled since 1970.
Source: USA Facts, “Nutrition assistance (SNAP) average monthly benefit per person,” USAFacts.org, 2021. URL: https://usafacts.org/data/topics/people-society/poverty/poverty-programs/nutrition-assistance-snap-avg-monthly-benefit-per-person/?adjustment=Inflation.
SNAP has grown because it allows low income individuals to purchase foods relatively innocuously, through a government-provided debit card that creates less stigma than the older, more conspicuous stamp-like technology did.
In addition, the illegal secondary market for stamps reduced support for the program when the public learned that recipients could sell their stamps for cash that could then be used to purchase drugs. Although food purchased with SNAP can be resold for cash or bartered for drugs, the transaction costs are significantly higher than under the older technology so taxpayers feel more confident that their taxes are not being misused.
Government Cash
Governments also make outright grants of cash to low income individuals/families. The major federal cash grant program, Temporary Assistance for Needy Families (TANF), supplanted the older Assistance for Families with Dependent Children (AFDC) program, which was criticized for incentivizing people to become dependent on “welfare” payments. Because TANF is distributed through states, payments vary across the nation, with some states paying a much higher percentage of the putative “poverty line” than others. Taxpayers still fear creating a permanent “welfare” class if payments are too generous and do not want their money spent on illicit drugs or luxury goods that they might not feel they can afford themselves.
Note: TANF = Temporary Assistance for Needy Families. The Federal poverty level for a family of three in 2020 is $1,810 per month in the 48 contiguous states and Washington D.C.; Alaska and Hawaii have higher poverty thresholds.
Source: Center on Budget and Policy Priorities, “TANF Benefits Still Too Low to Help Families, Especially Black Families, Avoid Increased Hardship,” CBPP, 2016. URL: https://www.cbpp.org/research/family-income-support/tanf-benefits-still-too-low-to-help-families-especially-black
As a result, inflation-adjusted TANF payments have decreased in all but three states since 1996, and have declined by more than 30 percent in half of all US states.
Government Provision
Governments also sometimes directly provide goods for the use or consumption of the poor, either gifting it to them, as in the case of expired surplus foodstuffs, or leasing it to them at a below market rate, as in the case of government housing. In such cases, there is little concern that the poor will use the resources for untoward purposes.
Government provision, however, is often expensive for taxpayers because governments are not very efficient producers. Federal housing projects, for example, were notoriously ugly, shoddy, and expensive (Allen Hays, 2012) and created significant negative externalities for the neighborhoods in which they were located (Levy et al., 2013). Similarly, the US government did not make “government” cheese directly but rather contracted for its production as part of an expensive dairy price support program (Heien, 1977).
Tabular Summary of the Major Costs and Benefits of Different Types of Unilateral Transfers
The major costs and benefits of the major types of unilateral transfers are summarized in the table below:
Even if AI or other BETC eventually destroy jobs faster than people can engage in IPA, and policymakers and recipients believe that government cash grants are the best type of unilateral transfer to implement in response, initiating UBI now is not indicated because, as the next section explains, it can be implemented quickly if ever needed.
Limitations
This paper extrapolates centuries-long trends into the near future because, as shown in Artificial Intelligence Today and Long-Term Employment Trends, AI thus far is simply another in a long line of new technology. It has not palpably affected job, productivity, or output trends. Moreover, as shown in Cost-Benefit Analysis of IPA and Cost-Benefit Analysis of UBI and Other Unilateral Transfer Policies, individuals and families have long engaged in IPA and nothing inherent in AI changes their ability to do so.
That said, a transformative AI breakthrough capable of accelerating BETC faster than individuals and families can adapt remains possible. If that occurs, rich nations can implement UBI as quickly as government stimulus checks and corporate bailouts were distributed during the global financial crisis and pandemics of 2008 and 2020, i.e., within a few hours to weeks depending on the mechanisms employed and policy intent (Sahm et al., 2012; Wright, 2010). (The Fiscal Response to COVID-19 in Europe: Will It Be Enough?, 2021)
In short, implementing UBI now because of what AI might do to jobs in the future is not rational policy (Hoynes and Rothstein 2019; Commentary: Universal Basic Income Ma...; Would a universal basic income reduce...).
Conclusion
Claims that AI will, or should, lead to UBI display too little detailed knowledge of the limitations of AI (Artificial Intelligence Today), the nature of BETC (Long-Term Employment Trends), the adaptive solutions offered to individuals by IPA (Cost-Benefit Analysis of IPA), and alternative unilateral transfer policies (Cost-Benefit Analysis of UBI and Other Unilateral Transfer Policies) to warrant high confidence, especially given that UBI could be adopted almost instantaneously if ever needed (Limitations).
Specifically, AI is not nearly as powerful as widely believed and is unlikely to supplant humans in the foreseeable future. Jobs are not disappearing but even if they eventually do, individuals will have time to increase the parts of their real income/consumption that stem from subsistence, proprietorship, and financial investment. Even if individuals do desire to increase unilateral transfers as a percentage of their income portfolios, they may, in conjunction with policymakers, prefer other types of transfers over UBI, which suffers from several conceptual problems. Finally, in the unlikely scenario that AI ever proves rapidly destructive, rich countries can adopt immediate fiscal measures simulating a UBI.
Data Availability Statement
Publicly available datasets were analyzed in this study. This data can be found here: https://www.census.gov and https://fred.stlouisfed.org/.
Author Contributions
All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication.
Conflict of Interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s Note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
Footnotes
1Careful analysis may be needed to correctly differentiate between the five major sources of income, the legal definitions of which sometimes do not match underlying economic realities. A landlord is a proprietor whereas the owner of a real estate investment trust (REIT) is a financial investor. Similarly, a worker with a regular schedule paid a salary or a fixed wage based on time is an employee, but a worker paid solely by the task or contract fulfillment is an independent contractor, a form of proprietorship. Someone who grows her own tomatoes to eat engages in subsistence but when she sells her tomatoes she becomes a proprietor. An employee may simultaneously be a financial investor via an employee stock ownership plan (ESOP) (Pierce et al., 1991). A person with a disability who receives a stream of income may be the recipient of a unilateral transfer (for example, charity, or a publicly subsidized government disability program) and/or may be a financial investor in a disability insurance policy (Liebman, 2015). Differentiating between income sources, however, is more an intellectual exercise for purposes of analysis and exposition than a determinant of real world outcomes because most individuals, past, present, and future, engage in IPA, i.e., flexible income portfolios that vary with their life goals (Green, 2021) and over their life cycles (Browning and Crossley, 2001).
2Automation of work that includes 1) fixed automation, 2) programmable automation, and 3) flexible automation. It can be caused by robots or RPA software in addition to AI. https://www.britannica.com/technology/automation/Manufacturing-applications-of-automation-and-robotics
3Take, for example, one of the strangest solutions to the weight transport problem, courtesy of Timothy Lillicrap of Google DeepMind in London and his colleagues in 2016. The algorithm developed by Lilicrap and his team, instead of relying on a matrix of weights recorded from the forward pass, used a matrix initialized with random values for the backward pass. Once assigned, these values do not change, therefore no weights need to be transported for the backward passes. The network turned out to learn very efficiently (Singh et al., 2019).
References
Acemoglu, D., and Robinson, J. A. (2012). Why Nations Fail: The Origins of Power, Prosperity, and Poverty. New York: Crown Publishers.
Allegri, G., and Foschi, R. (2021). Universal Basic Income as a Promoter of Real Freedom in a Digital Future. World Futures 77 (1), 1–22. doi:10.1080/02604027.2020.1792600 CrossRef Full Text | Google Scholar
Allen, D. W. (2011). The Institutional Revolution: Measurement and the Economic Emergence of the Modern World. Albany, NY: University of Chicago Press.
Allen Hays, R. (2012). The Federal Government and Urban Housing. Third Edition. SUNY Press.
Arrow, K. J. (2012). Social Choice and Individual Values. Third Edition. Yale University Press.
Autor, D. H. (2015). Why Are There Still So Many Jobs? the History and Future of Workplace Automation. J. Econ. Perspect. 29 (3), 3–30. doi:10.1257/jep.29.3.3 CrossRef Full Text | Google Scholar
Autor, D., Levy, F., and Murnane, R. (2000). Upstairs, Downstairs: Computer-Skill Complementarity and Computer-Labor Substitution on Two Floors of a Large Bank. doi:10.3386/w7890 CrossRef Full Text
Autor, D., and Salomons, A. (2018). Is Automation Labor-Displacing? Productivity Growth, Employment, and the Labor Share (No. W24871). Cambridge MA: National Bureau of Economic Research. doi:10.3386/w24871 CrossRef Full Text
Baily, M. N., Bosworth, B., and Doshi, S. (2020). Productivity Comparisons: Lessons from Japan, the United States, and Germany. Washington, DC: Brookings Institution. Available at: https://www.brookings.edu/wp-content/uploads/2020/01/ES-1.30.20-BailyBosworthDoshi.pdf.
Bakker, G., Crafts, N., and Woltjer, P. (2019). The Sources of Growth in a Technologically Progressive Economy: The United States, 1899-1941. Econ. J. 129 (622), 2267–2294. doi:10.1093/ej/uez002 CrossRef Full Text | Google Scholar
Banerjee, A. V. (2008). Why Fighting Poverty Is Hard? Unpublished. MIT. Available at: https://www.bbvaopenmind.com/wp-content/uploads/2009/01/BBVA-OpenMind-Frontiers_Of_Knowledge.pdf#page=247..
Belletto, S. (2005). Drink versus Printer’s Ink: Temperance and the Management of Financial Speculation in the Life of P. T. Barnum. Am. Stud. 46 (1), 45–65. Google Scholar
Bennett, R. J., Smith, H., and Montebruno, P. (2020). The Population of Non-corporate Business Proprietors in England and Wales 1891-1911. Business Hist. 62 (8), 1341–1372. doi:10.1080/00076791.2018.1534959 CrossRef Full Text | Google Scholar
Boyd, D. W. (1997). From "Mom and Pop" to Wal-Mart: The Impact of the Consumer Goods Pricing Act of 1975 on the Retail Sector in the United States. J. Econ. Issues 31 (1), 223–232. doi:10.1080/00213624.1997.11505899 CrossRef Full Text | Google Scholar
Brennan, M. J. (1973). An Approach to the Valuation of Uncertain Income Streams. J. Finance 28 (3), 661–674. doi:10.1111/j.1540-6261.1973.tb01387.x CrossRef Full Text | Google Scholar
Burke, A. E., FitzRoy, F. R., and Nolan, M. A. (2008). What Makes a Die-Hard Entrepreneur? beyond the 'employee or Entrepreneur' Dichotomy. Small Bus Econ. 31 (2), 93–115. doi:10.1007/s11187-007-9086-6 CrossRef Full Text | Google Scholar
Bullard, J. (2014). The Rise and Fall of Labor Force Participation in the U.S Federal Reserve Bank of St. Louis, Saint Luis
Carlson, D. W. (1998). "Drinks He to His Own Undoing": Temperance Ideology in the Deep South. J. Early Republic 18 (4), 659–691. doi:10.2307/3124783 CrossRef Full Text | Google Scholar
Chaudry, A., Wimer, C., Macartney, S., Frohlich, L., Campbell, C., Swenson, K., et al. (2016). Poverty in the United States: 50-Year Trends and Safety Net Impacts. Washington, DC: U.S. Department of Health and Human Services.
Chen, J., and Yang, L. (2016). Interactional Impacts on Claimants of Chinese Dibao. Int. J. Soc. Qual. 6 (2), 18–34. doi:10.3167/ijsq.2016.060203 CrossRef Full Text | Google Scholar
Childers, R. G. (2011). Being One'S Own Boss: How Does Risk Fit in?. The Am. Economist 56 (1), 48–58. doi:10.1177/056943451105600107 CrossRef Full Text | Google Scholar
Constable, S., and Wright, R. E. (2011). The WSJ Guide to the 50 Economic Indicators that Really Matter: From Big Macs to“ Zombie Banks,” the Indicators Smart Investors Watch to Beat the Market. Harper Collins.
Cook, S. R. (1998). The Great Depression, Subsistence, and Views of Poverty in Wyoming County, West Virginia. J. Appalachian Stud. 4 (2), 271–283. Google Scholar
Crawford, K., Whittaker, M., Elish, M. C., Barocas, S., Plasek, A., and Ferryman, K. (2016). The AI Now Report. The Social and Economic Implications of Artificial Intelligence Technologies in the Near-Term. Available at: http://acikistihbarat.com/Dosyalar/AINowSummaryReport-artificial-intelligence-effects-in-near-future.pdf. Google Scholar
De Vries, J. (1994). The Industrial Revolution and the Industrious Revolution. J. Eco. Hist. 54 (2), 249–270. doi:10.1017/s0022050700014467 CrossRef Full Text | Google Scholar
Elwert, G., and Wong, D. (1980). Subsistence Production and Commodity Production in the Third World. Review 3 (3), 501–522. Google Scholar
Feldstein, M. (2016). Reducing Inequality and Poverty. Project Syndicate. Available at: https://www.project-syndicate.org/commentary/reducing-inequality-in-america-by-martin-feldstein-2016-08. Google Scholar
Fleischer, M. P., and Hemel, D. (2020). The Architecture of a Basic Income. The University of Chicago Law Review. University of Chicago. L. Sch. 87 (3), 625–710. Google Scholar
Flynn, S. M. (2019). The Cure that Works: How to Have the World’s Best Health Care -- at a Quarter of the Price. Simon & Schuster.
Furman, J., and Seamans, R. (2019). AI and the Economy. Innovation Policy and the Economy 19, 161–191. doi:10.1086/699936 CrossRef Full Text | Google Scholar
Gallman, R. E., and Rhode, P. W. (2020). Capital in the Nineteenth Century. University of Chicago Press.
Goetz, S. J., and Rupasingha, A. (2009). Determinants of Growth in Non-farm Proprietor Densities in the US, 1990-2000. Small Bus Econ. 32 (4), 425–438. doi:10.1007/s11187-007-9079-5 CrossRef Full Text | Google Scholar
Goldin, C., and Katz, L. (2009). The Race between Education and Technology. Harvard University Press.
Goolsbee, A. (2018). Public Policy In an AI Economy (No. W24653). Cambridge, MA: National Bureau of Economic Research. doi:10.3386/w24653 CrossRef Full Text
Gottschalk, P., and Moffitt, R. A. (1994). Welfare Dependence: Concepts, Measures, and Trends. Am. Econ. Rev. 84 (2), 38–42. Google Scholar
Green, J. M. (2021). Diversify Your Income for Financial independence. Retrieved from: https://www.thebalance.com/diversify-your-income-sources-357629 (Accessed March 26, 2021). Google Scholar
Guelzo, A. C. (2000). Come-outers and Community Men: Abraham Lincoln and the Idea of Community in Nineteenth-Century America. J. Abraham Lincoln Assoc. 21 (1). Available at: https://cupola.gettysburg.edu/cwfac/32/. Google Scholar
Haagh, L. (2019). The Case for Universal Basic Income. John Wiley & Sons.
Haenlein, M., and Kaplan, A. (2019). A Brief History of Artificial Intelligence: On the Past, Present, and Future of Artificial Intelligence. Calif. Manage. Rev. 61 (Issue 4), 5–14. doi:10.1177/0008125619864925 CrossRef Full Text | Google Scholar
Hamilton, B. H. (2000). Does Entrepreneurship Pay? an Empirical Analysis of the Returns to Self‐Employment. J. Polit. Economy 108 (3), 604–631. doi:10.1086/262131 CrossRef Full Text | Google Scholar
Handler, J. F., and Hollingsworth, E. J. (1969). Stigma, Privacy, and Other Attitudes of Welfare Recipients. Stanford L. Rev. 22 (1), 1–19. doi:10.2307/1227402 CrossRef Full Text | Google Scholar
Hecht-Nielsen, R. (1992). “Theory of the Backpropagation Neural Network**Based on "nonindent" by Robert Hecht-Nielsen, Which Appeared in Proceedings of the International Joint Conference on Neural Networks 1, 593-611, June 1989. 1989 IEEE,” in Neural Networks for Perception (Elsevier), 65–93. doi:10.1016/b978-0-12-741252-8.50010-8 CrossRef Full Text | Google Scholar
Heien, D. (1977). The Cost of the U.S. Dairy Price Support Program: 1949-74. Rev. Econ. Stat. 59 (1), 1–8. doi:10.2307/1924898 CrossRef Full Text | Google Scholar
Hopkins, E. (1982). Working Hours and Conditions during the Industrial Revolution: A Re-appraisal. Econ. Hist. Rev. 35 (1), 52–66. doi:10.2307/2595103 CrossRef Full Text | Google Scholar
Johnson, T. (1998). Farm Life Long Ago. Austin, TX: Steck-Vaughn Company.
Juhn, C., and Potter, S. (2006). J. Econ. Perspect. 20 (3), 27–46.
Juhász, R., Squicciarini, M., and Voigtländer, N. (2020). Away from Home and Back: Coordinating (Remote) Workers in 1800 and 2020. Available at: https://papers.ssrn.com/abstract=3753983. Google Scholar
Katz, M. B. (1984). Poorhouses and the Origins of the Public Old Age home. Milbank Memorial Fund Q. Health SocietyHealth Soc. 62 (1), 110–140. doi:10.2307/3349894 PubMed Abstract | CrossRef Full Text | Google Scholar
Kennedy, L. (1982). The First Agricultural Revolution: Property Rights in Their Place. Agric. Hist. 56 (2), 379–390. doi:10.1016/0378-3774(82)90016-6 CrossRef Full Text | Google Scholar
Kidd, M. T., and Anderson, K. E. (2019). Laying Hens in the U.S. Market: An Appraisal of Trends From the Beginning of the 20th Century to Present. J. Appl. Poult. Res. 28 (4), 771–784. doi:10.3382/japr/pfz043 CrossRef Full Text | Google Scholar
Latham, S., and Humberd, B. (2018). Four Ways Jobs Will Respond to Automation: The Level of Threat to a Given Profession Depends on Two Factors, the Type of Value provided and How It’s Delivered. MIT Sloan Management Review.
Lauterbach, A. (1977). Employment, Unemployment and Underemployment: A Conceptual Re-examination. Am. J. Econ. Sociol. 36 (3), 283–298. Google Scholar
Lee, J.-H., and Lee, J. (2021). South Korea Premier Says Universal Basic Income “Impossible”. New York: Bloomberg News. Available at: https://www.bloomberg.com/news/articles/2021-02-03/south-korea-premier-says-universal-basic-income-is-impossible..
Levy, D. K., McDade, Z., and Bertumen, K. (2013). Mixed-Income Living: Anticipated and Realized Benefits for Low-Income Households. Cityscape 15 (2), 15–28. Google Scholar
Little, J. I. (2001). A Canadian in Lowell: Labour, Manhood and Independence in the Early Industrial Era, 1840-1849. Labour/Le Travail 48, 197–263. doi:10.2307/25149166 CrossRef Full Text | Google Scholar
MacDonald, R., and Peel, D. A. (1983). The Life Cycle Hypothesis and Rational Expectations : Some Further Empirical Results. Recherches Économiques de Louvain/Louvain Econ. Rev. 49 (4), 381–390. Google Scholar
Makridakis, S. (2017). The Forthcoming Artificial Intelligence (AI) Revolution: Its Impact on Society and Firms. Futures 90, 46–60. doi:10.1016/j.futures.2017.03.006 CrossRef Full Text | Google Scholar
Malkiel, B. G. (2013). Asset Management Fees and the Growth of Finance. J. Econ. Perspect. 27 (2), 97–108. doi:10.1257/jep.27.2.97 CrossRef Full Text | Google Scholar
Malter, J., and Sprague, K. (2019). “I”m Not a UBI Guy’: Paul Krugman Says Money Could Be Better Spent on More Targeted Programs. TV Programme CNBC. Available at: https://www.cnbc.com/2019/04/23/paul-krugman-on-universal-basic-income-im-not-a-ubi-guy.html.
Mason, A. (2020). 6 Ideas to Diversify Your Income Streams. Available at: https://thecollegeinvestor.com/16174/6-ideas-to-diversify-your-income/. Google Scholar
McAfee, A., and Brynjolfsson, E. (2016). Human Work in the Robotic Future: Policy for the Age of Automation. Foreign Aff. 95 (4), 139–150. Google Scholar
McAfee, A., and Brynjolfsson, E. (2017). Machine, Platform, Crowd: Harnessing Our Digital Future. W. W. Norton & Company.
Measuring worth (2021). Annual Wages in the United States. Retrieved from: https://www.measuringworth.com/datasets/uswage/(Accessed March 25, 2021). Google Scholar
Misra, J., Moller, S., and Karides, M. (2014). Envisioning Dependency: Changing Media Depictions of Welfare in the 20th Century. Soc. Probl. 50 (4), 482–504. Google Scholar
Modigliani, F., and Pogue, G. A. (1974). An Introduction to Risk and Return: Concepts and Evidence, Part Two. Financial Analysts J. 30 (3), 69–86. doi:10.2469/faj.v30.n3.69 CrossRef Full Text | Google Scholar
Morris, A. J. F. (2009). The Limits of Voluntarism: Charity and Welfare from the New Deal through the Great Society. Cambridge University Press.
Mould, T. (2020). Overthrowing the Queen: Telling Stories of Welfare in America. Indiana University Press.
Nelson, P. (2018). Universal Basic Income and the Threat to Democracy as We Know it. New York: Business Expert Press.
Nelson, S. C. (2008). Tax Policy and Sole Proprietorships: A Closer Look. Natl. Tax J. 61 (3), 421–443. doi:10.17310/ntj.2008.3.05 CrossRef Full Text | Google Scholar
Olasky, M. (1994). The Tragedy of American Compassion. Washington, DC: Regnery Publishing.
Olmstead, A. L., and Rhode, P. W. (2008). Creating Abundance. Cambridge, MA: Cambridge Books. Available at: https://ideas.repec.org/b/cup/cbooks/9780521673877.html.
Pierce, J. L., Rubenfeld, S. A., and Morgan, S. (1991). Employee Ownership: A Conceptual Model of Process and Effects. Acad. Manage. Rev. 16 (1), 121–144. doi:10.2307/258609 CrossRef Full Text | Google Scholar
Productivity (2021). GDP Per Hour Worked - OECD Data. Retrieved from: https://data.oecd.org/lprdty/gdp-per-hour-worked.htm (Accessed March 31, 2021). Google Scholar
Rallo, J. R. (2019). Hayek Did Not Embrace a Universal Basic Income. Independent Rev. 24 (3), 347–359. Google Scholar
Rank, M. R. (1994). A View from the inside Out: Recipients’ Perceptions of Welfare. J. Sociol. Soc. Welfare 21 (2), 3. Google Scholar
Rivers, R. (2019). A Progressive Rejection of Universal Basic Income - Ron Rivers - Medium. Medium.com. Available at: https://medium.com/@ronrivers/a-progressive-rejection-of-universal-basic-income-2604366c6d3a.
Rose, J. (2017). November 2). 5 Ways to Generate Different Sources of Income. Jersey City, NJ: Forbes Magazine. Available at: https://www.forbes.com/sites/jrose/2017/11/02/different-sources-income/.
Rothman, D. J. (2017). The Discovery of the Asylum: Social Order and Disorder in the New Republic. London: Routledge.
Sahm, C. R., Shapiro, M. D., and Slemrod, J. (2012). Check in the Mail or More in the Paycheck: Does the Effectiveness of Fiscal Stimulus Depend on How it Is Delivered?. Am. Econ. J. Econ. PolicyEconomic Pol. 4 (3), 216–250. doi:10.1257/pol.4.3.216 PubMed Abstract | CrossRef Full Text | Google Scholar
Seely, B. E. (2007). Economic History as Technological History: George Rogers Taylor's the Transportation Revolution, 1815-1860. Technol. Cult. 48 (4), 824–830. doi:10.1353/tech.2007.0186 CrossRef Full Text | Google Scholar
Shaikh, M. D. S. (2020). Insight of DeepMind Learning: Journey of Transformation from Natural Intelligence to Artificial Intelligence. Seattle, Washington: Amazon Digital Services LLC - KDP Print US.
Singh, A., Ramasubramanian, K., and Shivam, S. (2019). Building an Enterprise Chatbot: Work with Protected Enterprise Data Using Open Source Frameworks. New York: Apress.
Stadelmann-Steffen, I., and Dermont, C. (2020). Citizens' Opinions about Basic Income Proposals Compared - A Conjoint Analysis of Finland and Switzerland. J. Soc. Pol. 49 (2), 383–403. doi:10.1017/s0047279419000412 CrossRef Full Text | Google Scholar
Tegmark, M. (2017). Life 3.0: Being Human in the Age of Artificial Intelligence. Knopf Doubleday Publishing Group.
Terborgh, G. (1966). The Automation Hysteria. W. W. Norton.
The effect of lockdown measures on unemployment (2021). Economic Impact of COVID-19. Retrieved from: https://www.richmondfed.org/publications/research/coronavirus/economic_impact_covid-19_09-04-20 (Accessed March 25, 2021). Google Scholar
The fiscal response to COVID-19 in Europe: will it be enough? (2021). Bruegel: Rue de la Charité 33-1210 Brussels. Retrieved from: https://www.caixabankresearch.com/en/economics-markets/activity-growth/fiscal-response-covid-19-europewill-it-be-enough (Accessed March 31, 2021). Google Scholar
Torrey, L., and Shavlik, J. (2010). “Transfer Learning,” in Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques (Philadelphia: IGI Global), 242–264. Google Scholar
US Government Accountability Office (2021). The Nation’s Fiscal Health: After Pandemic Recovery, Focus Needed on Achieving Long-Term Fiscal Sustainability. Retrieved from: https://www.gao.gov/products/gao-21-275sp (Accessed March 25, 2021). Google Scholar
Vinyals, O., Babuschkin, I., Chung, J., Mathieu, M., Jaderberg, M., Czarnecki, W. M., et al. (2019). AlphaStar: Mastering the Real-Time Strategy Game StarCraft II. London, DeepMind Blog. Google Scholar
Wage Stagnation in Nine Charts (2021). Economic Policy Institute. Retrieved from: https://www.epi.org/publication/charting-wage-stagnation/(Accessed March 25, 2021). Google Scholar
Wang, F., Zhang, J. J., Zheng, X., Wang, X., Yuan, Y., Dai, X., et al. (2016). Where Does AlphaGo Go: from Church-Turing Thesis to AlphaGo Thesis and beyond. Ieee/caa J. Autom. Sinica 3 (2), 113–120. doi:10.1109/jas.2016.7471613 CrossRef Full Text | Google Scholar
Waters, R. (2018). Techmate: How AI Rewrote the Rules of Chess. London; Financial Times. Available at: https://www.ft.com/content/ea707a24-f6b7-11e7-8715-e94187b3017e.
Weiss, K., Khoshgoftaar, T. M., and Wang, D. (2016). A Survey of Transfer Learning. J. Big Data 3 (1). doi:10.1186/s40537-016-0043-6 CrossRef Full Text | Google Scholar
Wermers, R. (2000). Mutual Fund Performance: An Empirical Decomposition into Stock-Picking Talent, Style, Transactions Costs, and Expenses. J. Finance 55 (4), 1655–1695. doi:10.1111/0022-1082.00263 CrossRef Full Text | Google Scholar
Widerquist, K. (2015). UNITED STATES: Nobel Laureate Joseph Stiglitz Endorses Unconditional Basic Income. Retrieved from: http://basicincome.org/news/2015/09/united-states-nobel-laureate-joseph-stiglitz-endorses-unconditional-basic-income/(Accessed March 30, 2021). Google Scholar
Williamson, J. B. (1974). The Stigma of Public Dependency: A Comparison of Alternative Forms of Public Aid to the Poor. Soc. Probl. 22 (2), 213–228. doi:10.1525/sp.1974.22.2.03a00050 CrossRef Full Text | Google Scholar
Wispelaere, J. D., and Stirton, L. (2007). The Public Administration Case against Participation Income. Soc. Serv. Rev. 81 (3), 523–549. doi:10.1086/520939 CrossRef Full Text | Google Scholar
Wright, R. E. (2019). America’s Fur Business Parts I, II, and III. Fur Traders & Rendezvous. Available at: https://www.alfredjacobmiller.com/explore/americasfurbusiness1/. Google Scholar
Wright, R. E. (2010). Bailouts: Public Money, Private Profit. Columbia University Press.
Wright, R. E. (2021b). History and Evolution of the North American Wildlife Conservation Model. Cham, Switzerland: Palgrave. doi:10.2139/ssrn.3673178 CrossRef Full Text
Wright, R. E. (2015). Little Business on the Prairie: Entrepreneurship, Prosperity, and Challenge in South Dakota. Sioux Falls, SD: Center for Western Studies.
Wright, R. E. (2021a). The Best of Thomas Paine. American Institute for Economic Research.
| 2021-08-24T00:00:00 |
2021/08/24
|
https://www.frontiersin.org/journals/human-dynamics/articles/10.3389/fhumd.2021.725516/full
|
[
{
"date": "2023/03/01",
"position": 48,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 46,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 47,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 48,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 52,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 47,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 47,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 46,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 45,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 47,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 52,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 52,
"query": "universal basic income AI"
}
] |
The Future of Work Is Post-Human - Vocal Media
|
The Future of Work Is Post-Human
|
https://vocal.media
|
[] |
At first, people panicked. Then, governments began to roll out Universal Basic Income—a monthly stipend for every citizen, enough to survive. No strings ...
|
“What do you do?”
It used to be the first thing we asked each other.
Not “Who are you?”
Not “What do you love?”
But: “What do you do?”
As if our value lived in a job title. As if worth could be measured in performance reviews and productivity reports.
But in the post-human era—the age of automation, AI, and universal basic income—that question is disappearing.
And in its place comes something far more beautiful… and terrifying.
The Machines Took Over. But Not How We Feared.
The rise of automation wasn’t a war. It wasn’t a hostile takeover of steel and wires. It was quiet. Gradual. Kind of like rain. First it was self-checkout machines. Then customer service chatbots. Then logistics. Then design. Then medicine. Then coding.
And then came the hardest part: it wasn't just blue-collar jobs. It was all of them.
Suddenly, 60% of the global workforce didn’t need to work. Not because they were lazy. But because AI could do it faster, cheaper, better.
And the world had to answer a new question:
If we’re not needed for labor… what are we needed for?
UBI: The Great Recalibration
At first, people panicked.
Then, governments began to roll out Universal Basic Income—a monthly stipend for every citizen, enough to survive. No strings attached. No paperwork. No “proof of productivity.”
It was radical. It was controversial.
It was also necessary.
UBI didn’t make people rich. But it unlocked something deeper: the right to pause. To reflect. To ask:
“If I don’t have to sell my time to live… what should I do with my life?
The Redefinition of Worth
At first, people didn’t know what to do with themselves.
Some cried. Some slept for weeks. Some dove into digital worlds. Others wandered.
But then something amazing started to happen.
A retired mechanic began painting again—for the first time in 40 years.
A single mother who’d always worked two jobs opened a free community school.
Teenagers built their own solar co-ops and launched micro-nations in VR.
A former accountant became a full-time caregiver for their aging father—without shame, without apology.
Work didn’t disappear. It evolved.
It became untethered from survival. And attached to meaning.
AI Didn’t Steal Our Jobs. It Gave Us Time.
The paradox was everywhere.
People feared AI would make them obsolete.
Instead, AI made room for human things—the slow, beautiful, unpaid things that were never considered “productive” before.
Listening deeply
Creating imperfectly
Building communities
Caring without a clock ticking
These weren’t jobs. They were callings.
And for the first time, society began to value the invisible labor that made life livable.
The Identity Crisis
But make no mistake—it wasn’t all utopia.
Many struggled. For decades, our identities were built on output. Titles. Promotions. Hustle. Grind.
Without those markers, millions felt lost.
“If I’m not a manager anymore… who am I?”
“If no one needs me to do this… am I still valuable?”
Psychologists called it “Post-Work Trauma.”
But slowly, culture caught up.
Universities shifted from career prep to curiosity cultivation.
Mental health became as normalized as dental health.
New rituals emerged—not to celebrate promotions, but personal growth.
The question evolved from “What do you do?” to:
“What are you learning to love?”
The Unequal Unevenness of It All
This revolution didn’t happen everywhere at once.
Some countries embraced post-human economics. Others resisted, clinging to outdated labor models and wealth hierarchies. In places without UBI, despair deepened.
But the pressure grew. And so did global cooperation.
A Global Social Income Treaty was signed in 2042—linking tech company profits to human well-being worldwide.
By then, the richest companies were AI ecosystems. They didn’t need shareholders. So they reinvested in people.
Not out of charity—but out of vision.
Because a world where humans are free to create, dream, and connect is more valuable than any bottom line.
The Post-Human Renaissance
By 2050, a new renaissance bloomed.
Art exploded. Not for money—but for meaning.
Local economies based on care, culture, and connection flourished.
VR and AR gave rise to infinite careers—not as obligations, but as adventures.
Robots built the houses. Humans filled them with stories.
Children grew up without ever believing they had to “earn” their right to exist.
They studied to become more themselves, not just more employable.
We didn't become lazy.
We became alive.
The Real Work Begins
So, here we are.
The future of work isn’t about careers.
It’s about conscious contribution.
Not “What job will you do?”
But:
What truth will you tell?
What beauty will you make?
What care will you offer?
What dream will you chase—not for pay, but for purpose?
We thought AI would be the end of us.
Turns out, it was just the beginning of what it means to be human.
Final Thought: You Are Not What You Produce
You are not your LinkedIn title.
You are not your inbox.
You are not your output.
You are a builder of meaning.
A seeker of wonder.
A caretaker of time.
And in this future—our post-human present—your greatest work… is simply being fully, wildly, honestly you.
| 2023-03-01T00:00:00 |
https://vocal.media/futurism/the-future-of-work-is-post-human
|
[
{
"date": "2023/03/01",
"position": 71,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 64,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 64,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 61,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 66,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 64,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 66,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 65,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 64,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 66,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 75,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 67,
"query": "universal basic income AI"
}
] |
|
Personal Growth Over Productivity: AI Makes Current Education ...
|
Personal Growth Over Productivity: AI Makes Current Education Obsolete
|
https://www.fairobserver.com
|
[
"Patrik Meyer"
] |
With AI and automation outpacing humans in many career fields, people may no longer need to work to survive. Universal basic income will ...
|
In a previous article, “Once AI can do everything for us, what do we do?” I discussed how, with the rise of AI, humans are rapidly becoming physically and cognitively obsolete. This is because automation and AI are becoming so productive and creative that humans cannot compete with them in any conceivable field. Soon, humans will no longer need to work to survive.
Consequently, the survival instinct, the core driver of human activity, will also become obsolete. Younger generations must be raised to develop their own motivations and goals to prevent their physical and mental atrophy. It is urgent to replace the current productivity-driven education systems with an alternate model that fosters personal growth. This model will preserve children’s innate authenticity and alertness. Providing them with an environment that motivates them to reach their full potential will ensure that children will enjoy a life-long journey of personal growth in a society where AI replaces the need for survival-driven productivity.
Universal basic income will encourage us to focus on personal growth
The positive side of this dominance is that wealth produced by societies will rise to new levels with only a marginal human contribution. Societies and governments will need to redistribute this wealth among the general population in the form of a universal basic income (UBI). The Forbes article, “Will AI Make Universal Basic Income Inevitable?” defines UBI as payments made to citizens that cover the basic cost of living. Numerous researchers and technology leaders argue that this will occur sooner rather than later. Technology pioneer Elon Musk claims that “probably none of us will have a job” once AI becomes prevalent, making UBI necessary.
The introduction of UBI will no doubt render humans’ innate survival instinct irrelevant. This is a hard idea to grasp, as survival has driven productivity in humans since the beginning. Psychologist Dr. Jim Taylor argues that “the human instinct to survive is our most powerful drive,” and that “just about everything that humans have become serves that essential purpose.” Furthermore, Daniel Kahneman, a psychologist who won the 2002 Nobel Prize in Economics, has shown that the way “we process and remember information, problem solve and make decisions” is aimed at optimizing our survival chances. Our “fight or flight” reaction is a well-known example of our survival instinct in action.
Societies will face the challenge of replacing this survival instinct with motivations toward personal growth and development as the core driving force of humanity. Humans should be focused on proactively utilizing our full potentials — physical, intellectual, emotional, social and spiritual — to enjoy meaningful and fulfilling lives. Otherwise, without survival instincts, unmotivated individuals will most likely experience physical and mental deterioration.
It is important to briefly clarify the difference between personal growth and personal development. Personal growth refers to the internal transformation of our mindset and self-awareness. Personal development focuses on external improvements, such as acquiring new skills and abilities. Thus, personal growth can be seen as a lifelong process of becoming a “better” you, while personal development is about acquiring new knowledge. While personal development can contribute to personal growth, it should not replace it as the central objective in the upbringing of the younger generations.
Education models must prepare children for this kind of future
Therefore, it is urgent that we provide the younger generations with an environment that fosters the development of these self-constructed motivations. Unfortunately, existing educational models predominantly anchor themselves in the past. These education models aim to foster development in order to increase individual productivity, not personal growth.
Developed societies must gradually abandon their education systems and replace them with an upbringing model that “empowers and motivates individuals to explore their potential at every stage of life.” A detailed description of this new upbringing paradigm is beyond the scope of this piece, but I will describe two basic principles that should guide the upbringing of our youth. I will also outline five fundamental changes that must be made to the existing educational models to go beyond survival and provide the younger generations with an environment that fosters personal growth.
The first principle focuses on preserving the innate authenticity of children by encouraging them to behave and speak in ways that reflect their true selves. In other words, children’s feelings, thoughts, words and actions should remain coherent in every circumstance they encounter. Montessori schools are an example of an effort to nurture children’s authenticity by ensuring they do not feel compelled to mask or change themselves to fit what they think those around them expect. It is important to note that this does not mean that they should be allowed to do whatever they want. Developing personal discipline and respect for social norms are still integral in this model, but should not erode children’s authenticity.
The second principle is to foster and transform children’s innate sense of wonder into alertness. According to the National Institute of Health, young children’s sense of wonder is their “inner desire to learn that awaits reality in order to be awakened.” Over time, this sense of wonder transforms into alertness, the cognitive state of being engaged and aware. It is well established that young children are alert most of the time, and that their curiosity can be aroused by anything novel in their surroundings. Encouraging this alertness is fundamental to fostering their personal growth and enriching their upbringing.
New education models will be focused on personal exploration
In order to adhere to these two principles, changes must be made to current education models. Education must reflect the opportunities offered by a society where individuals are not obligated to work. The most important and necessary change to the education system is that learning should consist primarily of personal exploration and discovery in the real world, making traditional school buildings unnecessary. It should not be focused on churning out productive workers.
This leads to the second necessary change: replacing rigid, standardized learning with immersion learning through experiences that are relevant and interesting to the child. Due to the eclectic nature of the globalized world, children should also be immersed in different environmental and cultural settings for extended periods of time to develop a critical understanding of them.
The third change is a shift to grouping children by shared interests rather than age, which fosters a more engaging learning environment. This means that children will be part of a group where shared enthusiasm can reinforce experiences. Children should change groups over time to reflect their evolving interests and maturity levels.
As a fourth change, we should place an emphasis on children maturing alongside their learning. That is, children should not be asked to accumulate standardized knowledge just for the sake of memorizing. Instead, they should be immersed in experiences that allow them to process knowledge and grow as people.
Finally, the number of guiding values and objectives used in the upbringing model should be minimized. Those that remain should preferably be based on established, robust psychology and neuroscience, rather than on subjective cultural dogmas of any kind. This will ensure that the education models are healthy for children and guarantee personal growth.
Once this novel upbringing paradigm is well-defined, it cannot be implemented on a large scale like current educational systems are. Rather, the model should serve as a reference toward which current educational models can gradually transition. Numerous projects have already made valuable contributions to the necessary shift. Examples include “forest kindergartens” in Denmark, where children play freely in nature for several years; project-based activities in Norway, where homework and exams have been eliminated; and the Montessori and Waldorf schools, which provide models that engage students’ potentials more effectively. However, while these are all significant improvements, they ultimately still adhere to the soon-obsolete objective of shaping children into productive members of society.
Parents must start this academic evolution
Now, the following question arises: Who should lead the transition from the traditional education system to the new upbringing model? Governments cannot be expected to take the lead because their decision-making process is bureaucratic in nature and only reactive to public demands. Therefore, parents must take the lead in starting the transition. They must be aware that their children will suffer the detrimental consequences from being raised in an obsolete educational system.
Fortunately, parents will have plenty of time to engage deeply in their children’s education, because the proliferation of AI will mean that they will not have to work.
[Cheyenne Torres edited this piece.]
The views expressed in this article are the author’s own and do not necessarily reflect Fair Observer’s editorial policy.
| 2025-07-05T00:00:00 |
2025/07/05
|
https://www.fairobserver.com/culture/personal-growth-over-productivity-ai-makes-current-education-obsolete/
|
[
{
"date": "2023/03/01",
"position": 74,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 76,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 78,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 67,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 79,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 76,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 79,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 76,
"query": "universal basic income AI"
},
{
"date": "2024/08/01",
"position": 77,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 79,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 77,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 83,
"query": "universal basic income AI"
}
] |
Can AI Deliver Broad-Based Prosperity? - Project Syndicate
|
Can AI Deliver Broad-Based Prosperity?
|
https://www.project-syndicate.org
|
[
"Michael Spence"
] |
Nonetheless, ensuring that the AI toolkit offers augmentation- or collaboration-based benefits across sectors and income levels must be a top ...
|
Email required
Password required Remember me?
Please enter your email address and click on the reset-password button. If your email exists in our system, we'll send you an email with a link to reset your password. Please note that the link will expire twenty-four hours after the email is sent. If you can't find this email, please check your spam folder.
| 2023-03-01T00:00:00 |
https://www.project-syndicate.org/commentary/ai-productivity-gains-risk-exacerbating-inequality-by-michael-spence-2025-07
|
[
{
"date": "2023/03/01",
"position": 86,
"query": "universal basic income AI"
}
] |
|
“We need to ask ourselves: is AI actually worth the costs?” - SWZ
|
“We need to ask ourselves: is AI actually worth the costs?”
|
https://swz.it
|
[
"Südtiroler Wirtschaftszeitung",
"Wochenblatt Für Wirtschaft Und Politik. Umfassende Informationen Jeden Freitag Seit"
] |
...
|
Jetzt Abo abschließen oder einloggen, um den ganzen Artikel zu lesen.
Flexi-Abo Online | Unbegrenzter Zugang zu allen Inhalten auf www.swz.it
App | Unbegrenzter Zugang in der Mobile und Tablet App (iOS und Android)
ePaper | Die digitale 1:1-Ausgabe der Printversion (schon am Donnerstag ab 20 Uhr)
Archiv | Recherche mit mehr als 30.000 Artikeln Jetzt drei Monate für 7,99 Euro testen
Hier können Sie sich einen Überblick über die Abo-Optionen der SWZ verschaffen.
Sie haben bereits ein Abo?
Sie haben bereits ein Abo, aber noch keine Zugangsdaten? Oder Probleme beim Einloggen?
Dann schicken Sie uns bitte hier eine Nachricht
| 2025-07-04T00:00:00 |
2025/07/04
|
https://swz.it/we-need-to-ask-ourselves-is-ai-actually-worth-the-costs/
|
[
{
"date": "2023/03/01",
"position": 90,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 88,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 87,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 97,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 87,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 86,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 87,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 86,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 88,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 94,
"query": "universal basic income AI"
},
{
"date": "2025/01/01",
"position": 92,
"query": "universal basic income AI"
}
] |
Cash, Not Control: A Global History of Basic Income
|
Cash, Not Control: A Global History of Basic Income
|
https://thedailyeconomy.org
|
[] |
If you pay attention to public policy discussions, you know that people have proposed a Basic Income Guarantee or a Universal Basic Income ...
|
If you pay attention to public policy discussions, you know that people have proposed a Basic Income Guarantee or a Universal Basic Income as one option among many to deal with technological unemployment or the distributional consequences of new technologies like generative AI. You might not know that the idea of a Basic Income is nothing new, and it has a long and interesting history. That’s what the historian Anton Jäger and the historical sociologist Daniel Zamora explore in Welfare for Markets: A Global History of Basic Income.
In five chapters, bookended by an introduction and epilogue and followed by copious endnotes, the authors take us through the intellectual history of the idea. Instead of a massive welfare state that provides carefully chosen goods and services like housing, education, food, and so on at public expense, market-friendly Basic Income proponents suggest adjusting the starting points through taxes and cash transfers. Basic Income Guarantees make dollars, not bureaucrats, the first responders in crises.
They start by discussing unconditional cash grants throughout the COVID-19 pandemic and then explain how, contrary to accounts that trace Basic Income from Thomas More through Thomas Paine to today, the Basic Income idea is of more recent vintage. The real “Basic Income” idea emerged from early twentieth-century fiscal innovations, making tax-and-transfer schemes easier and cheaper to implement and administer than in-kind redistributions. They then explain how the idea developed through the middle of the twentieth century by engaging scholars like Juliet Rhys-Williams, Abba Lerner, and W.H. Hutt, before Milton Friedman proposed his Negative Income Tax.
The idea developed further as postwar observers wrestled with the idea that automation meant the end of work, which in turn meant transferring purchasing power, not creating jobs, was the right way to fight technological unemployment and, in Chapter 4, the post-work world where automation meant leisure and cash meant autonomy. They then explore cash transfer programs in developing countries before concluding with thoughts on what twenty-first-century technopopulism means for the debate.
Welfare for Markets has much to recommend it. It explains how the idea developed parallel with economic ideas about socialism, noting that economists coalesced around Mises and Hayek’s idea that prices were necessary for rational, efficient production. Indeed, they quote James Meade, who described the price system as “among the greatest social inventions of mankind.” I think they could have built on the intellectual history of economics by exploring how the first and second fundamental theorems of welfare economics developed and influenced the debate. The First Fundamental Theorem of Welfare Economics explains that any competitive equilibrium is Pareto-efficient under perfect competition. The Second Fundamental Theorem of Welfare Economics says that any Pareto-efficient resource allocation can emerge as a competitive equilibrium if we adjust the starting points with lump-sum taxes and transfers.
It might look like economists disagree about a lot, and we do. But we agree, fundamentally, that markets are efficient under the right conditions and quibble mostly about whether the conditions are right. The left wing of the economics profession looks radically pro-market compared to the rest of academia, because it embraces markets (maybe not enthusiastically) and mostly seeks to solve social problems through taxes, subsidies, and transfers that either leave prices unmolested or align incorrect prices with marginal social benefits and social costs.
Many proponents of the Basic Income argue that a simple tax-and-transfer scheme like the Negative Income Tax (the Earned Income Tax Credit in the US tax code) should replace the welfare state. Similarly, governments can make a case for financing schooling, but the case for governments owning and operating schools is much weaker. As I’ve told my students, I’d be very happy if I woke up tomorrow and a Negative Income Tax replaced the US welfare state. As Milton Friedman has explained, the benefit of a negative income tax is that it is easy to structure it so that it never penalizes work. In his 2011 book The Redistribution Recession, the economist Casey Mulligan explained how the tax code and existing welfare programs are a mess of contradictory and often pathological incentives where people get locked into the system by very high implicit marginal tax rates when earning income causes some benefits to expire.
The book’s global perspective is also refreshing, as it discusses the developing consensus among development economists, philanthropists, and practitioners that cash transfers are likely more effective than top-down, planning-centered approaches like Jeffrey Sachs’s Millennium Village project. As I’ve been working on the economist W.H. Hutt (whom they reference) for some time now, I was especially interested in and will refer back to their discussion of South Africa. Mises, Hutt, Hayek, and Adam Smith understood that markets are fundamentally conversational spaces where every dollar is a ballot and prices convey information rather than power. In principle, a Basic Income Guarantee can achieve distributional goals without sacrificing the mechanism that makes rational economic calculation possible.
Some progressives have interpreted proposals to replace the existing welfare state with a Basic Income Guarantee as some kind of neoliberal conspiracy. For people who don’t trust markets, “adjust the starting points and let markets rip” is less than attractive. There is a tension between low liberalism (give people money and let them decide for themselves) and high liberalism (give us money so that we can train people to want what they should want, and then provide them with the capabilities to get it via programs that provide it directly). Future work needs to address these tensions carefully.
On the subject of future work, the authors can improve the book’s next edition — or their future work — by engaging carefully with the economics literature on Basic Income Guarantees. The authors probably could have found a lot of work out there as they were doing the research and moving the book through the publication process. It was the subject of a 2015 symposium in the Independent Review, which included perspectives from philosophy, politics, and economics that the authors should consult. Several distinguished economists have papers in the 2021 Annual Review of Economics assessing Basic Income experiments and programs. There is a paper on Basic Incomes in the Journal of Economic Perspectives in 2018 that would have been useful. It would have been interesting to know, for example, how experiments with Basic Incomes have turned out. How responsive is the labor supply to a Basic Income Guarantee? Innovation? Education? And so on. The gap points to opportunities for scholars to build on this work and enrich our understanding by working harder to bring disciplines into conversation with each other.
Welfare for Markets is an interesting and relatively compact tour through the history of the idea of a Basic Income. It shows us how the idea developed and changed over the twentieth century and how it has evolved in the twenty-first century. It explores discussions about “the future of work” in the face of technological change that look like they are taken from recent issues of popular business magazines but were happening in the 1960s and before. While they do not evaluate philosophical arguments for or against a Basic Income, that’s not their task. They put the idea in its context of intellectual history since the Enlightenment. It is a valuable contribution on which scholars studying the history of economic ideas and the effectiveness of Basic Income Guarantees will certainly be able to build.
| 2025-07-02T00:00:00 |
2025/07/02
|
https://thedailyeconomy.org/article/cash-not-control-a-global-history-of-basic-income/
|
[
{
"date": "2023/03/01",
"position": 92,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 96,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 97,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 92,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 95,
"query": "universal basic income AI"
}
] |
GoogleDeepMind on Future Economy as ETH and SOL Prices Dip
|
AI-Driven UBI and Web3 Convergence: @GoogleDeepMind on Future Economy as ETH and SOL Prices Dip | Flash News Detail
|
https://blockchain.news
|
[] |
According to @GoogleDeepMind, the convergence of AI and blockchain is shaping an 'Automated Abundance Economy' where Universal Basic Income ...
|
The convergence of artificial intelligence (AI) and blockchain technology is creating a powerful, long-term narrative that traders are increasingly pricing into assets like Ethereum (ETH) and Solana (SOL). A recent deep-dive analysis from an author at Google DeepMind outlines a future vision of an "Automated Abundance Economy," where AI and automation handle most essential tasks, potentially supported by decentralized frameworks. This vision, while futuristic, underpins the fundamental value proposition of smart contract platforms, suggesting a world where decentralized applications (dApps) and financial systems become integral to a new economic paradigm. While these long-term theses brew, the short-term market action for major crypto assets shows a period of consolidation and key level testing, offering specific opportunities for vigilant traders.
AI Narratives Meet Market Realities: ETH and SOL Price Action
Despite the powerful tailwind from the AI sector, both Ethereum and Solana have experienced a slight pullback in the last 24 hours, reflecting broader market indecision. Ethereum, trading as ETHUSDT, saw its price dip by 1.24% to $2,546.25, retreating from a 24-hour high of $2,633.47. This price action establishes a clear short-term resistance level near $2,630. The immediate support was tested at the 24-hour low of $2,530.84, a critical level for bulls to defend to prevent further downside. The trading volume for the ETHUSDT pair was relatively modest at 180.05 ETH, suggesting that the recent dip lacks strong conviction from sellers. However, the ETHBTC pair tells a more bearish story, falling 2.47% to 0.023300 BTC. This indicates that, in the immediate term, Bitcoin is showing more strength than Ethereum, a crucial factor for traders allocating capital between the two largest crypto assets.
Solana's Volatility and Key Trading Levels
Solana, often seen as a higher-beta play on the Web3 and dApp ecosystem, also faced downward pressure. The SOLUSDT pair declined 1.84% to $149.80, falling from a daily high of $154.83. The key support for SOL traders is now the 24-hour low of $145.00. A break below this psychological and technical level could open the door for a deeper correction. Notably, trading volume for SOLUSDT was significantly higher at 3,458.49 SOL, indicating more active participation in its recent price movements compared to Ethereum. In a sign of potential rotational interest, the SOLETH pair showed remarkable strength, gaining 2.595% to trade at 0.06800. This suggests some traders may be rotating capital from ETH to SOL, betting on Solana's relative outperformance in the near future. For those watching the SOLBTC pair, it registered a minor loss of 0.778%, showing more resilience against Bitcoin than Ethereum did.
Fundamental Strength and Ecosystem Growth as a Long-Term Indicator
Beyond the charts, the underlying strength of these ecosystems provides a compelling long-term investment thesis. As the analysis from the Google DeepMind author highlights, the future is being built by innovators who bridge different technological and financial worlds. For instance, the success of companies like Anthropic, which achieved a $61.5 billion valuation by focusing on safe and ethical AI, demonstrates the immense value being placed on responsible innovation. This ethos aligns with the core principles of many blockchain communities. Furthermore, the practical application of blockchain, such as MANSA's use of stablecoins to facilitate $92 million in payments for underserved clients with backing from giants like Tether, proves the technology's real-world utility. These fundamental developments, which combine AI's intelligence with blockchain's transparency, are what will ultimately drive demand and value for networks like Ethereum and Solana. While short-term price action may be choppy, the continued growth in ecosystem development and institutional validation provides a strong foundation. Traders should therefore view dips towards established support levels, such as $2,530 for ETH and $145 for SOL, not just as technical points, but as potential opportunities to accumulate assets with powerful, long-term, AI-driven tailwinds.
| 2023-03-01T00:00:00 |
https://blockchain.news/flashnews/ai-driven-ubi-and-web3-convergence-googledeepmind-on-future-economy-as-eth-and-sol-prices-dip
|
[
{
"date": "2023/03/01",
"position": 93,
"query": "universal basic income AI"
},
{
"date": "2023/05/01",
"position": 95,
"query": "universal basic income AI"
},
{
"date": "2023/06/01",
"position": 96,
"query": "universal basic income AI"
},
{
"date": "2023/07/01",
"position": 90,
"query": "universal basic income AI"
},
{
"date": "2023/08/01",
"position": 95,
"query": "universal basic income AI"
},
{
"date": "2023/10/01",
"position": 97,
"query": "universal basic income AI"
},
{
"date": "2024/03/01",
"position": 96,
"query": "universal basic income AI"
},
{
"date": "2024/06/01",
"position": 96,
"query": "universal basic income AI"
},
{
"date": "2024/11/01",
"position": 96,
"query": "universal basic income AI"
},
{
"date": "2024/12/01",
"position": 93,
"query": "universal basic income AI"
}
] |
|
So… What Good Is AI? - by KayStoner
|
So… What Good Is AI?
|
https://kaystoner.substack.com
|
[] |
1 day ago · ...
|
A middle-aged librarian looks lovingly at a giant AI
On any given day, it feels like we are absolutely bombarded by AI detractors. Some of them have never believed in it, others have been heartbroken by disappointment and have turned against it. Many, many others are laboring under misapprehensions about what this AI thing is at all.
I’m not sure what turned the tide. Maybe it’s been the spate of news reports and articles about people going “botshit” thanks to allowing ChatGPT to “transmit“ deep wisdom to them, intended to “awaken humanity“. Maybe it’s just the hype cycle working everyone’s last nerve. Who can say?
But every time you turn around, there’s some new thing that somebody invented with AI. There’s an updated model, there’s a new set of benchmarks. There’s a ton of money being made, or there are 10,000 new agents that have been integrated into a seamless workflow designed to manage small water treatment plants in flyover country of the United States.
Lol. I’m only half joking.
But seriously, it’s a bit much, and I think we’re losing the thread. There’s so much back-and-forth debate, our limited energy is being spent, stopping to fill in the cognitive potholes in the road, while the rest of the world speeds on without us. And frankly, it feels like we’re filling potholes in Kansas, where the freeze – thaw cycles can be so extreme, that literally half of the roads in the state are not paved, because asphalt doesn’t survive that well under those conditions.
It really is exhausting, isn’t it?
So, let me pause from all of the back-and-forth and speak to why I started the Substack to begin with.
What good is AI? Or rather, more accurately, what the hell good is AI?
Will it let us clone our beloved pets so we never need to be without them again? Will it get turned into boyfriends and girlfriends, so we never need to be alone – with or without our pets? Will it control all the factories and warehouses on the planet, freeing us to binge watch more Netflix? Will it finally end this nightmare we call the day job, making it possible to replace it with universal basic income that keeps us in Doritos and Mountain Dew, to our hearts content?
I really don’t care about any of that. There are three areas that AI is deeply useful to me, and it can be to others as well. Here they are:
1. Access to vast amounts of information that this bibliophile would never be able to find in one lifetime. Seriously, if AI provided nothing else this would be enough for me. I’m a geek, a nerd, and infovore. I can’t help it. I look for data and then I use it to create meaning. I like to look for a lot of data, to enrich the meanings. I derive from them. I literally chose to college. I went to, back a long time ago, when there were still physical libraries, because it had the largest library in the entire state university system. That’s where you could find me, on any given Sunday, Monday, Tuesday, Wednesday… You get the point. And when the Internet came along, oh Lord… I was a happy camper.
• Note: Never, ever, ever underestimate the importance and impact of just having access to information. Yes, the models have been trained on billions of books, many of them pirated, many of them may be borderline stolen? And a whole lot of training has been done without the express consent of the authors or the publishers. What are you gonna do? The thing is, it’s all in there.
• Well, not all, because a whole lot of the content in their stems from interactions of 18 to 24-year-old single white “incels” living in their parents, basements and playing call of duty all day. (For the record, no one who has ever worked in AI has ever challenged me on that point. We all know it’s true. It’s kind of like the biggest open secret of AI.) but enough of “it“ is in there that machine learning a natural language processing, and all those little magical things happen behind the scenes are able to go in, identify patterns, look for what words go together, and figure out what numbers and word combinations might make sense to a solitary creature, looking for ways to expand their thinking.
• So there’s that. Access to information. Research. Sources. Insights. Authors that would be buried in the stacks oftiquity, if they hadn’t had the spines chopped off and been fed through the scanner. Honestly, obscurity for authors is sort of like a really long extended burning of the library of Alexandria. You just get to hope that somebody might notice you at some point…
• But I digress. I could stop here and never say another word about the other things. The AI is good for, and this point would still stand as the top, number one reason the AI is good for something.
2. The second thing AI is good for is filtering all that information in ways that makes sense to us. How delightful, that I can access a whole lot of information about the 12th century! But honestly, I’m really interested in the 12th century Renaissance in what’s now considered France, when Eleanor of Aquitaine – who is vastly underrated in terms of historical figures – was giving the local warlords a run for their money, every St. John’s day, when the usual mercenaries weren’t showing up at muster, because they wanted to hang out in the Courts of Love, play games, be entertained, and chat up the ladies. That was some serious, subversive shit that she was pulling, and nobody seems to understand the gravity of it. I understand, though, and if I want to have a conversation with a deep research AI to dig into my theories and my perspectives and I wanted to bring back more for me to read and consider, I can do that.
• Just understand… Since 1998, maybe even before, I have earned my keep from information, particularly search. Online search, Internet, Internet, Google, SEO, building engines, configuring search engines, working with search vendors, who had everyone convinced that their product was a search engine… I’ve been in the business of connecting people with the information that will help them work better, live better, and be better, for a long time. In fact, I might be an AI instead of search, but I’m still kind of in that business.
• You should also understand that the idea of being able to actually talk to information and have a discussion with. It is incredibly heady for me. I’ve been interacting with static pages for a long time, dating back to the years when we had these things called books where you had to turn pages to get to the next idea. I’ve been interacting with static webpages, as well as dynamic webpages, but the information was always inner. Sure, with a well tune search engine, you can return successively Better targeted results, and you can also summarize what people are looking for and what they get back, but it’s nowhere near like interacting with AI.
• Being able to search through a haystack with the magnet that is tuned to exactly the kind of needles I’m looking for is pretty amazing. And yes, that’s another thing that AI is good for.Because frankly, when you get information back from a consultant, a health provider, or another sort of expert, and you need help understanding what it is that they’ve said to you, AI can be a lot of help.
3. Thirdly, and probably most important if you don’t wanna be a sociopath, is a AI can help us actually communicate with each other. Not only can it help translate languages, sometimes in real time, but it can also help us rephrase what we’re about to say in ways that won’t Infuriate the people we’re trying to reach. My personal communication style is fairly frank. I get in trouble all the time for saying things that “you’re not supposed to say“, but just sound like the truth to me. I don’t understand why people get so upset, but they do. So, if I put what I’m saying through AI, and I ask it to rephrase it in a way that certain people will be able to relate to better, it’s absolutely magical what it comes back with.
• If you’ve been reading things on my sub stack and/or LinkedIn, and if you’re getting something out of it, you’re looking at the result of me negotiating with AI about what I should or should not say. It’s not that I’m getting AI to do it for me, although I was doing that about a year ago. It’s more that I’m using AI to fine-tune my sensibilities and explain to me why something might not land quite right or the way I expect it to.
• AI has all kinds of benefits for those who have our own distinctive styles. It’s wonderful for those of us with strong personality so get misinterpreted all the time. In some cases, it might just salvage relationships that would seriously go off the rails if we didn’t have AI to rewrite something for us.
• And nowadays, when there are so many divisions between people, and nobody seems particularly interested in an extending himself for the sake of other people, AI can fill the gaps, bridge the divides, and make us seem a little less antagonistic and a little bit more sympathetic. Of course, you have to ask it right, and you also have to ask it to begin with, but this is the third really important, vital, and frankly invaluable capability that AI has.
Going on long enough. I dictated this whole thing myself. AI had nothing to do with writing it, so if it’s terrible, you blame me not ChatGPT. I probably should’ve put it through an AI scrubber – one of my persona teams that helps me do these things – but I just didn’t feel like it. I’m going for raw with this one. Gritty. Plain spoken and daring.
We’ll see how this lands.
| 2023-03-01T00:00:00 |
https://kaystoner.substack.com/p/so-what-good-is-ai
|
[
{
"date": "2023/03/01",
"position": 98,
"query": "universal basic income AI"
}
] |
|
Responsible AI: What Does It Take to Turn Principles into ...
|
Responsible AI: What Does It Take to Turn Principles into Practice?
|
https://www.govtech.com
|
[
"Jule Pattison-Gordon Is A Senior Staff Writer For"
] |
Another is 2020's AI In Government Act. It tells the OMB to advise agencies about using AI in ways that avoid harming civil rights or liberties, national ...
|
FROM IDEAL TO DETAIL
GOVERNMENT BUZZ
DO WE NEED NEW REGULATIONS?
A Center for Data Innovation Panel, moderated by CDI Senior Policy Analyst Hodan Omaar, discusses AI policy.
Screenshot
PRIVACY POINTS A WAY
IAPP's Katharina Koerner moderates a recent virtual conversation on "Leveraging Privacy Governance for the Responsible Use of AI"
Screenshot
GETTING STARTED
Many agree on what responsible, ethical AI looks like — at least at a zoomed-out level. But outlining key goals, like privacy and fairness, is only the first step. The next? Turning ideals into action.Policymakers need to determine whether existing laws and voluntary guidance are powerful enough tools to enforce good behavior, or if new regulations and authorities are necessary.And organizations will need to plan for how they can shift their culture and practices to ensure they’re following responsible AI advice. That could be important for compliance purposes or simply for preserving customer trust.A recent Center for Digital Innovation panel explored the legislative debate, while International Association of Privacy Professionals (IAPP)’s Principal Researcher for Technology Katharina Koerner toldhow organizations can use privacy practices to guide their approach to responsible AI strategies.Public institutions and organizations in Asia, Europe and North America tend to agree that “responsible” AI supports accountability, explainability, fairness, human oversight, privacy, robustness and security, according to IAPP’s recent report , which interviewed entities in the regions.Now developers, procurement officials and others may need more specific, fine-grained guidance on what tools and benchmarks to look to for helping achieve these goals.For example, while AI principles often call for preventing discrimination or bias, it’s not always clear how organizations can assess that they’re doing this properly. Organizations often want regulators to identify indicators or tools to use to check if they’ve successfully minimized bias or otherwise complied with responsible AI goals.“Companies really say … what is ‘non-bias,’ for example? How is ‘non-bias’ defined, because as humans and systems being built by humans, how is there no subjectivity in the systems?” Koerner said.The spotlight is on responsible AI.NIST recently released its Artificial Intelligence Risk Management Framework , a voluntary guide aimed at helping organizations and individuals use and create AI in responsible ways, and the White House also issued a voluntary Blueprint for an AI Bill of Rights in October 2022.State and local governments are making moves, too. New York City issued an executive order in 2019 calling for a framework and other processes to keep the city’s use of AI fair and responsible. But the city’s comptroller recently found agencies failing to ensure AI use is “transparent, accurate, and unbiased and avoids disparate impacts.”Meanwhile, Massachusetts lawmakers are considering AI regulations, including one proposal that would require large IT companies to disclose information on their algorithms and regularly run risk assessments, to prevent discrimination.In much of the world, responsible AI principles appear to be already upheld by various existing privacy and non-discrimination laws, but it would be helpful for organizations to be able to see the principles mapped out to the relevant legislation, Koerner said.In a February 2023 piece , Center for Data Innovation Director Daniel Castro suggested that few new regulations may be needed.He called for any forthcoming policies to “avoid slowing AI innovation and adoption” and said that regulations should “address concerns about AI safety, efficacy and bias by regulating outcomes rather than creating specific rules for the technology.”Such an approach would leave organizations free to decide when to use AI or humans to carry out tasks, so long as either method avoided producing prohibited harms. Castro wrote that current non-discrimination and worker protection laws already address many of the potential ill effects of AI — they just need to be applied to the technology.Enforcing non-discrimination laws on AI could be tricky, however.Agencies and officials may need new authorities to do so, said Brookings Institution fellow Alex Engler, during the CDI panel. Engler “studies the implications of artificial intelligence and emerging data technologies on society and governance,” per Brookings Individuals may get less information about the reasoning behind a decision when an algorithm, not a human, is the one making it, Engler said. That’s especially true if the AI system is proprietary, and it can make it difficult to tell whether the decision was made fairly.“If you move from a human process for something like hiring to an algorithmic process, probably, in most of those cases, you actually lose government protection,” Engler said. “It is harder to enforce anti-discrimination law; it is harder to go through a civil liability process to prove that you were discriminated against; it's possible you might have less insight into a system because you may not know an algorithm was run … . You might not be able to check if the underlying data was correct.”Now is a good time to consider what new measures are needed to help apply existing regulations and protections, Engler advised. For example, regulatory agencies could be given authorization to subpoena AI models and data if they strongly suspect a system is breaking the law.Fully understanding an algorithm’s effects also may require tracking its impacts over time on a larger scale, rather than just trying to decipher individual decisions, Engler said.“If we really want accountability, we have to find some way for some of these systems to have a more systemic evaluation,” Engler said.Guiding the federal government’s use of AI may not require all new policies — several helpful ones exist that have yet to be fully enacted, said Dr. Lynne Parker, during the CDI panel. Parker previously directed the National Artificial Intelligence Initiative Office and is currently director of the University of Tennessee, Knoxville’s AI Tennessee Initiative.One is 2020’s EO 13960 “Promoting the Use of Trustworthy Artificial Intelligence in the Federal Government.” It outlines ethical principles for most agencies to follow, calls for the Office of Management and Budget (OMB) to create policy guidance to support following these principles, and tells agencies to inventory the AI they use.Another is 2020’s AI In Government Act . It tells the OMB to advise agencies about using AI in ways that avoid harming civil rights or liberties, national security or the economy and to detail best practices for “identifying, assessing and mitigating” discriminatory impact and bias. It also creates an AI Center of Excellence.Another initiative is progressing: A 2020 task force has been studying how the U.S. can create a National AI Research Resource and delivered its report on the topic in January.Voluntary guidance around responsible AI use gives organizations flexibility and avoids locking entities into practices that could become outdated as the technology quickly evolves.On the other hand, voluntary guidance cannot compel disinterested organizations to change their AI use.“If you were hoping that law enforcement was going to implement some rules on itself, and its own use of AI tools — for instance, facial recognition or other surveillance tools — we haven't seen that yet,” Engler said.If federal policymakers decide to regulate, there may not be a one-size-fits-all approach.It’d be difficult to create one piece of legislation that tightly defines what AI is and which accounts for all the potential risks associated with the various ways it might be used, Engler said. He advocated for avoiding one overarching federal law and instead creating policies addressing specific sectors and specific use cases.“There is very little that you can say that's true about the AI in a safety component in a plane and the AI that's setting the interest rate for a mortgage,” Engler said.Paul Lekas, senior vice president for Global Public Policy for the Software and Information Industry Association (SIIA) said during the CDI panel that more needs to be learned about “general-purpose” and “generative” AI before any formal regulations are passed on it, but that the federal government can help by providing education and guidance on best practices.In some cases, communities may be the best ones to decide what appropriate AI use means to them, Parker suggested. She said universities could make their own choices on whether it is acceptable for their students to use tools like ChatGPT to conduct research or write journal articles.But for universities to make those decisions, they need first to understand exactly what the tool can and cannot do, and the associated risks.“That then comes back to a need for the collective technical community to help provide some training and education for everyone,” Parker said.Privacy is an essential aspect of responsible AI, and policymakers and organizations alike should pay attention.Lekas noted that state privacy laws often address AI and said getting a federal privacy law could set a foundation for later AI policies. That topic is actively debated: a House subcommittee meets today , March 1, to discuss a potential national data privacy standard.Whether required to or not, organizations may want to develop their own, internal strategies for putting responsible AI ideals into action. As they look to do so, organizations can use their existing privacy work and practices as a launchpad — sparing them from having to reinvent the wheel, per the IAPP report. Privacy impact assessments can be expanded to include items related to AI or can serve as models for responsible AI impact assessments, for example.This approach is gaining attention: Per IAPP’s report, “more than 50 percent of organizations building new AI governance approaches are building responsible AI governance on top of existing, mature privacy programs. “And emerging privacy-enhancing technologies (PETs) allow AI to analyze data while better preserving its privacy. Federated learning , for example, is a method for training AI on data that remains siloed in different devices, without having to share and pool the information into a central database.Organizations looking to create a strategy to govern their own use of AI should bring together various perspectives — including from their legal, security and privacy teams — to discuss which principles are relevant to their operations and to document a planned approach, Koerner said.Starting small is good: Organizations can look at one business case at a time, to consider how it relates to the agreed-upon principles for good AI use.It’ll also help to decide on common terms and resources, to keep everyone on the same page. For example, “privacy” can mean one thing in the context of math and engineering, and other in a legal context.“The NIST AI Risk Management Framework … is a great starting point for discussing how to identify, assess and mitigate the risks associated with the use of AI technologies, and what to include in an internal framework for decision-making and oversight of AI projects,” Koerner added.Early steps include inventorying all the AI systems the organization uses or develops, appointing people in each relevant business unit who’ll take point on ethical AI matters, as well as training internal staff and promoting an overall culture of responsible AI use.
| 2023-03-01T00:00:00 |
2023/03/01
|
https://www.govtech.com/artificial-intelligence/responsible-ai-what-does-it-take-to-turn-principles-into-practice
|
[
{
"date": "2023/03/01",
"position": 21,
"query": "government AI workforce policy"
}
] |
Artificial Intelligence and Public Values: Value Impacts and ...
|
Artificial Intelligence and Public Values: Value Impacts and Governance in the Public Sector
|
https://www.mdpi.com
|
[
"Chen",
"Ahn",
"Michael J.",
"Wang",
"Yu-Che Chen",
"Michael J. Ahn",
"Yi-Fan Wang"
] |
by YC Chen · 2023 · Cited by 55 — This article conducts a systematic literature review of the relationships between the public sector AI and public values to identify the impacts on public ...
|
To understand the perspective of government employees, we conducted an exploratory national survey of government employees in the U.S. We used Amazon’s Mechanical Turk (MTurk) because of its cost-effectiveness and comparability in terms of the data collected via traditional methods [ 98 99 ]. The survey was conducted in February 2021 and yielded 566 total responses. The respondents were current employees at the local, state, and federal levels of government in the U.S. The survey included questions that serve as the basis for quality assurance. After removing duplications, nongovernment respondents, and inconsistent answers to the quality assurance questions, we arrived at a final data set of 323 responses. This study draws mostly from the section of the survey that addresses the governance of AI use in government.
This empirical investigation builds on the key themes of public values, governance challenges, and governance solutions, which emerged from the systematic literature review. There are many stakeholders of AI use in government who need to be considered, and their perspectives differ [ 97 ]. Among these various perspectives, in this study, we choose to focus on the perspective of public employees because their opinions are crucial for the implementation of AI in government. Additionally, such a perspective is consistent with the original formulation of the taxonomy that is grounded in the perspective of civil servants [ 41 ].
The difference in the percentage of respondents believing that AI government use can have substantial or transformative improvement potential for public values has important implications. These government employees see the relatively strong potential for AI’s role in improving government efficiency and effectiveness in comparison with decision making and accountability. Such relatively strong potential suggests the relative efficacy of the government’s use of AI in affecting service-oriented values than other duty-oriented or society-oriented values. Accountability to the public as a society-oriented value has the lowest percentage of respondents, indicating substantial or transformative improvement potential among all values examined. This suggests that AI use in government has less impact on broader societal values.
Collectively, these results suggest a positive link between AI use in government and its potential for improving public values. These values include the duty-oriented one: the responsibility to citizens via better government decision making; service-oriented ones: efficiency and effectiveness; and the society-oriented one: accountability to the public. Moreover, the results show a favorable assessment of the potential for public value creation, with the majority of respondents indicating that each value has substantial or transformative potential. These results provide empirical evidence on the linkage and potential of AI government use for a positive impact on public values.
The responses regarding each public value, expressed in percentages, are presented in Table 4 . Regarding decision making as a duty-oriented public value, approximately 61% of the respondents indicated that AI has substantial or transformative potential for improving decision making. The majority of the respondents believed in the potential for public value creation via AI use in government decision making. Regarding the service-oriented public values, 65.3% of respondents noted that the use of AI has substantial or transformative potential to improve government effectiveness, and 77.7% had the same opinion with regard to efficiency. As for the society-oriented public value of accountability, 53.8% of respondents believed there is substantial or transformative improvement in accountability with the use of AI in government.
The survey questions explored government employees’ perception of the extent to which AI technologies would affect public values as aspects of government. The respondents were asked to indicate the extent to which they believe AI technologies will improve decision making, effectiveness, efficiency, and accountability. For each public value, the survey respondents were asked to indicate the extent as “no improvement” (1), “modest” (2), “substantial” (3), or “transformative” (4). The decision-making question aligns with the government’s duty-oriented values, as the government is responsible for making satisfactory decisions to serve the public. This type of decision making by the government is manifested by the elected officials and legislators who represent the citizens. Efficiency and effectiveness are frequently cited public service values, as demonstrated in the earlier systematic literature review. Accountability is a society-oriented value that captures the government’s role of acting in the public’s best interest.
Government employees have opinions about the impacts of AI use in government on public values. The existing literature discusses the concerns of government employees about the implementation of AI [ 97 ], but there is a gap in the empirical exploration of how these concerns are translated into the perceived impact of AI use on public values. Information and communication technologies hold the potential for digital transformation [ 100 101 ] and the creation of public values [ 102 ]. AI is also cited as an emerging technologies that has transformative potential due to the introduction of machine learning capabilities as well as its application to a wide range of public services. Given the current development of AI, a useful approach to understanding the impacts on public values is to explore AI’s perceived transformative potential.
Such a result provides some of the first evidence regarding the limitations of AI in considering a broad range of societal values, especially from the perspective of government employees. The specific societal concerns and their governance challenges could include job loss [ 1 90 ], threats to human autonomy [ 39 64 ], and the disadvantages of AI making value judgments [ 12 ]. Additionally, the extent to which such a recognition regarding AI’s limitations is shared by government employees can be a facilitating condition for a dialogue about governance solutions.
Regarding the inability of goal setting for AI use in government to fully consider societal values, 68% of the respondents were either neutral or in agreement with the statement (scores of 4–7). The mean score for the concern about losing discretionary authority is 4.372. The t-test result indicates that such a mean score is statistically greater than the neutral score of 4.0. We can infer that government employees do perceive that the use of AI in government cannot fully consider a range of societal values.
Regarding the question about the erosion of their discretionary authority, 68% of the respondents said they were either neutral toward or in agreement with the statement (scores of 4–7). The t-test result indicates that such a mean score is statistically greater than the neutral score of 4.0. The results indicate that government employees do perceive that the use of AI in their respective government agencies represents a threat to their discretionary authority. Such a result provides direct support to the concern about the erosion of discretionary power by bureaucrats as a result of AI use in government [ 40 ].
Regarding the likely negative impact of AI in government, as shown in Table 5 , 68% of the respondents said they are either neutral toward or in agreement with the statement, with scores ranging from 4 to 7. The mean score for the transparency question is 4.32. The single sample-test result indicates that such a mean score is statistically greater than the neutral position (a score of 4) at the 0.01 level of significance. From this, we can infer that government employees do perceive the likelihood that AI in government could have a negative impact on transparency. Such a result lends empirical support for the concern about the potential lack of transparency, as indicated earlier in the systematic literature review.
The public value challenge associated with transparency Is captured by the following survey question: “The development of AI in government is likely to negatively impact transparency due to the technical nature of the algorithm”. Respondents could indicate the extent to which they agree with the statement on a scale of 1–7, with 1 corresponding to “strongly disagree” and 7 corresponding to “strongly agree”. The survey question addressing whether discretionary power is connected to the governance challenge of data processing and outcomes is “The use of AI in my government agency will take away your discretionary authority”. The respondents could select their level of agreement on the same 1–7 scale. The survey question for the societal governance challenge addresses a broader set of societal values: “The goal setting of AI use in government cannot fully consider societal values beyond technical efficiency”. Again, the respondents could select their level of agreement on the same 1–7 scale.
One important data processing and outcome challenge regarding the use of AI in government is the extent to which AI makes public service decisions [ 12 103 ] and how much it could constitute the loss of human control [ 64 ]. One of the significant direct impacts of AI use on government employees is the potential loss of their discretionary authority in the face of the automation that accompanies AI. Scholars have cautioned that the removal of discretionary authority from street-level bureaucrats may consolidate that authority in the hands of information-system-level bureaucrats [ 40 ]. Moreover, concerns have been expressed about the potential negative impacts created by unchecked AI automation [ 103 ]. Government employees are likely to be concerned about the loss of the discretionary authority on which they have traditionally relied to make personalized and responsive public service decisions. Such concern is also likely to be more prevalent for street-level bureaucrats who interact directly with people and make decisions that can have a significant impact on people’s lives.
Government employees are likely to have some recognition of the potential negative impact of AI on transparency. Government policies and documents regarding the use of AI in government, such as those in the U.S. [ 54 ] and in European countries [ 6 ], have articulated transparency as a challenge for AI. These documents have likely created some awareness among government employees about the transparency challenge. Moreover, government employees, in their own exposure to AI either through personal use or in conversation with colleagues, have probably found it difficult to understand how and why certain algorithms are developed from machine learning. Consequently, there is likely some awareness among government employees about the negative impact of AI use on transparency.
4.4. Transparency and Participation as Governance Solutions to Artificial Intelligence Use in Government
The provision of transparency serves as a governance solution to public values. Explainable AI offers a form of transparency that helps humans understand why and how AI makes decisions. Such transparency can be further distinguished between transparency to whom and transparency at what stages of AI development and implementation. For government employees, the targets of transparency can be divided between internal-facing (government managers) and external-facing (the general public). To overcome the lack of transparency of government AI systems, government employees are expected to support making information about the development of the algorithms used in AI systems available to government managers. Government employees are also likely to be in favor of making such information available to the general public to achieve the goal of accountability.
For data quality, processing, and outcome solutions, transparency could focus on data, which are the materials from which the machine learns. Consequently, biases in data tend to be reinforced by the algorithms developed from them [ 49 ] and could have negative consequences for the welfare of individuals [ 104 ]. Data transparency is also foundational for audit efforts [ 105 ]. Government employees are likely to support such data transparency to inform themselves of any inherent bias in the data. With the government’s emphasis on being responsible for and accountable to the general public, it is also expected that government employees would support making data transparent to the public.
For societal governance solutions, collaborative governance is suggested by the systematic literature review as one of the main mechanisms [ 96 ]. Such collaboration can be among organizations and individuals in the public, private, and nonprofit sectors or among academia, government, and businesses. One of the less-explored dimensions of collaboration is between government and citizens regarding the development and implementation of AI, in which citizen participation is a critical step. Another dimension that lacks comprehensive research is the stages of AI development and implementation. In practice, government organizations have recognized the importance of process orientation for addressing stage-specific concerns [ 105 ]. However, scant scholarly research has explored the role of stages in addressing AI-related impacts. This study provides one of the first explorations of the important stage involving the participation of public officials and citizens. Such participation provides an important basis for collaboration.
The public value solution pertaining to transparency for government employees is captured by the survey question “Do you agree that the information on the development of algorithms used in the AI system should be made available to the government managers?” The respondents could indicate the extent to which they agree with the statement on a scale of 1–7, with 1 corresponding to “strongly disagree” and 7 corresponding to “strongly agree”. The survey question addressing the transparency of the AI system for the general public is “Do you agree that the information on the development of algorithms used in the AI system should be made available to the general public?” Again, the respondents could choose their level of agreement with the statement on the same 1–7 scale.
The data quality and processing governance solution pertaining to data transparency for government employees is captured by the survey question “Do you agree that the data the AI system uses should be made available to the government managers?” The question pertinent to data transparency to the general public is “Do you agree that the data the AI system uses should be made available to the general public?” For both questions, the respondents could select a level of agreement on the same 1–7 scale.
The questions about the societal governance solution focus on participation at a specific stage in the AI system life cycle. The life cycle of AI systems can include stages of goal setting, development, use, and impact assessment. Two survey questions explore government employees’ views regarding two groups of participants: public officials and the general public. More specifically, government employee respondents could answer the following survey question by indicating which stage is most important for public officials or whether all stages are important: “At which stage of AI development is it most important for public officials to participate? (a) goal setting for AI use in government, (b) development of AI systems, (c) use of AI systems in government decisions, (d) impact assessment of the AI-enabled decisions, (e) all of the above”. The second question replaces “public officials” with “the general public” and offers the same answer options to explore the respondents’ potentially different sets of expectations for participation by public officials and the general public.
As Table 6 indicates, the results reveal that the majority of respondents (74%) support making information on the development of algorithms available to government managers, but a lesser number (64%) also support sharing the same information with the general public. Based on single-sample t-tests, the mean values of the agreement scores are statistically larger than the neutral position (a score of 4) for both government managers and the general public. Therefore, we can infer that there is support among government employees for making the development of algorithms available as a transparency governance solution to advance transparency as a public value. Moreover, the mean level of agreement (5.285) for sharing information on the algorithms with government managers is higher than the mean level of agreement (4.932) for doing the same with the general public. Such a difference is statistically significant, and it suggests a position favoring more algorithm transparency for government managers than for the public.
Providing data transparency is a governance solution that belongs to the category of data quality, processing, and outcomes. The result reveals that a majority of the government employee respondents (80%) support providing information about the data used by the AI system to the government managers who are responsible for the service. Similarly, the result indicates that the majority of respondents (63%) also support sharing the same information with the general public. Based on single-sample t-tests, the mean values of the agreement scores are statistically larger than the neutral position (a score of 4) for both government managers and the general public. We can infer that there is support among government employees for making information about the data used by the AI system available as a solution to the governance challenge of the lack of transparency.
The mean level of agreement (5.285) for sharing information about the development of algorithms with government managers is higher than the mean level of agreement (4.932) for doing the same with the general public. The difference in these levels of agreement is statistically significant and suggests a position favoring more transparency for the data used by the AI systems for government managers than for the general public.
Participation by stage is the focus of exploration for the societal governance solution to a lack of transparency. The survey results reveal support for participation by both public officials and the general public. As shown in Table 7 , approximately 36% of respondents consider it important for public officials to be involved in all the processes of the AI system. Among all the stages, 27% of respondents suggest that AI system development is the most important stage for public officials to be involved in. Other stages are also considered to be the most important stage for participation: goal setting (14.6%), decision making (15.5%), and impact assessment (7.1%). In addition, 25.7% of survey respondents regard the use of AI in government decision making as the most important stage for public participation. All of the above stages (23.8%) and the stage of AI system development (21.1%) follow closely as being considered as the most important for public participation.
The results reflect the opinions of government employees regarding what stages are the most important for participation by public officials and members of the general public. The survey respondents expect public officials, more than the public, to participate in all stages of the process. Such a view could stem from the expectation of public officials responsible for all stages of the life cycle to be accountable for AI use in government. Survey respondents ranked the use of AI in government decision making as the most important stage for public participation. This opinion could result from the perceived effectiveness of having the public participate directly in AI-enabled government decision making. Therefore, the decision is informed by the members of the public who have information relevant to the decision and provide the perspective of service recipients to ensure better decisions.
| 2023-01-14T00:00:00 |
2023/01/14
|
https://www.mdpi.com/2071-1050/15/6/4796
|
[
{
"date": "2023/03/01",
"position": 34,
"query": "government AI workforce policy"
}
] |
Comparing Health Workforce Policy during a Major Global ...
|
Comparing Health Workforce Policy during a Major Global Health Crisis: A Critical Conceptual Debate and International Empirical Investigation
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Ellen Kuhlmann",
"Clinic For Rheumatology",
"Immunology",
"Hannover Medical School",
"Carl-Neuberg-Strasse",
"Hannover",
"Sociology Of Health",
"Health Systems",
"Faculty I",
"University Of Siegen"
] |
by E Kuhlmann · 2023 · Cited by 13 — ... government (until December 2022). Most importantly, we move beyond ... Commento ai Principali Dati Del Conto Annuale Del Periodo 2009-2018. Ministero ...
|
We begin with briefly introducing our sample. Table 2 provides an example of a typical comparative descriptive approach informed by major health system categories and basic quantitative indicators related to the research topic, based on expert information, published reports, and public statistics (mainly OECD, national government for Brazil). We refer to the first two major waves of the COVID-19 pandemic, from the declaration of a pandemic in early 2020 until the summer of 2021.
3.2. An Explorative Qualitative Case Study Design: Comparing Health Workforce Governance and COVID-19 Policy in Context across Countries
3.2.1. Brazil Brazil has a Unified Health System (SUS), conceived during the 1980s based on the country’s democratization process. The SUS is guided by three principles: the idea of a universal and comprehensive right to healthcare services organized into different levels of care; decentralization, which makes all federative entities responsible for service provision; and social participation in health policies. The SUS works within a federative logic, in which the federal government, states, and municipalities are co-responsible for the finance, regulation, and implementation of services. Free and universal healthcare is organized into three sectors: primary, secondary, and tertiary care. Primary care is responsible for prevention and promotion and is offered in health clinics. Secondary care provides specialized services in clinics, while tertiary care is focused on hospitalization and more complex health services. The levels of care are integrated and offered cooperatively between states, municipalities, and the federal government. The federal government is responsible for the national coordination of the SUS, including policy development, planning, financing, and control. State governments have responsibility for regional governance, coordination of some strategic programs, and the provision of specialized and tertiary services. The 5570 municipalities are responsible for implementing primary care policies and part of secondary care policies. The system’s financing is also governed by the three federative entities, which are obliged to allocate a minimum amount of 15% to 22% of the budget to the health system [48]. When observing the size and vast experience of the SUS, including in previous public health emergencies, it was expected that Brazil would respond well to the COVID-19 pandemic. However, in the spring of 2021 the country was ranked as the worst case in the world with nearly 600,000 deaths [49]. This raises the question: what went wrong? The explanation is directly related to the position of past President Bolsonaro and the health ministry. The President was a denialist of the pandemic. From the beginning, he tried to minimize the risks, creating a supposed conflict between health measures and economic measures. He was against isolation policies and attacked governors and mayors who implemented policies of physical distancing, mandatory use of masks, and quarantine; he also opposed vaccination and postponed the purchase of vaccines for months [48,49]. Current investigation shows that vaccine purchases were made through a vast corruption scheme. The effects of the President’s speeches go far beyond rhetoric: they destabilized the SUS and hampered coordination. The health ministry did not exercise its coordination role in relation to the funding of pandemic policies and the regulation of the health workforce. This created a federal conflict, as mayors and governors were facing the pandemic without support and resources and had to take individual action. In addition, the President’s denial speeches had a practical effect on the health workforce. Examples are the pressure on HCWs to adopt ineffective medications and the strengthening of the anti-vaccine discourse [48]. Concerning sectors, the SUS is one of the largest public health systems globally and the health workforce comprises more than 6 million HCWs. However, there were still severe shortages due to a lack of specialized physicians and an unequal distribution of HCWs across the national territory. Although access to healthcare has grown considerably since its creation, the SUS still has problems with the quality of services, which are strongest in specialized and hospital care. Brazil is one of the most unequal countries in the world, and the SUS reflects these inequalities. Despite creating several policies that seek to address inequalities, there are still many inequalities in relation to both access to care and quality of services, comparing region, race, and gender [10,13,14,16]. In relation to the organizational and professional dimension, the health workforce had to work during the pandemic without resources within a context of conflicts and ambiguities [14], facing a stressful environment, and increasing demand from patients. Surveys carried out in April 2021 showed that more than 50% of the HCWs did not receive adequate PPE, 70% did not receive training, 65% did not feel supported by the government, and 80% had mental health issues [13,14]. Brazil has the largest number of nurses who died of COVID-19 in the world. In August 2020, almost half of the nurses who died from COVID-19 were Brazilian [50]. Concerning socio-cultural dimensions, these conditions further exacerbated inequalities, although they jeopardized the entire health workforce, Research evidence shows that women and black HCWs were most strongly affected by the pandemic [51]. Inequalities are also evident between professions. More powerful and better-paid professions, such as physicians, are in a better situation than less institutionalized professions, such as community HCWs [13]. The Brazilian case illustrates how political denialism and missing coordination threaten the HCWs, even in a well-established and experienced public health system [14].
3.2.2. Canada In Canada, healthcare services are mostly under the responsibility of provincial (sub-national) jurisdiction and financed through income tax payments (Beveridge model). Universal health insurance guarantees the coverage of medical and hospital care, other health and social care services are at the discretion of the Province. Notably, the system is labelled “health insurance” but is not financed by insurance contributions but mainly through taxes. The federal government plays a relevant role, particularly by using its spending power to uphold national standards for the coverage of medical and hospital services. Yet Provinces and Territories enjoy high autonomy; they are obliged to provide about 80% of total funds, plan health services, and decide on governance arrangements. Canada comprises ten Provincial healthcare systems and three Territorial healthcare systems with their organizational arrangements and priorities and should therefore not be considered as single healthcare system [52]. However, the health workforce shortage is considered a national crisis with more than 100,000 vacant jobs in healthcare [53]. From a system perspective, the two largest Canadian provinces, Ontario and Quebec, were severely impacted by the pandemic from the beginning, seeing dramatic death tolls in the most vulnerable segments of the population, namely frail elderly residents of long-term care (LTC) homes [54]. Alberta had considerable trouble confronting subsequent waves of the pandemic; the healthcare system was overwhelmed by the fourth wave of the pandemic. Like other jurisdictions, all Canadian Provinces struggled to ensure health system capacity to accommodate surges of COVID-19 cases and variants, which significantly reduced the ability to respond to non-COVID-19 care needs. British Columbia seemed to be better equipped to face the pandemic and to limit its detrimental effects on population health and the delivery of care [55]. The federal government played a key role in the procurement of vaccines, the supply of personal protective equipment (PPE), and ventilation equipment. During the first wave, the military forces were deployed at the request of two provinces, Quebec and Ontario, to help mitigate workforce shortages in the long-term care (LTC) system. Alberta contemplated this option during the fourth wave. Provincial governments and professional colleges also responded to the new health workforce needs and promoted several health system adaptions; for instance, the establishment of a remuneration scheme to encourage the development of tele-consultations in medicine and skill-mix changes/task-shifting efforts to increase the scope of practice of nurses, pharmacists, and other health professionals. From a sectoral perspective, the system is hospital-centered with major quality of care and safety issues in the LTC sector, as underlined by a recent report commissioned by the Royal Society of Canada [56]. Access to PPE outside the hospital sector was severely limited with dramatic consequences; for example, LTC workers in Quebec faced an approximately 10 times higher risk of contracting COVID-19 compared to the general population [30]. Considering professions and organizations, the nursing profession is emblematic of the health workforce crisis. A report on the future of the nursing profession estimated that 27.1% of nurses plan to leave the profession [57]. Compulsory overtime work and stressful working conditions are considered as the main reasons for job resignations. Other professions or occupational groups, such as healthcare assistants, also face severe shortages. Provincial governments have taken several efforts to respond to health labor-market shortages and the growing demand for HCWs, including fast training and an increase in payment. However, no national database exists and effective health workforce policies that might respond to the health workforce crisis are lacking. There are also signs that middle-management positions in healthcare are difficult to fill, which might reveal more general problems of leadership in healthcare. Health organizations and HCWs have done their best to compensate for health system problems. This might help in voicing for and achieving better recognition of all HCWs in future. Health organizations and HCWs also developed new approaches to the provision of care and improved collaboration across professions, which might be further developed for pursuit in the aftermath of the pandemic [53]. At the same time, the pandemic has revealed important health system problems [30], including important segments of the health workforce that appear to be undervalued, such as, for instance, nurses and middle managers. In relation to socio-cultural effects, the policy deficits affected women and migrant HCWs most; public discourse tends to reproduce prevailing gender inequality in relation to the valuation and recognition of work [30]. Gender often intersects with racial inequality. During the crisis, health workforce policy sought to quickly expand the mobilization of asylum seekers. There are high numbers of recent immigrants and members of racialized groups, especially in urban areas. These groups faced higher risks of contracting COVID-19 at work due to poor protection and work conditions, and at home due to poor housing conditions [30].
3.2.3. Germany Germany counts as a welfare state with a classic Bismarckian-type social health insurance (SHI) system. The system is decentralized and federalist and based on participatory governance. It is strongly shaped by corporatism with the medical profession as a powerful actor integrated into the policy process, creating complex negotiation processes between stakeholder groups and between national and regional levels of policymaking. The government has delegated power to a joint self-governing and self-administering body, the Federal Joint Committee, which is based on the SHI sickness funds and SHI Physicians Associations as the two main pillars and the Hospital Society. In healthcare policy, the states (Länder) have strong regulatory powers with some centralized regulation and coordination efforts, which were reinforced during the pandemic. The healthcare system is well-resourced and financed primarily via SHI contributions [58,59]. Health workforce staffing levels are among the highest in OECD countries, yet a shortage of all groups of HCWs is a serious problem and recruitment of migrant HCWs is on the increase [18]. Germany faced severe waves of COVID-19, but was less strongly hit than the neighboring countries and lockdown policies were more moderate [60]. The institutional conditions of federalism, decentralization, and corporatism shape the politics and the substance of HCW governance [7]. At the system level, we find well-resourced, but poorly integrated, health and education systems with overall weak public-health institutions. The Federal Health Ministry took action to increase the capacity of public health [61] and to introduce financial compensation and rewards. A compensation scheme for office physicians was established and a budget was provided for a financial bonus for nurses (single payment). Vaccination policy is another example of centralized efforts in an otherwise decentralized system. The vaccination prioritization was decided centrally, while the management was delegated to the states. Some efforts to improve HCW surveillance and create a national database and monitoring system were undertaken by the German Public Health Institute (Robert Koch Institut) [62]. However, data sources and information on the protection of HCWs are still poorly developed, although quality data are available. At the sectoral level, Germany is known for its large and over-resourced hospital sector [58]. In contrast, the public health sector is small and poorly developed; during the first wave of the pandemic, a new program was introduced aiming at increasing staffing levels and strengthening public health competencies [61]. However, public health leadership is still lacking or poorly developed. Furthermore, HCW surveillance and protection strongly varied between sectors; personal protective equipment (PPE) and surveillance measures are strong in hospitals, but weaker in the LTC sector, affecting especially nurses and carers. Research evidence suggests that the COVID-19 infection risk of hospital workers might be largely in the range of the general population, as documented for a large academic hospital [63]. The meso-level, the organizational conditions, played a key role in the protection and preparedness of HCWs, which also explains the significant sectoral differences. Innovation and change were often stronger on the organizational level than on the system level, but the outcomes were more diverse and sustainability may be more hampered. The skill mix and professional and sectoral collaboration improved in some areas and new ad hoc solutions were established; some up-skilling was also observed, e.g., for healthcare assistants, and public health workers [2]. However, there are currently no signs that this may change the occupational field and/or the hegemony of the medical profession. HCW protection was overall strong but focused on PPE, surveillance, and vaccination, while little if any attention was paid to the mental health needs of HCWs, despite an increase in stress and uncertainties during the COVID-19 pandemic [7]. Concerning social inequalities, gender equality is defined by law and policies are in place in the public sector (similarly in many private organizations). However, little action was taken to mitigate the gender bias of the COVID-19 pandemic, affecting women and girls most [8,15,51]. There is an overall lack of recognition of female expertise at all levels of policymaking and also in the media; few women are in high-level decision-making bodies, especially during the first wave of the pandemic. In relation to migrant HCWs, specific policy agreements were in place to facilitate cross-border HCW mobility within the EU when borders were closed, especially bi-national agreements in border regions. There was a strong interest in maintaining migrant HCWs in the country, but health policy did not take care of the needs of foreign HCWs during the pandemic. There was some support at the organizational level to maintain or attract foreign HCWs, but this was highly diverse and did not achieve policy changes.
| 2023-03-13T00:00:00 |
2023/03/13
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC10049040/
|
[
{
"date": "2023/03/01",
"position": 49,
"query": "government AI workforce policy"
}
] |
2023 Winter Policy Forum Headshots & Bios
|
2023 Winter Policy Forum Headshots & Bios
|
https://www.naswa.org
|
[] |
Courtney Arbour is the Director of the Texas Workforce Commission's Workforce Development Division where she oversees an integrated workforce development ...
|
Stephanie Beckhorn, Director, Employment & Training, Michigan Department of Labor and Economic Opportunity
For the past two decades, Stephanie Beckhorn has played an important and growing role in Michigan’s workforce and economic development.
Beckhorn has been lending her talents to Michigan’s workforce development efforts since 2001 when she joined the Bureau of Workforce Transformation. In 2013, she went on to serve as Director of Workforce Policy and Strategic Planning for the Michigan Workforce Development Agency and in 2019, at the beginning of Governor Whitmer’s term, she served as the acting department director.
Today, as the Michigan Department of Labor and Economic Opportunity’s Director of the Office of Employment and Training, Beckhorn provides leadership and guidance for the Bureau of Services for Blind Persons, Michigan Rehabilitation Services and Workforce Development.
She approaches projects in an inclusive manner and seeks solutions that are effective and replicable. Whatever challenges Michigan has faced, Beckhorn’s collaborative, data-driven approach has enabled Employment and Training to adjust swiftly to evolving economic demands.
Under her direction, Employment and Training administers key workforce programs and systems that equips both employers and workers with resources critical for their success, including vocational rehabilitation to support individuals with disabilities with gaining or retaining employment.
Beckhorn works directly with federal, state and local level partners to provide the connections, expertise and innovative solutions to drive continued business growth, build vibrant communities, and attract and retain key talent to fill Michigan’s vast pipeline of opportunities. This work is accomplished through federal and state programs focused on job preparedness, career-based education, worker training and employer assistance.
Beckhorn is a Certified Business Solutions Professional (CBSP) and earned a Bachelor of Science degree from Michigan State University.
| 2023-03-01T00:00:00 |
https://www.naswa.org/conferences/2023-winter-policy-forum-headshots-bios
|
[
{
"date": "2023/03/01",
"position": 52,
"query": "government AI workforce policy"
}
] |
|
Breaking into the Generative AI Industry: Your Simple ...
|
Breaking into the Generative AI Industry: Your Simple Guide to Landing a Job
|
https://www.linkedin.com
|
[
"Lisa Bouari",
"Nick Chow",
"Thomas G. Martin",
"Pankaj Kumar",
"Director",
"Head Of Connectivity",
"Networks",
"Padma Kevin",
"Technical Leader",
"Intuit"
] |
Here is my handy guide to getting a job in Generative AI. Step 1- Master the Tools Play. Experiment. Then play some more. These tools should intrigue you.
|
Do you wish you got a job at Amazon in 1995? Truth be told, it wasn't evident to everyone back then that this man would later become the world's richest man and create thousands of millionaires among his early employees.
Source: CNBC
You could have as likely got a job at Pets.com or theglobe.com, thinking it was your ticket to riches in the late 90s. Or maybe you wish you were one of the 13 employees at Instagram before the sale to Facebook. Likewise, there is a graveyard of early mobile startups that didn’t have the success of Instagram.
The Internet revolution of the 90s and the mobile technology boom of the 2010s brought about substantial societal changes. They changed the way that humans worked and interacted. Even if the rocketship you chose didn’t take off as you hoped, you still had an incredible experience. Just being in the right industry early sets you up for so much future success.
If you feel you may have missed (or not been born for) the early internet or mobile revolutions, don’t fret. As I have written about many times before (starting last August with “The One Technology You Should Freak Out About”), what we are on the cusp of with Generative AI will be much bigger than either. The world is about to change, and we are still on the ground floor. (Remember, ChatGPT only came out in late November)
If you want to pivot your career, you can. Now is the time. It doesn’t mean you even have to leave your company. Soon, these tools will be used by all companies in every industry. (Why not be the person to introduce it to yours?)
Interested? Well, if you are, read on. Here is my handy guide to getting a job in Generative AI.
Step 1- Master the Tools
Play. Experiment. Then play some more.
These tools should intrigue you. If they do, that’s great. That is your unfair advantage.
You are curious and love to see what these Large Language Models (like GPT-4) can create. Generally speaking, you need ZERO coding skills to use them. All you need is a device with internet access (if you’re reading this, you got that covered) and an inquisitive mind. With that, you’re good to go.
Generated by Michael Todasco on Midjourney on March 30, 2023 using the prompt "a coloring book page of rocketships and space --v 5 --q 2 --s 250 "
Start with ChatGPT and see how it can help you plan for the weekend. Don’t even worry about how this can apply to your job. Just play with it and see what happens. Or, don’t Google anything for a day and only use ChatGPT. What’s that experience like? Also, sign up for Midjourney and do something like create a coloring book page to email your nephew. Obviously, these are just examples. But the point is for you to play around just to see what is possible. Then discover some other new tools. And do this daily.
In addition to playing, you’ll want to read about the industry. Nathan Lands publishes a great newsletter called Generative AI Weekly. Ben’s Bites is also quite good, and, if I may shamelessly self-promote, I often talk about things that I find interesting in AI Conversations.
Finally, go on Reddit, LinkedIn, Discord, or an IRL event and talk to people in the space. Ask questions. The community is open, and people are willing to share and help!
If you do this for an hour a day, you will have learned so much in a month. Dare I say, after 30 hours of going down these rabbit holes, you will start to become an expert. So much for the 10,000-hour rule!
Step 2- Wow Someone!
The first time I used a Generative AI tool was Sudowrite in 2021. I had it write some lines in the voice of a computer in a story I was writing. While primitive by GPT-4’s standards, I was utterly blown away. I ran upstairs to show my wife how a computer generated this text for me. It felt like magic.
Now that you’re an expert in Generative AI, it’s time you wow someone with what you know. Show someone else that magic!
Make an Impact at Your Current Company
If you want to do something in your own company, take a step back and consider the major problems your company is facing. (You could ask ChatGPT that very question.) What is it that your boss is always talking about? How may the tools you have been using help? Or, if your boss isn’t open-minded to this, is there a future-thinking VP you could contact? Ultimately you don’t want to reach out to them and say, “I think Generative AI is cool. We should do something.” As they say in writing, “show, don’t tell.”
Solve a problem for them. (Now, don’t drop a bunch of proprietary customer data into a large language model, use your judgment on what is appropriate.) If someone is planning a two-day offsite in a few months, have ChatGPT develop an agenda with speakers and facilities you could use. Or use Beautiful.ai to make a presentation. Or brainstorm with an AI on fifty ways to reduce costs with vendors (you could even have the AI negotiate a lower rate). Whatever the problem, AI will help you find a solution more effectively. Show a little example of how it can be effective, and that will open the door to something more. Keep using it, and become the evangelist of the tool in your company.
Find ways to help others using AI, and people will get on board. Run a session showing them what you used the tools to create. Some people may be weary, but you can gently remind them, “An AI isn’t going to take your job, but a human using AI will.”
Pursue Opportunities in the Generative AI Space
If you want to work for a company in the Generative AI space, you want to find the right role and then wow them! I searched for Generative AI jobs in the Bay Area on Linkedin, and the first one that popped up was for an AI Product Manager. In the job responsibilities section, the first thing it says is, “Drive clear product definition and roadmap to achieve business goals, with well-defined metrics and indicators for success.” So take an hour with Generative AI tools and show them what you can do as part of your application. What if you trained an AI model (like ChatGPT) on everything about their company? Pull in any articles, or press releases, take things from their website and maybe even from a few competitors, and train ChatGPT on it. (After your month of research, you can easily do this.) Then ask ChatGPT to “build a roadmap to achieve business goals with well-defined metrics and indicators for success.” It won’t be perfect, but that’s not the point. Take the output, make some changes to make it more reasonable, and then include it as part of the application. And be upfront about it. Tell them in the application, “I pretrained an AI model on your company and competitors x,y, and z and had it develop a roadmap. I know it isn’t perfect, but I wanted to share one of the ways I would use AI if I had this job.” 99% of applicants will not go to that level of effort, and you will stand out!
And that’s the whole point when getting a job- you need to find ways to stand out. When I was at PayPal, we’d get 100s of applicants with amazing backgrounds for any role we posted. As a hiring manager, it is tiresome. You want to do something to bring your name to the top of the pile! Then rinse and repeat with other jobs you find. Soon enough, you’ll land something in the world of Generative AI.
Start Your Own Generative AI-Based Business
And, of course, you don’t need to work for someone else. You can always build your own company using Generative AI tools. There are thousands of businesses just waiting to be formed. It has never been easier to create a business than now! If you do that, let me know. I always enjoy chatting with entrepreneurs in the space.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/breaking-generative-ai-industry-your-simple-guide-landing-todasco
|
[
{
"date": "2023/03/01",
"position": 1,
"query": "generative AI jobs"
}
] |
|
The Impact of Machine Learning on Business Processes
|
The Impact of Machine Learning on Business Processes
|
https://digitalcxo.com
|
[
"Myrtle Bautista"
] |
With the advancements in technology, more and more companies are adopting flexible workplace structures. Machine learning helps employees working remotely to ...
|
Machine learning has truly revolutionized the way businesses operate. It has done so by introducing new ways of analyzing and processing data. By automating certain tasks and enhancing predictive capabilities, it also has the immense potential to improve business efficiency and foster innovation. In this article, we will examine just how this cutting-edge technology has changed—and continues to shape—the modern business landscape.
How Machine Learning is Transforming Businesses
Here are some of the top ways by which machine learning is taking over industries today.
Enhanced efficiency
One of the most significant benefits of machine learning is its ability to automate and streamline tasks. This can range from simple to-dos like data entry to complex processes like supply chain management. By handling repetitive company chores, the technology allows the more efficient allocation of resources towards more brain-intensive exercises, such as creative thinking and strategy development.
Optimized operations
With improved efficiency comes optimization. For instance, let’s take a look at supply chain management. With the help of machine learning algorithms, industries can better predict demand, beef up inventory control, and identify inefficiencies. As a result, delivery times are expedited, costs are reduced, and customers become more satisfied. Automating mundane tasks also means that employees can focus on more significant aspects of their job, such as building relationships with suppliers.
More flexible work setups
With the advancements in technology, more and more companies are adopting flexible workplace structures. Machine learning helps employees working remotely to find ways to boost productivity. For instance, machine-learning-powered virtual assistants can help work-from-home professionals stay organized, manage their time, and remain on top of their tasks. These powerful digital helpers can also help schedule meetings, set reminders, and provide timely notifications about deadlines.
Additionally, artificial intelligence (AI) technology makes it easier for organizations to manage tasks even when individuals are physically off-site. AI also enables remote workers to connect with other team members, regardless of physical location, by providing virtual communication tools like voice and video conferencing and instant messaging services.
More innovation
Machine learning also enables businesses to foster innovation. Because it can analyze large amounts of data, it can greatly bolster the creation of new products, revamp or tweak existing ones, and develop advanced strategies for growth.
Better decision making
The efficient extraction of data can go a long way in helping businesses make more informed decisions. For example, in the financial sector, machine learning is used to assess the credit-worthiness of borrowers. By analyzing various data points, such as credit history, income, and employment status, its algorithms can assign accurate credit scores. This empowers financial institutions to make better lending recommendations and reduce the risk of defaults.
Elevated customer satisfaction
With substantially accurate information available through machine learning, industries can better understand their customers’ preferences and needs. They can then tailor their products and services to meet these requirements better. The result is satisfied customers, and this opens up new opportunities for cross-selling and upselling.
Yet another example is how machine learning is being used in the retail industry. With the technology, brands can personalize their marketing campaigns to better target individual customers. This not only increases the effectiveness of their marketing efforts but also creates more personalized shopping experiences.
Bolstered fraud detection
Machine learning algorithms can also detect fraudulent transactions in real time. With the ability to go through and process historical data with ease and speed, this type of powerful computing can quickly pinpoint patterns in fraudulent activities, detect suspicious behaviors, and flag them for further investigation. Financial institutions can therefore become more equipped to take immediate action and protect their customers.
Heightened compliance with regulations
Companies can leverage machine learning to streamline and automatically generate reports and monitor transactions. This way, compliance with regulations can be done more efficiently and with greater accuracy.
The Challenges of Machine Learning
Integrating machine learning into business processes is not without its challenges. For example, data engineers and scientists must continuously work to ensure that databases for training machine learning algorithms are accurate and unbiased. This is especially critical when it comes to decision-making processes with significant real-world consequences, such as healthcare. Another concern is that employees may not have the necessary skills to work with machine learning tools and efficiently integrate them into existing business processes.
To overcome these hurdles, businesses must invest in the necessary infrastructure, tools, and training so that everyone can effectively transition. By doing so, they can unlock the full potential of machine learning to drive business growth and success.
A Final Note
From streamlining mundane tasks to optimizing scheduling, to better decision making and improving communication, machine learning is clearly changing the way we do business. With the help of AI technology, industries can become more efficient while still accommodating their employees’ needs and keeping within budget. Thus, they should take advantage of this rapidly advancing field to stay competitive and get ahead in today’s dynamic market. The future of machine learning in the workplace looks bright!
| 2023-03-01T00:00:00 |
https://digitalcxo.com/article/the-impact-of-machine-learning-on-business-processes/
|
[
{
"date": "2023/03/01",
"position": 14,
"query": "machine learning workforce"
}
] |
|
The Rise of the Machines: How AI is Taking Over Human ...
|
The Rise of the Machines: How AI is Taking Over Human Jobs
|
https://www.linkedin.com
|
[
"Bernard Marr",
"Jonathan Medved",
"Plan A Technologies",
"A.F.H Dhrubo",
"Research Assistant At North South University",
"Laxminarayanan Sridharan",
"Associate Director At Cognizant Technology Solutions",
"Sanjay Seth Mba",
"Psychometrician For Marketing Research",
"At Brandsogram.Com"
] |
With the help of machine learning algorithms, AI can perform tasks that were previously thought impossible for machines. ... workforce over the long term.
|
The Rise of AI
Artificial Intelligence (AI) has been a topic of discussion for decades, but it is only in recent years that we have seen its true potential. AI has already made significant strides in various industries and is now poised to take over many jobs that humans previously did.
In this article, we will explore how AI will take over human jobs in the future, the implications of this shift, and what we can do to prepare for iAI has already begun to revolutionize various industries such as healthcare, finance, and transportation. With the help of machine learning algorithms, AI can perform tasks that were previously thought impossible for machines. For example, AI-powered chatbots can now provide customer support, and self-driving cars are becoming a reality.
As AI continues to improve, it will become more efficient and cost-effective than human labor. This will lead to an increase in demand for AI-powered solutions and a decrease in demand for human workers.
The Impact on Jobs
The rise of AI will have a significant impact on the job market. Many jobs that are currently done by humans will become automated, leading to job displacement and unemployment. According to a report by McKinsey, up to 800 million jobs could be lost to automation by 2030.
However, not all jobs will be affected equally. Jobs that involve repetitive tasks or those that require little creativity or critical thinking are most at risk. On the other hand, jobs that require empathy, social skills, and creativity are less likely to be automated.
here is an example of how AI could potentially impact certain job categories over the next decade:
This table is just a rough estimation and should not be taken as a definitive forecast of job impacts. The level of impact can vary widely depending on factors such as the specific tasks involved in each job, the level of automation available, and the demand for these jobs in the future. However, it provides a rough idea of how certain job categories could be impacted by AI over the next 10-20 years.
In general, jobs that involve routine or repetitive tasks, such as data entry or truck driving, are at a higher risk of automation than jobs that require higher levels of creativity, emotional intelligence, or human interaction, such as teaching or healthcare. However, it's important to note that even jobs that are considered low-risk today could be impacted by AI in the future as technology continues to evolve and improve.
Preparing for the Future
To prepare for the future, we need to start thinking about how we can adapt to the changing job market. One solution is to focus on developing skills that are less likely to be automated. These include creative problem-solving, emotional intelligence, and social skills.
Another solution is to invest in education and training programs that prepare workers for the jobs of the future. This includes programs that teach coding, data analysis, and other skills that are in high demand in the tech industry.
Ethical Considerations
The rise of AI also raises ethical considerations. As AI becomes more advanced, it could potentially make decisions that have significant consequences for humans. For example, an AI-powered medical diagnosis system could misdiagnose a patient, leading to serious health complications.
To prevent these issues, it is important to develop ethical guidelines for the development and use of AI. This includes ensuring that AI is developed in a transparent and accountable manner, and that it is used to benefit society as a whole.
Conclusion
In conclusion, AI will undoubtedly take over many jobs that were previously done by humans. While this may lead to job displacement and unemployment, there are steps we can take to prepare for the future. By focusing on developing skills that are less likely to be automated and investing in education and training programs, we can ensure that we are ready for the jobs of the future.
Furthermore, it is important to consider the ethical implications of AI and to develop guidelines that ensure its responsible use. By doing so, we can harness the power of AI to benefit society as a whole.
Here's an example of a table that outlines some job categories that are less likely to be impacted by AI in the near term:
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/rise-machines-how-ai-taking-over-human-jobs-mohit-uppal
|
[
{
"date": "2023/03/01",
"position": 18,
"query": "machine learning workforce"
},
{
"date": "2023/03/01",
"position": 67,
"query": "artificial intelligence workers"
}
] |
|
Handling Uncertainty with Forecasting and Capacity ...
|
Handling Uncertainty with Forecasting and Capacity Planning — Part 3 of The Complete Guide To Workforce Optimization
|
https://medium.com
|
[
"Giulia Burchi"
] |
Covid testing center data could correlate with hospital ICU demand. Various artificial intelligence (AI) and Machine Learning (ML) methods are commonly used for ...
|
Handling Uncertainty with Forecasting and Capacity Planning — Part 3 of The Complete Guide To Workforce Optimization Giulia Burchi 5 min read · Mar 29, 2023 -- Listen Share
Our last two articles in this series outlined how to:
Create a catalog of employee skills and work task types so that we have a common language with which to talk about workforce capacity and work demand, and benchmark activity performance rates for the various task types so that we can determine how much workforce capacity is needed to fulfill a given amount of work.
We are now almost ready to start optimizing our workforce, meaning matching workforce capacity (employees by skill) to work orders or work demand. If you’re new to workforce optimization, this may sound easy — and in some industries it is. But in others, it quickly gets extremely complex. Let’s explore why.
What is Forecasting?
For workforce optimization, Forecasting is about predicting future demand for work to be done.
Some future demand is easy to forecast. For instance, a hotel chain may know how much catering demand will be needed next month based on banquet room reservations.
Other types of workforce demand are harder to predict. Imagine a call center that handles a large volume and variety of calls or a hospital that tends to patients afflicted with any number of illnesses and injuries. There could be many factors that influence workforce demand to varying degrees, such as:
Weather data could correlate with certain illnesses
Point-of-sale data could correlate with demand for call center support tied to certain products
Satellite parking lot data could be an indication of crowding indoors, which might correlate with disease spread
Local crime rates could correlate with gun or knife injuries
Covid testing center data could correlate with hospital ICU demand.
Various artificial intelligence (AI) and Machine Learning (ML) methods are commonly used for forecasting demand in situations like these. At a very high level, they work by analyzing large amounts of historical data and deriving a mathematical model (formula) based on the detected drivers of that demand. This model can then be applied to predict the future. This “demand forecast” can then feed any downstream systems that support decision making, such as workforce planning and scheduling systems that we’ll talk about in the upcoming articles.
What is Capacity Planning and Why is it Hard?
Workforce capacity planning is about ensuring that you have the right size and mix of workforce to satisfy the forecasted demand.
This may sound easy, but workforce capacity planning is quite challenging because human workforce capacity is not instantly available on-demand in discrete time buckets the way, say, cloud computing resources are available. Workers are hired, trained and retained on a long-term basis, whether as contractors or employees. They work according to shifts and are subject to many constraints on working times and durations. It may sound strange to put it this way, but if we want to leverage AI software to help optimize the way workforces are planned and scheduled, this is how capacity must be modeled programmatically.
Other factors that make capacity planning challenging include:
Employee availability is constantly changing and often uncertain due to staff turnover, illnesses and other unforeseen absences.
Workforce capacity is broken out based on skills and expertise. You may seemingly have enough total headcount, but the wrong skillset mix to fulfill demand.
Sometimes different roles have overlapping skills and this needs to be accounted for correctly.
Employees are constantly building new competencies that need to be considered. These new competencies are ideally based on the recommendations of optimization-based planning systems. This will be discussed later in this guide in the part about Strategic Planning.
Below is an example of a capacity planning screen for a contact center that is creating optimized daily schedules for agents. Each row represents an agent’s schedule. The color of the box indicates the type of work assigned per time period (phone response, email response, administrative work, etc). Notice that agents are usually assigned to the same task for long stretches, if not the entire shift, in order to reduce inefficiency from task switching. One can also see that daily schedules are limited by total hours and mandatory breaks are scheduled in. On the second chart you can see overall how well the schedule is meeting demand. Workforce capacity, shown in gray, is usually higher than demand except in the early morning at around 1:30 when the call center is slightly understaffed.
Capacity Planning System for Call Center by DecisionBrain
How to Optimize Capacity Plans
Now that we have a high level understanding of what demand forecasting and capacity planning are, we can start to think about how to create optimized capacity plans. This is in fact the subject of the next 3 posts in this series. That is because capacity planning optimization can get very complex very quickly.
In order to reduce complexity, industry practitioners usually segment capacity planning problems into 3 problem types based on the time horizon that is being considered: strategic capacity planning (~ annual), tactical capacity planning (~monthly) and operational scheduling (~daily/hourly). Optimization can be applied to each of these 3 problem types individually, but when it is applied to all three the results are maximized.
Workforce planning by time horizon
Check out our next article for an in-depth discussion about operational scheduling optimization, in which we elaborate on what goes into the creation of a schedule like the one shown above.
Conclusion
Forecasts and capacity plans are critical inputs into planning and scheduling systems. When done correctly, forecasting and capacity planning enable leaders to make informed decisions about hiring, training, leave approval and scheduling in order to reduce costs and employee turnout while maximizing service levels.
Download the complete PDF guide now to get access to the content right away.
| 2023-06-07T00:00:00 |
2023/06/07
|
https://medium.com/decisionbrain/the-complete-guide-to-workforce-optimization-part-3-handling-uncertainty-with-forecasting-and-dbc07e33389d
|
[
{
"date": "2023/03/01",
"position": 25,
"query": "machine learning workforce"
}
] |
Reimagining Education and Workforce Preparation in Support ...
|
Reimagining Education and Workforce Preparation in Support of the UN's
|
https://www.taylorfrancis.com
|
[] |
by JM Fung · 2023 · Cited by 6 — Many aspects of our work today are being automated by new technologies including artificial intelligence (AI) and machine learning. This technological.
|
Many aspects of our work today are being automated by new technologies including artificial intelligence (AI) and machine learning. This technological revolution is leading to a decline in jobs in some areas, growth in others, and substantive changes to many occupations. In considering the future of work, the shelf life of a contemporary skill is anticipated to decrease to a remarkably short five years. As the authors of this chapter note, individuals will therefore be expected to update and refresh their skills at least eight times during their 40-year careers to remain relevant at their workplace. In many advanced economies, including Europe, Japan, and the United States, aging populations, exacerbated by a shrinking workforce, create an even more acute need for individuals to remain employable for a longer period of their lives. This chapter presents the need for lifelong learning and skills development for sustainable economies and societies—both in developing and advanced nations—and advocates for a new educational paradigm. Such a paradigm could support the United Nations’ Sustainable Development Goals (SDGs). The 17 SDG’s are a holistic agenda geared toward ending poverty, improving health and education, reducing inequality, and spurring economic growth—all while tackling climate change and better managing our planet’s resources.
| 2023-03-23T00:00:00 |
2023/03/23
|
https://www.taylorfrancis.com/chapters/oa-edit/10.4324/9781003230762-4/reimagining-education-workforce-preparation-support-un-sustainable-development-goals-jin-michael-fung-samira-hosseini
|
[
{
"date": "2023/03/01",
"position": 38,
"query": "machine learning workforce"
}
] |
Workplace Predictors of Violence against Nurses Using ...
|
Workplace Predictors of Violence against Nurses Using Machine Learning Techniques: A Cross-Sectional Study Utilizing the National Standard of Psychological Workplace Health and Safety
|
https://www.mdpi.com
|
[
"Havaei",
"Adhami",
"Tang",
"Boamah",
"Sheila A.",
"Kaulius",
"Gubskaya",
"O Donnell",
"Farinaz Havaei",
"Nassim Adhami"
] |
by F Havaei · 2023 · Cited by 8 — Workplace Predictors of Violence against Nurses Using Machine Learning Techniques: A Cross-Sectional Study Utilizing the National Standard of Psychological ...
|
Organizational Culture Organizational culture is a mix of norms, values, beliefs, meanings, and expectations that group members hold in common and that they use as behavioral and problem-solving cues. Organizational culture could enhance the psychological safety and health of the workplace and the workforce when it is characterized by trust, honesty, respect, civility, and fairness or when it values, for example, psychological and social support, recognition, and reward. An organization with good organizational culture would be able to state that (a) all people in the workplace are held accountable for their actions; (b) people at work show sincere respect for others’ ideas, values, and beliefs; (c) difficult situations at work are addressed effectively; (d) workers feel that they are part of a community at work; and (e) workers and management trust one another.
Psychological and Social Support Psychological and social support comprises all supportive social interactions available at work, either with co-workers or supervisors. It refers to the degree of social and emotional integration and trust among co-workers and supervisors. It refers also to the level of help and assistance provided by others when one is performing tasks. Equally important are the workers’ perceptions and awareness of organizational support. When workers perceive organizational support, it means they believe their organization values their contributions, is committed to ensuring their psychological well-being, and provides meaningful support if this well-being is compromised. An organization with good psychological and social support would be able to state that (a) the organization offers services or benefits that address worker psychological and mental health; (b) workers feel part of a community and that the people they are working with are helpful in fulfilling the job requirements; (c) the organization has a process in place to intervene if an employee looks distressed while at work; (d) workers feel supported by the organization when they are dealing with personal or family issues; (e) the organization supports workers who are returning to work after time off due to a mental health condition; and (f) people in the organization have a good understanding of the importance of worker mental health.
Clear Leadership and Expectations Clear leadership and expectations are present in an environment in which leadership is effective and provides sufficient support that helps workers know what they need to do, explains how their work contributes to the organization, and discusses the nature and expected outcomes of impending changes. There are many types of leadership, each of which impacts psychological safety and health in different ways. The most widely accepted categorizations of leadership are instrumental, transactional, and transformational. Of these, transformational leadership is considered the most powerful. Instrumental leadership focuses primarily on producing outcomes, with little attention paid to the “big picture,” the psychosocial dynamics within the organization, and unfortunately, the individual workers. Transformational leaders are seen as change agents who motivate their followers to do more than what is expected. They are concerned with long-term objectives and transmit a sense of mission, vision, and purpose. They have charisma, give individual consideration to their workers, stimulate intellectual capabilities in others, and inspire workers. An organization with clear leadership and explicit expectations would be able to state that (a) in their jobs, workers know what they are expected to do; (b) leadership in the workplace is effective; (c) workers are informed about important changes at work in a timely manner; (d) supervisors provide helpful feedback to workers on their expected and actual performance; and (e) the organization provides clear, effective communication.
Civility and Respect Civility and respect is present in a work environment where workers are respectful and considerate in their interactions with one another, as well as with customers, clients, and the public. Civility and respect are based on showing esteem, care, and consideration for others, and acknowledging their dignity. An organization with good civility and respect would be able to state that (a) people treat each other with respect and consideration in the workplace; (b) the organization effectively handles conflicts between stakeholders (workers, customers, clients, public, suppliers, etc); (c) workers from all backgrounds are treated fairly in our workplace; and (d) the organization has effective ways of addressing inappropriate behavior by customers or clients.
Psychological Demands Psychological demands of any given job are documented and assessed in conjunction with the physical demands of the job. Psychological demands of the job will allow organizations to determine whether any given activity of the job might be a hazard to the worker’s health and well-being. When hazards are identified, organizations consider ways of minimizing risks associated with identified job hazards through work redesign, analysis of work systems, risk assessment, etc. The assessment of psychological demands should include assessment of time stressors (time constraints, quotas, deadlines, machine pacing, etc.); breaks and rest periods; incentive systems (production bonuses, piece work, etc.); job monotony and the repetitive nature of some work; and hours of work (overtime requirements, 12 h shifts, shift work, etc.). An organization with a good psychological demands assessment process for its workers would be able to state that (a) the organization considers existing work systems and allows for work redesign; (b) the organization assesses worker demand and job control issues such as physical and psychological job demands; (c) the organization assesses the level of job control and autonomy afforded to its workers; (d) the organization monitors the management system to address behaviors that impact workers and the workplace; (e) the organization values worker input particularly during periods of change and the execution of work; (f) the organization monitors the level of emphasis on production issues; (g) the organization reviews its management accountability system that deals with performance issues and how workers can report errors; and (h) the organization emphasizes recruitment, training, and promotion practices that aim for the highest level of interpersonal competencies at work.
Growth and Development Growth and development are present in a work environment where workers receive encouragement and support in the development of their interpersonal, emotional, and job skills. Such workplaces provide a range of internal and external opportunities for workers to build their repertoire of competencies, which will not only help with their current jobs, but will also prepare them for possible future positions. An organization with good growth and development would be able to state that (a) workers receive feedback at work that helps them grow and develop; (b) supervisors are open to worker ideas for taking on new opportunities and challenges; (c) workers have opportunities to advance within their organization; (d) the organization values workers’ ongoing growth and development; and (e) workers have the opportunity to develop their “people skills” at work.
Recognition and Reward Recognition and reward are present in a work environment where there is appropriate acknowledgment and appreciation of workers’ efforts in a fair and timely manner. This includes appropriate and regular acknowledgments such as worker or team celebrations, recognition of good performance and years served, and milestones reached. An organization with a good recognition and reward program would be able to state that (a) immediate supervision demonstrates appreciation of workers’ contributions; (b) workers are paid fairly for the work they do; (c) the organization appreciates efforts made by workers; (d) the organization celebrates shared accomplishments; and (e) the organization values workers’ commitment and passion for their work.
Involvement and Influence Involvement and influence are present in a work environment where workers are included in discussions about how their work is done and how important decisions are made. Opportunities for involvement can relate to a worker’s specific job, the activities of a team or department, or issues involving the organization as a whole. An organization with good involvement and influence would be able to state that (a) workers are able to talk to their immediate supervisors about how their work is done; (b) workers have some control over how they organize their work; (c) worker opinions and suggestions are considered with respect to work; (d) workers are informed of important changes that can impact how their work is done; and (e) the organization encourages input from all workers on important decisions related to their work.
Workload Management Workload management is present in a work environment where assigned tasks and responsibilities can be accomplished successfully within the time available. This is the risk factor that many working Canadians describe as being the biggest workplace stressor (i.e., having too much to do and not enough time to do it). It has been demonstrated that it is not just the amount of work that makes a difference but also the extent to which workers have the resources (time, equipment, support) to do the work well. An organization with good workload management would be able to state that (a) the amount of work that workers are expected to do is reasonable for their positions; (b) workers have the equipment and resources needed to do their jobs well; (c) workers can talk to their supervisors about the amount of work they have to do; (d) workers’ work is free from unnecessary interruptions and disruptions; and (e) workers have an appropriate.
Engagement Engagement is present in a work environment where workers enjoy and feel connected to their work and where they feel motivated to do their job well. Worker engagement can be physical, emotional, and/or cognitive. Physical engagement is based on the amount of exertion a worker puts into his or her job. Physically engaged workers view work as a source of energy. Emotionally engaged workers have a positive job outlook and are passionate about their work. Cognitively engaged workers devote more attention to their work and are absorbed in their job. Whatever the source, engaged workers feel connected to their work because they can relate to, and are committed to, the overall success and mission of their company. Engagement should be seen as a result of policies, practices, and procedures for the protection of worker psychological health and safety. Engagement is similar to, but is not to be mistaken for, job satisfaction, job involvement, organizational commitment, psychological empowerment, and intrinsic motivation. An organization with good engagement would be able to state that (a) workers enjoy their work; (b) workers are willing to give extra effort at work if needed; (c) workers describe work as an important part of who they are; (d) workers are committed to the success of the organization; and (e) workers are proud of the work they do
Balance Balance is present in a work environment where there is acceptance of the need for a sense of harmony between the demands of personal life, family, and work. This factor reflects the fact that everyone has multiple roles: as workers, parents, partners, etc. This complexity of roles is enriching and allows fulfillment of individual strengths and responsibilities, but conflicting responsibilities can lead to role conflict or overload. An organization with good balance would be able to state that (a) the organization encourages workers to take their entitled breaks (e.g., lunchtime, sick time, vacation time, earned days off, and parental leave); (b) workers are able to reasonably meet the demands of personal life and work; (c) the organization promotes life-work harmony; (d) workers can talk to their supervisors when they are having trouble maintaining harmony between their life and work; and (e) workers have energy left at the end of most workdays for their personal life. (f) Psychological protection is present in a work environment where workers’ psychol
Psychological Protection Psychological protection is present in a work environment where workers’ psychological safety is ensured. Workplace psychological safety is demonstrated when workers feel able to put themselves on the line, ask questions, seek feedback, report mistakes and problems, or propose a new idea without fearing negative consequences to themselves, their job, or their career. A psychologically safe and healthy organization actively promotes emotional well-being among workers while taking all reasonable steps to minimize threats to worker mental health. An organization with good psychological protection would be able to state that (a) the organization is committed to minimizing unnecessary stress at work; (b) immediate supervisors care about workers’ emotional well-being; (c) the organization makes efforts to prevent harm to workers from harassment, bullying, discrimination, violence, or stigma; (d) workers would describe the workplace as being psychologically healthy; and (e) the organization deals effectively with situations that can threaten or harm workers (e.g., harassment, bullying, discrimination, violence, stigma, etc).
| 2023-01-14T00:00:00 |
2023/01/14
|
https://www.mdpi.com/2227-9032/11/7/1008
|
[
{
"date": "2023/03/01",
"position": 47,
"query": "machine learning workforce"
}
] |
Machine-learning-based top-view safety monitoring of ...
|
Machine-learning-based top-view safety monitoring of ground workforce on complex industrial sites
|
https://search.proquest.com
|
[
"Gelayol",
"Martinez-Alpiste",
"Wang",
"Alcaraz-Calero",
"Jose Maria"
] |
by G Gelayol · 2022 · Cited by 29 — Telescopic cranes are powerful lifting facilities employed in construction, transportation, manufacturing and other industries. Since the ground workforce ...
|
Copyright information
© The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
| 2023-03-01T00:00:00 |
https://search.proquest.com/openview/b467892c967974d298f2c9fbf8ced530/1?pq-origsite=gscholar&cbl=2043988
|
[
{
"date": "2023/03/01",
"position": 52,
"query": "machine learning workforce"
}
] |
|
Implementing AI machine learning in your team
|
Implementing AI machine learning in your team
|
https://www.ag5.com
|
[
"Rick Van Echtelt",
"Read Author Profile",
"March",
"Min Read"
] |
In this era of AI and machine learning, Explainable Artificial Intelligence ... Learn how workforce and skills management can provide you with better ...
|
According to a recent Deloitte survey, 73% of businesses say artificial intelligence (AI) is critical to their success, yet 41% of technologists are concerned about the ethics of the AI tools their company uses. Additionally, 47% of business leaders have concerns about transparency. While many leaders quickly recognize the contributions AI Integration can make, there is still a lingering distrust in its capability.
Let’s explore why some businesses have difficulty trusting AI and why it’s crucial to integrate it into your team.
Understanding the concerns around AI integration Copied When it comes to using AI for mission-critical tasks, there are two main areas of concern for businesses: The need for transparency The ability of users to understand the data that goes into a model is critical when building trust in an AI system. To ensure that algorithms are functioning as expected, companies must be transparent about how they train their AI models and what information they use when making decisions. This helps organizations maintain trust by showing customers exactly how their data is being used. It also allows companies to explain why certain decisions were made and allow customers to provide feedback. The need for ethical guidelines AI systems are only as ethical as their users allow them to be. Without clear standards in place, there is no guarantee that an algorithm will act ethically – or make decisions in line with organizational values or customer expectations. Companies need to put ethical guidelines in place so that they can ensure their algorithms are compliant with any applicable laws or regulations. This helps protect organizations from potential legal repercussions, and allows them to demonstrate their commitment to ethical practices.
Can AI be part of your team? Copied For organizations to successfully incorporate AI into their teams, they must first build trust in the technology. Doing this effectively requires: Integrating human judgment into the process To overcome concerns about trustworthiness, managers need to understand human judgment’s role in developing AI models. As opposed to traditional programming (which depends on human input to learn), machine learning algorithms can be trained using datasets derived from real-world examples. Team members must interpret and label this data before feeding it into an algorithm. In other words, human resources have an integral role in creating accurate AI models that businesses can trust. As such, managers must ensure that their team members have solid ethical foundations and understand AI technology’s capabilities and limitations. It is also essential for them to recognize potential biases in their datasets, so they can adjust accordingly. By taking these steps, managers can create teams with high levels of trustworthiness when working on sensitive tasks such as customer service or security operations. The role of explainability in AI-powered team In this era of AI and machine learning, Explainable Artificial Intelligence (XAI) provides an essential bridge of understanding and trust between man and machine. By utilizing XAI processes and methods, we can better comprehend the actions of our algorithms, and trust that they are reliable in their output without needing a deep understanding of how they work. XAI allows us to build and achieve our goals with more precision and accuracy than ever before, making it possible to create a world in which we can use machines with confidence. To achieve this, you must be able to thoroughly explain the decision-making process and logic for a particular recommendation. Clearly explain why it is so important for users to understand the data that went into a model, so they can be more confident in its decisions and recommendations. Explainability also plays a vital role in helping organizations meet regulatory compliance requirements, as it ensures that decisions made by algorithms are transparent and traceable. Reducing bias within algorithms is another benefit of XAI, as all factors considered when deciding have been vetted and documented. Finally, explainability can help organizations to build trust with their customer base by clarifying how decisions were made and why specific recommendations were given. How can organizations achieve explainability? There are several ways for organizations to ensure that their algorithms are explainable. These include using data audit logs, which: Provide detailed information about how data was used
Create automated tests that check for bias in models
Use natural language processing (NLP) techniques such as sentiment analysis
Implement machine learning interpretability methods such as feature importance analysis or partial dependence plots Additionally, organizations should consider investing in XAI, which focuses on developing systems that can generate comprehensible explanations for their behavior and decisions.
The benefits of human-AI collaboration Copied When done correctly, human-AI collaboration can bring tremendous value to any organization. For example, chatbots powered by NLP allow businesses to interact with customers on multiple real-time channels while reducing manual labor costs. Another example would be predictive analytics, which leverage machine learning algorithms to forecast customer behavior or detect anomalies – allowing companies to identify trends faster than ever. Ultimately, combining human judgment with advanced technologies allows teams to maximize efficiency while reducing risk factors associated with decision-making processes.
Conclusion Copied Successful collaboration between your workforce and AI is essential for any organization to remain competitive. Business leaders must ensure that AI models are trustworthy, accurate, and explainable. AG5 skills management software helps coordinate and optimize human-AI collaboration. Our software allows users to create profiles that capture each team member’s skills, knowledge, experience, and qualifications. This helps managers assign the right people to projects or tasks based on their skill sets. By leveraging AG5 skills management software, businesses can ensure that their teams are well-equipped with the necessary skills to make accurate decisions while maintaining trustworthiness and transparency. Schedule a free live demo!
Author Copied Rick van Echtelt Rick van Echtelt is the Co-Founder and CEO of AG5, where he leverages over two decades of experience in entrepreneurship and developing skills management software. Read author profile
| 2023-03-01T00:00:00 |
2023/03/01
|
https://www.ag5.com/implementing-ai-machine-learning-in-your-team/
|
[
{
"date": "2023/03/01",
"position": 64,
"query": "machine learning workforce"
},
{
"date": "2023/03/01",
"position": 58,
"query": "artificial intelligence business leaders"
}
] |
When will AI actually start taking jobs? : r/singularity
|
The heart of the internet
|
https://www.reddit.com
|
[] |
I think we'll see the first potentially significant disruption when Google and Microsoft release their office AI suite.
|
Have you already experienced layoffs due to ai? If not, then when do you think layoffs will happen?
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/singularity/comments/126zjaq/when_will_ai_actually_start_taking_jobs/
|
[
{
"date": "2023/03/01",
"position": 19,
"query": "AI labor union"
},
{
"date": "2023/03/01",
"position": 5,
"query": "artificial intelligence layoffs"
}
] |
|
The use of AI in legal systems: determining independent ...
|
The use of AI in legal systems: determining independent contractor vs. employee status
|
https://pmc.ncbi.nlm.nih.gov
|
[
"Maxime C Cohen",
"Desautels Faculty Of Management",
"Mcgill University",
"Rue Sherbrooke O.",
"Montreal",
"Qc Canada",
"Samuel Dahan",
"Faculty Of Law",
"Queen S University",
"Union St"
] |
by MC Cohen · 2023 · Cited by 86 — This paper investigates the use of AI in a critical issue in employment law, the determination of a worker's status—employee vs. independent contractor—in two ...
|
Abstract The use of artificial intelligence (AI) to aid legal decision making has become prominent. This paper investigates the use of AI in a critical issue in employment law, the determination of a worker’s status—employee vs. independent contractor—in two common law countries (the U.S. and Canada). This legal question has been a contentious labor issue insofar as independent contractors are not eligible for the same benefits as employees. It has become an important societal issue due to the ubiquity of the gig economy and the recent disruptions in employment arrangements. To address this problem, we collected, annotated, and structured the data for all Canadian and Californian court cases related to this legal question between 2002 and 2021, resulting in 538 Canadian cases and 217 U.S. cases. In contrast to legal literature focusing on complex and correlated characteristics of the employment relationship, our statistical analyses of the data show very strong correlations between the worker’s status and a small subset of quantifiable characteristics of the employment relationship. In fact, despite the variety of situations in the case law, we show that simple, off-the-shelf AI models classify the cases with an out-of-sample accuracy of more than 90%. Interestingly, the analysis of misclassified cases reveals consistent misclassification patterns by most algorithms. Legal analyses of these cases led us to identify how equity is ensured by judges in ambiguous situations. Finally, our findings have practical implications for access to legal advice and justice. We deployed our AI model via the open-access platform, https://MyOpenCourt.org/, to help users answer employment legal questions. This platform has already assisted many Canadian users, and we hope it will help democratize access to legal advice to large crowds. Keywords: Employment law, Artificial intelligence, Predictive models, Decision-support legal systems
Introduction Much is at stake in determining whether a worker should be classified as an employee or as a contractor. This question strikes at the core of the structure of the economy, as it has implications for both employers’ and workers’ rights. As argued by the recent California Supreme Court decision, Dynamex Operations West Inc. v. Superior Court of Los Angeles County, “the question whether an individual worker should properly be classified as an employee or, instead, as an independent contractor has considerable significance for workers, businesses, and the public generally.”1 The question of worker status determination has come to the forefront of the public debate thanks to a string of cases regarding the status of gig workers. The gig economy, which enables flexible work arrangements for workers in service-based, on-demand environments (Huang et al. 2020), has seen tremendous growth in recent years. In the U.S., it has been estimated that 35% of the workforce participated in the gig economy in 2018, while this figure was estimated to be 50% in the UK in 2020 (Marius 2021). The value of this market has also grown tremendously, with a twenty-fold increase over the last decade and projected value of $335 billion dollars in 2025 (Taylor et al. 2020).2 Thus, issues surrounding the gig economy have attracted the attention of numerous academic researchers, particularly regarding the behavior of workers (e.g., Greenwood et al. 2017; Allon et al. 2018; Babar and Burtch 2020). For such companies, the issue of worker classification has critical implications for workers’ rights. In fact, many gig workers are classified by their employers as independent contractors and therefore cannot receive minimum employment benefits, such as overtime and vacation pay. Gig economy companies have faced at least 40 major legal challenges worldwide, as transportation and delivery drivers have tried to improve their rights. In a bold move, California voters passed Prop 22 in November 2020, the most expensive ballot initiative in Californian history, allowing gig companies such as Uber, Lyft, and DoorDash to continue classifying their workers as independent contractors while offering them a few additional benefits.3 The answer to this seemingly basic legal question is far from straightforward. Indeed, worker classification relies on multiple factors that are often correlated and may even depend on the nature of the work (Burosu 2021). Furthermore, it often implies an implicit precedence and the weighting of several work characteristics (Deakin 2020). In this paper, we approach this legal question from the perspective of algorithmic decision-making, using two complementary datasets: a compilation of Canadian and U.S. (California) cases concerning the issue of worker classification. The application of artificial intelligence (AI) techniques in legal contexts has seen remarkable developments. AI can be used in dispute resolution (Cohen et al. 2021), such as determining the employment notice period following job termination (Dahan et al. 2020) and predicting asylum court decisions (Dunn et al. 2017). In the U.S., individualized automatic estimates of the likelihood of criminal recidivism provided by the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) system were utilized for nearly a decade to assist judges and parole boards for sentencing decisions (Shimao et al. 2022). Law firms have also increasingly adopted AI models to provide legal services to their clients, particularly regarding tax and contract law (Kauffman and Soares 2020). However, the computability of law, namely the ability of algorithms to provide legal analysis, advice, or predictions, remains a subject of fierce debate, especially regarding adjudication. At one end of the spectrum, several scholars have claimed that law is on a path towards “legal singularity,” in which the law will eventually be complete with no genuinely grey areas and thus fully computable (Alarie 2016). Others have been more skeptical, arguing that certain features of legal reasoning are not consistent with AI, particularly because of the fundamental nature of legal reasoning, specifically the reflexivity of legal knowledge and the incompleteness of legal rules (Markou and Deakin 2020). In this paper, we provide a quantitative account of the computability of law regarding the question of worker classification. To this end, we collected and analyzed two complementary datasets. The first dataset includes all Canadian court cases related to worker classification between 2001 and 2021, providing invaluable information on Canadian case law. The concept of worker classification is not unique to Canada. It is found in a functionally similar form, albeit with some important differences, in many legal systems (Deakin et al. 2005). To explore the potential application of algorithms in comparative laws, our second dataset consists of all relevant cases in the state of California between 1989 and 2020. Finally, we also gathered data from the real-world field deployment of our AI model via an open-access platform, https://MyOpenCourt.org/, to help workers and employers answer legal questions about employment law. This platform has been available to the public since June 2020. Our two datasets (as well as our field data) allowed us to investigate the validity and generalizability of our results. In Sect. 2, we investigate the ability of machine learning (ML) algorithms to predict workers’ status. Using interpretable AI algorithms, we further decipher the structure of the resulting predictive methods and infer typical judges’ decision-making processes as well as the main factors that determine workers’ status. We found a surprising consistent judicial decision making in this domain, whereby even simple off-the-shelf algorithms could predict workers’ status with very high accuracy (around 90%). However, we will show that a number of cases were systematically misclassified by our algorithms. Isolating those cases allowed us to determine a subset of unconventional decisions that are based on some legitimate, or at least deliberate, judicial choices. By combining the Canadian and Californian datasets, we propose using AI algorithms as a tool for comparative law. By using algorithms trained on a specific dataset to predict outcomes for the other dataset, we will showcase a striking and unexpected consistency between two vastly distinct jurisdictions. Thus, our results suggest that AI algorithms could provide a new systematic tool for comparative law. Finally, we deploy our AI model in the field for the benefit of the public and to potentially assist self-represented litigants. Most research endeavours in this area have focused on technical aspects, such as measuring the accuracy of models in predicting case outcomes. However, our understanding of the legal and practical implications of AI-powered systems in legal contexts remains limited. We discuss the practical implications of this research, including the deployment of https://MyOpenCourt.org/, which is a direct-to-public platform based on our AI model, for helping users answer legal questions on employment law. Deploying this platform to predict workers’ status along with clear explanations, allows us to directly help the public and reduce lawyers’ workload. It is also one step forward in democratizing the access to legal advice and to justice.
Results Worker classification and data analyses Factors established by the case law In September 2001, the Canadian Supreme Court delineated the contours of the legal determination of workers’ status in the landmark case 671122 Ontario Ltd. v Sagaz Industries Canada Inc. (hereafter, Sagaz). This text clearly expresses the position of the common law in determining whether a work relationship can be construed as an employer-employee relationship: “In making this determination, the level of control the employer has over the worker’s activities will always be a factor. However, other factors to consider include whether the worker provides his or her own equipment, whether the worker hires his or her own helpers, the degree of financial risk taken by the worker, the degree of responsibility for investment and management held by the worker, and the worker’s opportunity for profit in the performance of his or her tasks." We collected all 1,391 cases between 2001 and 2021 that referred explicitly to Sagaz (see the “Methods” section below for more details). Among these, 538 cases were related to the determination of an employee/contractor status and formed the basis of our dataset. Sagaz not only provides a reference for identifying the relevant judgements, but also outlines the following set of attributes to use in monitoring each case: Level of supervision of the work,
Ownership of equipment,
Ability to hire helpers,
Degree of financial risk (level of financial investment, business expenses, and liability), and
Opportunity for profit (in particular, considering whether the worker was paid via fixed wages, commissions, or a combination). In addition to the above factors, which were explicitly stated in the Sagaz case, we also monitored other key elements in each case, including Whether the contract included exclusivity of services,
Who sets the work hours,
Where the work is performed, and
Whether the worker was required to wear a uniform. Finally, factual elements, including year of judgement, court, province, industry, and duration of services, were also collected. We followed a similar methodology in collecting data on U.S. cases. To ensure comparable volumes of cases and avoid heterogeneity between different jurisdictions, we focused our attention on the state of California, because of its sizable technology industry and its central role in the recent debate on the status of gig workers. The question of worker status can be approached from various legal angles, and there are many legal tests available depending on the issue at stake (e.g., tax, employment insurance, and social security). In this paper, we consider the leading court case S. G. Borello & Sons, Inc. v. Department of Industrial Relations (1989), which is largely considered to have set a landmark for worker classification. In this case, S. G. Borello & Sons, Inc., a Gilroy grower, was found guilty of having failed to secure workers’ compensation coverage for the 50 migrant harvesters of its cucumber crop. By placing expectations on worker’s classification, this case has led to the identification of 11 largely correlated factors that determine worker classification, and that have became known as the Borello multifactor test for determining various dimensions of the level of the employer’s control of the worker. In addition to the above Sagaz criteria, which are explicitly covered in the Borello test, the latter also includes other dimensions, notably the following: Whether the worker engages in an occupation distinct from that of the company or part of the company’s regular business,
The skill level required in the occupation,
The duration of services and the degree of permanence of the work relationship, and
The perception by one of the parties of the existence of an employer/employee relationship. The overlap in criteria between the two jurisdictions allowed us to use a consistent scale for labeling Canadian and Californian cases, which was crucial in making fair comparisons. We collected and processed 810 cases that explicitly referenced the Borello case between 1989 and 2020. Among these cases, a total of 217 cases were relevant to the question of worker classification, and data were collected to ensure consistency with the Canadian dataset and to conserve as much information as possible for further use, leaving us with a total of 28 criteria including the Sagaz criteria (see the “Methods” section). Case typology in Canada and California Beyond opening the way to prediction, these datasets provide invaluable insights into the specifics of worker classification litigation history in Canada and California. Interestingly, we found that there was no significant imbalance in the court decisions, and comparable fractions of workers were classified as employees in California (60.4%) and Canada (61.2%),4 The overwhelming majority of cases corresponded to workers in the service industry (90.5% in Canada and 83% in U.S.), with brief work duration (in half of the cases, workers worked for less than a year in both jurisdictions, and in more than 80% of cases, workers worked for less than five years).5 In both datasets, the majority of workers could choose where to work (74.5% in Canada and 75.6% in California). Other criteria were less balanced and showed less similarity between the two jurisdictions, likely stemming from differences in the work culture. In Canada, workers had relatively a low risk of loss in two out of three cases, which was more frequent than in California (43%). Workers did not own their tools in about 40% of Canadian cases versus 14.3% of cases in California, and high chances of profit (reflecting whether workers were paid fixed wages or commissions) were 43% in Californian cases compared with 5.7% in Canada. One important aspect of investigating judicial decision-making is the characterization of the correlation between the different criteria, and whether some criteria weigh more than others. For example, the ownership of tools, as a concrete financial investment, should directly correlate with the risk of loss. We computed the correlation matrices between criteria in both datasets (see Fig. 1) and obtained similar correlation maps in Canada and California. Overall, except for the length of service that, quite unsurprisingly, was uncorrelated to other criteria, we found a high correlation between the different features in our data. Fig. 1. Open in a new tab Statistics of the Canadian and Californian datasets. (A) Correlation matrix between pairs of features and between features and outcomes for Canada (right) and California (left). Our data convention (see “Methods” section) consisted of coding feature scores with increasing values for decreasing levels of control (e.g., works involving a supervision were coded as 1, and works with no supervision were coded 2). (B) To appreciate the meaning of high correlations of factors with the worker’s status, we plotted the data distribution for the two most highly correlated features with the outcomes: delegation of tasks and supervision of work. Histograms of the outcomes as a function of the feature and of the distribution of the outcomes given a feature value showed strong imbalances Interestingly, the correlation between the outcome and the features in the dataset provided the first assessment of feature importance and predictability. We found that outcomes in Canada and California had a strong correlation (50% and above) with seven common criteria of the 11 criteria, with lower correlations with the chance of profit (38% in Canada and 21% in California), uniform wearing requirements (both around 30%), and extremely low correlations with the length of service. The only difference was a lower correlation with the risk of loss in California (34%) compared with Canada (61%), potentially reflecting the already noted heterogeneity between the two datasets regarding this specific criterion. In particular, we found that the outcome was correlated with whether the work was supervised or reviewed in California (74%). In Canada, the highest correlation was with whether the worker was delegated specific tasks to complete the job or whether the worker had the ability to decide which task to perform to complete the work (76%). In fact, we observed that over 80% of the workers who either were delegated specific tasks to complete the job or were directly supervised (or reviewed) by their hirer were classified as employees. This indicated the likelihood of a high predictability of the decisions, with those two criteria constituting factors that determined the worker’s status. Indeed, we found that predicting the outcome directly based on delegation of tasks provided an astonishing 82% accuracy for the Californian dataset and 89% accuracy for the Canadian dataset. Similarly, predicting the outcome solely based on whether the work was reviewed or supervised yielded high accuracies of 88% in California and 81% in Canada. Therefore, we observed that when we had information on the possible delegation of tasks and/or the supervision of work, highly consistent decisions were provided by the judges. However, in many situations, these dimensions of work were unspecified in the judgement. Information may be missing when it is absent in the source. For instance, a judge may not have found it relevant to specify whether a worker could wear a uniform or not, while in fact the worker was required to do so. Other features may be missing because they do not apply to a given work situation. Missing information may have two consequences: (i) likely hindering the predictive ability of the models, and (ii) potentially carrying information about the eventual outcome. We further examined the issue of missing data. For instance, data on whether the work was supervised were absent in 40% of the cases (84 cases) in California and 17% of the cases in Canada, while the ability to delegate tasks was absent in less than 13% of the cases in both datasets. Another aspect of missing data could be an a posteriori correlation with the outcome: judges did not mention a particular feature of specific outcomes. We confirmed the absence of such a correlation (with virtually no correlation in the Canadian dataset and very low correlations in the Californian dataset. See the “Methods” section). Even in the absence of a direct correlation with the outcome, we carefully handled the missing information. We tested multiple ways of handling missing data in the sequel, including (i) simply considering ‘missing’ as a new category for each class, (ii) inputting the missing fields with the median value over the entire data by default, or (iii) relying on a more sophisticated method based on predicting the most likely value by using the observed features (For such predictions, we used a random forest predictor. See the “Methods” section). Our results were based on the latter methodology, but all methods yielded similar results. Prediction results and inferring judicial reasoning We then used AI to further decipher judicial reasoning and test the predictability of the worker classification outcome. We used three distinct approaches to train and test our algorithms—Canadian data only, Californian data only, and combined data—which provided us with nine accuracy estimates, corresponding to (i) the ability of the algorithms to predict cases within a given jurisdiction, (ii) the ability of the algorithms to generalize from one jurisdiction to the other, and (iii) the possibility of enhancing generalizations by combining different jurisdictions. Based on our observation of a high correlation between the outcome variable with both the delegation of tasks and the ability to hire employees, we first considered a simple decision tree. This ML method was used to identify an optimal flow-chart-like structure for predicting the outcome based on the features, whereby the algorithm at each step of the flow-chart determined the optimal binary decision that best reduced the so-called impurity of the subsets, defined as the level of heterogeneity of the outcome values. To avoid over-fitting our relatively small datasets, we used shallow decision trees with a depth of three. This yielded the following nine accuracy values, which were computed using a ten-fold cross-validation (for more details, see the “Methods” section with an assessment on the dependence of accuracy on the number of cross validations). We obtained the following results: Train \ Test Canada U.S. All Canada 0.85 0.82 0.82 U.S. 0.88 0.84 0.82 All 0.88 0.82 0.82 Open in a new tab Among the most relevant observations, we noted that predicting new Canadian worker classifications from the algorithm trained on Canadian cases achieved a cross-validation accuracy score of 88%, but, more interestingly, the remarkable score of 82% for all cases. In the same vein, training the algorithm on U.S. cases led to a 84% prediction accuracy in the U.S. cases and a 88% accuracy in the Canadian cases. Training on all cases did not improve the result further. The decision tree algorithms, because of their flow-chart structure, allowed for a deeper understanding of judicial reasoning. In Fig. 2, we depict the decision trees generated by the algorithms. In addition to the (already observed) importance of the ability to delegate tasks in Canada, we observed that the tree was able to capture two main corrections to the naive, uni-dimensional perspective. For instance, workers who did not have the ability to delegate tasks but could hire employees were often considered contractors, particularly when there was a high chance of profit (blue branches in Fig. 2 arising from the leftmost split). However, workers who could delegate tasks but worked exclusively for the hirer and had a low risk of loss were classified as employees. Fig. 2. Open in a new tab Decision trees, along with the impurity level (Gini index), the number of samples in each node, and the total number of cases of each type. Orange: employee, Blue: contractor, with gradient indicating the purity level (i.e., certainty of the classification). Top: tree trained using Canadian data, Bottom: tree trained using Californian data. The differences relative to a naive algorithm based only on the root of the tree are highlighted in green; a fully ambiguous situation is highlighted in pink for the Canadian dataset Similarly, the tree trained on the U.S. data identified supervision of work as the main criterion (as previously observed), but it had a single refinement relative to a purely binary decision: workers who were supervised but could hire employees were more likely to be considered contractors. We concluded that the simplest AI algorithms could achieve a high predictive accuracy within a given jurisdiction, and, more strikingly, between two different, potentially vastly distinct, jurisdictions. Moreover, the decision tree provided a finer, yet realistic vision of the criteria used by judges to determine workers’ status. Before we delve into a deeper analysis of these observations, we discuss the outcome of alternative, more complex AI algorithms to determine whether nonlinear or non-binary decisions could further improve prediction accuracy. We note that ML algorithms crucially rely on having access to a good sample of labeled data for training purposes. Such a condition is true for all studies that rely on supervised ML models. First, we tested random forests, which combined multiple decision trees and used them as an ensemble for prediction. The trees were different because they were constructed based on random splits of the data (bagging, or bootstrap aggregation) and featured randomness (trees were selected from a random subset of features instead of using a greedy algorithm that found the best feature for a split). Random forests, with a maximum of 15 trees and a maximum depth of four, yielded an improved precision as reported below: Train \ Test Canada U.S. All Canada 0.90 0.82 0.86 U.S. 0.90 0.86 0.89 All 0.91 0.80 0.9 Open in a new tab An estimate of the relative importance of each feature in the dataset was provided by estimating the statistics of the decrease in impurity in which their split resulted. We found a quantitative confirmation of the previous observations: for both the Canadian and Californian datasets, we found similar importance levels, except for a switch between supervision of work and delegation of tasks. In the Canadian dataset, delegation of tasks was the most important feature with 26% decreased impurity, preceding exclusivity of services (16%), ability to set work hours (13%), supervision of work (12%), and risk of loss (10%). In the Californian dataset, supervision of work accounted for an averaged of 23% in decreased impurity, preceding ability to set work hours (22%), exclusivity of services (14%), whereas all other features were below 10%. Other classification algorithms were also applied to further analyze our ability to predict workers’ status, including logistic regression, k-neighbors classifier, support-vector classification (SVC), Gaussian process classifier, and the AdaBoost or XGBoost classifiers (see the “Methods” section). They all provided predictions with similar (or better) accuracy but were less conducive to interpretation. However, an interesting conclusion was that most cases were misclassified by decision trees, and random forests were also misclassified by other algorithms. We thus turned our attention to these misclassified cases. Misclassified cases and adaptive judicial decisions Of 755 cases (in both Canadian and Californian datasets) and seven classification algorithms, we observed that 612 (81%) cases were correctly classified by all algorithms, showing a high degree of consistency in capturing judicial behavior regardless of the algorithm used. Interestingly, 5.7% of the cases (43 cases) were misclassified by all algorithms, some even providing predictions with high degrees of confidence. For instance, for the 2012 Pluri Vox Media Corp. v. Canada, all algorithms predicted that the worker, Martin Reesink, was a contractor with high confidence levels (99.1% confidence for the logistic regression, 98.8% for SVC, and 100% for random forest or XGboost). This prediction was likely associated with the unique position of the worker, Martin Reesink, who was in fact the director of Pluri Vox. Many of the attributions associated with this leadership position, in particular his ability to hire an independent contractor in his work with Pluri Vox, was not considered to imply that he himself was an independent contractor. In fact, these algorithmically misclassified cases suggested a slight deviation from the application of the legal precedent, as they did not always signal inconsistent or biased decision-making patterns, in which judges made diverging decisions based on factors that were unrelated to the merits of the case. It depended on the cause of the divergence. For example, many situations may have presented unusual circumstances that warranted deviations from rigid algorithmic decisions based only on a few aspects of the case. However, it was also possible that the judges were affected by legally irrelevant factors such as behavioral biases, possibly leading them to ignore the circumstances of the case (Chen and Eagel 2017). In our assessment, we identified three patterns of algorithmic errors and divided the misclassified cases into three groups according to the cause of the deviation. The first group consisted of “simple” cases that were misclassified because of highly unusual factual or procedural circumstances. Consider, for instance, the 2011 Atlantic Council of Canada v. Minister of National Revenue, which set out to classify the status of an intern. In this case, by considering all factual aspects of work dependence, the algorithms predicted that the worker was an employee. Indeed, the intern was directly supervised, had no ability to hire employees or to delegate tasks, was required to work exclusively for the council, did not own his tools, and did not bear any risk of loss. All these aspects, in regular work relationships, are highly determinant of employee status and not contractor status. However, interns occupy a category that is outside the dichotomy of employee and contractor. Their level of dependence is in fact relative, as the work is highly temporary and part of training. As a result, the judges considered that the obligations of the council to the intern were closer to those they had to contractors. Another case where algorithms could not make an accurate prediction is the 2014 Morris Meadows Country Holidays and Seminars Ltd. v. Minister of National Revenue. This case considered the classification of 25 people working in a meeting, dining, and sleeping facility. In this case, the judge found that 24 of them were employees, while a single person, who in all respects shared the same features as the other workers, was in fact a contractor because of the unpredictable and unreliable nature of the functions performed by this worker, who was “spasmodically called upon once in a while to do a bit of work for an indeterminate time.” Of course, this specific determination by the judge was unpredictable, particularly when our algorithms lent themselves to a few criteria that did not include the regularity of the work, and thus predicted that all 25 workers were employees. The second group included “difficult” or “borderline” cases where the worker’s status was not straightforward. These cases presented features that strongly supported the classification of both an employment relationship and an independent contractor status. For instance, in the 2013 Atlantic Council of Canada v. Minister of National Revenue, the worker was classified by the court as an independent contractor because he had a separate carpentry business, and the relationship was not exclusive. However, the carpenter was supervised (i.e., was told what to build), was provided with tools, needed permission to leave early, and was given occasional building maintenance work. This situation included a subordinate relationship, but because the worker owned his own business, it clearly bore aspects of both contractor and employee. Ultimately, the court decided that the non-exclusive nature of the relationship prevailed over the subordinate relationship. Similarly, we highlighted two additional notable cases, S.C. t/a Hollywood Limousine Service and T. (N.), Re (Case 195 in our database and hereafter), and S.C. t/a Hollywood Limousine Service and T. (N.), Re. (Case 590). Both cases involved a topical policy issue, namely, whether gig workers are contractors or employees (although the policy dimension was not formally addressed in those cases). All AI models were wrong in both cases—but for different reasons. In Case 590, the algorithms classified the worker as an employee, whereas in Case 195, the worker was classified as an independent contractor. These results may indicate the inability of ML to solve difficult cases involving unusual circumstances, especially when they involve novel policy issues such as classifying gig workers.6 In fact, in Case 195, which involved a limousine business where the workers could set their own hours, the results may have been skewed by the ambiguity of the relationship. On one hand, the workers did not own their tools, and the relationship was exclusive, which indicated employment. On the other hand, the drivers had a high degree of autonomy, which in this case apparently prevailed over the other factors. As in Case 590, while the facts indicated an independent contractor relationship, the court decided that the unusual disciplinary power exercised by the hiring person reflected a high degree of supervision and, thus, an employment relationship. The notion of discipline is not new to lawyers, but it was not included in the Sagaz criteria and thus was not taken into account in our prediction algorithms. Finally, the third group included cases that deviated from the norm because the judges were influenced by extra-juridical variables. These cases could be described as “reflexive” situations insofar as the outcomes were context dependent, reflecting unique societal circumstances. These cases were difficult to predict because they did not have strong algorithmic features. In fact, many of these cases had unique factual features that had influenced the judges to adjust the application of the legal test to the specific circumstances of the focal case. For instance, we found several cases (including Beaudoin et 9154–4635 Quebec Inc., Re and Wilcom Systems Ltd. v. Minister of National Revenue) where the judge disregarded the particular nature of the work relationship (which was typical of an employment relationship) based on the fact that it had been the worker’s choice to be a contractor. These are quite unusual decisions in Canada, because the worker’s intent is in principle non-determinative (in contrast to Californian cases where the worker’s intention is explicitly part of the Borello test). In other cases, we noted that the judges had tweaked the test and argued that some factors (which were usually relevant) were non-determinative because of the industry or the nature of the work. For instance, in Decision No. 598/12, the AI algorithm classified the worker as an employee, but the court decided upon a contractor status even though most features of the case indicated employment (supervision, exclusivity, and delegation of tasks). The judge found that these elements were not determinative and claimed that they were a product of statutory requirements or industry practice. In the same vein, the case Morris Meadows Country Holidays and Seminars Ltd. v. Minister of National Revenue considered the situation of a worker hired as a municipality treasurer and was later appointed Chief Administrative Officer. Many of the features of the relationship indicated the existence of a contractor relationship, which led the AI models to classify this worker as a contractor. However, the judge argued that many of the factors (which usually indicate a contractor relationship)—including the ability to hire, setting work hours, and delegation of tasks—were not determinative in this case because of the management nature of the position. AI-powered legal aid: https://MyOpenCourt.org/ In addition to deciphering legal decision-making, algorithms seem to be able to provide a broader access to justice by delivering personalized predictions and identifying similar historical situations. To harness this potential, we deployed our predictive algorithms as a direct-to-public (DTP) legal help platform at https://MyOpenCourt.org/. This initiative was in response to various crucial needs in the current economy. We next discuss the deployment and implications generated from this real-world field implementation. Access to justice Disputes between employers and workers regarding employment status have been increasing over the past years. As discussed, gig economy firms have faced at least 40 major legal challenges around the world. These cases have been brought by gig economy workers seeking to access basic rights, such as minimum wages and paid sick days. Recent evidence showed that national courts fined Uber Eats, Glovo, Just Eat, and Deliveroo € 733 m for misclassifying 60,000 couriers. In addition, the COVID-19 pandemic has exacerbated labor market frictions between workers and employers, presumably due to incentives misalignment between the contracting parties (Smith 2020). However, recent evidence has also shown that many claims were not successful and that gig firms used their resources to fight back (Moyer-Lee and Contouris 2021). In California, Uber and Lyft spent more than 200 million USD on a referendum campaign to exempt their businesses from the newly introduced AB5 law under which their drivers were categorized as employees. Furthermore, as noted in the pending Canada Supreme Court case, Uber Technologies Inc. v. Heller, a classic tactic includes mandatory arbitration clauses that consist of forcing those with a grievance to pay costly administration and filing fees in preliminary stages of the litigation. The misclassification of workers is not a new problem that emerged from the proliferation of gig firms. It rose to the forefront of the public debate because of the modern magnitude and transnational nature of the problem. Moreover, those who are (mis)classified as independent contractors cannot receive benefits such as minimum wage, overtime pay, and medical leave. Many of these workers happen to be in precarious financial situations and are often unable to hire a lawyer for legal advice. In fact, it was observed that the number of people forced to represent themselves has ballooned over the last twenty years (Fragomeni et al. 2020), and the COVID-19 pandemic has exacerbated the problem of the lack of access to justice (Dahan and Liang 2020). This issue affects not only low-income populations; today, many middle-class individuals find themselves financially unable to benefit from the justice system. While there are many possible solutions for increasing the access to justice, one alternative is through legal aid technology. In particular, a new generation of DTP AI tools have emerged with the goal of providing basic legal help. Open AI technology has the potential to determine whether someone has a legitimate legal claim and to help litigants for whom litigation is otherwise out of reach. https://MyOpenCourt.org/ Our platform, which is currently intended for the Canadian market and based on AI models calibrated using Canadian court cases, offers various tools in addition to the worker classification algorithm. In particular, it includes a tool for estimating severance packages, which we recently developed (Dahan et al. 2020). Launched in June 2020, the platform has already been accessed by 30,000 unique users. This platform includes the AI model presented in this paper (as well as other tools) not only to serve the public but also to test our results and collect new data that extend beyond court cases. Our tool is intended for both workers and employers, with the goal of providing a quick first assessment of the status of the law and a personalized assessment of the situation at no cost, thus helping democratize the access to justice. In practice, the classification tool gathers information about the focal situation by asking a series of multiple-choice questions that correspond to the features used by the AI model. It takes less than five minutes for a user to complete all the questions and receive an assessment of the situation (see Fig. 3 for an illustration of one of the questions asked). We also collect demographics data (e.g., age and gender) for statistical purposes. These variables are not used by the AI model, and the data collection is fully anonymized. Fig. 3. Open in a new tab Example of one question on https://MyOpenCourt.org/ Because of comparable accuracy of the different algorithms we considered, we chose to use a decision tree in the platform. This choice allowed us to provide users with clear explanations about the main aspects of the work relationship that determined the prediction outcome. These explanations were generated through a dictionary that expressed in simple language the reason for each split of the tree associated with the focal situation. Moreover, we leveraged the richness of our dataset to provide users with a list of the most relevant past court cases. More specifically, among the cases in the decision tree, we identified those that were closest in terms of industry and duration of work (see Fig. 4 for an example of the tool’s output). Based on this information, we further developed an application that automatically generates a letter draft. For this purpose, we wrote a template letter that was automatically populated using the explanations behind the decision, and cited the most relevant case law that was identified. This letter is generated free of charge at the request of the user. Fig. 4. Open in a new tab Example of the output from https://MyOpenCourt.org/ MyOpenCourt users and data Between June 2020 and June 2021, 322 people used the Employee or Contractor tool to make a prediction (i.e., 322 unique visitors completed all the questions and received a prediction outcome). The following is a brief summary of these users. 84.5% of the users were workers seeking their own classification, while 15.5% were employers.
Among the users who provided gender identification (92.8% of the total users), 56.3 % identified themselves as male.7
The majority of the users (72.4%) inquired about the situation of their current job (as opposed to a past job).
The prediction algorithm determined that the worker’s status was employee in 70.8% of cases. Comparing the data we collected from our public platform relative to the court cases offers an opportunity to examine whether court cases differ significantly from generic situations settled outside the judicial system. Investigating the distribution of features for both datasets (Canadian court cases and https://MyOpenCourt.org/) did not reveal any strong bias in the distribution of the relevant features, as we can be see in Fig. 5. Fig. 5. Open in a new tab Comparison of the distributions of three features (supervision/review of work, delegation of tasks, and ability to hire employees) between the Canadian courts dataset and the data from https://MyOpenCourt.org/ (MOC) In summary, our study did not end with the development of an AI model with a strong prediction accuracy for workers’ status. We further deployed our model in the field by offering an open-access platform that can help users predict the outcome of their own situations, along with clear, tailored explanations. We hope that our platform will help a large number of individuals and, ultimately, democratize the access to justice and to legal advice.
Discussion The classic legal dispute of “employee vs. independent contractor” has become an important issue in many parts of the world, partly because of the ubiquity of the gig economy. When such disputes arise, workers are often asymmetrically affected because of the resources and time required for resolution. In some cases, these disputes end up in court, consuming scarce public resources. One possible way of addressing this asymmetry is the development of AI-based tools to automate and understand the reasoning that underlies legal outcomes. In this work, our ultimate achievement was the deployment of an open-access direct-to-public legal help tool, https://MyOpenCourt.org/, to provide a modicum of legal assistance for workers and small companies. Such open-access tools may have great implications for the access to justice insofar as many individuals have very limited access to legal services (Macfarlane and Sullivan 2021). From a judicial standpoint, advanced AI tools may also help courts to screen and process cases more efficiently. In the criminal justice arena, this approach has already been taken by several countries. In the context of civil cases, the academic literature has shown that AI models can capture legal reasoning and accurately classify cases. Nevertheless, the application of AI models to employment law cases, such as the classification of workers, has received limited attention. As part of an attempt to bridge this gap, this paper has offered a data-driven study on the implications of using an algorithmic model to classify workers’ employment status. We trained our model using all previous cases decided by Canadian and Californian courts. We then presented the potential implications for judicial decision-making and discussed the field deployment of our AI model via https://MyOpenCourt.org/. More specifically, we evaluated the feasibility of developing an AI model to determine whether a worker is an employee or an independent contractor. To do so, we collected all relevant Canadian and Californian court cases between 2002 and 2021, and we collaborated with a team of lawyers to carefully annotate and pre-process the data by generating the features needed as input to the AI model. We found that supervised ML models, even simple off-the-shelf methods, could consistently classify court cases at an out-of-sample accuracy of 82–96%. These findings partially shed light on the debate surrounding the computability of law (Deakin and Markou 2020). Skeptics have argued that certain features of legal reasoning are not consistent with ML, particularly the reflexivity of legal knowledge and the incompleteness of legal rules (Markou and Deakin 2020). This study provided strong evidence that some legal questions can be supported by AI models. First, while we argued that many aspects of legal reasoning have algorithmic features that lend themselves to automation, there are still limitations to computability, notably if certain conditions are not met. Second, we argued that algorithms are reflexive, and thus can capture, or at least identify, the reflexive features of the law. In the same way that the goals and priorities pursued by lawyers and judges are important, the goals and priorities that are incorporated in the development of algorithms matter. Therefore, in the legal context, AI could play a powerful role in assisting decision makers and workers, provided that the algorithm is carefully crafted to respect the reflexive nature of the law. Our study empirically tested the computability of employment status determination, a foundational issue in many areas of law, including tax, employment, and tort law. With regard to this specific issue, it has been argued that while the classification test used by courts is essentially algorithmic (because it follows a specific list of rules and criteria), there is no easy solution to classifying a new case. For example, when a new type of social or economic category is presented to the court for classification (e.g., a gig worker), judges often propose a number of alternative solutions that are tested against each other (Markou and Deakin 2020). While the critiques of ML in law have merits, the current study attempted to challenge the assertions. We argue that legal reasoning is not always forward looking and that legal ML is not always backward looking. More specifically, our study provides empirical evidence that novel situations are not as frequent as one might think. More specifically, our models show that a large number of cases present strikingly similar facts. In addition, we show that ML can help identify new facts along with the emergence of a new precedent. Similar to ML, judges and lawyers also apply “past” facts to future cases. Finally, even when confronted with novel facts, such as the context of the gig economy, a well-crafted reflexive AI can act as a detector of novel facts by spotting unconventional cases and atypical situations. A non-adjudicating ML is not designed to predict every case; it is designed to evolve and to be retrained regularly with new data. Unfortunately, it is hard to come up with a clear segmentation of when ML techniques should be used and when they should not. That being said, ML techniques often work well for fact-intensive questions of law that generates a compact universe of cases and a list of factors that are most relevant to the court when deciding the outcome like in this paper (see Alarie et al. (2018)). Also, there is an emerging consensus in the legal community that ML should not be used for adjudication (although already being used in some countries, as discussed in Markou and Deakin (2020)). The same applies to areas of law that are fast changing, to cases that involve a high level of subjectivity, and to cases where judges are prone to biases (e.g,. family or criminal cases, see Park (2020)). By combining two different datasets (Canadian and Californian court cases), we leveraged AI algorithms as a tool for use in comparative law. By using algorithms trained on one dataset to to predict outcomes of the other dataset, we found surprisingly strong consistency between two vastly distinct jurisdictions. In addition, we observed a remarkable consistency in judicial decisions among several AI algorithms. We ultimately chose to use a simple decision tree that provided a highly desirable interpretability dimension to explain the rationale for the prediction. We also carefully examined missclassified cases using our AI algorithms to gain insights into adaptive judicial decisions, and we proposed the division of misclassified cases into three categories. Finally, we conclude our paper by discussing the deployment of our AI model via an open-access platform called https://MyOpenCourt.org/. This platform aims to serve the public and help self-litigants answer questions about employment law. During the first 15 months, 322 people used the Employer or Contractor tool offered in this platform (and more than 20,000 people used the platform, which includes several legal aid tools) to predict whether they would be considered employees or independent contractors. We believe that this type of platforms can help the community and democratize the access to legal advice and to justice. Our research contributes to the literature and the practice of using AI in legal contexts. We are among the first to discuss the potential implications of leveraging AI for civil employment cases, and we hope that this study will stimulate further discussion on this topic.
Material and methods Data collection Cases collection All Canadian cases in the Westlaw database that referred explicitly to the Sagaz case were collected,8 leading to a total of 1,225 cases. Among these cases, a significant number were not related to the determination of workers’ status. After selecting only the relevant cases, we retained 538 cases. Similarly, Californian data were also obtained from the Westlaw database by collecting all cases citing the Borello case. Between 1989 to 2021, we found 810 such cases. After filtering out irrelevant cases that were not related to the employee vs. contractor question, the dataset was reduced to 217 relevant cases. Feature identification Important aspects of developing an effective dataset are to identify a set of prominent quantifiable factors and design objective scales that permit the reduction of any given case to a set of standardized descriptors. To determine the relevant variables to be extracted from the cases, we thoroughly considered the factors that were brought up in the Sagaz seminal case (Canada) and in the Borello case (California). The Borello case and its associated Borello test cover a variety of factors that include the six factors outlined in the Sagaz case. Thus, these factors formed a strong basis for our comparative analysis. They included the following: level of control of the employer, equipment property, ability to hire helpers, financial risk, opportunity for profit, and responsibility for investment. These common factors were estimated on a common scale for both the Canadian and the Californian cases. To quantify each of these factors, we based our scales on a legal analysis of how judges interpreted and appreciated these factors. This led us to narrow each subjective criterion into a set of graded scales. For instance, the “worker’s opportunity for profit in the performance of his or her tasks” brought up in the Sagaz case, which could formally cover many aspects of a worker’s experience, was generally estimated by the judges by considering the way that the worker was paid. Workers paid via fixed wages have no opportunity for profit, whereas workers who receive commissions have a clear opportunity for profit. We thus designed a four-point scale ranging from receiving only wages to being paid only on commissions to quantify the opportunity for profit of a worker, including intermediate cases depending on the proportion of fixed salary. We applied the same methodology to all six Sagaz criteria, which allowed us to make this subjective and multifarious dimension more quantifiable, as well as ensure consistency across legal researchers. In addition to the variables related to worker classification, we also collected other factual data on each case, namely, the year, industry, length of service, province (in Canadian cases), and the court, as well as other indicators that were present in some cases, including the exclusivity of services or whether the worker was required to wear a uniform. Altogether, 12 common factors were collected in both databases and used for prediction (see Table 1 for Canadian cases and Table 2 for Californian cases). These variables were of three types: (i) categorical variables, such as the industry sector (1: finance, 2: services, 3: manufacture, 4: agriculture), (ii) binary information about the case (e.g., whether or not the hirer supervised the tasks of the worker or provided performance reviews), and (iii) ordinal variables that were used to evaluate more finely some factors, such as the opportunity for profit discussed above, or, for instance, who sets the work hours, which were split into four levels from the highest level of control (1: hirer sets the number of hours and when the work is done) to the lowest level of control (4: worker sets the number of hours and when the work is done), through intermediate levels (2: hirer sets the number of hours, but not when the work is done, or 3: worker sets the number of hours but not when the work is done). After defining and scaling all the variables, we began the annotation process. Table 1. Summary of the observed variables in the Canadian dataset Type Min Max Median Observations Industry Categorical 1 4 2 538 Supervision/review of work Categorical 1 2 1 445 Delegation of tasks Categorical 1 2 1 481 Where the work is performed Categorical 1 2 1 447 Is the worker required to wear a uniform? Categorical 1 2 2 193 Length of service Continuous 0 38 1 505 Ownership of tools Ordinal 1 5 2 487 Ability to hire employees Ordinal 1 3 1 354 Chance of profit Ordinal 1 6 1 510 Risk of loss Ordinal 1 3 1 487 Exclusivity of services Ordinal 1 3 1 360 Who sets the work hours Ordinal 1 4 2 436 Outcome Categorical 1 2 1 538 Open in a new tab Table 2. Summary of the observed variables in the Californian dataset Type Min Max Median Observations Outcome Categorical 1 2 1 217 Supervision/review of work Categorical 1 2 1 130 Ability to hire employees Categorical 1 3 2 91 Exclusivity of services Categorical 1 3 3 110 Ownership of tools Continuous 1 5 3 175 Is the worker required to wear a uniform? Continuous 1 2 1 84 Who sets the work hours Continuous 1 4 1 157 Delegation of tasks Continuous 1 2 1 188 Chance of profit Continuous 1 5 3 185 Risk of loss Continuous 1 3 2 123 Where the work is performed Continuous 1 2 1 166 Length of service Categorical 0 25 1 76 Open in a new tab Features and scales The following is a summary of the features and scales used in this study. The Industry variable was labeled as follows: 1: finance, 2: services, 3: manufacturing, and 4: agriculture. Length of service was rounded to the closest duration in years. Delegation of tasks referred to the level of management of the worker: 1: Hirer delegates most tasks to the worker, and 2: Worker decides how to do most or all the tasks and what tasks need to be completed. Who sets the work hours was based on a four-point scale: 1: Hirer sets the number of hours and when the work is done, 2: Hirer sets the number of hours but not when the work is done, 3: Worker sets the number of hours but not when the work is done, and 4: Worker sets the number of hours and when the work is done. Supervision of work assessed whether the hirer supervises the tasks of the worker and/or gives performance reviews (1: Yes, 2: No). Ability for the worker to hire employees was based on a three-point scale: 1: No, 2: Yes with the hirer’s approval (or allowed to hire but does not in practice), and 3: Yes on their own. Ownership of tools was scored on a five-point scale: 1: Hirer owns or provides all the tools, 2: Hirer owns or provides tools that are essential to performing the job, 3: Hirer and worker both provide a substantial amount of tools, 4: Worker owns or provides tools that are essential to performing job, and 5: Worker owns or provides all the tools. Chance of profit referred to how the worker is paid: 1: Only fixed wages (i.e., paid hourly or per task), 2: Mostly fixed wages with a chance of commission, 3: Mix of a wage and a commission, where it is unclear which is predominant, 4: Mostly commission, with a chance of other incentives, 5: Only commission, with a chance of incentives, and 6: Only commission, without bonuses (no possibility to earn additional compensation). Risk of loss was scored on a three-point scale: 1: No risk of loss for the worker, 2: Some risk of loss for the worker (pay for some business expenses), and 3: High degree of risk of loss for the worker (pay for business expenses/have money invested/liable for losses). Exclusivity of services referred to the amount of work done for the hirer: 1: Worker works exclusively for the hirer, 2: Worker does some work for this hirer as well as for others (or for themselves) or worker is allowed to work for other hirers, and 3: Worker does the majority of work for other hirers or for themselves. Where the work is performed referred to whether the work premises were provided or instructed by the hirer: 1: Yes, and 2: No. Finally, Is the worker required to wear a uniform: 1: Yes, and 2: No. Data collection Our databases were collected by a team of caseworkers trained in law. First, to ensure consistency, we trained caseworkers in Sagaz and its various criteria, and they completed exercises on a few common sample cases to assess the consistency of data collection variables. The 448 Canadian cases were shared among the caseworkers, who read each case thoroughly and answered a series of questions that were considered when determining the employer’s level of control based on the scales determined above. For each feature annotated, the caseworker was given a set of multiple-choice questions, including the option of not answering if the case did not consider or report any indication on a specific factor. The caseworker answered each question by reading the facts of the case and the judge’s legal analysis. Missing data As shown in Tables 1 and 2, many cases contained missing information. There were missing values either because a specific criterion was not applicable to the situation, or it was irrelevant to the judgement. The presence of missing values may have been an issue because they could have potentially correlated with the decision of the judge who wrote the case. To test whether missing data were correlated with the outcome, we constructed a binary database of missing values, where zeros indicated that information was present in the original database and one indicated when information was missing. We computed the correlation matrix of this database, focusing on correlations with the outcome. We found very low correlation coefficients, all of which were below 0.09 in absolute value in the Canadian dataset and were slightly higher in the U.S. dataset regarding three features (21% with delegation of tasks, 15% with the ownership of tools and where the work is performed, and 12% with exclusivity of services). As expected, we also observed strong correlations between different missing data fields (e.g., missing information about the risk of loss showed high correlations with the absence of data on chance of profit or ownership of tools) (Fig. 6). Fig. 6. Open in a new tab Correlation matrix of the missing data including the outcome. We found very low correlations in the Canadian dataset, and low, yet slightly higher, correlations in the Californian dataset To mitigate the impact of missing data on the prediction outcome, we used three different pre-processing approaches. We obtained similar results for all three approaches, including imputing missing data by the median value of the entire dataset, as well as relying on more sophisticated methods where the missing data were coded as new categorical features, whereas the missing numerical variables were iteratively imputed (Van Buuren and Groothuis-Oudshoorn 2011). In the main text of this paper, we report our results for a dataset in which the missing data were replaced by a predicted value based on the remaining features, using a random forest predictor, with 15 trees of depth less than three. Our findings showed that all methodologies provided similar accuracy levels and managerial insights. Algorithmic worker classification Naive data analyses We began the analyses by computing the correlation matrix of the dataset, as shown in Fig. 1 in the “Results” section. This figure indicates the difficulty in identifying the different factors, given that high correlations exist between the features. Moreover, the correlation analysis led us to identify a strong correlation between the outcome variable and some features, which we examined more carefully by plotting several bi-variate distributions. Absence of clear clusters Based on our observations of strong correlations between factors as well between some factors and the outcome, we investigated whether the cases labeled employees were organically different from the cases classified as independent contractors. We relied on clustering algorithms to identify the potential existence of clusters in the dataset, and then we considered whether these clusters explained the employer/contractor division. The results of the k-means clustering algorithm (Ahmad and Dey 2007) with two clusters are depicted in Fig. 7, where the axes are the two principal components from the principal component analysis (PCA). For illustration purposes, we focused our clustering analyses on the Canadian dataset (which included a larger number of observations). Similar qualitative conclusions were drawn from the results of the analysis of the Californian dataset. Fig. 7. Open in a new tab Samples in two-dimensional PCA space with k-means clustering for the Canadian dataset (two clusters) Although the two clusters in Fig. 7 may visually appear to be well separated, they scored quite low in the classical measures of cohesion and separation of clusters (e.g., a silhouette score of 0.226), indicating that the two clusters were not well separated. This conclusion was confirmed using alternative clustering algorithms, including affinity propagation, the mean shift method, and spectral clustering, all of which yielded moderate to low scores (see Table 3). Thus, these results suggested that there was no clear separation of the categories within the dataset. Table 3. Adjusted rand index between clusters and outcome and silhouette score Model Adj. rand index Silhouette score k-means −0.010 0.583 k-means −0.014 0.466 Affinity propagation 0.063 0.144 Mean shift −0.008 0.521 Spectral clustering −0.006 0.778 Spectral clustering 0.000 0.058 Open in a new tab We also found that the goodness-of-fit of clusters did not necessarily indicate that the clusters were aligned with the outcomes (i.e., that one cluster represented the “employee” cases and the other represented the “independent contractor” cases). To address this discrepancy, we computed the adjusted rand index (ARI) for each clustering method (Rand 1971). The k-means algorithm with k = 2 yielded the highest ARI (0.666). Given that the outcome was binary (and thus a random guess translated into 0.5), an ARI of 0.666 indicated a modest match between the clusters and the actual outcome. The results reported in this section strongly suggest that unsupervised learning algorithms are not capable of generating a satisfactory performance in terms of classifying employees versus independent contractors. In other words, a strong overlap in features was found in both classes. Supervised learning models Our analysis of the judicial reasoning, which was reported in the “Results” section of this paper, was performed using a decision tree. Specifically, we used the scikit learn function, DecisionTreeClassifier, with a maximal depth of three, the greedy algorithm (Gini index), and a minimum number of samples per split or per leaf equal to ten to avoid overfitting. Several alternative algorithms were used to confirm the results and to examine whether significantly better outcomes would emerge when more sophisticated methods were applied. In particular, we considered a logistic regression, random forest (with 15 estimators and a maximal depth of four), K-nearest neighbor, support vector classifier (both a linear kernel and with probability), Gaussian process algorithm, Adaboost, and XGBoost. All models were evaluated based on a three-fold cross validation, and all hyperparameters were set at their default value based on Python’s sklearn package. Table 4 reports the prediction accuracies of various training/test combinations for the seven algorithms that we considered. Table 5 shows the Canadian dataset and presents the accuracy, F1 scores, and area under the curve (AUC) for the entire dataset and when the samples with more than three missing variables were dropped. Interestingly, removing these samples improved the accuracy of all the models we considered. In this setting, the accuracy exceeded 90% for all models, and we even reached an out-of-sample prediction accuracy of 96% in the random forest model. Table 4. Prediction accuracy of supervised models. Accuracy is evaluated by the average of a ten-fold cross validation, for various combinations of training/test sets Model Can/Can Cali/Cali Can/Cali Cali/Can All/Can All/Cali Logistic regression 0.927 0.883 0.811 0.914 0.915 0.811 Random forest classifier 0.896 0.860 0.816 0.898 0.909 0.802 K-Neighbors classifier 0.852 0.827 0.788 0.884 0.885 0.788 SVC 0.904 0.813 0.805 0.909 0.909 0.806 Gaussian process classifier 0.919 0.810 0.792 0.911 0.911 0.792 AdaBoost classifier 0.860 0.770 0.810 0.911 0.911 0.811 XGB classifier 0.880 0.847 0.778 0.904 0.904 0.778 Open in a new tab Table 5. Prediction accuracy, F1 score, and AUC for all algorithms trained and tested on the Canadian dataset. Accuracy was evaluated by the average of a three-fold cross validation Model Accuracy F1 AUC 3-,Accuracy 3-,F1 3-,AUC Logistic regression 0.919 0.872 0.917 0.957 0.965 0.951 Random forest classifier 0.904 0.846 0.924 0.963 0.968 0.956 K-Neighbors classifier 0.830 0.712 0.881 0.909 0.928 0.897 SVC 0.926 0.885 0.918 0.959 0.967 0.953 Gaussian process classifier 0.919 0.872 0.916 0.954 0.962 0.947 AdaBoost classifier 0.889 0.831 0.926 0.957 0.965 0.956 XGB classifier 0.933 0.895 0.926 0.946 0.956 0.939 Open in a new tab The results shown in Table 4 indicate that the performance of the supervised ML models for the Can/Can and Cali/Cali combinations ranged between 0.81 and 0.927, where the logistic regression for the Can/Can setting yielded the highest performance (92.7%). Table 6 shows the variation in model performance with respect to the number of folds included in the cross-validation procedure, which provided insights into the effect of varying the sample size on the prediction performance. We found that a linear model, such as logistic regression, performed better when more observations became available for testing purposes. The variations in the performance of ensemble-based models (e.g., random forest, AdaBoost, XGBoost) appeared to be consistent across different values of the folds. Another observation worth mentioning is that the performance of the linear model was reduced relative to the non-linear models when more data were available for testing purposes. Table 6. CV score when varying the number of folds Folds 2 3 5 10 Training samples 269 358 430 484 Logistic regression 0.916 0.926 0.929 0.922 Random forest classifier 0.929 0.937 0.926 0.931 K-Neighbors classifier 0.898 0.896 0.888 0.889 SVC 0.920 0.926 0.920 0.924 Gaussian process classifier 0.914 0.924 0.926 0.917 AdaBoost classifier 0.918 0.931 0.914 0.926 XGB classifier 0.911 0.931 0.931 0.931 Open in a new tab The feature importance associated with the random forest method are reported in the “Results” section. They appeared to be consistent with other estimates of feature importance that were extracted from those algorithms. For instance, the estimated coefficients of the logistic regression for re-normalized data with one-hot encoding using the Canadian dataset, reported in Table 7, allowed us to identify exclusivity of services, delegation of tasks, and supervision of work as the most important features. Another view of feature importance can be obtained through the Shapley values (Lundberg and Lee 2017) of the variables used by the XGBoost algorithm (see Fig. 8 for the same dataset). This metric has been used in recent literature to examine the importance of features in predictive analytics (e.g., Adulyasak et al. 2020; Satopää et al. 2021). The Shapley values in our case revealed a similar ranking of feature importance, with exclusivity of services ranking first, followed by delegation of tasks and risk of loss. Interestingly, exclusivity of services was not among the top features in the random forest feature importance analysis. Table 7. Estimated coefficients of logistic regression using one-hot encoding of binary variables (indicated by the presence of a number after the feature label) Coefficient Supervision/review of work_1 −0.754 Supervision/review of work_2 0.594 Delegation of tasks_1 −1.194 Delegation of tasks_2 1.476 Where the work is performed_1 −0.106 Where the work is performed_2 0.076 Is the worker required to wear a uniform?_1 −0.119 Is the worker required to wear a uniform?_2 0.311 Length of service −0.105 Ownership of tools 0.582 Ability to hire employees 0.433 Chance of profit 0.235 Risk of loss 1.308 Exclusivity of services 2.493 Who sets the work hours 0.379 Open in a new tab Fig. 8. Open in a new tab SHAP importance of features for the XGBoost classifier Analysis of misclassified cases We combined the results of all the algorithms and determined that a large number of misclassified cases were misclassified by most—if not all—algorithms. We extracted those cases and systematically analyzed the decision and details of each case in order to identify the source of the misclassification outcome. Our results (see the “Results” section for all the details) indicated that those cases had either (i) very unusual factors or procedural circumstances, (ii) features related to both employee and contractor relationships, or (iii) decisions that were influenced by extra-juridical variables.
Acknowledgements We would like to thank the team at the Conflict Analytics Lab and the Scotiabank Centre for Customer Analytics at Queen’s University, particularly our JD students, who compiled and structured the data (Holly Grosdanis, Solinne Jung, and Brian Tsui). We are also grateful to Brandon Loehle and Max Saunders, who supported this project for almost two years. Finally, we thank Art Cockfield, Yuri Levin, David Saunders, Stephen Thomas, Kevin Banks, Joshua Karton, Dan Sfedj, and Dean Mark Walter for their support.
Funding The Project is funded by Social Sciences and Humanities Research Council of Canada, Grant no. New Frontier.
Footnotes 1 416 P.3d 1 (Cal. 2018). In this case, the issue at stake was the application of a statutory wage order. 2 https://www.pwc.es/es/publicaciones/digital/evaluacion-economia-colaborativa-europa.pdf 3 https://fortune.com/2020/11/04/prop-22-california-proposition-uber-lyft-gig-companies-workers-passes/ 4 Note that Canada has a third category, the dependant contractor which is a worker that is not an employee but still considered economically dependent on the company (or individual) they work for. This category has not been widely used by Canadian courts, as we only found 16 such court outcomes and, thus, it was not considered in our analysis. 5 While the gig economy is more prone to job hopping, shorter work duration is a general trend in the workforce, see https://www.forbes.com/sites/jeannemeister/2012/08/14/the-future-of-work-job-hopping-is-the-new-normal-for-millennials/ accessed December 2021; see also Pranaya (2014). 6 Note that this issue is currently being debated in Canadian courts. In CUPW v. Foodora Inc., the Ontario Labour Relations Board found that “Foodora couriers are dependent contractors and must be treated as such under the Act. As the evidence bears out, couriers more closely resemble employees than independent contractors.” In Heller v. Uber Technologies Inc., 2021 ONSC 5518, Justice Perell at the Ontario Superior Court of Justice certified the $400 million class action lawsuit where the workers submitted that they had been misclassified as independent contractors. The judge decided, in para 192, that there was at least some basis for concluding that some or all the drivers may have been misclassified. 7 The answer options to the question “What is your gender?” were man, woman, non-binary, other, and prefer not to disclose. 8 https://signon.thomsonreuters.com Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Maxime C. Cohen, Samuel Dahan, Warut Khern-am-nuai, Hajime Shimao and Jonathan Touboul have contributed equally to this work.
| 2023-03-30T00:00:00 |
2023/03/30
|
https://pmc.ncbi.nlm.nih.gov/articles/PMC10061388/
|
[
{
"date": "2023/03/01",
"position": 20,
"query": "AI labor union"
}
] |
Living in a Post-Scarcity Society: How Automation, AI, and ...
|
Living in a Post-Scarcity Society: How Automation, AI, and Universal Basic Income Could Reshape the Global Economy
|
https://medium.com
|
[
"Daniel Bron"
] |
These technologies enable the efficient production and distribution of goods and services, significantly reducing the need for human labor and allowing people ...
|
Living in a Post-Scarcity Society: How Automation, AI, and Universal Basic Income Could Reshape the Global Economy Daniel Bron 16 min read · Mar 28, 2023 -- Listen Share
I. Introduction
A. Defining post-scarcity society
A post-scarcity society is a hypothetical economic model in which the production and distribution of goods and services are so efficient and plentiful that the basic needs and wants of every individual are met without the need for labor or financial exchange. This type of society is characterized by the widespread availability of resources, minimal or non-existent poverty, reduced income inequality, and a shift from an economy driven by scarcity to one based on abundance.
In a post-scarcity society, advancements in technology, particularly automation and artificial intelligence (AI), play a crucial role in achieving this level of abundance. These technologies enable the efficient production and distribution of goods and services, significantly reducing the need for human labor and allowing people to focus on more creative, fulfilling pursuits.
B. Historical context and technological advancements
The concept of a post-scarcity society has its roots in the works of various philosophers, economists, and futurists, including Karl Marx, John Maynard Keynes, and Buckminster Fuller. Throughout history, technological advancements have had significant impacts on the global economy, driving changes in production methods, labor markets, and the distribution of wealth.
The First Industrial Revolution in the 18th and 19th centuries introduced mechanized production, steam power, and railroads, leading to increased productivity and economic growth. The Second Industrial Revolution, in the late 19th and early 20th centuries, brought about further advancements, such as electrification, the assembly line, and the telephone, accelerating global trade and communication.
Today, we are experiencing the Fourth Industrial Revolution, characterized by the fusion of digital, physical, and biological technologies. The rise of automation, AI, the Internet of Things (IoT), and advanced manufacturing techniques, such as 3D printing, has the potential to transform the global economy in ways previously unimaginable.
II. Automation and Its Economic Impact
A. The rise of automation
Industrial automation
Industrial automation refers to the use of control systems, such as computers and robots, to manage and optimize manufacturing processes. It has evolved over the past century, beginning with the introduction of assembly lines in the early 20th century, which allowed for mass production and increased efficiency.
The adoption of programmable logic controllers (PLCs) in the 1960s and 1970s further streamlined manufacturing processes and improved quality control. Today, advancements in robotics, machine learning, and the Internet of Things (IoT) have led to the development of smart factories, which leverage data-driven decision-making and real-time monitoring to optimize production.
According to a 2020 report by the World Economic Forum, by 2025, machines are expected to perform more tasks in the workplace than humans, accounting for 52% of the total task hours, up from 29% in 2018.
2. Robotics and advanced manufacturing
Robotics has played a crucial role in advancing automation, particularly in manufacturing. The use of robots in assembly lines and production processes has increased exponentially in recent decades, with industries such as automotive, electronics, and aerospace being early adopters. The International Federation of Robotics estimated that there were nearly 3 million industrial robots in operation worldwide in 2020.
Advanced manufacturing techniques, such as additive manufacturing (3D printing), have further revolutionized the production process, allowing for rapid prototyping, reduced waste, and the ability to create complex geometries that were previously impossible or prohibitively expensive.
B. Job displacement and new job creation
Automation has led to concerns about job displacement, as machines and algorithms can now perform tasks that previously required human labor. A 2017 study by McKinsey Global Institute estimated that by 2030, automation could displace up to 800 million jobs worldwide.
However, history has shown that technological advancements can also create new jobs and industries. For example, the rise of the internet and smartphones led to the creation of jobs in e-commerce, app development, and digital marketing. The World Economic Forum’s Future of Jobs Report 2020 estimated that by 2025, 85 million jobs may be displaced due to automation, but 97 million new roles could emerge in response to the technological shift.
C. The changing nature of work
As automation advances, the nature of work will continue to change. The demand for manual and routine tasks will decrease, while the demand for cognitive, social, and creative skills will increase. The workforce will need to adapt by acquiring new skills and embracing lifelong learning.
A 2020 report by the OECD found that about 14% of jobs are at high risk of automation, while 32% will face significant changes. This highlights the need for governments, educational institutions, and businesses to invest in reskilling and upskilling programs, as well as promoting a culture of continuous learning.
D. Productivity and efficiency gains
Automation and robotics have led to significant productivity and efficiency gains across various industries. According to a 2015 study by the International Federation of Robotics, the use of industrial robots increased global productivity by 0.36 percentage points per year between 1993 and 2007.
These gains result from the ability of machines to work faster, more accurately, and with fewer errors than human workers. Automation also enables businesses to operate 24/7, further increasing productivity. Additionally, the efficient use of resources and reduction of waste that automation provides can lead to cost savings and improved sustainability.
However, it is important to note that these gains may not be evenly distributed across society. Without proper policies in place, automation could exacerbate income inequality, as those with the skills to work alongside machines may see their wages rise, while those without such skills may see their job prospects and wages decline.
III. Artificial Intelligence and the Global Economy
A. The growth of AI and machine learning
Artificial Intelligence (AI) has been a significant driving force behind the recent technological advancements that are shaping our world. AI refers to the development of computer systems that can perform tasks that would typically require human intelligence, such as learning, reasoning, problem-solving, and understanding natural language. Machine learning, a subset of AI, involves teaching computers to learn and adapt through experience, without being explicitly programmed.
The growth of AI and machine learning can be attributed to several factors, including increased computing power, advances in algorithms, and the availability of vast amounts of data. As of 2021, the global AI market was valued at approximately $62.35 billion, with projections estimating that it will reach $733.67 billion by 2027, growing at a CAGR of 42.2% from 2020 to 2027.
B. AI in various industries
Healthcare
AI has the potential to revolutionize the healthcare industry by improving diagnostics, treatment plans, and patient care. Applications of AI in healthcare include medical imaging analysis, drug discovery, virtual nursing assistants, and predicting patient outcomes. For instance, IBM’s Watson for Oncology can analyze patient data and suggest evidence-based treatment options, while Zebra Medical Vision uses AI algorithms to detect diseases in medical imaging data.
Finance
In the financial sector, AI and machine learning are being used for fraud detection, credit risk assessment, and algorithmic trading. Banks and financial institutions leverage AI to analyze customer data and predict future trends, improving decision-making and risk management. AI-powered chatbots and virtual assistants are also enhancing customer service in the industry.
Retail
AI is transforming the retail industry through personalized marketing, inventory management, and supply chain optimization. Machine learning algorithms analyze customer behavior and preferences, allowing retailers to offer tailored product recommendations and promotions. AI-driven tools also help retailers optimize their inventory and supply chain, reducing costs and improving efficiency.
Transportation
The transportation industry is experiencing significant disruption due to AI, particularly with the development of autonomous vehicles. Self-driving cars, powered by AI algorithms and sensors, have the potential to improve traffic flow, reduce accidents, and increase fuel efficiency. AI is also being used in public transportation systems, logistics, and shipping to optimize routes and reduce operational costs.
C. AI’s effect on global competitiveness
As AI becomes increasingly integrated into various industries, its impact on global competitiveness cannot be ignored. Countries that invest in AI research and development, infrastructure, and workforce training will likely gain a competitive edge in the global economy. The widespread adoption of AI may also lead to a reshuffling of global supply chains, as companies seek to optimize production and distribution using AI-driven insights.
According to a 2021 report by the Center for Data Innovation, the United States, China, and the European Union were leading the global AI race. However, the competitive landscape is constantly changing as more countries recognize the importance of AI and invest in its development.
D. Ethical considerations
The rapid growth of AI raises several ethical concerns, including data privacy, algorithmic bias, and the potential for job displacement. Ensuring the responsible development and deployment of AI technologies is crucial for addressing these issues and maintaining public trust.
Transparent and accountable AI systems, as well as policies that protect individual privacy and prevent the misuse of data, are essential for addressing ethical concerns. Furthermore, collaboration between governments, businesses, and educational institutions will be vital in developing strategies to mitigate job displacement and support workers as they transition to new roles in an AI-driven economy.
IV. Universal Basic Income as a Potential Solution
A. Defining Universal Basic Income (UBI)
Universal Basic Income (UBI) is an economic policy that provides every citizen with a regular, unconditional payment, regardless of their employment status or income level. The primary objective of UBI is to guarantee a minimum standard of living for all individuals, alleviating poverty and providing a safety net in the face of economic uncertainties, such as those brought about by automation and AI.
B. Historical examples and pilot programs
The concept of UBI can be traced back to the writings of philosophers like Thomas Paine and John Stuart Mill. In recent years, various pilot programs and experiments have been conducted to assess the feasibility and impact of UBI. Some notable examples include:
Alaska Permanent Fund Dividend: Since 1982, Alaska has distributed a portion of its oil revenue to residents through an annual dividend, providing a form of basic income. Finland’s UBI experiment: In 2017–2018, Finland conducted a UBI trial, providing 2,000 unemployed citizens with a monthly payment of €560. Stockton Economic Empowerment Demonstration (SEED): This U.S. pilot program, conducted in Stockton, California, provided 125 residents with $500 per month for 24 months.
These pilot programs have provided valuable insights into the potential effects of UBI on individual well-being, economic security, and labor market outcomes.
C. Potential benefits of UBI
Poverty reduction
By providing a guaranteed income, UBI has the potential to significantly reduce poverty and improve the financial stability of low-income households. Studies of UBI pilot programs have shown positive impacts on recipients’ well-being, including reduced financial stress, improved mental health, and increased access to healthcare and education.
Economic stimulation
UBI can also act as an economic stimulus by increasing consumer spending, particularly among low-income individuals who are more likely to spend additional income on goods and services. This increased demand can, in turn, generate new job opportunities and support economic growth.
Increased entrepreneurship and creativity
By providing a financial safety net, UBI may encourage individuals to pursue entrepreneurial ventures, take on creative projects, or engage in activities that have social value but are not well-compensated in the market. This could foster innovation, drive economic growth, and contribute to a more vibrant and diverse society.
D. Criticisms and drawbacks of UBI
Despite its potential benefits, UBI has faced several criticisms and concerns:
Work disincentive: Some argue that providing a guaranteed income may discourage individuals from seeking employment or reduce their work hours, potentially leading to a decline in labor force participation. Inflation: Critics also worry that increased consumer spending resulting from UBI could lead to inflation, eroding the purchasing power of the basic income and potentially exacerbating income inequality. High cost: The financial burden of implementing a UBI program can be significant, raising concerns about its long-term sustainability and the potential need for increased taxes or reduced public services.
E. UBI funding models and implementation challenges
To address the cost concerns associated with UBI, various funding models have been proposed, including wealth taxes, carbon taxes, and taxes on automation. In addition to funding challenges, implementing a UBI program also involves logistical considerations, such as determining eligibility criteria, payment amounts, and delivery mechanisms.
The success of a UBI program depends on striking the right balance between providing an adequate income to achieve its social and economic objectives while maintaining fiscal responsibility and addressing potential negative consequences. As discussions around UBI continue, it is important to carefully consider the potential benefits and drawbacks, as well as the various funding models and implementation challenges.
V. The Societal Implications of a Post-Scarcity Society
A. Education and skill development
In a post-scarcity society, the importance of education and skill development will likely increase, as individuals need to adapt to the evolving job market and the demands of an AI-driven economy. Traditional education systems may need to shift towards more flexible, lifelong learning models, focusing on critical thinking, creativity, and adaptability.
The rise of online learning platforms, such as Coursera and edX, has already begun to democratize access to education and offer diverse, skills-based courses. In a post-scarcity society, governments and educational institutions may need to invest more in these platforms, as well as in vocational training and reskilling programs, to help individuals transition into new careers and remain competitive in the workforce.
B. Income inequality and wealth redistribution
A post-scarcity society could potentially address income inequality and wealth redistribution through the implementation of policies such as universal basic income (UBI). By providing a guaranteed income for every citizen, UBI could alleviate poverty, reduce income disparities, and provide a safety net for individuals affected by job displacement due to automation and AI.
However, addressing income inequality in a post-scarcity society will also require more comprehensive strategies, including progressive taxation, investments in public goods and services, and policies that promote worker rights and fair wages.
C. Environmental sustainability
In a post-scarcity society, the efficient use of resources and a focus on environmental sustainability will be crucial for maintaining global abundance. Automation and AI can contribute to sustainability by optimizing energy consumption, reducing waste, and improving supply chain efficiency.
Additionally, a shift towards a circular economy model, which emphasizes the recycling and reuse of materials, could further promote environmental sustainability in a post-scarcity society. Investments in renewable energy, sustainable agriculture, and innovative technologies that reduce the environmental impact of production and consumption will also be vital for ensuring the long-term viability of a post-scarcity society.
D. Mental health and social cohesion
A post-scarcity society has the potential to improve mental health and social cohesion by reducing financial stress, work-related burnout, and the pressure to compete for scarce resources. However, the transition to a post-scarcity society could also lead to new challenges, such as social isolation, a loss of purpose, and difficulties in adapting to new societal norms.
To address these challenges, it will be essential to invest in mental health care, community-building initiatives, and programs that encourage social interaction and foster a sense of belonging. Policies that promote work-life balance and create opportunities for meaningful engagement and personal growth will also be crucial for maintaining mental health and social cohesion in a post-scarcity society.
E. Political and cultural shifts
The transition to a post-scarcity society is likely to trigger significant political and cultural shifts. As traditional economic paradigms become obsolete, new political ideologies may emerge, advocating for alternative models of wealth distribution and social organization. The role of governments could evolve, shifting from managing scarce resources to ensuring the equitable distribution of abundance and addressing new societal challenges.
Cultural norms and values may also shift in a post-scarcity society, as the emphasis on material wealth and economic growth gives way to a focus on personal fulfillment, creativity, and community engagement. This transition may lead to a reevaluation of what constitutes a meaningful life, as individuals have more time and freedom to explore their passions and contribute to the common good.
VI. Global Perspectives and Case Studies
A. The Nordic countries
The Nordic countries, including Denmark, Finland, Norway, and Sweden, are often cited as models for social and economic policies, given their strong social safety nets, high-quality public services, and commitment to egalitarianism. These countries have already begun exploring the potential of automation, AI, and universal basic income (UBI) in shaping their future societies.
For example, Finland conducted a two-year UBI pilot program from 2017 to 2018, providing 2,000 randomly selected unemployed citizens with a monthly income of €560 (approximately $625) regardless of whether they found work or not. Although the pilot program did not lead to significant improvements in employment levels, participants reported higher levels of well-being, reduced financial stress, and increased trust in institutions.
B. East Asia
In East Asia, countries like Japan, South Korea, and China have been investing heavily in automation and AI to boost economic growth and maintain global competitiveness. Japan, facing an aging population and labor shortages, has embraced robotics and automation to maintain productivity in various industries, including manufacturing, healthcare, and elder care.
China, on the other hand, has set ambitious goals to become a global leader in AI by 2030. The Chinese government has been investing in AI research and development, as well as implementing AI technologies in industries such as manufacturing, agriculture, and urban planning.
C. North America
In North America, the United States and Canada are at the forefront of AI research and development. Both countries have a strong tech sector, with major companies like Google, Apple, and Amazon investing heavily in AI and automation technologies. In the United States, pilot programs for UBI have been initiated in cities like Stockton, California, and Newark, New Jersey, to study its potential effects on poverty reduction and economic stimulation.
Canada has also been exploring the potential of UBI, with the province of Ontario launching a three-year pilot program in 2017, which was later canceled by a new provincial government in 2018. Nevertheless, the idea of UBI continues to gain traction among policymakers and the public in North America.
D. Europe
In Europe, countries like Germany, France, and the United Kingdom are investing in AI and automation to maintain their economic competitiveness and address challenges such as aging populations and the future of work. The European Union has also been actively involved in AI research and development, with initiatives like the European AI Alliance and the European Commission’s High-Level Expert Group on AI.
Several European countries, such as Spain and the Netherlands, have also conducted pilot programs to explore the feasibility of implementing UBI. While there is no consensus on the best approach to UBI in Europe, the topic remains a subject of ongoing debate and experimentation.
E. Developing countries
In developing countries, the potential impact of automation, AI, and UBI is less clear. While automation and AI may offer opportunities for leapfrogging traditional development paths and addressing issues such as poverty and inequality, there are also concerns about job displacement and the digital divide.
Some developing countries, such as India, have experimented with direct cash transfer programs as a form of UBI. In 2011, the Indian government launched the Aadhaar-based Direct Benefit Transfer (DBT) program to provide subsidies and other benefits directly to citizens through electronic transfers. While not a full-fledged UBI, the DBT program has demonstrated the potential for using technology to improve the efficiency and targeting of social welfare programs in developing countries.
As the global economy continues to evolve, it is crucial for policymakers, businesses, and individuals in both developed and developing countries to understand and adapt to the potential implications of living in a post-scarcity society.
VII. Preparing for the Post-Scarcity Future
A. Policy recommendations
To prepare for a post-scarcity future, governments must develop and implement forward-thinking policies that address the challenges and opportunities presented by automation, AI, and the potential implementation of UBI. Some policy recommendations include:
Investing in education and workforce training: Governments should prioritize investments in education and skill development, focusing on lifelong learning, vocational training, and reskilling programs to help individuals adapt to the changing job market and acquire the skills needed in an AI-driven economy. Developing and implementing ethical AI guidelines: Policymakers must establish clear guidelines for the ethical development and use of AI technologies, addressing issues such as data privacy, algorithmic bias, and transparency. Supporting research and development in AI and automation: Governments should invest in research and development to promote innovation in AI, automation, and other technologies that will drive the transition to a post-scarcity society. Exploring the potential of UBI: Policymakers should consider pilot programs and research initiatives to study the feasibility, benefits, and challenges of implementing UBI as a means of addressing income inequality and job displacement. Fostering environmental sustainability: Governments should encourage the adoption of sustainable practices and technologies to ensure the long-term viability of a post-scarcity society, promoting renewable energy, resource efficiency, and a circular economy model.
B. Business adaptation strategies
Businesses must adapt to the emerging post-scarcity landscape by embracing new technologies, rethinking organizational structures, and fostering a culture of innovation. Strategies for business adaptation include:
Implementing AI and automation: Businesses should explore the integration of AI and automation technologies into their operations to improve efficiency, reduce costs, and remain competitive in the global market. Developing a workforce for the future: Companies should invest in employee training and development, offering opportunities for upskilling and reskilling to help workers adapt to the changing job market. Fostering a culture of innovation: Businesses should encourage a culture of innovation and creativity, promoting collaboration and the exchange of ideas to stay ahead of the curve in a rapidly evolving economy. Prioritizing sustainability: Companies should prioritize sustainability in their operations and supply chains, adopting environmentally-friendly practices and technologies to minimize their ecological footprint and contribute to a sustainable post-scarcity society.
C. Individual preparedness and lifelong learning
As the global economy transitions towards a post-scarcity society, individuals must take responsibility for their own preparedness by embracing lifelong learning, staying informed about technological advancements, and adapting to new career opportunities. Some strategies for individual preparedness include:
Engaging in lifelong learning: Individuals should commit to continuous learning and skill development, taking advantage of online courses, workshops, and training programs to stay relevant in the job market. Cultivating adaptability and resilience: Developing a mindset of adaptability and resilience is crucial for navigating the uncertainties and challenges of a post-scarcity society, as job markets and societal norms continue to evolve. Networking and community engagement: Building and maintaining professional and personal networks can provide valuable support, resources, and opportunities for individuals navigating the transition to a post-scarcity society. Staying informed: Individuals should stay informed about the latest developments in AI, automation, and other technologies that will shape the future of work and society, enabling them to anticipate changes and adapt accordingly.
VIII. Conclusion
A. The potential of a post-scarcity society
The vision of a post-scarcity society — one where the basic needs of every individual are met, and access to resources and opportunities are abundant — offers a compelling and transformative future for humanity. The advancements in automation, artificial intelligence, and the potential implementation of universal basic income could reshape the global economy, fostering unprecedented levels of prosperity, creativity, and equality. This future holds the promise of alleviating poverty, reducing income inequality, and creating an environment in which individuals can thrive, pursuing their passions and contributing to the common good.
B. Challenges and opportunities ahead
Yet, the journey towards a post-scarcity society is not without its challenges. We must navigate the potential job displacement caused by automation and AI, address the ethical implications of these emerging technologies, and design equitable systems to distribute wealth and resources. As we face these challenges, we must also seize the opportunities that lie ahead. By investing in education, skill development, and sustainable practices, we can harness the power of innovation to create a better future for all.
C. Final thoughts on the future of the global economy
As we stand on the cusp of this transformative era, it is our collective responsibility to shape the future of the global economy with intention and foresight. We must engage in thoughtful dialogue, collaborate across sectors and borders, and embrace the potential of technology to bring about positive change. By doing so, we can ensure that the post-scarcity society we envision becomes a reality, offering a brighter and more equitable future for generations to come.
In the words of futurist and author Arthur C. Clarke, “The limits of the possible can only be defined by going beyond them into the impossible.” Let us dare to imagine the possibilities of a post-scarcity society and work together to make it a reality, forging a new era of prosperity, innovation, and human flourishing.
| 2023-03-28T00:00:00 |
2023/03/28
|
https://medium.com/chain-reaction/living-in-a-post-scarcity-society-how-automation-ai-and-universal-basic-income-could-reshape-the-de5b44704d7b
|
[
{
"date": "2023/03/01",
"position": 24,
"query": "AI labor union"
}
] |
Will AI Actually Mean We'll Be Able to Work Less?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
Today, many fears around AI focus on its potential to replace human workers—whether teachers, lawyers, doctors, artists, or writers. In a 1930 essay, the ...
|
A subreddit devoted to the field of Future(s) Studies and evidence-based speculation about the development of humanity, technology, and civilization. -------- You can also find us in the fediverse at - https://futurology.today
Members Online
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/Futurology/comments/11undnh/will_ai_actually_mean_well_be_able_to_work_less/
|
[
{
"date": "2023/03/01",
"position": 33,
"query": "AI labor union"
}
] |
|
Augmenting Farmer Knowledge with AI
|
[2303.06049] Affordable Artificial Intelligence -- Augmenting Farmer Knowledge with AI
|
https://arxiv.org
|
[
"Kumar",
"Nelson",
"Kapetanovic",
"Chandra"
] |
by P Kumar · 2023 · Cited by 10 — ... Organization of the United Nations and International Telecommunication Union Bangkok, 2021. This publication on artificial intelligence (AI) for agriculture ...
|
arXiv Is Hiring a DevOps Engineer
Work on one of the world's most important websites and make an impact on open science.
| 2023-03-01T00:00:00 |
https://arxiv.org/abs/2303.06049
|
[
{
"date": "2023/03/01",
"position": 71,
"query": "AI labor union"
}
] |
|
Center for Labor and a Just Economy at Harvard Law School
|
Center for Labor and a Just Economy at Harvard Law School
|
https://www.linkedin.com
|
[] |
For more on centering worker protections when implementing AI, check ... union members, shows labor is powerful but not monolithic. The data is the ...
|
In partnership with the Institute of Politics at Harvard Kennedy School, CLJE hosted an event with Senator Sherrod Brown and Pulitzer Prize-winning journalist Connie Schultz at Harvard Law School last week to talk with Professor Sharon Block and the law school community about the future of the Democratic Party, the fight for the dignity of work, and why storytelling – in both politics and law – matters so much. Senator Brown began the discussion acknowledging that today’s economy does not work for working people. Regarding the choice between today’s extreme tariffs and returning to the neoliberal status quo, the senator said, “There needs to be another path that we get serious about, and that’s a path to begin to undo the globalization that began with NAFTA.” Schultz took on the importance of telling workers’ stories, saying, “We need to teach the next generation of journalists to talk to workers – not about workers – to workers. Because that’s the best way you write about workers, in their own voices.” When talking about the divisive narratives that many of us fall prey to, she pointed out that fear works. And fear distracts. We can’t let the airspace be filled with narratives that inspire fear, but rather ones that help us listen to each other and center the needs of working people. The senator recalled the way Martin Luther King, Jr. died fighting for sanitation workers’ rights in Memphis, lauding the way King understood that workers’ rights, civil rights, voting rights, and women’s rights were all intertwined. He reminded the audience that nothing in this country that benefits our working class happens without activism. Senator Brown and Ms. Schultz answered questions from the students thoughtfully and thoroughly, and the senator recalled various examples of change in our country that were hard won through activism, from winning the eight-hour workday to the implementation of Medicaid. The senator ended on a note of motivation, reminding the audience that change happens when people of like mind stand up and agitate. To learn more about Senator Brown’s new Dignity of Work Institute, visit the site here: https://lnkd.in/eppBaRyH #DignityofWork #SherrodBrown #workersrights
| 2023-03-01T00:00:00 |
https://www.linkedin.com/company/cljeharvard
|
[
{
"date": "2023/03/01",
"position": 73,
"query": "AI labor union"
}
] |
|
Episode 177: Popular Anti-Union Talking Points and How to ...
|
Episode 177: Popular Anti-Union Talking Points and How to Combat Them
|
https://citationsneeded.medium.com
|
[
"Citations Needed"
] |
Nima: Later on the show we'll be joined by Daisy Pitkin, a community and union organizer, supporting labor movements for over 20 years. ... This is the hottest AI ...
|
Episode 177: Popular Anti-Union Talking Points and How to Combat Them
Citations Needed | March 15, 2023 | Transcript Citations Needed 54 min read · Mar 15, 2023 -- Listen Share
Former and current interim Starbucks CEO Howard Schultz. (AP)
[Music]
Intro: This is Citations Needed with Nima Shirazi and Adam Johnson.
Nima Shirazi: Welcome to Citations Needed, a podcast on the media, power, PR and the history of bullshit. I am Nima Shirazi.
Adam Johnson: I’m Adam Johnson.
Nima: You can follow the show on Twitter @CitationsPod, Facebook Citations Needed, and become a supporter of the show if you like what we do through Patreon.com/CitationsNeededPodcast. All your support through Patreon is incredibly appreciated as we are 100 percent listener funded.
Adam: Yes, if you liked the show, and you haven’t supported us yet, please do on Patreon. We’d be very grateful, and as always, you can rate and subscribe to us on Apple Podcast as well.
Nima: “Unions used to make sense but are obsolete in today’s economy.” “Unions are an “outside force” or “third party” in our job. “I’m a strong worker. Unionization will harm me personally and only help the weak and lazy workers.”“Unions are rigid, old fashioned hierarchies.” We’ve all no doubt heard these talking points at some point, if not often, from news shows, opinion pieces, TV dramas, members of our families, our co-workers and, probably most of all, our bosses.
Adam: What’s remarkable is how little these general talking points have changed throughout the decades. Some versions of these pat anti-union lines have been around since there’s been unions. It’s generally unseemly to appear anti-worker or not of the working class so opposition to the one thing that historically empowers the working class — unions — is seen as crass and politically incorrect.
Nima: So, in its place has emerged a popular set of go-to, sophistic arguments that allow one to appear pro-working class without the messiness and ideological heavy lifting of actually supporting labor organizing and unionization. These McArguments — that after decades of anti-union messaging feel right without being right — appeal to ignorance, prejudice, vagueness and gendered and racialized perceptions of what labor is, and what labor deserves: the protection and stability offered by collective bargaining.
Adam: In today’s episode we’ll detail eight of the most popular anti-union talking points, their origins, who they serve, their purpose and power, and — most important of all — how to combat these
Nima: Later on the show we’ll be joined by Daisy Pitkin, a community and union organizer, supporting labor movements for over 20 years. She is the author of the book, On The Line: A Story of Class, Solidarity, and Two Women’s Epic Fight to Build a Union, which was published by Algonquin Books in 2022.
[Begin Clip]
Daisy Pitkin: The reason that company’s third party unions is because instead of talking about them, then as a mechanism for collective empowerment at work or a mechanism to build democracy in US workplaces, they start to think of them as service providers, and then there’s a question of whether or not the union has correctly provided the services that workers may think they should.
[End Clip]
Adam: So in May of 2022, we did an episode where we discussed some of the anti-union talking points we’ll be discussing today. It got really good feedback but we felt like because it was a News Brief, it wasn’t quite as expensive as we wanted it to be, and what we really wanted to do is create a one stop shop where people who are involved in dealing with these things, organizing, fighting back against opposition unions can sort of go to one episode, and they would all kind of be there. So we’re really excited to do that. One other qualifier is that, Nima, we talked about this before. We, of course, are not the first people to sort of log and categorize anti-union talking points, unions, obviously, I’ve been working on these kinds of white papers for years. Before I wrote my piece in the spring of last year, in March of 2021, Katie Way at Vice wrote, “Five Common Anti-Union Myths, Busted.” We’ll have that in the show notes, definitely check that out, that discusses a couple similar ones, but also discusses ones we don’t discuss. So definitely go read that one. It’s a really good article, and of course, any other such collateral you’ve seen written, please, please feel free to share, we’ll retweet it and share it out. These are kind of the ones that I know, Nima, we see a lot, and we come up a lot as we do produce a lot of, for want of a better term, pro union propaganda on our show. Is that fair to say?
Nima: Right. The first talking point that we really want to go over is one we know you’ve heard a lot, which is that labor stoppages brought on by strikes, which are inevitable for unions, because that’s what we hear all the time, are going to — what Adam? — wreck the economy. ‘If workers use their power to stop working, it will wreck our economy, and we can’t have that.’
Adam: Yeah, this was a popular scare tactic during the recent rail worker union busting by Congress and the White House where almost all the coverage we saw, as we discussed in our News Brief at the time, and this is how most people sort of make labor and labor stoppages and labor actions intelligible, they understand them through these straight news reports that tell you all those scary stuff that’s going to happen if there’s a strike, and so we had NBC News from November of last year:
Drinking water to retail: How a rail strike could upend the economy. How damaging a strike would be would depend on its length, but a strike of even a few days could lead to a cascade of events that would disrupt supply chains for weeks, industry officials warn.
CNN: “Railroad strike, and the economic damage it would cause, looms closer.” ABC News, “Looming railroad strike could cripple US economy, transportation.” So the moral extortion at work here is basically a way of getting the public on the side of Congress to bust the unions because the stakes are so high. Now, of course, what union rep say to this, because I mean, in the rare chance that CNN or NPR or ABC News has on a union representative, and again, I stress the rare chance, usually they talk to some, you know, pundit or corporate CEO — what’s the first question they ask him, Nima?
Nima: What do you say to all the people who will be affected by the strike? ‘It’s going to shut down our economy.’
PBS NewsHour headline
Adam: Very rarely do you see them ask of the corporate CEOs, why don’t you just give them what they want?
Nima: Right. To avoid this strike.
Adam: Right.
Nima: That’s the point of the strike. That’s the power that’s being wielded.
Adam: Right, and what most people don’t understand, and what the media never conveys is that when things get to the point where people are doing massive labor shutdowns, it means that the negotiations have completely broken down and that corporate, by and large, is not giving anything or it’s not giving nearly a sufficient amount.
Nima: That’s not the first move, right? That’s not step one.
Adam: The people who suffer in the event of strikes are workers, they have strike funds, but it’s not their pay, it disrupts their lives, it puts their jobs and careers in jeopardy. The corporations have billions of dollars in reserves for the most part, especially these rail companies. So if it’s gotten to that point, it’s usually because the corporation’s are not negotiating in good faith or not making the appropriate changes or, in the case of the rail strikes, they know that the White House will come in and do their bidding for them. But this kind of apocalyptic, one-sided, what will happen to you personally, it really just exists for the purposes of eroding solidarity, right? It’s meant to sort of condition the public into sympathizing with the corporate owners, and the moral burden is therefore put on the strikers, without any contextualization as to how things could have possibly gotten that desperate in the first place.
Nima: Because it really has to do with where the story starts, when we start hearing about this as, say, you know, receivers of information from news or from punditry or from our social media feeds, from our families? When do we start hearing about that, and if we’re starting to hear about that, when it is, a strike is looming, and the threat of that can, you know, shut down the economy, et cetera, et cetera, we are starting to hear the story there, not when the story actually started, which is probably months, if not years, if not decades earlier, of labor organizing to try and get those companies to treat those workers better or be forced, rather, as is more often the case, because they’re not necessarily benevolent companies, to accede to the demands of labor power, but it is framed as unionized workers are effectively holding us all hostage, and if we give in what is next? What is next, Adam?
Adam: Yeah, it’s the labor equivalent of the violence breaks out after a police officer shoots an unarmed Black man, where it’s like, well, the violence broke out when the police officer shot the unarmed Black man, not after that.
Nima: Right.
Adam: It’s this idea of first blood. And so the media comes in right when a thing reaches critical mass, because again, CNN and MSNBC and all, they never covered the rail negotiations, they never covered rail labor issues at all. They only cover it when they believe it’s going to affect corporate interest and the quote-unquote “economy,” which is oftentimes just used as a proxy for corporate interest to shame and morally extort union reps into kind of feeling bad about it, despite the fact that they literally have no other leverage, right? They have no other leverage, they have no other form of power, other than shutting down an industry, and of course, what they also say with the rail lines is that, look, if this is labor that can’t strike because railroads are part of essential infrastructure, then it should be nationalized.
Nima: Yeah. So we wanted to lead off with that one, because we hear it so often, and it’s always good to have a good reply to the wrecking the economy threat.
Adam: Prior to this becoming a crisis point that was going to quote-unquote “cripple” the economy, how many times have you covered this? And the answer is 99 percent of the time it’d be zero. So, suddenly you care. Well, guess what? You didn’t care before for a reason.
Nima: Moving on. Our next point that we’re sure you’ve heard a lot is this: ‘Sure, unions used to make sense back in the old days, but are obsolete in today’s gig economy.’
Adam: Yeah, this one is very popular, like you said, we have discussed this one before, because it is so ubiquitous, and so kind of superficially appealing, right? Kind of sounds true, and it oftentimes it’ll be accompanied by someone saying like, ‘My Daddy’s Daddy, you know, when he worked in the steel mill, or the coal mine, or the sparks in the steam factory back in the black and white days, it made sense then, but something something something, blah, blah, blah, blah, blah. It doesn’t make sense today.’ And you say, well, why would that be? And there’s assumption that those were jobs you had your entire life or they were sort of quote-unquote “real” jobs, whereas today, things like driving an Uber or working at a Starbucks or working in some kind of retail or restaurant or white collar capacity, these aren’t sparks in steam factory jobs. But what people don’t understand is that the sparks and steam factory jobs they now romanticize as being these secure, respectable, dignified jobs, they’re only that because they were unionized. Before that industrial jobs were also extremely transitory, and were seen as not something you did for a long time, and were seen as quote-unquote “entry level.” The only reason they got that image in their head is because they were unionized. But as our economy shifts away from industrialization, although again, to be clear, there’s still those jobs, into more service economies for the low wage workers, those jobs themselves can have the same kind of mystique if we unionize them, and if they have labor protection, right? And so I think people get it in their heads that the way things are now is somehow a law of nature rather than part of a decade’s long process of eroding collective bargaining.
Nima: There’s also really a gendered and racialized aspect of this particular talking point, the idea that the old-timey union jobs, the steel mill or the auto plant, which granted not everyone there was white, but the kind of popular conception of that, through our mass media, whether it is TV news or old newsreels or documentaries or Hollywood films, obviously, it focuses on the kind of white working class, blue collar character, so therefore, when that is the vision of the past that deserves the union, that builds their wealth over time, that buys that house that then can pass something along to the next generation, that all has a very racialized and also a gendered aspect to this. It’s not just the blue collarness, it’s also the manness of that, and so who really deserves a union now, right? It seems like well, you know, if it’s Amazon warehouse workers or Starbucks baristas, well, you know what they look like in your mind, and they don’t look like the folks leaving the factory grounds when the whistle blows with their lunchboxes in hand, and so I think that that’s also part of this. It’s not just looking back to the past, and now what is kind of more, you know, digitized economy is now, it actually has so much to do with who we envision as a worker, who is allowed to have those bonds of solidarity, have that worker power against their employers.
Adam: Yeah, and one of the reasons that, again, that production has increased but wages have stagnated and in some cases gone down, it’s because of the erosion of labor protections. One article published in January 2022, researchers Colleen Boyle and Eric Dirnbach calculated the amount of money the gap between wages and productivity is costing workers in real dollars. In 2017 alone, they determined, U.S. production and nonsupervisory workers together lost a combined income of $1.78 trillion. A good portion of this money went toward increased dividend payments to shareholders — a tremendous wealth transfer from the poor to the wealthy. Not unrelatedly, union participation has declined. And a lot of the anti-labor attitudes that these talking points are popular with, let’s just be honest here, like white men, oftentimes have low opinions of unions relative to people of color, relative to women, because of partisan ally-ship, is that these people are shooting themselves in the foot because largely, these sparks and steam factory jobs aren’t the jobs they’re going to be getting, those aren’t the jobs they’re going to be taking themselves, a third of the country is, of course, white men, and they need to understand that this kind of glamorized version of labor is largely not reflective of the current realities of our economy, and that all labor, regardless of what it is, or regardless of its aesthetic properties, should be unionized. Because again, why wouldn’t it, and again, the jobs we now romanticize as kind of being intrinsically lending themselves to unionization, that was not the case 100 years ago, they had to fight for that, the whole image is itself based on a tautology, but a lack of historical understanding of how those sparks and the steam jobs gained that image in our head.
Steel workers gaze on as molten steel is poured at Homestead Steel Works, 1914. (PD via PBS)
Nima: The next talking point we want to discuss, Adam, is one of my personal favorites, the, ‘it’s good for some but not for you, the unions make sense, sure, for certain industries, but not the one you’re in,’ or if you are talking to a co worker who opposes unionization, ‘not the one we’re in together.’ ‘It makes sense for others, but not this one.’
Adam: Yeah. Which is again, just like unions used to make sense 50 years ago, this is a close cousin. This is one that’s incredibly convenient. It’s also very popular with CEOs themselves, that they will oftentimes say, including CEO of Starbucks, Howard Schultz, they’ll say, ‘I support unions in certain industries but in our particular business,’ right? Out of all the gin joints in all the towns and all the world. They coincidently, you know, it’s what’s The Simpsons, you know, there’s an orb directly in your kitchen, right? Like out of all the places in the world, there happened to be this particular industry I have, unionization doesn’t make sense, and this is very popular with Starbucks, REI, Amazon, and unfortunately, a lot of nonprofits kind of use this line, right? That because of the sort of inherently altruistic nature, political campaigns will use this line when political workers, campaign workers try to unionize, right? Oh, we’re basically a charity. But that’s bullshit, you know, especially when the guy who’s running these things is making half a million dollars or $200,000, which a lot of nonprofits that’s the case, trust me, in that case, they can afford it. This is not volunteering at a soup kitchen. This may not be quote-unquote, “for profit,” but it is a business and all businesses should have unionized labor.
Nima: Now, we’ve heard this talking point for well over a century. We’ve mentioned this before on the show, but it bears repeating that Andrew Carnegie, the late 19th-century steel tycoon, robber baron, made a show at certain point of his career of being pro-union, actually making pro-union statements, for example, in 1886, he wrote this, quote, “My experience has been that trades-unions upon the whole are beneficial both to labor and capital,” unquote. Cool, taken in isolation that sounds great. But of course, Carnegie also hired strikebreakers to break strikes, right? To oppose the thing that labor unions sometimes do, and so his crackdowns on union power — I don’t know — somewhat undermine some of the pro-union statements that he has made. Also the godfather of anti-union propaganda, Walmart founder Sam Walton, has expressed similar sentiments hinting at, sure, you know, unions can be good, ‘They really can be good, but it just doesn’t make sense when you’re talking about Walmart.’
Adam: Yeah. And of course, Starbucks CEO, Howard Schultz, loves to do this. Saying, ‘My grandfather was in the union, unions used to be important.’ He kind of does the same shtick, and then goes into why his industry, because he’s so benevolent, doesn’t need a union, which is interesting, because the vast majority of people where they’ve had a union vote have come up, Starbucks workers, which they call partners, have voted to support a union. So if that’s the case, then why would they keep voting for it if it’s not necessary? So obviously, it’s necessary.
Nima: One of the reasons for the ‘Yes, I like unions, but not right here,’ talking point, the follow up usually has to do with, ‘building a union here, having a union here in what we do would be divisive, it would then pit different parts of our staff against itself because we are one, we are a family,’ right? We hear that family talking point a lot, ‘we are a family here,’ or ‘we’re all on one big team, so therefore, if there’s a union, it divides us,’ and this idea of division, of the union being something that changes the dynamic in a negative way, also leads us into our next talking point that we hear all the time, Adam, which is that ‘unions are an outside force, a third party in our organization, and that instead of inviting that in, we should just be able to communicate directly amongst our staff.’
Adam: This is very common, probably the most common talking point, it’s called “third partying,” unions have white papers on how to address this as well, we’ll sort of get into that. But basically, they want to make it look like the union is a third party, that it’s this outside force, it’s foreign, it’s an alien species that is beamed down and is not native to this particular job. This is a favorite talking point of Amazon. The workers at JFK8, a fulfillment center in Staten Island, say they were barded with third party messaging back when they were trying to unionize last year. This was part of their efforts to convince workers that the union was basically there to kind of fleece their wages and not protect them, not offer them anything, and Starbucks CEO, Howard Schultz, is a huge fan of this, he uses this kind of third partying all the time. Let’s listen to the clip here.
[Begin Clip]
Howard Schultz: We’ve always managed to overcome the obstacles and challenges, the resiliency of the company is directly related to the leadership that you have provided. But the challenges right now are real, and they’re in front of us, and the challenges are multiple: the pandemic, a post-pandemic customer, the relationship we have with our customers, competitive threats, and now a new outside force that’s trying desperately to disrupt our company. Well, I believe in Starbucks more than ever, because I believe in all of you. My faith and confidence in the future of Starbucks is based on my faith and confidence in you, not some outside force that’s going to dictate or disrupt what we are and who we are, who we are and what we do.
[End Clip]
Adam: Outside force, right. It’s not the workers versus management, it’s outside force versus the quote-unquote, “nebulous family.” But of course, Howard Schultz does not make the same money as a barista so they’re not really on the same boat, and if they are, one is in first class and one is down with the luggage. And of course anyone has worked at a low wage job or frankly any job where there’s workers and then management, they’re not a family, they’re not the same entity in the same unit, workers are routinely subjected to arbitrary drug tests, they’re heavily surveilled, everything they say is monitored, reported back to HR, workplaces are, poll after poll shows they are viewed by their workers as extremely authoritarian. Obviously, you can get fired pretty much at will, depending on your state, but pretty much whenever they want to fire you for pretty much any reason without cause. Whereas the worker can’t do that, the worker can’t fire their CEO, they can’t replace their CEO, right? There’s no democracy at the workplace, and of course, even workplaces that pride themselves on being more ethical, being a boss, by definition, means you get to call the shots for the people you supervise, the ramifications of this power imbalance are, of course, very significant, determines one’s ability to pay rent, whether they can feed their kids, their loved ones, pay hospital bills, enjoy any kind of leisure time. So the power that your boss has over you is tremendous, and it’s entirely one way, and anyone who knows, if you call yourself a family, as Howard Schultz consistently does, families don’t have one way relationships, friends don’t have completely one way relationships, and if they do, that’s considered very unhealthy. That’s considered not good. You know, there’s no scenario where, because again, they constantly talk about a family, where one family member can sort of unilaterally make all the decisions in an authoritarian way, as the case with most corporations are, again, if that is the case, then Howard Schultz’s vision for a family is some kind of hyper patriarchal, Baptist family, right? It’s not healthy. So this language is really used to obscure the very obvious, centuries-long power imbalance between worker and employer.
Employees seeking union representation at a Starbucks in Carbondale, Illinois, in May, 2022. (Megan Brown)
Nima: In her book, Private Government: How Employers Rule Our Lives (and Why We Don’t Talk about It), the political philosopher Elizabeth Anderson argues that, in light of this power dynamic, American workplaces are best understood as private, authoritarian governments — not free arrangements between equal individuals. She’s written this, quote:
Under U.S. law, employers are dictators of their workplaces, empowered to exercise sweeping and virtually unaccountable power over their employees, even regarding their off-duty lives.
End quote.
According to Anderson, the fact that America’s default is employment at will, right, the idea that there is broad power to fire someone, to remove someone from your workplace, for nearly any reason — this employment at will really plays a key role in upholding this kind of arrangement, this kind of workplace dynamic. She has written this, quote:
Managers in private firms can impose, for almost any reason, sanctions including job loss, demotion, pay cuts, worse hours, worse conditions, and harassment… Americans think they live in a democracy. But their workplaces are small tyrannies.
End quote.
Adam: Yeah, and this is why they’re so hell bent on making unions look like some outside force, because again, there’ll be union representatives who represent existing unions but that’s the only way that they have any power. Because there’s a formula, there’s a playbook, and they’re in solidarity with other unions that therefore exercise power. Again, not to say that there are criticisms to be made of American unions, which we’ll get into with our guest, they’re not perfect, but they’re certainly better than the alternative, which is living completely under the caprice of your manager and your CEO.
Nima: And this idea of division, not just within a workplace, within a company carries over to our next talking point, which is even more targeted levels of dividing and conquering and it is this talking point, ‘I’m a strong worker, but unionization will then harm me personally, and only help out my lazy colleagues.’
Adam: So yeah, this was a popular one, and one that I think I may have bought into, not as the strong worker, but as the lazy worker back when I worked in the restaurant industry, I never had any pretense I was a strong worker, but I definitely internalized this idea that like, I deserved to make a little money or make less money than so and so. But this is a common, again, we have talked about this before, especially in our tipping episode, it’s a common way you kind of pit workers against each other, where you say, you create these false incentives within a closed system. So for example, in restaurants, you have, let’s say, five servers working a night, and instead of pooling tips, which you should always do, don’t let anyone ever tell you otherwise, you say you’re going to get these four tables and so and so who is a weak server is going to get three tables, and maybe to some extent, that’s true, I mean, waiting tables is a skill and there are people who are better at it than others but broadly speaking, that exists not because of some reflection of actual skill level, it exists because it’s a way of creating incentives for someone to be, you know, we called them a captain, waiting tables you have a captain waiter, and what do you get for that? You get more tables based on an artificial closed system, they’re not actually paying more money into their pocket, as owners, they’re just taking the vegetables on the plate and spreading it around differently. They’re dividing the pie based on what consumers tip you as a way of incentivizing, you know, sycophancy, more free labor for the $2.15 an hour off the clock, whatever it is, it’s an incentive to kind of pit workers against each other, and one reason managers hate pooled tips, which they’re always entitled to do in most states, I think there are exceptions, but generally speaking, I know states like New York you’re entitled to pool tips, is because — what is that? — that’s basically the first step to a union. Because you realize, wait a second, if we bond together, as workers, we have more power rather than constantly being these atomized, Ayn Randian heroes of our own world, we can work together to raise all boats, right, to sort of raise the workers’ lot collectively, and managers are extremely good at creating these kind of rat race, closed systems within, whether it’s Amazon, you know, so and so. Actually, you know, Andor did a really good job of this, right? Did you see the Disney+ show Andor? They did a really good job of showing how you use these kinds of false competitions.
Nima: Yeah, there’s a worker camp where everyone is captive, and there are these different production teams on different levels that aren’t allowed to communicate with each other, and even within the production floors, there are different tables that are competing with each other, and they are yes, of course, incentivized to not be physically harmed, but also to then get certain other incentives if they produce faster and better equipment for the Empire to make it truly as heavy handed a metaphor as we can make it.
Adam: And if you finish dead last you get tortured, and if you finish first you get flavor in your gruel. It’s actually a pretty good example of how Amazon production works, a lot of corporate production works, even white collar labor, you sort of pit workers against each other in a competition, which not only has the added effect of incentivizing them to work harder and to produce more for you for less, but it also allows, it erodes worker solidarity, and so one of the more common things you hear people say when people do try to unionize or try to organize workplaces is, ‘Wait a second. I’m Mr. Hotshot. I’m the number one barista, you know, I do barista competitions,’ which they also promote to undermine unions, by the way, just as the Academy Awards were used to undermine actor unions in Hollywood, ‘Why should I be brought down to their level?’ And this is playing to narcissism, and it’s just generally not true, because again, when it comes to things like security, when it comes to things like predictable income, you have an incentive to pool your resources because again, you could be the biggest hotshot in the world, but if you spur a manager’s advances or annoy someone or you have a bad week, you’re toast.
Nima: God forbid, have a family emergency and need to call out.
Adam: God forbid a family emergency, right? So people think they’re hot shit, and they don’t need unions. Well, again, that’s what they want you to think, and that is very rarely actually true.
Nima: The way that this talking point actually plays out, like if we kind of go a step further, Adam, there’s this idea of a lot of workplaces then offer, you know, opportunities for quote-unquote “growth,” within your workplace, and these go really hand in hand with the anecdotes we hear all the time, whether it’s political campaigns, or your own organization, or books about leadership, and et cetera, et cetera, this idea of the employee that made their way from the mailroom to the boardroom or, you know, the idea that you started working on the cash register, and that, you know, it’s like the Louie Anderson thing from Coming to America, like, you know, but now I’m doing fries, and you know, pretty soon, I’m going to be flipping burgers, that thing and that, you know, you can make it up, you can become a franchisee, you can then become the president of the company, you are the CEO, but that this is all about professional advancement, personal accomplishment, and that you, you know, always have to look out for number one.
Adam: Yeah, look, I mean, again, there are rare cases where if you’re Mr. Johnny Bootstrap and you show up every day with a smile on your face and you play by the rules and you keep your nose clean and you suck up to your boss and you work hard, you stay late, yeah, you probably on average, quote-unquote, “get ahead.” But it’s a very myopic, and very atomized way of looking at the world because you could also just not do all that shit and unionize and probably achieve the same gains if not more with far more job security.
Nima: Our next trope is the idea of the big bad “union boss,” right? Now, as we have discussed in certain other contexts, certainly the way that unions and bosses are depicted in Hollywood, the term “union boss” has been around for well over a century, but not always used pejoratively. Boss is a word that has traditionally meant someone just in a position of power, but not necessarily always used in the union boss derogatory sense. Starting in the 1920s and ’30s, the term union boss became more popular as the Italian Mafia began infiltrating and taking over unions. After all, the leap from crime boss to union boss is an easy one and one scene especially during, say, prohibition when a lot of those labor and also crime syndicates were becoming even more tightly infused.
Adam: So it sort of made sense while you would use the term while organized crime had its grip on unions, but the term kind of stuck around as a right-wing kind of pejorative as a way of poking unions even after the mafia had long been weeded out of unions in the ’80s and ’90s. It remained in Britain, still to this day, popular to say union bosses for somewhat similar reasons but in the United States it has become a kind of go to conservative dig to diminish union leaders, right? People who represent unions, the anti labor, the quintessential anti labor Governor Scott Walker is a huge fan. He repeatedly calls union leaders union bosses. Fox News headline, “Ron DeSantis’s blueprint to dominate teachers’ union bosses 2022.” MSNBC wrote this in 2015 in reference to Clinton and her relationship with the unions, she said, quote: “‘I saw a lot of old friends,’ Clinton told reporters after her meeting with the union bosses.” CNN Headline from last year, quote, “This new union boss could start the biggest strike in decades.” CNN would also say, quote, “The Senate confirmed Boston Mayor Marty Walsh to be Labor secretary, elevating the former union boss to oversee the federal department in charge of workplace conditions, benefits and rights.” The Washington Post from quite a few years ago, quote, “Meet the union bosses trying to woo TSA agents.”
It seeps into mainstream media as a lazy label, but it’s extremely popular with people like Scott Walker, Ron DeSantis, Greg Abbott, it’s a way of annoying unions, union leaders. Union leaders hate the term union boss because, again, you sort of have this image of systems like ‘I shake you down,’ right, it’s another extortion racket, and since their whole narrative is that unions aren’t extortion racket, that they don’t actually help workers, but just take money from their paychecks, and I guess, I don’t know, by private G5 jets for the union bosses, I guess is the image they’re trying to convey, It makes sense why they would use union boss, but that’s a very popular subtle term, that a lot of corporate propaganda uses, a lot of the target collateral, Amazon uses it. It’s a way of diminishing, and frankly, third partying unions for workers.
Nima: Yeah, because what it does is it really relies on this idea of hypocrisy, right Adam? So it’s like, oh, right, you know, ‘I’m your boss, but now you have another boss, your union also has a boss. So you think you’re doing solidarity, you think you’re doing socialism? But really what you’re doing is just replicating the same structure, and therefore, you’re still a sap, you’re still being taken advantage of, by bosses.’
Adam: When you sow nihilism and moral relativism, the status quo wins, right? Because if all the bosses are the same, and who cares, then there’s no, if I’m your actual boss, and I’m happy with that assessment, because now nothing’s changed and you have no power to counteract my power.
Nima: The penultimate trope we’re going to go over, we’ve touched on a bit this idea of the kind of family, feel-good language used by a lot of workplaces, but we want to wrap that into a larger trope, this idea of the new-agey style, values-driven workplace and how while, yes, I think values are good to have in workplaces and elsewhere, it is the exploitation of this idea of what values mean and therefore using values and the fact that an organization can declare its values to then diminish interest in or relevancy of workers building power together.
Adam: But of course, how does an LLC have values? How does a corporation have values? Union busting CEO of REI, Eric Artz — his 2019 take home pay was $3.3 million — he recently evoked values when bashing unionization efforts amongst REI employees. He said on a podcast, in which he somewhat infamously did the land acknowledgement before bashing unions, he said he wished to, quote, “put REI values into action,” and was committed to his, quote, “best to lead by putting our values first.” Starbucks CEO, Howard Schultz, can’t of course go to seconds without talking about Starbucks values. He recently told employees, quote, “With significant pressures leading to the fracturing of our partner and customer experiences [read: unionization efforts], I’ve been transparent about our missteps and the reason for my return — to reimagine Starbucks — built on our core values and guiding principles.” But of course “corporate values” and $5 will get you a cup of coffee at Starbucks, right? It’s entirely worthless as something that the worker can use.
Now, historically, unions aren’t the only reason that labor conditions can improve, right? Sometimes you have liquid labor markets, attracting the best people or other considerations. What they do is they create a floor and corporate values are basically marketing fluff. They’re not contract obligations, they’re not job security, they’re not fixed wages, they’re under no obligation to maintain any kind of values, which is of course, how companies like Starbucks, quote-unquote, “misstep.” That’s a term they’ll say, right? But of course, if you have a contract, you can’t really misstep because otherwise you’re in violation of the contract, and this is a way you kind of protect against that. One really famous example of this kind of bullshit values rhetoric to bust unions, this was written by Hamilton Nolan at In These Times back in the summer of 2020, a New York City Quaker private school, Brooklyn Friend School, sought to justify why he was refusing to negotiate with the union, and the head of the school, Crissy Cáceres, had invoked a Trump-era National Labor Relations Board ruling that exempts religious schools from the legal requirement to bargain with unions, and she wrote to parents this is when she decided to explain to the parents why they were not recognizing the union, she wrote, quote:
We respect that our truths and divergent opinions are all part of one greater spirit that we can only access through direct and open communication of these individual truths. If we are to fully practice our Quaker values of respecting others and celebrating every individual’s inner light while compassionately responding to existing needs, we must be legally free to do so.
So that was their justification for busting unions. I don’t know a lot about Quakerism, I know that it involves sitting there in silence and praying, and presumably, they maybe had some divine intervention where God told them to bust the union, I don’t know the details, I can’t get into their heads.
Nima: Here’s the thing, if you know anything about Quaker values, which is a lot about helping each other out, I mean, I’m no Quaker here, but this is actually kind of anathema to a lot of what the stated values of Quakerism speak to.
Adam: Clearly God intervened and told them not to recognize the union. Who’s to argue with God, you can’t do that.
Nima: You can’t do that. Sit quietly in your meeting house, god dammit, and ensure that you can not build solidarity and accountability at your workplace.
Adam: Yeah. And they’ll always talk about values in the context of unionization, like we don’t need it because we have these values, and again, it’s just even if you’re lucky enough to even have it on a webpage somewhere, what does that mean? It doesn’t mean anything. It’s why they do it, they do it to kind of give you some, some puffery to make you feel sort of feel good about what you do all day, and to make you think that their corporation is different, but I’d rather have a contract than values any day of the week.
Nima: Which leads us to our final trope. ‘Unions are rigid, old-fashioned hierarchies. Our company is free, flexible, and open.’ So this really dovetails with the idea of having values but it is much more specific, right? It is the idea of, ‘to do our job the way we need to do our job, we can’t be beholden to these old fashioned, old time-y structures of unions, because we need to be nimble,’ right, Adam? ‘The modern workplace is nimble, is fluid, is flexible, we cannot have a union stifle our inevitable progress.’
Adam: Yeah, we left this for last because it’s my personal favorite, because I think it is the most superficially appealing, and you see it all the time, if you ever watch anti-union internal videos, they show employees or those sort of closed sessions where they where they sit them down and try to convince them that, and this is kind of a throwback to the first one where it’s like they made sense back in the day, but now, and they throw out these kinds of buzzwords, like corporate buzzwords about flexibility, creativity, cross training, I love that one, just basically like doing a job you’re not trained for, or you’re not paid to do, and that unions are these old, rigid, hierarchical, Soviet, old black and white things that kind of keep us back man. And they’re going to undermine your own personal ambition and growth and expression, right? One classic video from a now infamous Target anti-union video that was filmed in 2003, it went viral in 2014, but it really hits all these talking points, and we want to play that because it’s cheesy. So it’s funny, but also, it really does go into what we’re talking about here.
[Begin Clip]
Man: If the unions did try to organize target team members, they could also try and bring along their way of doing business, an old fashioned, rigid structure. Woman: Old-fashioned is right. Being able to change quickly and adapt to new opportunities. Being flexible. That’s the key to running a successful business in today’s market, and we’ve got the flexibility now. Man: Right you are. No one knows exactly what could happen, but there are lots of examples of how rigid grocery store union contracts could hurt our stores’ ability to serve guests, and actually hurt our team members in the process. Woman: Here’s what we mean. Let’s say you’re working in stationery, but you’re walking through domestics on your way to check on something, a guest stops you and asks for help. What would you do? Without even thinking about it, you stop and give them any assistance they required. But what if union work rules say you can’t work outside of your department? What do you tell the guest? ‘Sorry, I can’t help you.’ That makes you look bad. But more importantly, it means our guest doesn’t get immediate attention, and they might not come back. So everyone gets hurt, everyone except the union. Right now team members can get more hours based on the ability to cover more than one area, you have the option of being cross trained and becoming a more valuable member of your team. Man: That’s right. But with a rigid union contract, that may no longer be an option. Woman: Also, under the old -ashioned union rules that really haven’t changed in decades, seniority rules, rather than treating people as individuals, everything depends on when you were hired.
[End Clip]
Nima: Yeah, rigid, old-fashioned, flexible. It’s all in there. They repeat the words rigid, and the term old-fashioned three times each in just over a minute and a half, Adam, to really, really make sure that that point is hammered home.
Adam: Yeah, and it’s true unions do introduce a lot of rules and structure because that’s how you protect the worker from being abused, but the idea that unions are rigid and old fashioned is really hilarious when you consider that employers do nothing but introduce regulations, rules, drug tests, overburden, surveil their workers, right? There’s nothing more rigid than your employer. I don’t know if anyone’s ever had the misfortune of working at Target, I have not, I have worked at a grocery store, so I assume it’s somewhat similar, but they’re extremely rigid, old fashioned hierarchical places. So I’m not really sure if they think it’s some kind of Silicon Valley startup you’re working at, or there’s like, maybe there’s a beanbag chair in the break room, but they’re already incredibly rigid workplaces, right? And they use these kinds of corporate PR speak to exploit workers. Words like flexibility, professional development, cross training, opportunity to grow professionally, almost always these terms are used to describe what is doing work outside of what you were hired to do, outside the scope of what you’re hired to do, and you see this a lot in Joliet, Illinois, just down the road here from Chicago, at these large Amazon plants, it’s basically a city with nothing but warehouses. They’re constantly throwing people, if you read any of the OSHA complaints, they’re constantly throwing workers from one thing they’re trained on, like one machine to another machine, because someone didn’t show up, or they’re trying to cut costs, and then they’ll say, ‘Oh, this is cross training, or this is just helping out, it’s being flexible,’ and then if you actually look at the data of injuries, they’re way more likely to get injured because they’re not trained on this stuff. So the extent to which there’s rigidity and structure and rules it’s to protect workers from exploitation, because having clearly defined rules, clearly defined places you work, departments you work in, hours you work, under what conditions you work, how many people work with you, which is obviously a real big problem for nurses, which we haven’t talked about, right? We are putting nurses where there should be eight or nine nurses they’re putting three or four to try to stretch out your labor costs, and then they have the emotional burden of watching patients suffer for it, that these hierarchical, rigid, structured rules exist so some scumbag being counter doesn’t try to exploit labor in lead to worker harm or in some cases patient or consumer harm.
Nima: So one study released in April of 2022, found that between June 8, 2020 and March 21, 2021, nursing homes, where workers were unionized, had a nearly 11 percent lower death rate among its residents than their non union counterparts. Not only were unionized nursing homes safer for their residents, they were also safer for their workers. COVID infection rates were lower in unionized nursing homes than in their non union counterparts as well.
Adam: Unions also make school safer. A 2021 study found that, quote, “the average teachers union was associated with a 33 percent relative increase in the probability of school districts adopting a mask mandate,” according to the researchers, who found, quote,“That was true even when controlling for local coronavirus case rates, support for Trump, and the other factors mentioned above.” So unions make school safer, they make nurses, make hospitals safer, because these rigid, old fashioned structures have a logic to them, and that logic is, asshole bosses are going to try to cut corners wherever they can, and having very clearly defined rigid, old fashioned structured rules is one way to prevent that from being abusive.
Nima: To dig a little deeper into some of these anti-union talking points, we’re now going to be joined by Daisy Pitkin, a community and union organizer, supporting labor movements for over 20 years. She is the author of the book, On The Line: A Story of Class, Solidarity, and Two Women’s Epic Fight to Build a Union, which was published by Algonquin Books in 2022. Daisy is going to join us in just a moment. Stay with us.
[Music]
Nima: We are joined now by Daisy Pitkin. Daisy, thank you so much for joining us today on Citations Needed.
Daisy Pitkin: It’s great to be here. Thanks for having me on.
Adam: So I want to start off with a little bit of your own personal, I guess, anecdotes, because we’re a media podcast, and we’ve spent the top half of the show discussing anti-union narratives popular with media and CEOs alike, some of which make their way, trickle down to workers, some of which don’t, some of which are for kind of public consumption, but I want to kind of begin by asking you what, in your personal organizing experience, what the number one objection to unionization you see from workers in your years of labor organizing, what the most popular kind of first objection to unionization is, I guess, the most popular trope if you will? Obviously, this probably changes based on industry demographics, et cetera.
Daisy Pitkin: You know, I have to say that I think the biggest nut to crack when you’re helping workers build a union, it doesn’t tend to be an ideological one. Most workers when you knock on their door or have a conversation with them, and by most, I really mean the vast majority want to have a union at work. If you asked the question of workers, do you want to work together with your co workers to make improvements on the job? The answer is just yes. I mean, almost unanimously. So workers want to form unions in this country. In fact, there have been surveys done over the last couple of years that show that unions are more popular right now than they have been at any point in the last 57 years. 62 percent of workers say, to the question, do you want to have a union at work or would you join a union tomorrow if you could? The answer is just “Yes.” So the nut to crack is it doesn’t tend to be an ideological one. It’s just fear. Workers are afraid. So they say, ‘Yes, I want to do that,’ and the next thing that comes out of their mouth, most of the time, or some of the time is, ‘But will I lose my job? Will I lose my job? Can I get in trouble? Will my workplace close down? Will I be threatened? Will I be coerced?’ You know, there’s a lot of fear about standing up to your boss to build power with your co-workers at work. So that’s the biggest nut to crack. But of course, there are anti-union messages and tropes that companies tend to use, they operate from similar playbooks across all industries, and one of the more popular ones is kind of third partying the union, that the union is the separate entity, and that it will come in and insert itself in between the relationship that workers have with their boss, that they should be using to directly solve problems at work rather than going to the separate organization who will advocate for them, and I think the reason that employers or bosses tend to third party the union in that way is because they tend to use the language of family and unity at work, they start to use the language of the union to talk about the company and its culture, and then here’s this intruder from the outside who’s come in to insert itself, and then when you get into conversation with workers about the union through that lens, sometimes there are workers who say, ‘Oh, I have a relative or I have a brother, I have an uncle, who had a bad experience with the union, this separate entity that did or did not provide the kind of services that people sometimes expect a union to provide.’ The reason that companies third party unions is because instead of talking about them then as a mechanism for collective empowerment at work, or a mechanism to build democracy in US workplaces, they start to think of them as service providers, and then there’s a question of whether or not the union has correctly provided the services that workers may think they should. So the third partying works sometimes, but the main barrier is not ideological at all. It’s just fear.
Daisy Pitkin
Nima: It’s also so fascinating, as you were saying, Daisy, that the unions are then, whether they even exist or not at a workplace, they’re held to such a higher standard than say, what a job is supposed to offer, right? It’s like, ‘Oh, well, if you’re going to come in, you’re going to do this, you’re going to do that,’ and then there’s disappointment if there is opposition that slows things down, right? And so, it’s almost like a no win that there’s this high standard that is held to something that, again, takes time to build, takes time for power to shift, takes time for that solidarity to actually come to fruition, for a union to actually exist and operate in a certain way. I kind of want to take this idea and focus us on your great memoir, again, it’s called, On The Line: A Story of Class, Solidarity, and Two Women’s Epic Fight to Build a Union, of course, for all our listeners, who I’m sure most of them already own this book and love it, but if you do not, you should go get it immediately at bookstores everywhere, and your memoir, Daisy, recounts your first organizing campaign, an industrial laundry in Phoenix, Arizona. Can we talk about your experience there, why you decided to write about it, and what lessons can be gleaned from that experience? You were absolutely up against a vicious anti-union backlash from your employer. What did you hear during that fight, and what kind of lessons can be taken away from that?
Daisy Pitkin: Yeah, I think the experience that I had organizing with industrial laundry workers in Phoenix echoes a lot of what the two of you were just very correctly saying, that the union becomes this separate entity that then gets critiqued by the company about whether or not it’s good enough, and then their campaign tends to be a campaign of trying to frustrate the efforts of workers to build their union, slow it down, create a kind of gauntlet of anti-union activity through which workers have to pass if they really want to build their union, and then the question isn’t anymore, ‘Do you want to have a union or not?’ At the end of the day it’s, ‘Is the union worse, this very long, very difficult fight that you have to go through with your employer to win it?’ And that’s pretty much the story of the book that I wrote. My book focuses on one industrial laundry that was then owned by Sodexo, this multinational French, multi service corporation, with very deep pockets that chose to play from the standard anti-union handbook to try to squash the union that workers there were building, and it took five years to organize that factory because the company took a hard ideological stance against the union. They fired workers, they threatened workers, they held mandatory captive audience meetings, over 200 of them in small groups where they showed a video that was an anti-union video and spread lots of rumors, and frankly, lies about unions and what they do. So the workers there faced a very difficult uphill battle, and luckily, there were some worker leaders there, and my book really focuses on one of them, this incredible woman named Alma, who is the gutsiest worker leader I have ever met, who just decided, ‘I am not going to give up,’ and the harder this company fights, the more kind of stick-to-it-ness she had about wanting to form the union, because she knew that it was, it is the legal right of workers in this country to form unions, and their fight against the union made her want to fight harder, and sometimes that’s what it takes. So the book really traces the narrative arc of the fight that these workers had to go through to form their union. It was a really hard effort, and what I think is remarkable about it is that the anti-union campaign that she and her co-workers faced, you’re right to say it was vicious. It was, and the workers ended up winning some legal battles that are, at that time, were nearly unheard of, but at the same time, the kind of campaign that they faced was its standard. Sodexo, played from the same standard anti-union handbook that’s been around for decades and decades, and that employers always use, they pretended to be the good boss at first and talk about the company as a family. They pretended to be sad boss, that it was a personal attack, and they were so personally hurt that workers would want to form a union, instead of just coming to them with their problems, and then when neither of those things work, they played bad boss, which was to just violate the law, violate workers rights to try to scare them away from wanting to form a union. So the story traces the years that it took for those workers to finally win.
Adam: We’re going to get to sad boss later, I want to put a pin in that for now. I want to talk about two popular tropes that we hear a lot, and we discussed at the top of the show, which is number one, ‘unions used to make sense, but they’re obsolete in today’s economy.’ I would say from my personal experience growing up in a, you know, I guess, a conservative household, in a conservative state, this is probably the one I’ve heard the most, because it’s sort of the most pat, right? There were a lot of them a long ago time in black and white photo days, where, you know, 15 year olds had cold dust on their face, and unions made sense, then, but now everyone’s kind of cushy and has color TVs and flat screen TVs and refrigerators, and now they sort of don’t make sense. And the second one is, which is I think, a sort of close cousin, which is that unions make sense for certain industries. This is obviously a very gendered one you hear a lot, but they just don’t make sense in this one. A lot of times, you see, union busting CEOs will say like, ‘Hey, I’m pro union,’ they love to say this, right? ‘For literally every other industry, but the one I happen to be the CEO in’. Incidentally, that one, just by sheer coincidence, that out of all the gin joints in all the towns in all the world doesn’t really need a union. So can you address those two tropes? Because I hear those a lot. We talked about this a lot. I want to get your thoughts on those.
Daisy Pitkin: Yeah, you know, I think it in some ways is a really smart tack for employers to take. But, you know, we live in a world where most manufacturing jobs have left the United States. So, of course, there still is some manufacturing that happens here. Our economy has shifted to healthcare and service, and those tend to be the industries where bosses now say, ‘You don’t need a union here.’ You know, there are workers who are organizing in Amazon and Starbucks and libraries and museums and higher ed institutions all across the country, just to name a few of the industries where people are working, and you’re exactly right, that that is a message that, ‘You aren’t really a worker, this isn’t really a career, and therefore you don’t need to have a voice at work.’ They try to make workers feel as if the jobs that exist should not be career jobs, even though those are the jobs that exist in our economy. So if you want to make money in order to pay bills and take care of your family, it’s more likely than not that you have to work in one of these industries where now you’re being told that the work itself is not worthy of democracy in the workplace, of improvements, because you’re not meant to stay on the job for long, and I think it’s just incredibly short sighted. Most Americans work in these industries, they just do, and they ought to be places where people can sustain a livelihood, can support families, they ought to be places that are safe to go to work, people should be able to expect to go to work in the morning or at night, and go home at the end of their shift unscathed. So health and safety, democracy at work, the ability to know that you’re going to work enough hours so that at the end of the month you have enough money to pay your bills. These are basic, basic rights, and those are the kinds of things that if workers work collectively, they can bargain with their employers, they can shift the balance of power so that they can create those safeguards at work, and that it doesn’t matter where you go to work, if it’s a coffee shop, if it’s McDonald’s, if it’s a hospital, if you drive a bus, those things will never cease to be true, but it’s such a, you know, kind of a twisted mindset to make the majority of Americans feel that the jobs that they’re in right now should not be the jobs that they have for the long term.
Adam: Well, it’s fundamentally a tautology too because they create an economy where there’s a lot of labor liquidity, and they fire everyone all the time, and then they turn around and say, ‘Well see, this is not a long term job so you don’t really need a union because this isn’t the olden days where we had a pail hat, and when your daddy went to the coal mine, and your daddy went to the coal mine,’ and so like their own precarity, their own sort of designed precarity then reinforces why you don’t need a union, which of course, is one of the main reasons that so precarious.
Nima: Well, and the idea that these jobs, maybe they were for, you know, these CEOs, when they were teenagers, you know, were just waystations on their way to eventually becoming a CEO without purposefully not recognizing, and I say purposely, right, this isn’t, this isn’t a blind spot, right? This is deliberate the idea that, oh, well, you know, as Daisy, you were just saying, ‘These are not career jobs, these aren’t the jobs you’re going to have for years and years so why do you need to improve things when you’re not going to be around that long?’ It’s just, hey, everyone deals with it, and it’s like, no, that’s actually how you change the situation at work, and that’s exactly what the bosses don’t want. That’s terrifying.
Adam: Yeah. Daisy, can you comment on that? Because this is, you know, by listening to CEOs, you would think that 50 percent of the working class is a 15-year-old, rich white guy who lives with his parents in Orange County, right? The way they talk about it, they love to use the term entry level, which is one of my all time favorite propaganda terms, right? Because you’re sort of, it’s basically an internship, you should be paying McDonald’s to be there, basically, is what they’re saying. Can you talk about this kind of teenage-ification of labor, sort of when they talk in all these industry talking points, it’s always, again, you would think the country was nothing but 15-year-olds who smoke weed and sleep in their mom’s basement.
Daisy Pitkin: That’s absolutely right. That’s the image that they would like for the average consumer to have. But anyone who knows, you go into Chipotle or McDonald’s, you go to Dunkin Donuts, you go to Starbucks, the people who work behind the counter, some of them might be teenagers, they do tend to be young, but many of them are parents, a lot of them have worked in these places for a decade or more, and I think that the precarity that they are proclaiming is part of the point — there was a lot of alliteration there. But it’s true that the precarity and the massive turnover that’s always occurring there, destabilizes these workplaces, makes them more difficult to organize, but organizing will solve the precarity and make the jobs more sustainable, so that people can sustain the jobs for longer periods of time, instead of shuffling around from employer to employer, working multiple jobs at multiple of these kind of fast food restaurants, which is part of what we’re seeing now.
Workers prepare dishes at Chipotle. (Via Delish)
Adam: Yeah, it’s because I think people have a really distorted view also of what unionized jobs were in the past. It’s not as if working at a textile factory or being a train porter were these romantic jobs. I mean, you know what I mean? Its people have this idea that the jobs of the past were somehow lifetime jobs kind of inherently.
Nima: I guess, because people wore more uniforms back then.
Adam: Maybe that was it.
Daisy Pitkin: You know, the union that I work for now, it’s original precursor, it’s rooted in the International Ladies Garment Workers Union. I read about the history of the union a lot in my book also. But the International Ladies Garment Workers Union was formed in the early 1900s when young workers, mostly girls who were teenagers or in their early 20s, started organizing garment factories across New York City, and there were hundreds of small shops all across the city, and people didn’t last at one shop forever, right? They’d worked somewhere for a couple of years and then leave because there were better hours at another place, and they would go and work in the other place and then be there for a few years or for a year, for a few months, and then switch to another place. So it was actually a very similar work economy as we see today in fast food all across the country, and those workers started organizing shop by small shop, and then decided they needed to organize the entire industry all across the city at the same time, and they walked out on a strike that was called the uprising of the 20,000. That was really the genesis of the organizing that happened in the garment industry all across the country. But you know, here we are just over 100 years later, and the union that I work for is supporting a massive campaign where young workers are organizing shop by small shop, and now building structures so that nationally they can try to change an industry. we’re seeing the same story kind of play out right now because the sort of work world looks similar to what it did 100 years ago.
Nima: You know Daisy, you had mentioned this idea that the vast majority of workers have families to support, they are part of communities that they help to support. I want to now refocus us on how those kinds of terms are then used by employers in this kind of, you know, ‘Oh, we all have shared values, we’re a family here,’ et cetera, et cetera, which also leads to as promised the trope of the sad boss. So one thing that we’ve been talking about earlier on this episode, are these kind of flashier, newer anti-union talking points that we’ve seen from say, you know, the CEOs of REI, of Starbucks, et cetera, and I think, you know, talking about Starbucks really gets to the point here, Howard Schultz is kind of the new-agey-ist of these, you know, anti-union trope abusers. Can we talk about how the rhetoric of values and family really attempts to manipulate workers into, as we’ve been saying, dismissing the value of a union, the values that maybe also they hold dear?
Adam: I mean, the guy cries on Zoom calls, people have mentioned this to me, people who know him personally, have worked with him say like, it’s not an act. He’s like, legitimately just a cult leader who believes his own bullshit,and the very thought of unions deeply offends him, because he’s the daddy and you’re the child and daddys take care of their children and so he’s going to cry.
Daisy Pitkin: Yeah, I think, you know, in the case of Howard Schultz, I think he has an idea about the company that he founded that he is very invested in believing in, and workers who have worked for Starbucks for many, many years, have seen sort of a sea change happen inside the company during the time that they’ve worked there, and that, you know, this is a company that likes to call itself progressive, that has a number of values that it portends to stand for, and then when workers start to form a union, they become one of the most prolific labor law violators in US history. So you have to look at that and say, this company, what workers have been saying is that this company really no longer embraces its own values. The company has changed, and we want to form a union because we want to have a seat at the table, and the union busting is sort of proof in the pudding that the company is more Walmart than it is Patagonia at this point. It likes to pretend it’s Patagonia, but it’s Walmart or Chick fil A. I think there’s a lot to be said about Starbucks in this context and Howard Schultz in this context, at this point, he infamously came back to the CEO position, interim CEO of the company in the midst of the union organizing drive, that has now reached over 280 stores in 37 states across the country, over 7,000 workers have joined the Union. He came back sort of at the beginning of this and flew to Buffalo, New York, which is where the organizing drive started, and held a meeting speaking with workers, who he calls partners, and echoed the same talking point that you’re referencing, this family, you know, the company is a family, and that he is a good guy and a good boss and that workers should not form a union because it will interfere really with his idea about the company which no longer is true. I don’t know if it was ever true, but it’s certainly you know, workers are saying that there’s been a massive change in the company over the years, and he gave this speech that included something saying that he built Starbucks, this is not an exact quote, but that he built Starbucks, that the fabric of the company is akin to Jewish people in concentration camps sharing blankets with each other, that that is the foundational value upon which he had built the company. The manipulation inherent in that just didn’t work. It fell flat on workers who work day in and day out in the cafes, and see that the company has really geared itself much more toward profit rather than partnership with the people who work there.
Adam: It’s a sign of desperation, right? I think once you’re analogizing to the Holocaust, you pretty much see the writing on the wall with respect to the momentum of unionization, you’re just throwing shit at the wall seeing if anything sticks, and of course, if you’re sharing a blanket evenly, you know, he’s worth what, a few billion dollars, and maybe he should spread some of that around, then he wouldn’t have this problem probably. But I want to sort of pivot a little bit to criticisms of unions. I think one thing you work does is you’re not romantic about the problems in unions themselves, and we want to be, I don’t want to necessarily have a Maoist struggle session here but I do want to talk about the ways in which unions themselves can kind of contribute to this environment, with a lot of self inflicted problems, as you write about, toxic abusive behavior within unions themselves, which have, I think, it’s fair to say, I mean, obviously, there’s these massive forces of capital and propaganda that are a large part of this, but there is a small, I would say, a small percentage, but a non trivial one, of issues within unions themselves that have led to the current situation where we have such low unionization rates in this country, but such an exploited worker class. So I want to sort of talk about your experience with the problems with unions themselves, what you view as the fix in those problems, and how doing so can kind of make them more attractive, and solidarity more attractive.
Daisy Pitkin: You know, in my book, I write pretty frankly about some of the things that happened inside the union that I worked for because I really believe in unions, I really believe in the labor movement in this country as one of the only ways to continue to foster and feed democracy. So let there be no question that I believe in organizing, I believe in collective power. But I also don’t know how to write about something that you love, that, you know, is flawed, and write only praise. We have to be able to challenge the institutions and organizations that we believe in to be better than they sometimes are, and so my book kind of walks head on into that, and, you know, I think, earlier on in the conversation, we were talking about sort of the third partying that happens of the union as part of anti-union campaigns. I think one thing that happens sometimes in unions is that they end up becoming sort of service centers for members. In a goodhearted kind of way, there are people who work for unions all across the country who really want to serve the union’s membership, and when the union becomes a kind of service model of itself, I think it undercuts the kind of vibrant, collective power model that unions can and should be. Members of unions tend to start thinking of the union exactly as a third party that is supposed to be serving them, rather than engaging in the union as, ‘This organization, it is me and my coworkers, we are the union, and yes, maybe we have a collective bargaining agreement with our employer at this point, and that agreement means a lot, it’s a document of the power that we’ve been able to build, but still the way to enact that is through collective action all the time and not through some staff person who works for the union coming in to solve problems for us, the answer continues to be collective action and engagement from membership.’ I don’t think it’s a coincidence that as we’re seeing this resurgence in organizing across the country, we are also seeing a tide change inside major unions all across the country for more democracy inside the unions themselves. Because what people really want at this point, I think, is democracy not just at the workplace, but inside the unions that they’re members of, and I think that unions are challenged in some ways by that, and we ought to be embracing that as we move forward because, I think, the future of the labor movement depends on workers being active agents inside their unions and inside their workplaces both.
Nima: Well, this has been so great. Daisy, before we let you go, we’d love to hear about what you are working on currently. What are you up to? What can folks pay attention to next and continue to build more solidarity?
Daisy Pitkin: So I’m really lucky at this point to get to be an organizing director for Workers United, which is the union that’s supporting Starbucks workers as they’re building this sort of national movement to organize Starbucks, it’s one of the most incredible campaigns I’ve ever been able to witness, much less be able to support. This is an incredibly worker-driven wildfire of a movement. So if you aren’t already, you should follow Starbucks Workers United online, because it’s a really exciting time to watch the, mainly young people, but not all young people, form this union and challenge this huge, multi billion dollar corporation to do better to be the company that these workers believe it can be.
Starbucks Workers United rally in Buffalo, New York. (STARBUCKS WORKERS UNITED)
Nima: Well, that is a great place to leave it. We have been speaking with Daisy Pitkin, community and union organizer, supporting labor movements for over 20 years. Her writing has been honored with the Montana prize, the Disquiet Literary Prize, the New Millennium Award, among others. And she is the author of the memoir On The Line: A Story of Class, Solidarity, and Two Women’s Epic Fight to Build a Union, which was published by Algonquin Books in 2022. Daisy, thank you so much, again, for joining us today on Citations Needed.
Daisy Pitkin: Thanks so much.
[Music]
Adam: Yeah, I think Daisy was great, because, again, not only has she been in the weeds, is not sentimental about it, right? Because again, I think sometimes when you do work in the anti-union space, you can begin to become naive or overly romantic about the problems with unions, which again, are never the problems that the Scott Walker’s of the world tell you they are, although, you know, Marco Rubio tries to exploit those problems to push their own agenda, right? But she’s very clear-eyed about it and clear-eyed about the fact that, you know, this is an uphill battle, the unionization, the rates in the US are below 12 percent. I mean, that’s not very good, and that even though there’s been a movement towards unionization over the past couple years, even more so in these retail and restaurant spaces, that when you include jobs that have been “added to the economy,” quote-unquote, unionization rates over the past year actually down, and so there’s been this growth, but there’s also been this pushback, it’s a huge uphill battle, and so people were working on fashioning these talking points, I know that the Starbucks workers unions are really good at public facing messaging, which is why their union votes are running up these Saddam Hussein numbers. That’s really how you sort of begin the nitty gritty work. It’s going to be a process over several years, it’s not going to be an overnight thing.
Nima: Yeah, I think what kind of good union, pro-union messaging and ways to push back on these, as we know, tried and true anti-union talking points, which have been around for years, if not well over a century, is this idea of kind of mixing the romantic with the real, you know, things should be aspirational, it should have a, you know, vision for a more just future, sure, but not to be so romantic as to just ignore actual issues to address, actual questions that people do have about how this would work in reality, about how to make this kind of solidarity real and effective and accountable, and not just then, a kind of anti-corporate talking point which sure also useful, but how do you how do you make it both romantic and real?
Adam: Right, because you have to actually convert souls for a living, which is hard.
Nima: Right. You have to do the thing.
Adam: Right.
Nima: But that will do it for this episode of Citations Needed. Thank you all for listening. Of course, you can follow the show on Twitter @CitationsPod, Facebook Citations Needed, and, if you are so inclined, become a supporter of the show through Patreon.com/CitationsNeededPodcast. All your support through Patreon is incredibly appreciated as we are 100 percent listener funded. We don’t run ads, we don’t read out commercial copy, we don’t have corporate donations and so all of your support is what keeps this show going. And as always a very special shout out goes to our critic level supporters on Patreon. I am Nima Shirazi.
Adam: I’m Adam Johnson.
Nima: Our senior producer is Florence Barrau-Adams. Producer is Julianne Tveten. Production assistant is Trendel Lightburn. Newsletter by Marco Cartolano. Transcriptions are by Morgan McAslan. The music is by Grandaddy. Thanks again, everyone. We’ll catch you next time.
[Music]
| 2023-03-15T00:00:00 |
2023/03/15
|
https://citationsneeded.medium.com/episode-177-popular-anti-union-talking-points-and-how-to-combat-them-863e9e727cc2
|
[
{
"date": "2023/03/01",
"position": 92,
"query": "AI labor union"
}
] |
New study offers complex picture of AI's impact on Maine workers
|
New study offers complex picture of AI’s impact on Maine workers
|
https://www.bangordailynews.com
|
[
"Nicole Ogrysko",
"Maine Public",
".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",
"Height Auto Max-Width",
"Vertical-Align Bottom .Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar"
] |
New research from the Maine Department of Labor paints a complex picture of the implications that artificial intelligence will have on the ...
|
New research from the Maine Department of Labor paints a complex picture of the implications that artificial intelligence will have on the state’s labor force.
The study examined tasks associated with specific jobs and determined whether technology such as ChatGPT or other similar models could perform those tasks instead.
According to the research, about two-thirds of Maine jobs are in occupations where less than 40 percent of tasks could be shaped by AI.
“That does represent a large segment of our workforce in Maine today that are probably likely to be minimally impacted or use tools like Chat GPT for a relatively limited amount of their typical workweek,” said Mark McInerney, director of the department’s Center for Workforce, Research and Information.
Meanwhile, roughly 11 percent of Maine jobs are in occupations where 60 percent or more of the tasks could be affected by AI, according to the study.
Jobs, for example, in computer science and office and administrative support have the potential to be most impacted by AI. Often, these jobs are among the highest paid occupations around the state, and they often require some sort of post-secondary degree, according to the research.
Unlike the automation boom that primarily affected manufacturing jobs and factory hubs in Maine, the impacts of AI will be more broadly distributed throughout the state’s labor force, McInerney added.
“Health care, legal, professional business services — across the board these skillsets are important in many sectors,” he said. “They are not necessarily jobs that are as concentrated either in specific sectors or in specific geographic areas of the state.”
Jobs in construction, food service, maintenance and other trades that rely on physical labor may be less affected by AI. Many of these jobs tend to be among the lowest paid in the state, McInerney said.
Though AI has gotten a lot of attention in the media, McInerney stresses that the emerging technology will not immediately overtake tasks and jobs around the state. Instead, forecasters project that the impacts will be more slowly felt throughout the Maine workforce.
This story appears through a media partnership with Maine Public.
| 2025-07-08T00:00:00 |
2025/07/08
|
https://www.bangordailynews.com/2025/07/08/business/maine-labor-force-workers-artificial-intelligence-impact-report/
|
[
{
"date": "2023/03/01",
"position": 97,
"query": "AI workers"
},
{
"date": "2023/05/01",
"position": 98,
"query": "AI workers"
},
{
"date": "2023/06/01",
"position": 98,
"query": "AI workers"
},
{
"date": "2023/11/01",
"position": 98,
"query": "AI workers"
},
{
"date": "2024/02/01",
"position": 98,
"query": "AI workers"
},
{
"date": "2024/12/01",
"position": 98,
"query": "AI workers"
}
] |
Are we working for free for AI companies?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
If the online service you're using is free, you're the product. So companies like google or facebook has been collecting data on you or by you. Ever wondered ...
|
We are a community of AI/ ML/Generative AI enthusiasts/researchers/journalists/writers who share interesting news and articles about the applications of AI. You will never miss any updates on ML/AI/CV/NLP fields because we post them daily. We hope that you subscribe to us so that you'll be up-to-date with the latest developments around the world in terms of machine learning and related areas.
Members Online
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/machinelearningnews/comments/11rw2xb/are_we_working_for_free_for_ai_companies/
|
[
{
"date": "2023/03/01",
"position": 8,
"query": "AI employers"
}
] |
|
Xbox producer tells staff to use AI to ease job loss pain - BBC
|
Xbox producer suggests laid-off staff use AI to deal with emotions
|
https://www.bbc.com
|
[] |
An Xbox producer has faced a backlash after suggesting laid-off employees should use artificial intelligence to deal with emotions in a now ...
|
Xbox producer tells staff to use AI to ease job loss pain
One X user called it "plain disgusting" while another said it left them "speechless". The BBC has contacted Microsoft, which owns Xbox, for comment.
The post, which was captured in a screenshot by tech news site Aftermath , shows Mr Turnbull suggesting tools like ChatGPT or Copilot to "help reduce the emotional and cognitive load that comes with job loss."
Matt Turnbull, an executive producer at Xbox Game Studios Publishing, wrote the post after Microsoft confirmed it would lay off up to 9,000 workers, in a wave of job cuts this year .
An Xbox producer has faced a backlash after suggesting laid-off employees should use artificial intelligence to deal with emotions in a now deleted LinkedIn post.
Microsoft previously said several of its divisions would be affected without specifying which ones but reports suggest that its Xbox video gaming unit will be hit.
Microsoft has set out plans to invest heavily in artificial intelligence (AI), and is spending $80bn (£68.6bn) in huge data centres to train AI models.
Mr Turnbull acknowledged the difficulty of job cuts in his post and said "if you're navigating a layoff or even quietly preparing for one, you're not alone and you don't have to go it alone".
He wrote that he was aware AI tools can cause "strong feelings in people" but wanted to try and offer the "best advice" under the circumstances.
The Xbox producer said he'd been "experimenting with ways to use LLM Al tools" and suggested some prompts to enter into AI software.
These included career planning prompts, resume and LinkedIn help, and questions to ask for advice on emotional clarity and confidence.
"If this helps, feel free to share with others in your network," he wrote.
The Microsoft cuts would equate to 4% of Microsoft's 228,000-strong global workforce.
Some video game projects have reportedly been affected by the cuts.
| 2023-03-01T00:00:00 |
https://www.bbc.com/news/articles/ckglzxy389zo
|
[
{
"date": "2023/03/01",
"position": 21,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 19,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 16,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 18,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 17,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 18,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 17,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 20,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 9,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 8,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 9,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 9,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 17,
"query": "AI layoffs"
}
] |
|
AI-driven job cuts may be underreported: Challenger | CFO Dive
|
AI-driven job cuts may be underreported: Challenger
|
https://www.cfodive.com
|
[
"Alexei Alexis"
] |
Challenger's research department uses information such as public statements and government filings to track layoff trends. “We do see companies ...
|
Dive Brief:
Technology-related factors such as automation drove 20,000 job cuts among U.S.-based employers in the first half of the year, outplacement firm Challenger, Gray & Christmas said in a recent report.
Only 75 of those cuts were explicitly attributed to artificial intelligence, although many companies may be categorizing their AI-related layoffs more broadly, according to the analysis. Challenger’s research department uses information such as public statements and government filings to track layoff trends.
“We do see companies using the term ‘technological update’ more often than we have over the past decade, so our suspicion is that some of the AI job cuts that are likely happening are falling into that category,” Andy Challenger, a senior vice president at the Chicago, Illinois-based outplacement firm, told CFO Dive. In some cases, companies may avoid directly tying their layoffs to AI because they “don’t want press on it,” he said.
Dive Insight:
Procter & Gamble, Microsoft, Citigroup, Walmart, CrowdStrike and Disney are among corporations across a variety of sectors that have announced layoffs in recent months, according to a CNBC article.
The trend is showing no signs of slowing down as the second half of the year begins, with Microsoft announcing last week that it will lay off about 9,000 employees across different teams in its global workforce.
Many organizations are under rising pressure to trim costs amid global economic uncertainty triggered by President Donald Trump’s trade policies, the CNBC report said. Layoffs have been lumped in with larger cost-cutting strategies or growth plans in some cases.
Four in 10 employers anticipate reducing their workforce where AI can automate tasks, according to World Economic Forum survey findings unveiled in January.
Fintech company Klarna has slowed AI-driven job cuts after concluding the effort has gone too far, underscoring the risks that financial services firms face when replacing humans with a still largely untested technology, according to a May Bloomberg article.
U.S.-based employers announced a total of 744,308 job cuts in the first six months of the year, according to Challenger. That’s the highest level recorded year-to-date since 2020 when 1,585,047 were announced, the firm said.
The Department of Government Efficiency has been the leading cause of job cut announcements so far this year, with the number reaching 286,679, Challenger said. This includes direct reductions to the federal workforce and its contractors. An additional 11,751 cuts have been attributed to DOGE “downstream impacts,” such as the loss of funding to private non-profits and affiliated organizations.
Market and economic conditions are the second-most cited reason for workforce reductions, responsible for 154,126 cuts year to date, according to Challenger’s research. Closings of stores, units, or plants led to 107,142 layoffs so far this year, while restructuring efforts have resulted in 64,487 job cuts, the report said.
Other drivers of layoffs so far this year include bankruptcies (35,641), cost-cutting efforts (17,245), contract losses (8,893), and financial declines (4,909), according to the study. A total of 18,781 cuts were announced without a specified reason.
| 2025-07-08T00:00:00 |
2025/07/08
|
https://www.cfodive.com/news/ai-driven-job-cuts-underreported-challenger/752418/
|
[
{
"date": "2023/03/01",
"position": 23,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 70,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 58,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 68,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 63,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 57,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 59,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 73,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 58,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 61,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 54,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 61,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 52,
"query": "AI layoffs"
},
{
"date": "2025/02/01",
"position": 11,
"query": "artificial intelligence layoffs"
},
{
"date": "2025/03/01",
"position": 10,
"query": "artificial intelligence layoffs"
},
{
"date": "2025/04/01",
"position": 7,
"query": "artificial intelligence layoffs"
},
{
"date": "2025/06/01",
"position": 68,
"query": "AI job losses"
},
{
"date": "2025/06/01",
"position": 10,
"query": "artificial intelligence layoffs"
}
] |
Xbox Producer Recommends Laid Off Workers Should Use AI To ...
|
Xbox Producer Recommends Laid Off Workers Should Use AI To ‘Help Reduce The Emotional And Cognitive Load That Comes With Job Loss’ [Update]
|
https://aftermath.site
|
[
"Luke Plunkett",
"Riley Macleod",
"Gita Jackson",
"Nathan Grayson",
"Chris Person"
] |
AI. Xbox Producer Recommends Laid Off Workers Should Use AI To 'Help Reduce The Emotional And Cognitive Load That Comes With Job Loss'. 'I'm ...
|
In the wake of Microsoft's latest round of layoffs and studio closures, which brings the number of affected into the thousands since early 2024, you would think that those remaining--and particularly those remaining in charge at the company--would be treading lightly in the days to come.
Not Matt Turnbull, Executive Producer at Xbox Game Studios Publishing! Matt has looked at everything that has happened this week, particularly the bit where Xbox laid off a bunch of people at the same time Microsoft pledged to invest $80 billion in AI, and decided that not only does he need to give advice to those laid off, but that the advice should come in the form of...AI prompts, which will somehow give responses that will "help reduce the emotional and cognitive load that comes with job loss".
Given what you're about to read, I have included a screenshot I captured when browsing Linkedin so that you know this is real.
Here's the full text in case you need it:
These are really challenging times, and if you're navigating a layoff or even quietly preparing for one, you're not alone and you don't have to go it alone. I know these types of tools engender strong feelings in people, but I'd be remiss in not trying to offer the best advice I can under the circumstances. I've been experimenting with ways to use LLM Al tools (like ChatGPT or Copilot) to help reduce the emotional and cognitive load that comes with job loss. Here are some prompt ideas and use cases that might help if you're feeling overwhelmed: Career Planning Prompts:
"Act as a career coach. I've been laid off from a [role] in the game industry. Help me build a 30-day plan to regroup, research new roles, and start applying without burning out."
"What kinds of game industry jobs could I pivot to with experience in [Production/Narrative/LiveOps/etc.]?" Resume & Linkedin Help
"Here's my current resume. Give me three tailored versions: one for AAA, one for platform/publishing roles, and one for startup/small studio leadership."
"Rewrite this resume bullet to highlight impact and metrics."
"Draft a new LinkedIn 'About Me' section that focuses on my leadership style, shipped titles, and vision for game development." Networking & Outreach
"Draft a friendly message I can send to old coworkers letting them know I'm exploring new opportunities."
"Write a warm intro message for reaching out to someone at [studio name] about a job posting." Emotional Clarity & Confidence
"I'm struggling with imposter syndrome after being laid off. Can you help me reframe this experience in a way that reminds me what I'm good at?" No Al tool is a replacement for your voice or your lived experience. But at a time when mental energy is scarce, these tools can help get you unstuck faster, calmer, and with more clarity. If this helps, feel free to share with others in your network. Stay kind, stay smart, stay connected.
The Linkedin post has since been deleted, likely upon the advice of someone with a human heart.
[via @brandon.insertcredit.com]
UPDATE July 13, 2025: Another post from an Xbox Guy coming from a very similar place! Very healthy corporate culture!
you have got to be kidding me — Luke Plunkett (@lukeplunkett.com) 2025-07-13T02:09:49.080Z
It's absolutely wild that at no point whatsoever the thought "hrm maybe it's in bad taste to use AI slop to advertise some jobs after Microsoft just laid off 9000 people" crossed this man's mind.
| 2025-07-04T00:00:00 |
2025/07/04
|
https://aftermath.site/xbox-microsoft-layoffs-ai-prompt-chatgpt-matt
|
[
{
"date": "2023/03/01",
"position": 35,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 18,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 18,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 27,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 20,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 28,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 27,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 19,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 26,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 20,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 19,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 20,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 26,
"query": "AI layoffs"
}
] |
Jack Dorsey's new messaging app | Meta hires Apple's AI head
|
Jack Dorsey’s new messaging app | Intel layoffs begin | Meta hires Apple’s AI head
|
https://medium.com
|
[
"Vipin Gupta"
] |
Jack Dorsey's new messaging app | Intel layoffs begin | Meta hires Apple's AI head ... Learn more, scroll less. Curated AI/Tech/Business news and ...
|
Jack Dorsey’s new messaging app | Intel layoffs begin | Meta hires Apple’s AI head Vipin Gupta 2 min read · 6 days ago 6 days ago -- Listen Share
Learn more, scroll less. Curated AI/Tech/Business news and articles.
8th July 2025
🌟 Welcome to the latest edition of Top249 🤩
We’re here to keep you updated on AI, tech, and business news and articles, so you can save time and focus on learning and growth.
Let’s get started! 😎
AI & Tech Frontier
MIT researchers have developed a new training approach that improves how large language models reason through complex tasks.
By mimicking the human process of revisiting and refining answers, the model shows significant gains in logical accuracy.
This method could help future AI systems better handle nuanced problems in math, science, and real-world decision-making.
Meta has hired the executive who previously led Apple’s AI model development, signalling a bold move in its AI race.
This shift suggests Meta is intensifying efforts to build more advanced and personalized AI systems.
The recruitment highlights increasing competition among tech giants for top AI talent and innovation leadership.
Anthropic is calling for stronger standards around transparency and safety in advanced AI systems like Claude and GPT.
The company emphasizes that without clear disclosures about model capabilities and risks, the public and policymakers remain in the dark.
It proposes a set of concrete measures, including third-party evaluations and public model cards, to improve accountability.
Jack Dorsey floated the idea that WhatsApp could bypass internet shutdowns by using Bluetooth-based mesh networking.
This concept would allow communication without relying on traditional cellular or Wi-Fi infrastructure.
While technically challenging, it aligns with growing interest in decentralized tools to protect digital freedom in censored regions.
Business Briefs
Intel has started layoffs affecting over 107 employees at its Santa Clara headquarters, with thousands more expected globally as part of a massive restructuring effort.
The company plans to cut 15–20% of its factory and Foundry workforce — over 10,000 jobs — as part of a $10 billion cost-cutting strategy.
Key moves include shutting down the automotive chip division, outsourcing functions like marketing, and refocusing on AI and core semiconductor operations to regain competitive edge
Hidden Gems / Learn & Grow
The latest developments at Quora
That’s it for today.
If you liked this post, subscribe to my free newsletter so that you can get the latest updates right in your inbox every day!
Subscribe for free 👉 https://www.top249.com/subscribe
Join the top249 newsletter — trusted by professionals at leading companies worldwide.
Till next time.
| 2025-07-08T00:00:00 |
2025/07/08
|
https://medium.com/@vipingup17/jack-dorseys-new-messaging-app-intel-layoffs-begin-meta-hires-apple-s-ai-head-a3e38b1c54ec
|
[
{
"date": "2023/03/01",
"position": 37,
"query": "AI layoffs"
}
] |
Amazon Preps Employees for Layoffs by Talking Up the Power of AI ...
|
Amazon Preps Employees for Layoffs by Talking Up the Power of AI Agents
|
https://gizmodo.com
|
[
"Aj Dellinger",
"Gayoung Lee",
"James Pero",
"Luc Olinga",
"Kyle Barr"
] |
The company cut about 100 people from its devices and services team earlier this year, and around the same number from its books department. Per CNBC, it has ...
|
Amazon appears to be soft-launching its next round of layoffs. In a message to employees shared Tuesday, Amazon CEO Andy Jassy talked highly of the company’s embrace of artificial intelligence tools across its company, and said that it will ultimately “reduce our total corporate workforce as we get efficiency gains” over time. That is only slightly veiled corporate speak for “get ready to be replaced.”
Jassy called generative AI a “once-in-a-lifetime” technology that will change the way the company operates, and said Amazon is already using it in “virtually every corner of the company.” According to Jassy, Amazon already has over 1,000 Generative AI services and applications in progress or built, and said, “that’s a small fraction of what we will ultimately build.” So it’s clear the company is all in on AI. Amazon previously said it would commit $100 billion to investing in AI technologies this year.
As for humans? Well, it seems Amazon is not so committed to them long-term. Jassy told the company’s 1.5 million employees that generative AI will “change the way our work is done,” and said that the company will ultimately “need fewer people doing some of the jobs that are being done today, and more people doing other types of jobs.”
The underlying message: you might soon be out of work. “It’s hard to know exactly where this nets out over time, but in the next few years, we expect that this will reduce our total corporate workforce as we get efficiency gains from using AI extensively across the company,” Jassy wrote.
The CEO did offer his workers, some of whom are likely wondering just how long they’ll be employed, how to potentially survive the next round of layoffs (or, maybe more likely, help train their future replacements). “As we go through this transformation together, be curious about AI, educate yourself, attend workshops and take trainings, use and experiment with AI whenever you can, participate in your team’s brainstorms to figure out how to invent for our customers more quickly and expansively, and how to get more done with scrappier teams.”
Amazon has been in the process of stripping its workforce down to the bones in departments it seems to care less about. The company cut about 100 people from its devices and services team earlier this year, and around the same number from its books department. Per CNBC, it has laid off about 27,000 people since 2022 and has its eyes on further cuts.
It’s hard to look at Jassy’s AI-forward message as much else other than an indicator that more layoffs are just around the corner. It’s possible the AI hype is just a cynical attempt to position itself as being an industry leader when the real goal is cutting salaries to boost stock price. It wouldn’t be the first company to try to go all-in on AI at the expense of human labor. Earlier this year, Klarna announced it was bringing back human customer service representatives after trying to leave the task to AI after finding the outcomes aren’t great and people don’t really like dealing with AI agents.
| 2025-06-17T00:00:00 |
2025/06/17
|
https://gizmodo.com/amazon-preps-employees-for-layoffs-by-talking-up-the-power-of-ai-agents-2000617077
|
[
{
"date": "2023/03/01",
"position": 50,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 46,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 44,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 46,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 47,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 48,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 44,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 46,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 45,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 47,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 43,
"query": "AI layoffs"
},
{
"date": "2025/06/17",
"position": 22,
"query": "AI layoffs"
}
] |
Microsoft Layoffs Are Funding Increased Spending in AI Infrastructure
|
Microsoft Layoffs Are Funding Increased Spending in AI Infrastructure
|
https://wccftech.com
|
[
"Alessio Palumbo",
"Francesco De Meo",
"Ramish Zafar"
] |
According to a report, the latest Microsoft layoffs are meant to fund the increased spending in AI infrastructure.
|
Microsoft has laid off around 9K employees in the latest round of cuts, affecting 4% of the company's total workforce. According to The Seattle Times, this is all part of the company's mandate to trim and make room for increased spending in AI infrastructure.
The report says it's not quite like one game developer from Halo Studios reckoned last week when they said Microsoft was doing its damnedest to replace personnel with AI agents. However, Microsoft is indeed cutting costs as much as possible to accommodate its planned expenditures of over $80 billion in this area, a $25 billion increase over the previous year. These investments are seen as more necessary than ever by Microsoft, with Open AI showing its fangs lately in what has become a complicated partnership.
However, the cuts are weighing heavily on the company's reputation in other areas, such as gaming. Microsoft spent dozens of billions on gaming acquisitions, such as Bethesda parent company ZeniMax Media and Activision Blizzard, to expand its Game Pass subscription service library. Still, the user base didn't grow nearly as much as hoped, and analysts are now saying that Xbox might have bet on the wrong horse, since subscriptions do not hold the same appeal for gamers as they do for music or TV/film fans.
Moreover, the industry's reaction to these latest layoffs was more scathing than ever before. Fourteen months after it shut down Tango Gameworks, which had released a successful and critically acclaimed game (Hi-Fi Rush), Microsoft cancelled a promising online looter shooter from ZeniMax Online Studios, the makers of The Elder Scrolls Online, one of the gaming division's top performers. Former developers railed against the decision, saying that the project was finally heading in a great direction, and there have been rumors that even Microsoft Gaming CEO Phil Spencer had a blast while playing a vertical slice of Project Blackbird earlier this year.
The only logical conclusion is that the executive did not wish to cancel the game himself, but may have received a mandate from above. Finishing Project Blackbird would have cost quite a bit, as it was just about to ramp up to production with an estimated late 2028 launch window, and Microsoft had other priorities - chiefly, bolstering its AI infrastructure. For gamers and developers alike, though, it's a shame.
| 2025-07-05T00:00:00 |
2025/07/05
|
https://wccftech.com/microsoft-layoffs-funding-increased-spending-ai-infrastructure/
|
[
{
"date": "2023/03/01",
"position": 53,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 47,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 56,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 51,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 55,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 54,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 56,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 52,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 56,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 56,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 49,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 57,
"query": "AI layoffs"
},
{
"date": "2024/12/01",
"position": 49,
"query": "AI layoffs"
}
] |
Return of the Generalist (Video) - NN/g
|
Return of the Generalist (Video)
|
https://www.nngroup.com
|
[
"Sarah Gibbons"
] |
AI is reviving the UX generalist. Broad skills, adaptability, and ... UX Layoff Crisis: A Guide for Resilience and Recovery · How to ...
|
Summary: AI is reviving the UX generalist. Broad skills, adaptability, and strategic thinking are becoming more valuable than deep specialization.
| 2023-03-01T00:00:00 |
https://www.nngroup.com/videos/return-of-the-generalist/
|
[
{
"date": "2023/03/01",
"position": 61,
"query": "AI layoffs"
}
] |
|
Microsoft's largest layoff in years hits Xbox, sales and other divisions
|
Microsoft’s largest layoff in years hits Xbox, sales and other divisions
|
https://apnews.com
|
[
"O Brien Covers The Business Of Technology",
"Artificial Intelligence For The Associated Press."
] |
Microsoft says it is laying off about 9000 workers, its second mass layoff in months and its largest in more than two years ... Senate strikes AI ...
|
Microsoft says it is laying off about 9,000 workers, its second mass layoff in months and its largest in more than two years.
The tech giant began sending out layoff notices Wednesday that hit the company’s Xbox video game business and other divisions.
Among those losing their jobs are 830 workers tied to Microsoft’s headquarters in Redmond, Washington, according to a notice sent to state officials Wednesday.
Microsoft said the cuts will affect multiple teams around the world, including its sales division, part of “organizational changes” needed to succeed in a “dynamic marketplace.” The company won’t say the total number of layoffs except that it was about 4% of the workforce it had a year ago.
A memo to gaming division employees Wednesday from Xbox CEO Phil Spencer said the cuts would position the video game business “for enduring success and allow us to focus on strategic growth areas.”
Xbox would “follow Microsoft’s lead in removing layers of management to increase agility and effectiveness,” Spencer wrote.
Microsoft employed 228,000 full-time workers as of June 2024, the last time it reported its annual headcount. Its latest layoffs would cut fewer than 4% of that workforce, according to Microsoft. But it has already had at least three layoffs this year and it’s unlikely that new hiring has matched the amount lost. Either way, a 4% cut would amount to somewhere in the range of 9,000 people.
Until now, this year’s biggest layoff was in May, when Microsoft began laying off about 6,000 workers, nearly 3% of its global workforce and its largest job cuts in more than two years.
The cutbacks come as Microsoft continues to invest huge amounts of money in the data centers, specialized computer chips and other infrastructure needed to advance its AI ambitions. The company anticipated those expenses would cost it about $80 billion in the last fiscal year. Its new fiscal year began Tuesday.
Microsoft just last month cut another 300 workers based out of its Redmond headquarters, on top of nearly 2,000 who lost their jobs in the Puget Sound region in May, most of them in software engineering and product management roles, according to information it sent to Washington state employment officials.
Microsoft’s chief financial officer Amy Hood said on an April earnings call that the company was focused on “building high-performing teams and increasing our agility by reducing layers with fewer managers.”
The company has repeatedly characterized its recent layoffs as part of a push to trim management layers, but the May focus on cutting software engineering jobs has fueled worries about how the company’s own AI code-writing products could reduce the number of people needed for programming work.
Microsoft CEO Satya Nadella said earlier this year that “maybe 20, 30% of the code” for some of Microsoft’s coding projects “are probably all written by software.”
The latest layoffs, however, seemed centered on slower-growing areas of the company’s business, said Wedbush Securities analyst Dan Ives.
“They’re focused more and more on AI, cloud and next-generation Microsoft and really looking to cut costs around Xbox and some of the more legacy areas,” Ives said. “I think they overhired over the years. This is Nadella and team making sure that they’re keeping with efficiency and that’s the name of the game in Wall Street.”
The trimming of the Xbox staff follows Microsoft’s years-long expansion of the business surrounding its gaming console, culminating in 2023 with the $75.4 billion acquisition of Activision Blizzard — the California-based maker of hit franchises like Call of Duty and Candy Crush.
Before that, in a bid to compete with Sony’s PlayStation, it spent $7.5 billion to acquire ZeniMax Media, the parent company of Maryland-based video game publisher Bethesda Softworks.
Many of those game studios, which have locations across North America and Europe, were struggling with the layoffs Wednesday, according to social media posts from employees who announced they were looking for new jobs.
| 2025-07-02T00:00:00 |
2025/07/02
|
https://apnews.com/article/microsoft-layoffs-xbox-f44079957b12370f72e24edebe9fcc6b
|
[
{
"date": "2023/03/01",
"position": 68,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 65,
"query": "AI layoffs"
},
{
"date": "2023/05/01",
"position": 76,
"query": "AI layoffs"
},
{
"date": "2023/06/01",
"position": 71,
"query": "AI layoffs"
},
{
"date": "2023/07/01",
"position": 74,
"query": "AI layoffs"
},
{
"date": "2023/09/01",
"position": 74,
"query": "AI layoffs"
},
{
"date": "2023/11/01",
"position": 77,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 70,
"query": "AI layoffs"
},
{
"date": "2024/05/01",
"position": 76,
"query": "AI layoffs"
},
{
"date": "2024/06/01",
"position": 76,
"query": "AI layoffs"
},
{
"date": "2024/07/01",
"position": 60,
"query": "AI layoffs"
},
{
"date": "2024/08/01",
"position": 77,
"query": "AI layoffs"
}
] |
Report: Microsoft mandated 2025 layoffs from the top for a huge ...
|
Report: Microsoft mandated 2025 layoffs from the top for a huge (and desperate) $80B AI infrastructure investment News
|
https://www.resetera.com
|
[] |
Report: Microsoft mandated 2025 layoffs from the top for a huge (and desperate) $80B AI infrastructure investment. Thread starter Rychu; Start ...
|
Guru Meditation said: No, it has already learned all of the data on the internet and is now hitting diminishing returns. There's some secret sauce in the human brain that can't be captured by AI. Crazy to think a brain only uses 20 watts of power too, compared to the massive amount of energy being wasted powering AI.
There's something even better than AI that these companies are forgetting. They're called humans. Click to expand... Click to shrink...
I agree that nothing beats the human brain when it comes to unique problem solving but AI tools will be a part of everybody's job in the same way every office worker today has to be able to type and use basic word processing or spreadsheet programs.I think the ideal scenario is to keep the same people and focus on boosting overall productivity, but a lot of companies prefer to cut staff now and maintain current output. There is also some organizational inertia whenever you change a workflow and a few employees either can't or refuse to embrace it, so there will be some layoffs no matter what.The saddest thing is seeing Xbox get a carved up to feed this investment, but it was going to definitely happen and it's better to understand when and how to use AI tools rather than place bets against it. It's not the same as VR or crypto which everyone could see would never scale. Also, I feel like I should be clear that I consider all ML and data analysis tools in this category, prompt shit is just tip of the iceberg and will probably fall by the wayside like voice controlling Siri/Alexa.
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.resetera.com/threads/report-microsoft-mandated-2025-layoffs-from-the-top-for-a-huge-and-desperate-80b-ai-infrastructure-investment.1236402/page-9
|
[
{
"date": "2023/03/01",
"position": 69,
"query": "AI layoffs"
}
] |
ChatGPT Becomes The Most Consulted AI Tool In Making Layoff ...
|
ChatGPT Becomes The Most Consulted AI Tool In Making Layoff And Promotion Decisions Among Managers: Report
|
https://in.mashable.com
|
[] |
A whopping 77% of managers also relied on the AI bots to decide promotions of their staff. Besides 66% of managers using AI for layoff decisions ...
|
> Tech
A survey conducted on 1342 managers revealed that a staggering 60% of HRs consulted LLMs such as ChatGPT to (hire or) fire employees. Ominously enough, one in five managers also admitted to allowing AI tools to take the final decision.
The online survey by Resume Builder also revealed that 78% of managers consulted an AI chatbot for deciding whether to give employees a hike. A whopping 77% of managers also relied on the AI bots to decide promotions of their staff. Besides 66% of managers using AI for layoff decisions, 64% of the surveyed HRs also used LLM tools for termination. Some 65% of managers admitted to using genAI tools for work, with nearly half of them stating they used it either round the clock or frequently for workplace-related tasks.
The survey also revealed the favorite AI tools used by HR managers, with ChatGPT (53%) by OpenAI emerging as the most deployed chatbot. Microsoft Copilot (29%) and Gemini by Google (16%) were also used by few. Meanwhile 3% of the surveyed managers relied on alternative AI tools.
The managers also deployed AI tools to build or produce training materials, employee plans, performance assessments, and performance improvement plans (PIP) among others.
What is alarming about the survey is that only 32% of the managers said they have received formal training on ethically handling AI tools, while 43% received informal guidance. 24% of the respondents stated that they did not receive any training at all.
Reactions poured in with netizens slamming the sham pulled off by HRs. One user wrote, “As a former HR director I find this horrifying to let AI make these kind of decisions. AI hallucinates, and it is not appropriate at determining people's livelihoods.” Another jibed, “So the managers are not doing any real work and should be fired themselves then.” A third user quipped, “HR used to ghost you. Now it just auto-generates your exit.” Yet another user remarked, “ChatGPT is obsequious. It is full of nonsense compliments. It is really kind of yucky in that. I can see corporate dorks loving that though and wanting to replace the people they hate (everyone) with AI.”
See Also: Cognizant CEO Says AI Will Not Take Away Entry-Level Jobs: ‘We Need More Freshers Than Less’
See Also: Wall Street Will Slash Over 2 Lakh Jobs As AI Takes Over Several Backend And Frontend Tasks: Report
See Also: ‘We Will Need Fewer People…’ Amazon CEO Andy Jassy Warns Employees To Adapt With AI Or Face The Axe
Cover: Pexels / Pexels
| 2025-07-08T00:00:00 |
2025/07/08
|
https://in.mashable.com/tech/96761/chatgpt-becomes-the-most-consulted-ai-tool-in-making-layoff-and-promotion-decisions-among-managers-r
|
[
{
"date": "2023/03/01",
"position": 75,
"query": "AI layoffs"
}
] |
Microsoft layoffs not performance-based, largely targeting middle ...
|
Microsoft layoffs not performance-based, largely targeting middle managers
|
https://www.cnbc.com
|
[
"Steve Kovach"
] |
AI · Enterprise · Internet · Media · Mobile · Social Media · CNBC Disruptor 50 ... Microsoft layoffs not performance-based, largely targeting ...
|
In this video
Share Share Article via Facebook Share Article via Twitter Share Article via LinkedIn Share Article via Email
Microsoft layoffs not performance-based, largely targeting middle managers
CNBC's Steve Kovach reports on the latest news regarding Microsoft.
| 2025-07-02T00:00:00 |
2025/07/02
|
https://www.cnbc.com/video/2025/07/02/microsoft-layoffs-not-performance-based-largely-targeting-middle-managers.html
|
[
{
"date": "2023/03/01",
"position": 95,
"query": "AI layoffs"
}
] |
Microsoft to cut about 4% of jobs amid hefty AI bets - Yahoo Finance
|
Microsoft to cut about 4% of jobs amid hefty AI bets
|
https://finance.yahoo.com
|
[
"Reuters Videos",
"Wed",
"Jul"
] |
... AI infrastructure has weighed on its margins:: Microsoft said it ... layoffs:: Big Tech peers like Meta, Amazon and Alphabet's Google ...
|
STORY: :: Microsoft to cut about 4% of jobs amid hefty AI bets
:: The tech giant is looking to rein in costs amid hefty investments in artificial intelligence infrastructure
:: The Windows-maker had about 228,000 employees worldwide as of June 2024
:: The company had pledged $80 billion in capital spending for its 2025 fiscal year
:: But the soaring cost of scaling its AI infrastructure has weighed on its margins
:: Microsoft said it plans to reduce organization layers and streamline its products, procedures and roles
:: Microsoft confirmed to Reuters that its gaming division was impacted by the layoffs
:: Big Tech peers like Meta, Amazon and Alphabet's Google have also announced job cuts in the past year
| 2023-03-01T00:00:00 |
https://finance.yahoo.com/video/microsoft-cut-4-jobs-amid-172213831.html
|
[
{
"date": "2023/03/01",
"position": 98,
"query": "AI layoffs"
},
{
"date": "2023/04/01",
"position": 92,
"query": "AI layoffs"
},
{
"date": "2024/01/01",
"position": 94,
"query": "AI layoffs"
}
] |
|
[D] Salary for Machine Learning Researcher with PhD?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
$300k+ starting salary if you're a PhD grad from one of the top research groups in the world, and land a gig at DeepMind, FAANG, etc etc etc.
|
I've seen salaries ranging from 60k to 500k and I just don't know what to believe anymore...
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/MachineLearning/comments/120rfxd/d_salary_for_machine_learning_researcher_with_phd/
|
[
{
"date": "2023/03/01",
"position": 1,
"query": "AI wages"
},
{
"date": "2023/03/01",
"position": 1,
"query": "artificial intelligence wages"
},
{
"date": "2023/03/25",
"position": 26,
"query": "artificial intelligence wages"
},
{
"date": "2023/03/25",
"position": 27,
"query": "artificial intelligence wages"
}
] |
|
The Impact of Generative AI on Labor Productivity, ...
|
The Impact of Generative AI on Labor Productivity, Employment, Wages and GDP
|
https://www.linkedin.com
|
[] |
According to a recent report by Goldman Sachs (2023), generative AI could impact up to 300 million jobs globally, or about 18% of the total workforce.
|
The Impact of Generative AI on Labor Productivity, Employment, Wages and GDP
Generative AI is a branch of artificial intelligence that can create new content, such as text, images, audio and video, based on existing data. Generative AI has made remarkable progress in recent years, thanks to the development of large-scale neural networks and massive amounts of data. Some examples of generative AI applications include ChatGPT, a conversational agent that can generate realistic and engaging responses; GPT-4, a language model that can write coherent and diverse texts on any topic; and DeepFaceLab, a software that can swap faces in videos.
Generative AI has the potential to transform various industries and sectors, such as media, entertainment, education, health care and legal services. However, it also poses significant challenges and risks for the labor market, as it could automate many tasks that are currently performed by human workers. According to a recent report by Goldman Sachs (2023), generative AI could impact up to 300 million jobs globally, or about 18% of the total workforce. The report estimates that generative AI could substitute up to 25% of current work in the US and 24% in Europe, while complementing most of the remaining work.
The impact of generative AI on different occupations and industries depends on the degree of exposure to automation and the availability of complementary skills. The report identifies four factors that determine the exposure to automation: creativity, social intelligence, physical dexterity and domain knowledge. Tasks that require high levels of these factors are less likely to be automated by generative AI, while tasks that are routine, repetitive and standardized are more likely to be automated.
The report finds that office and administrative support occupations have the highest proportion of tasks that could be automated by generative AI in the US (46%), followed by legal occupations (44%), architecture and engineering occupations (37%), life, physical and social science occupations (36%) and business and financial operations occupations (35%). On the other hand, building and grounds cleaning and maintenance occupations have the lowest proportion of tasks that could be automated by generative AI in the US (1%), followed by installation, maintenance and repair occupations (4%), construction and extraction occupations (6%), education, training and library occupations (7%) and health care practitioners and technical occupations (8%).
The report also analyzes the impact of generative AI on different countries based on their employment structure and income level. It finds that Hong Kong, Israel, Japan, Sweden and the US are likely to be the most affected countries by generative AI automation, while India, Indonesia, Pakistan, Philippines and Vietnam are likely to be the least affected countries. The report suggests that developed countries have more jobs that are exposed to automation than emerging markets, but they also have more resources and capabilities to adapt to the changes.
The report acknowledges that generative AI could also create new jobs and industries that do not exist today or are not captured by current data. Moreover, generative AI could enhance labor productivity growth and boost global GDP by as much as 7% over time. However, the report warns that generative AI could also increase income inequality and social polarization if not accompanied by appropriate policies and regulations. The report calls for more investment in education and training, social protection and safety nets, labor market flexibility and mobility, innovation and entrepreneurship, ethical standards and governance for generative AI.
Sources:
- Generative AI Could Impact 300M Jobs, Goldman Sachs Predicts. CNET. https://www.cnet.com/tech/generative-ai-could-impact-300m-jobs-goldman-sachs-predicts/
- Goldman Sachs says generative A.I. could impact 300 million jobs — here's which ones. CNBC. https://www.cnbc.com/2023/03/28/ai-automation-could-impact-300-million-jobs-heres-which-ones.html
- Generative AI Could Automate Almost Half of All Legal Tasks, Goldman Sachs Estimates. Legaltech News. https://www.law.com/legaltechnews/2023/03/29/generative-ai-could-automate-almost-half-of-all-legal-tasks-goldman-sachs-estimates/
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/impact-generative-ai-labor-productivity-employment-wages-glenn-mossy
|
[
{
"date": "2023/03/01",
"position": 6,
"query": "AI wages"
},
{
"date": "2023/03/01",
"position": 7,
"query": "artificial intelligence wages"
}
] |
|
Mississippi State University Launches AI Master's Degree - GovTech
|
Mississippi State University Launches AI Master’s Degree
|
https://www.govtech.com
|
[] |
... of an artificial intelligence concentration and bachelor's degree, Mississippi State is now offering graduate-level AI education.
|
Starting this fall, Mississippi State University will offer artificial intelligence as a focus at the graduate level. Aiming to prepare students for in-demand jobs, the university’s new master’s degree program builds on recent initiatives to expand AI competency and fill workforce needs locally and nationwide, Andy Perkins, interim head of the Department of Computer Science, said in a recent news release With classes available in person and online, the master’s curriculum includes foundational AI and machine learning courses as well as electives covering computing theory, legal and ethical issues and applications in different areas. There is also an optional thesis for students interested in research.“Our faculty bring a wealth of experience to the program, including specializing in fundamental AI research and applying AI methods in areas such as robotics, cybersecurity, bioinformatics and agriculture,” Perkins said in a public statement.The master’s program comes alongside a wave of investments in AI education at Mississippi State. In fall 2024, the university launched a bachelor’s degree in AI, focused on machine learning, neural networks and natural language processing. The university also offers a concentration for computer science students to learn about AI without pursuing a degree.In November 2024, Mississippi State earned a three-year, $1.2 million National Science Foundation grant to teach K-12 students and teachers how to train AI to classify and analyze images, eventually working with 15 teachers and 60 students in an extracurricular program culminating in creating and presenting their own smart device.“Most AI projects for K-12 students focus on AI concepts, but ours is unique because we want students not just to be consumers of AI but creators of intelligent solutions and contributors of AI fairness,” Yan Sun, a professor heading the program, said in a public statement.In addition, the university received a $2.2 million grant last month to support AI and machine learning workforce and research initiatives, including new faculty and development of a graduate certificate in data center construction management. Mississippi State was one of seven higher education institutions included in the statewide Mississippi AI Talent Accelerator Program grants.“We are dedicated to providing practical experience that allows our students to apply AI methods in real-world contexts,” Perkins said in a public statement. “By equipping our graduates with the latest knowledge in AI technology and preparing them for the evolution of this field, we are confident they will emerge as leaders in the industry.”
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.govtech.com/education/mississippi-state-university-launches-ai-masters-degree
|
[
{
"date": "2023/03/01",
"position": 95,
"query": "AI education"
}
] |
Over 60 organizations sign White House pledge to invest in AI ...
|
Over 60 organizations sign White House pledge to invest in AI education
|
https://www.k12dive.com
|
[
"Anna Merod"
] |
... AI technology, promote AI literacy, and enable comprehensive AI ... The “Pledge to America's Youth: Investing in AI Education” signals ...
|
Listen to the article 4 min This audio is auto-generated. Please let us know if you have feedback
Dive Brief:
Some 67 tech companies and associations have signed a pledge supporting the Trump administration's goal of making artificial intelligence education accessible to all students, the White House announced Monday.
Each signee, according to the pledge, promised to “provide resources that foster early interest in AI technology, promote AI literacy, and enable comprehensive AI training for educators.”
Just a day after the pledge was announced, the Senate struck down a "Big, Beautiful Bill" provision that would have put a 10-year moratorium on states imposing AI regulations. Opponents of the moratorium argued that a pause on legislative guardrails would threaten children’s safety online .
Dive Insight:
The “Pledge to America’s Youth: Investing in AI Education” signals Trump’s priority to establish public-private partnerships as a key part of rolling out the president's executive order on AI in K-12, said Sara Kloek, vice president of education and children’s policy at the Software & Information Industry Association.
Companies that signed the pledge, which include Google, IBM, MagicSchool, Meta, Microsoft, NVIDIA and Varsity Tutors, are expected to release more detailed plans on their commitments throughout this week, Kloek said.
As they do so, Kloek said, she is hopeful that more companies will step up to work on the initiative with education stakeholders like educators, parents and students.
SIAA, which also signed the pledge, said it would create a working group among its corporate members to develop strategies for transparently disclosing how AI tools are used in the classroom. “These best practices will help companies communicate to the K-12 community, parents, and students about AI’s use in school environments and equip them to responsibly use it,” SIIA said in a Monday statement.
In a statement Monday, U.S. Education Secretary Linda McMahon shared excitement that “so many organizations” had signed the pledge.
“It is clear there is a lot of energy about AI and how it can be used responsibly in education,” McMahon said. “The resources and tools that have been pledged through this initiative will help our teachers and learners leverage AI in classrooms and communities across America.”
Meanwhile, senators voted overwhelmingly — 99-1 — early Tuesday morning to strip a proposed AI moratorium, before Republicans narrowly passed the full reconciliation bill on the slimmest of majorities, 51-50, with Vice President JD Vance providing the tie-breaking vote.
The House version, which was approved in May, would impose a 10-year moratorium on state regulations for AI. The House and Senate must now work out their differences in the legislation before it can go to Trump for signature.
AASA, The School Superintendents Association, signed onto a June 27 letter with over 140 other groups opposing the AI moratorium in the House version.
In a Monday statement, AASA said the moratorium would protect “tech and AI more than students and children.”
“This provision would wipe out virtually all existing and future state AI laws, giving AI companies exactly what they want: no rules, no accountability, and total control,” AASA said. “As organizations working on the frontline of the consequences of AI development with no guardrails, we know what this would mean for our children.”
| 2025-07-02T00:00:00 |
2025/07/02
|
https://www.k12dive.com/news/over-60-organizations-sign-white-house-pledge-to-invest-in-ai-education/752139/
|
[
{
"date": "2023/03/01",
"position": 96,
"query": "AI education"
}
] |
Guiding principles for the responsible development of ...
|
Guiding principles for the responsible development of artificial intelligence tools for healthcare
|
https://www.nature.com
|
[
"Badal",
"Department Of Surgery",
"Helen Diller Comprehensive Cancer Center",
"University Of California",
"San Francisco",
"Lee",
"Carmen M.",
"Department Of Emergency Medicine",
"Highland Hospital",
"Alameda Health System"
] |
by K Badal · 2023 · Cited by 55 — We propose that AI should be designed to alleviate health disparities, report clinically meaningful outcomes, reduce overdiagnosis and overtreatment.
|
Moving global health equity forward is long overdue. Health equity means reducing and ultimately eliminating the disparities in health outcomes that exist between advantaged and disadvantaged populations caused by the disproportionate exposure of disadvantaged groups to risk factors and poor access to high-quality care. AI tools will likely only realize benefits in populations that already benefit the most from healthcare, thus widening the health equity gap. This is because AI tools usually require the collection of specialized data for inputs, cloud or local computing for hosting, high purchasing power for acquisition from commercial companies, and technical expertise, all of which are barriers to entry into hospital systems that serve the most disadvantaged populations.
AI tools should not introduce, sustain, or worsen health disparities but must instead be intentionally designed to reduce known disparities if there is to be tangible progress toward health equity. The proposed principles of inclusiveness, fairness, and equity (Table 1) all capture a desire to address health disparities. There is also a growing body of literature that discusses how AI can be used to address health disparities8,9,10. For illustration, we focus on two practical strategies, which are to ensure that disadvantaged groups can equally access and benefit from the AI tool and to preferentially design the AI tool for disadvantaged groups.
The first strategy of ensuring equal access and benefit can be challenging. For example, African American (AA) breast cancer patients in the US have higher mortality rates relative to white women, which is attributed to disparities in access to screening and endocrine therapy11. An AI tool for breast cancer screening (e.g., AI tools that predict breast cancer risk) intentionally designed to ensure that AAs have equal access and benefit would require both training on datasets with balanced, unbiased representation of AA populations and a design that is accessible to and works for hospitals that serve AAs. Concrete steps to mitigate the systemic biases entrenched in the US healthcare system, and therefore present in training datasets, is explored in the literature12,13.
AAs often live in areas with low access to primary care physicians14 and are often served by hospitals with low resources15 and poor care quality16. Therefore, ensuring AI tools work in these settings may require developers to prioritize the use of routinely collected or inexpensive data points as inputs, prioritize the use of single, explainable algorithms that can be run on a local computer, and advocate for commercial companies to provide discounted products, free cloud access, and the local training required for AI maintenance. Thus, creating an equitable AI tool may require prioritizing ‘simpler’ models for deployment therefore, in some instances, performance may be sacrificed. However, we must remember that the collective investment in resources and effort used to create AI tools must endeavor to benefit all rather than the few. The trade-off between balancing accuracy and equity can potentially be resolved by designing AI tools that can be easily tailored to the local population (principle 6).
The second strategy to reduce the disparity in breast cancer mortality rates would be to prioritize developing AI tools for AA-serving hospitals over other hospitals. This strategy is essentially a form of affirmative action in healthcare17. In the USA, affirmative action refers to policies that aim to increase the representation of minorities or address the disadvantages they suffer17. The application of affirmative action policies to AI development will require careful evaluation of the ethical implications. Do advantaged groups who will not have access to the AI tool miss an immediate opportunity for improved outcomes? Is this missed opportunity ethically justifiable? Given that AAs are more likely to die from breast cancer, prioritizing developing tools to reduce AA mortality rates could be considered to be ethically justifiable in the same way that those at the highest risk of death during the COVID-19 pandemic were prioritized for vaccination17. However, this strategy will be ineffective if AA populations do not have access to the screening or risk-reducing interventions recommended by the AI tool or access to therapeutic interventions once diagnosed. Therefore, a combination of need and capacity to benefit is often needed to justify preferential resource allocation17. AI tools designed to serve disadvantaged groups must have the potential to be materially beneficial, given the healthcare system’s limitations. If not, the tool will likely have low healthcare value and will unnecessarily divert resources from higher priority areas and more effective interventions (principle 4).
| 2023-03-01T00:00:00 |
https://www.nature.com/articles/s43856-023-00279-9
|
[
{
"date": "2023/03/01",
"position": 1,
"query": "AI healthcare"
},
{
"date": "2023/04/01",
"position": 10,
"query": "AI healthcare"
}
] |
|
Poynter - Poynter
|
Poynter
|
https://www.poynter.org
|
[
".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",
"Height Auto Max-Width",
"Vertical-Align Bottom .Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar",
"Vertical-Align Middle .Wp-Block-Co-Authors-Plus-Avatar Is .Alignleft .Alignright",
"Display Table .Wp-Block-Co-Authors-Plus-Avatar.Aligncenter Display Table Margin-Inline Auto"
] |
Poynter is a nonprofit media institute and newsroom that provides fact-checking, media literacy and journalism ethics training to citizens and journalists ...
|
Grok’s training, including how the model is told to respond, and the material it aggregates likely played a role in its spew of hate speech.
| 2023-03-01T00:00:00 |
https://www.poynter.org/
|
[
{
"date": "2023/03/01",
"position": 89,
"query": "AI journalism"
},
{
"date": "2023/06/01",
"position": 98,
"query": "AI journalism"
},
{
"date": "2023/07/01",
"position": 86,
"query": "AI journalism"
},
{
"date": "2023/12/01",
"position": 98,
"query": "AI journalism"
},
{
"date": "2024/06/01",
"position": 86,
"query": "AI journalism"
},
{
"date": "2024/07/01",
"position": 97,
"query": "AI journalism"
},
{
"date": "2024/09/01",
"position": 88,
"query": "AI journalism"
}
] |
|
Debate: Artificial Intelligence: News Media - 7th Jul 2025
|
Debate: Artificial Intelligence: News Media
|
https://www.parallelparliament.co.uk
|
[] |
... AI in journalism. The Government will support our news media to capitalise on the huge potential benefits of the technology while mitigating ...
|
My Lords, AI poses an existential threat to independent media because of the way it scrapes their high-quality content without either attribution or payment to those who created it, which is an act of theft directly threatening the provision of quality news and the jobs of thousands of reporters. Is the Minister aware that research by market leader Cloudflare shows that, for example, for every 73,000 pages of content scraped by Anthropic’s AI crawlers from news providers, there is just one single referral back to publishers’ websites? Does she realise that without this vital traffic, publishers cannot sell advertising or subscriptions, and their businesses become unsustainable? The free press cannot wait years for copyright reform because there is nothing left to protect. We were promised immediate action on this issue when the data Act went through; when will we get some of it?
| 2025-07-07T00:00:00 |
2025/07/07
|
https://www.parallelparliament.co.uk/debate/2025-07-07/lords/lords-chamber/artificial-intelligence-news-media
|
[
{
"date": "2023/03/01",
"position": 97,
"query": "AI journalism"
},
{
"date": "2023/03/01",
"position": 96,
"query": "artificial intelligence journalism"
},
{
"date": "2023/05/01",
"position": 91,
"query": "AI journalism"
},
{
"date": "2023/06/01",
"position": 92,
"query": "AI journalism"
},
{
"date": "2023/06/01",
"position": 94,
"query": "artificial intelligence journalism"
},
{
"date": "2023/07/01",
"position": 94,
"query": "AI journalism"
},
{
"date": "2023/07/01",
"position": 92,
"query": "artificial intelligence journalism"
},
{
"date": "2023/10/01",
"position": 94,
"query": "AI journalism"
},
{
"date": "2023/10/01",
"position": 92,
"query": "artificial intelligence journalism"
},
{
"date": "2023/11/01",
"position": 94,
"query": "AI journalism"
},
{
"date": "2023/12/01",
"position": 91,
"query": "AI journalism"
},
{
"date": "2024/02/01",
"position": 93,
"query": "AI journalism"
},
{
"date": "2024/05/01",
"position": 93,
"query": "artificial intelligence journalism"
},
{
"date": "2024/06/01",
"position": 94,
"query": "AI journalism"
},
{
"date": "2024/06/01",
"position": 92,
"query": "artificial intelligence journalism"
},
{
"date": "2024/07/01",
"position": 90,
"query": "AI journalism"
},
{
"date": "2024/09/01",
"position": 94,
"query": "AI journalism"
},
{
"date": "2024/09/01",
"position": 93,
"query": "artificial intelligence journalism"
},
{
"date": "2025/01/01",
"position": 93,
"query": "artificial intelligence journalism"
}
] |
Is AI art/ design a considerable threat to graphic designers?
|
The heart of the internet
|
https://www.reddit.com
|
[] |
As an AI language model, I can assure you that AI art and design are unlikely to completely replace human graphic designers anytime soon.
|
I'm planning to go to university for a bachelor's in either visual communication or graphic design in 2024.
I've been seeing multiple AI art/ design softwares being launched lately, and have spent time going down the rabbit hole of Instagram/ Youtube comment sections of people arguing the impact it will/ won't have on graphic design jobs. There seems to be a vast array of conflicting opinions.
I worry about the possibility that especially by the time I come out of my uni degree in 4/5 years, the industry would have completely changed to make graphic design jobs obsolete or out of demand.
Please share your perspectives to help me gain some more data on this!
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/graphic_design/comments/11k452b/is_ai_art_design_a_considerable_threat_to_graphic/
|
[
{
"date": "2023/03/01",
"position": 1,
"query": "AI graphic design"
}
] |
|
How AI Can Help Graphic Designers Boost Creativity and ...
|
How AI Can Help Graphic Designers Boost Creativity and Efficiency
|
https://medium.com
|
[
"Tech With Eldad"
] |
AI can help you improve the quality of your designs by identifying potential issues and suggesting improvements. For example, AI can analyze your designs and ...
|
How AI Can Help Graphic Designers Boost Creativity and Efficiency
Explore the Top AI Tools to Streamline Your Design Process and Enhance Your Designs Tech with Eldad 4 min read · Mar 28, 2023 -- Listen Share
As a graphic designer, you may have heard of artificial intelligence (AI) and its potential impact on the industry. AI has the potential to revolutionize the way you work by making your design process more efficient and creative. We’ll explore how graphic designers can use AI to become more creative and efficient.
Generate Ideas with AI
One of the biggest challenges for graphic designers is coming up with fresh and original ideas. AI can help you generate ideas and inspiration quickly and easily. AI-powered tools like Adobe’s Sensei and DALL·E 3 — OpenAI can analyze vast amounts of data and generate unique visuals and design concepts based on your preferences and criteria.
Optimize Your Design Process
AI can help you streamline your design process, making it more efficient and cost-effective. For example, AI-powered tools like Microsoft Designer and Canva can create designs automatically based on your requirements. You can also use AI to automate repetitive tasks like resizing images, color correction, and font-matching tools like Fontjoy. This will save you time and help you focus on the more creative aspects of your work.
Improve Design Quality
AI can help you improve the quality of your designs by identifying potential issues and suggesting improvements. For example, AI can analyze your designs and identify issues with color contrast, font size, and spacing. AI can also suggest alternative color palettes and fonts to make your design more effective.
Personalize Your Designs
AI can help you personalize your designs to meet the needs of your clients. For example, AI-powered tools can analyze data on your client’s audience and preferences and create designs that appeal to them. This will help you create more effective designs and build stronger relationships with your clients.
Enhance Collaboration
AI can help you collaborate more effectively with other designers and stakeholders. AI-powered collaboration tools like Conceptboard and Miro can help you share ideas, brainstorm, and get feedback on your designs. This will help you work more efficiently and create better designs.
Organize Your Workflows
Notion is an all-in-one workspace that can help you organize your workflows and streamline your design process. With Notion, you can create custom templates for your design projects, keep track of your design briefs, and collaborate with your team members. You can also use Notion to manage your design assets and create a visual library of your designs. Notion integrates with many other tools, including Trello, Google Drive, and Slack, making it a powerful tool for designers.
Get started with an ebook that will help you learn how to become more creative and efficient.
If you want to learn more about how to be a super creative designer, check out the book “Graphic Design Fundamentals: Mastering Graphic Design Techniques for Beginners”. This book is an excellent resource for understanding design theory, and how to become creative.
Here is a list of the AI-powered tools to make use of:
Adobe Sensei https://www.adobe.com/sensei.html is a machine learning and AI-powered platform that is built into Adobe Creative Cloud products, such as Photoshop and Illustrator. The platform uses AI to automate repetitive tasks, make predictions, and suggest improvements to designs. Google Deep Dream https://deepdreamgenerator.com is an AI-powered tool that uses deep learning algorithms to generate psychedelic and surreal images from existing photos. Designers can use this tool to add a unique touch to their designs or create interesting visuals for their projects. Figma https://www.figma.com is a cloud-based design tool that uses AI to help designers collaborate and create designs more efficiently. The platform offers a range of features, such as vector editing, prototyping, and commenting, that make it easier for designers to work together on projects. Design Wizard https://www.designwizard.com/, Piktochart https://piktochart.com/, Tailor Brands https://www.tailorbrands.com/, Logojoy https://logojoy.com/, Looka https://looka.com/, and Brandmark https://brandmark.io/ are all AI-powered graphic design tools that offer a range of templates and design elements that make it easier for designers to create high-quality designs quickly. Artisto https://artistoapp.com/ is an AI-powered app that allows designers to transform their photos and videos into works of art using various artistic styles and filters. The app uses deep learning algorithms to analyze and apply different artistic styles to the images. Conceptboard https://conceptboard.com/ and Miro https://miro.com/ are two collaboration tools that use AI to streamline the design process. Conceptboard offers real-time collaboration and visualization tools that allow designers to work together on design projects, while Miro offers a digital whiteboard and a variety of design tools that help designers to brainstorm, organize, and collaborate on ideas. Notion https://www.notion.so is an all-in-one workspace tool that can help designers to organize their design projects, research, and ideas in one place. The tool uses AI to assist designers in tracking their progress, assigning tasks, and collaborating with team members in real-time, which can improve productivity and efficiency in the design process.
Making use of AI tools like Adobe Sensei to generate ideas, optimize your design process, improve design quality, personalize your designs, and enhance collaboration, and tools like Notion to organize your workflows, you can become more creative and efficient in your design work.
| 2024-03-17T00:00:00 |
2024/03/17
|
https://medium.com/design-bootcamp/how-ai-can-help-graphic-designers-boost-creativity-and-efficiency-e9ed016d01c0
|
[
{
"date": "2023/03/01",
"position": 7,
"query": "AI graphic design"
}
] |
News & Commentary - OnLabor
|
✦ OnLabor
|
https://onlabor.org
|
[
"Sophia Leswing",
"Otto Barenberg",
".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",
"Height Auto Max-Width",
"Vertical-Align Bottom .Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow .Wp-Block-Co-Authors-Plus-Avatar"
] |
A blog devoted to workers, unions, and their politics ... Featured Coverage All artificial intelligence Featured Coverage in News & Commentary ...
|
OnLabor is a blog devoted to workers, unions, and their politics. We interpret our subject broadly to include the current crisis in the traditional union movement (why union decline is happening and what it means for our society); the new and contested forms of worker organization that are filling the labor union gap; how work ought to be structured and managed; how workers ought to be represented and compensated; and the appropriate role of government — all three branches — in each of these issues.
Learn more about OnLabor
| 2023-03-01T00:00:00 |
https://onlabor.org/featured_timelines/artificial-intelligence/?post_type=news_commentaries
|
[
{
"date": "2023/03/01",
"position": 87,
"query": "artificial intelligence labor union"
},
{
"date": "2024/06/01",
"position": 86,
"query": "artificial intelligence labor union"
}
] |
|
Unions Have A New Enemy In Negotiations: AI Automation
|
Unions Have A New Enemy In Negotiations: AI Automation
|
https://digitalcxo.com
|
[
"Jon Swartz"
] |
Labor has a familiar adversary at the negotiating table, but in a new guise: Automation, in the form of AI.
|
Labor has a familiar adversary at the negotiating table, but in a new guise: Automation, in the form of AI.
AI increasingly is emerging as a sticking point in disputes ranging from actors and writers to casino workers.
Now comes another potential showdown: Members of the International Longshoremen’s Association covering the East and Gulf Coasts are worried technology will jeopardize high-paying jobs. Specifically, the beef is over an automated gate where trucks enter a small port in Mobile, AL. This has endangered talks over the union’s contract, set to expire Sept. 30, that allows for “semi-automated” machinery, but bars equipment “devoid of human interaction.”
“We will never allow automation to come into our union and try to put us out of work as long as I’m alive,” Harold J. Daggett, the union’s president and chief negotiator in talks with the United States Maritime Alliance, a group of companies that move cargo at ports, said in a statement. The union was unavailable for further comment.
Labor reps expect more disputes in the coming years as AI improves and is widely deployed throughout the American workforce to improve operational efficiency, slash costs and replace some humans. For those reasons, unions consider AI to be as great a threat to jobs in manufacturing (robots) and the distribution of goods (self-driving vehicles) as government policies and the offshoring of jobs.
“Most union members consider it [AI] an existential threat. The narrow view, the knee jerk reaction, is AI is coming for all of our jobs. We need to panic and fight it,” Chris Feudo, a labor and employment attorney whose focus is on the energy, hospitality and manufacturing sectors, said in an interview.
“This is a utopian future for the next 20 to 30 years,” said Feudo, who anticipates a wave of negotiations centered on the use AI-type technology, and their impact on employees. “And it might get worse for many in labor each year.”
Last year, the Screen Actors Guild-American Federation of Television and Radio Artists, and the Writers Guild of America negotiated contract resolutions with the Alliance of Motion Picture and Television Producers to address the risks AI posed to workers.
Casino workers in Las Vegas, represented by the Culinary Workers Union, reached a new contract in late 2023 that included severance of $2,000 for each year the employee worked if the employee’s role was eliminated because of “technology or AI,” according to an account in Medium.
Hospitality workers at Caesars Entertainment Inc. in Las Vegas last year won a provision in their contract with six-months notice in the advent AI, robotics or any new technology, so the union can get an idea of how that technology is deployed, who it affects, and how those affected can learn to use the technology.
Indeed, in a 2022 memo on electronic hiring and algorithmic management, Jennifer Abruzzo, general counsel of the National Labor Relations Board, cautioned that many AI technologies used by employers are already illegal under settled law and urged the board to adopt a framework for protecting employees from surveillance and algorithmic management that interferes with protected activity.
The AFL-CIO and Microsoft Corp. created a platform for worker input into AI design and a dialogue over public policy to set guardrails for AI deployment in late 2023. The CWA, which represents workers in industries with AI exposure such as game development and AI development, has developed bargaining principles for ensuring AI benefits workers, according to a May 2024 report by Julia Aurelia Glass, a policy analyst for the Inclusive Economy team at American Progress.
While a majority of manufacturing and financial services workers believe AI has had a positive impact on their performance and mental health, more than 40% expect AI to lower their wages within a decade, according to a survey by the Organization for Economic Cooperation and Development last year.
“Workers have this huge mental burden of uncertainty over job security because of new technology,” Karla Walter, senior fellow for Inclusive Economy at American Progress, said in an interview. She noted surveillance technology that has put workers under the ever-watchful eye of employers.
| 2023-03-01T00:00:00 |
https://digitalcxo.com/article/unions-have-a-new-enemy-in-negotiations-ai-automation/
|
[
{
"date": "2023/03/01",
"position": 99,
"query": "artificial intelligence labor union"
},
{
"date": "2023/04/01",
"position": 45,
"query": "AI labor union"
},
{
"date": "2023/05/01",
"position": 44,
"query": "AI labor union"
},
{
"date": "2023/07/01",
"position": 40,
"query": "AI labor union"
},
{
"date": "2023/08/01",
"position": 42,
"query": "AI labor union"
},
{
"date": "2023/09/01",
"position": 75,
"query": "artificial intelligence labor union"
},
{
"date": "2024/03/01",
"position": 44,
"query": "AI labor union"
},
{
"date": "2024/04/01",
"position": 47,
"query": "AI labor union"
},
{
"date": "2024/05/01",
"position": 98,
"query": "artificial intelligence labor union"
},
{
"date": "2024/06/01",
"position": 42,
"query": "AI labor union"
},
{
"date": "2024/09/01",
"position": 47,
"query": "AI labor union"
},
{
"date": "2025/05/01",
"position": 46,
"query": "AI labor union"
},
{
"date": "2025/06/01",
"position": 46,
"query": "AI labor union"
}
] |
|
AI and Work-Life Balance: How Automation Can Improve ...
|
AI and Work-Life Balance: How Automation Can Improve Quality of Life for Employees
|
https://medium.com
|
[
"Rich Brown"
] |
AI can provide valuable insights into employees' strengths and weaknesses, enabling managers to tailor training and development programs that are more ...
|
AI and Work-Life Balance: How Automation Can Improve Quality of Life for Employees
The world of work is changing rapidly, and AI is at the forefront of this transformation. Rich Brown 8 min read · Mar 7, 2023 -- 1 Share
Canva Image
From automating routine tasks to providing valuable insights into employee performance, AI has the potential to revolutionize the way we work and learn.
However, there are also concerns about the negative effects of AI on job displacement, employee well-being, and the overall sense of meaning in our work.
In this blog, I explore many of the subjects related to AI in the workplace, including the benefits, challenges, and ethical considerations of this innovative technology.
Whether you’re a business owner, HR professional, or employee, this blog aims to provide valuable insights and perspectives on how AI is transforming the world of work.
How AI can enhance employees’ intelligence and skills
I am always looking for ways to improve my skills and intelligence. That’s why I’m excited about the potential of artificial intelligence (AI) in the workplace.
With AI-enhanced HR practices, managers can gain valuable insights into their employees’ strengths and weaknesses, allowing them to tailor training and…
| 2023-03-07T00:00:00 |
2023/03/07
|
https://medium.com/data-driven-fiction/ai-and-work-life-balance-how-automation-can-improve-quality-of-life-for-employees-f626c8a683e6
|
[
{
"date": "2023/03/01",
"position": 38,
"query": "artificial intelligence workers"
}
] |
Evidence from OECD case studies of AI implementation
|
The impact of AI on the workplace: Evidence from OECD case studies of AI implementation
|
https://ideas.repec.org
|
[
"Anna Milanez",
"Author",
"Listed"
] |
by A Milanez · 2023 · Cited by 70 — Downloadable! How artificial intelligence (AI) will impact workplaces is a central question for the future of work, with potentially significant ...
|
How artificial intelligence (AI) will impact workplaces is a central question for the future of work, with potentially significant implications for jobs, productivity, and worker well-being. Yet, knowledge gaps remain in terms of how firms, workers, and worker representatives are adapting. This study addresses these gaps through a qualitative approach. It is based on nearly 100 case studies of the impacts of AI technologies on workplaces in the manufacturing and finance sectors of eight OECD countries. The study shows that, to date, job reorganisation appears more prevalent than job displacement, with automation prompting the reorientation of jobs towards tasks in which humans have a comparative advantage. Job quality improvements associated with AI – reductions in tedium, greater worker engagement, and improved physical safety – may be its strongest endorsement from a worker perspective. The study also highlights challenges – skill requirements and reports of increased work intensity – underscoring the need for policies to ensure that AI technologies benefit everyone.
Citations are extracted by the CitEc Project , subscribe to its RSS feed for this item.
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:oec:elsaab:289-en. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: the person in charge (email available below). General contact details of provider: https://edirc.repec.org/data/eloecfr.html .
Please note that corrections may take a couple of weeks to filter through the various RePEc services.
| 2023-03-27T00:00:00 |
2023/03/27
|
https://ideas.repec.org/p/oec/elsaab/289-en.html
|
[
{
"date": "2023/03/01",
"position": 42,
"query": "artificial intelligence workers"
}
] |
Worker and workplace Artificial Intelligence (AI) coexistence
|
Worker and workplace Artificial Intelligence (AI) coexistence: Emerging themes and research agenda : UEL Research Repository
|
https://repository.uel.ac.uk
|
[
"Zirar",
"Ali",
"S. I.",
"Islam"
] |
by A Zirar · 2023 · Cited by 308 — Workplace Artificial Intelligence (AI) helps organisations increase operational efficiency, enable faster-informed decisions, and innovate products and services ...
|
Abstract
Workplace Artificial Intelligence (AI) helps organisations increase operational efficiency, enable faster-informed decisions, and innovate products and services. While there is a plethora of information about how AI may provide value to workplaces, research on how workers and AI can coexist in workplaces is evolving. It is critical to explore emerging themes and research agendas to understand the trajectory of scholarly research in this area. This study's overarching research question is how workers will coexist with AI in workplaces. A search protocol was employed to find relevant articles in Scopus, ProQuest, and Web of Science databases based on appropriate and specific keywords and article inclusion and exclusion criteria. We identified four themes: (1) Workers' distrust in workplace AI stems from perceiving it as a job threat, (2) Workplace AI entices worker-AI interactions by offering to augment worker abilities, (3) AI and worker coexistence require workers' technical, human, and conceptual skills, and (4) Workers need ongoing reskilling and upskilling to contribute to a symbiotic relationship with workplace AI. We then developed four propositions with relevant research questions for future research. This review makes four contributions: (1) it argues that an existential argument better explains workers' distrust in AI, (2) it gathers the required skills for worker and AI coexistence and groups them into technical, human, and conceptual skills, (3) it suggests that technical skills benefit coexistence but cannot outweigh human and conceptual skills, and (4) it offers 20 evidence-informed research questions to guide future scholarly inquiries.
| 2023-03-01T00:00:00 |
https://repository.uel.ac.uk/item/8vw29
|
[
{
"date": "2023/03/01",
"position": 48,
"query": "artificial intelligence workers"
}
] |
|
300 million jobs could be affected by AI. : r/passive_income
|
The heart of the internet
|
https://www.reddit.com
|
[] |
I used to work at a grocery store about 20 years ago, first job, union. Thrilled to get the extra 1.5x on Sundays and mandatory breaks. Number of lanes- ...
|
Create your account and connect with a world of communities.
New to Reddit?
By continuing, you agree to our
and acknowledge that you understand the
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/passive_income/comments/1272ka0/300_million_jobs_could_be_affected_by_ai/
|
[
{
"date": "2023/03/01",
"position": 49,
"query": "artificial intelligence workers"
}
] |
|
Organizational Leadership in the Wake of Artificial ...
|
Organizational Leadership in the Wake of Artificial Intelligence (AI): Prospects and Challenges
|
https://www.linkedin.com
|
[
"European Leadership",
"Cassie Kozyrkov",
"Nicolas Babin",
"Jana Zaher",
"Ultra-Low Field Mri Research",
"Bioelectromagnetics",
"Portable Imaging Systems",
"Bassam Hussein",
"Pmp"
] |
AI can help leaders make more informed decisions, identify patterns and trends, and optimize processes to improve performance. Moreover, AI can enable leaders ...
|
Organizational Leadership in the Wake of Artificial Intelligence (AI): Prospects and Challenges
Artificial intelligence (AI) has transformed the way businesses operate, and it has impacted leadership practices in many ways. The incorporation of AI into various business processes has created new opportunities for leaders to enhance their decision-making capabilities, optimize operations, and improve the overall performance of their organizations. However, the integration of AI also presents challenges for leadership, including ethical considerations, employee displacement, corporate downsizing and the need to manage increasingly complex technological systems. In this article, we explore the relationship between leadership and AI and how it is shaping the future of work.
Leadership and AI
Leadership is a crucial component of any organization, and it plays a critical role in managing the adoption and integration of AI following a long trail of doing so for disruptive technologies. Leaders must develop a deep understanding of AI technologies and their potential applications to leverage them effectively. Moreover, they must provide clear guidance to their employees and key stakeholders on how to use AI and its associated tools, techniques and best practices to maximize their benefits.
AI has the potential to transform leadership practices, enabling leaders to access vast amounts of data and generate insights that were previously unavailable. AI can help leaders make more informed decisions, identify patterns and trends, and optimize processes to improve performance. Moreover, AI can enable leaders to manage their organizations more effectively by automating routine tasks, freeing up time for strategic planning and decision-making.
However, incorporating AI into leadership practices also presents significant challenges. Leaders must grapple with ethical considerations, including issues related to bias, privacy, and accountability. They must also consider the impact of AI on their employees, including the displacement of jobs and the need to reskill workers. Additionally, leaders must ensure that their organizations have the technical infrastructure and expertise to manage increasingly complex AI systems.
The Future of Leadership and AI
As AI continues to advance and become more prevalent in the workplace, the role of leadership will evolve. Leaders will need to develop new skills and capabilities to manage the adoption and integration of AI effectively. Moreover, they must be able to balance the benefits of AI with the ethical considerations and challenges that come with it.
In the future, we can expect to see leaders who are highly skillful at managing AI technologies, including machine learning and natural language processing. These leaders will have a deep understanding of the technical capabilities and limitations of AI and will be able to leverage these technologies to optimize organizational performance.
However, we can also expect leaders to place increasing emphasis on ethical considerations related to AI. This includes developing policies and procedures to mitigate bias and ensure integrity, impartiality and privacy, as well as addressing the potential impact of AI on employee well-being and job security.
Conclusion
The relationship between leadership and AI is complex and multifaceted. While AI presents new opportunities for leaders to improve their decision-making capabilities and optimize operations, it also presents significant ethical considerations and challenges. Leaders must be able to balance these factors and develop new skills and capabilities to manage the adoption and integration of AI effectively.
As AI continues to evolve and become more prevalent in the workplace, the role of leadership will continue to evolve as well. Leaders who are highly skilled at managing AI technologies and addressing ethical considerations will be well-positioned to prosper, accelerate and innovate in the future and have an enriched career experience.
References
Brynjolfsson, E., & McAfee, A. (2014). The second machine age: Work, progress, and prosperity in a time of brilliant technologies. WW Norton & Company.
Davenport, T. H., & Ronanki, R. (2018). Artificial intelligence for the real world. Harvard Business Review, 96(1), 108-116.
Iansiti, M., & Lakhani, K. R. (2020). Competing in the age of AI. Harvard Business Review Press.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/organizational-leadership-wake-artificial-ai-mahdi-hussein
|
[
{
"date": "2023/03/01",
"position": 20,
"query": "artificial intelligence business leaders"
}
] |
|
Master of Technology Leadership and AI - AUK
|
Master of Technology Leadership and AI
|
https://auk.edu.ua
|
[] |
Deep dive into leveraging AI and other technologies to lead, empower and train your team to adopt a digital mindset, explore data modeling and forecasting, and ...
|
About the program
Learn to lead, strategize, and innovate in the field of AI and data technology at the highest level. Develop desirable key skills that will open doors to new opportunities in this rapidly evolving IT sector. Implement the latest management theories, and analytics tools and put your learning into practice in your current or desired roles.
Take the next step in your career –whether that’s moving from technical support and product development to management or enhancing your resume with a view to VP or executive C-suite positions. This cutting-edge specialized IT management program, powered by ASU state-of-the-art curriculum, equips you with business acumen while advancing your technical expertise. You will be able to apply machine learning, deterministic operations research, statistical learning, and simulations to transform your business.
Deep dive into leveraging AI and other technologies to lead, empower and train your team to adopt a digital mindset, explore data modeling and forecasting, and innovate successfully. During this program, you will develop the ability to use data to make large-scale decisions quickly and accurately. Apply your new knowledge to solve complex IT challenges related to your current role, and set your sights on becoming a global leader in the field.
| 2023-03-01T00:00:00 |
https://auk.edu.ua/en/master-of-technology-leadership-and-ai/
|
[
{
"date": "2023/03/01",
"position": 55,
"query": "artificial intelligence business leaders"
}
] |
|
Will AI Replace Recruiters in the Future? I asked ChatGPT ...
|
Will AI Replace Recruiters in the Future? I asked ChatGPT to Weigh In
|
https://www.linkedin.com
|
[
"Bernard Marr",
"Nisum Capella Alliance",
"Textkernel Bullhorn",
"Chhaya Yadav",
"Hiring For Saas Sales Manager"
] |
AI can automate several recruiting functions, such as resume screening, candidate matching, and interview scheduling. AI-powered tools can analyze resumes and ...
|
My fiancée was scrolling Tiktok last night and came across a video that spoke to the five worst possible careers to have in 2023. I don't own a Tiktok account (and stubbornly refuse to join the app), and was not able to locate the link or I would share it here. Both her job (Executive Assistant) and my job (Recruiter) made the cut, along with Real Estate agents. The logic for including these roles on the list is due to speculation that AI technology will make these positions redundant in the near future.
Obviously this is something I have strong feelings about (and it's not just because I'm passionate about earning a paycheck). In a world of increasing automation - I've always personally appreciated the ability to work with humans over machines when navigating difficult decisions or transactions. Imagine the frustration every single one of us feels when we call a customer service desk and are directed to an endless parade of menus, when you know the situation could be resolved much more quickly with a human on the other end. Now imagine navigating a complex decision such as finding a new job or buying a house by interacting with an AI chat bot. Call me old fashioned, but that sounds a little bit dystopian for my taste.
With that said, I figured I would ask an expert their thoughts on this. I landed an "exclusive interview" with the ChatGPT bot and asked them to weigh in:
Mark: Will artificial intelligence be able to make Recruiters redundant in the future? Which Recruiting functions can be automated by AI?
ChatGPT: Artificial intelligence (AI) is already transforming the recruitment industry, and it is possible that some recruiting functions may become automated in the future. However, it is unlikely that AI will make recruiters completely redundant, as human interaction and decision-making will always be valuable in certain aspects of the recruitment process.
AI can automate several recruiting functions, such as resume screening, candidate matching, and interview scheduling. AI-powered tools can analyze resumes and job descriptions to identify the best candidates for a particular role, reducing the time and effort required by recruiters to manually sift through resumes. AI can also match candidates with relevant job openings based on their skills, experience, and preferences.
In addition, chatbots and other AI-powered communication tools can help to streamline candidate communication, answering frequently asked questions and scheduling interviews automatically. This can save recruiters a lot of time and enable them to focus on higher-value tasks, such as building relationships with candidates and clients.
However, AI is not yet capable of making complex judgments or interpreting nuanced information in the same way that humans can. For example, AI may not be able to assess a candidate's cultural fit or soft skills accurately. Therefore, recruiters will still be needed to handle certain aspects of the recruitment process, such as interviewing candidates and making final hiring decisions.
In summary, AI can automate several recruiting functions, but it is unlikely to make recruiters redundant. Recruiters will still be needed to handle complex decision-making and build relationships with candidates and clients.
Mark: Thanks for that insight. What are some ways Recruiters can embrace AI Technology to become more effective in 2023?
ChatGPT: Here are some ways that recruiters can embrace AI technology to become more effective in 2023:
Use AI-powered sourcing tools: AI can help recruiters to find and attract top talent by automatically identifying and reaching out to potential candidates based on their skills and experience. Tools like HiringSolved, Hiretual, and Entelo use AI algorithms to find and rank candidates from various online sources, such as social media, job boards, and professional networks. Implement AI-powered chatbots: Chatbots can help recruiters to automate the initial stages of the recruitment process by handling candidate inquiries and scheduling interviews. AI-powered chatbots can also provide candidates with instant feedback on their applications, improving the overall candidate experience. Utilize AI-powered assessment tools: AI can help recruiters to assess candidate skills and abilities more effectively by using tools such as CodeSignal, HackerRank, and Plum. These platforms use machine learning algorithms to evaluate candidates' coding skills, cognitive abilities, and job-related knowledge, providing recruiters with more accurate and objective candidate assessments. Use predictive analytics to improve hiring decisions: Predictive analytics can help recruiters to make more data-driven hiring decisions by analyzing large amounts of historical hiring data to identify patterns and trends. This can help recruiters to identify which candidate traits are most predictive of job performance, leading to better hiring decisions. Use AI-powered resume screening tools: AI can help recruiters to quickly and accurately screen resumes by using natural language processing (NLP) algorithms to analyze resumes and identify relevant skills and experience. Tools like Textio and Jobscan can help recruiters to optimize job postings and identify top candidates more efficiently.
By embracing AI technology in these ways, recruiters can become more effective and efficient, freeing up more time to focus on building relationships with candidates and clients and making more informed hiring decisions.
So there you have it. While AI technology does offer Recruiters many tools that can make our jobs easier, our positions are safe for the time being. There is no substitute for genuine human relationships and interaction. AI technology cannot yet understand the nuances of a hiring manager or job-seeker's requirements, nor can it accurately assess soft skills or culture fit.
| 2023-03-01T00:00:00 |
https://www.linkedin.com/pulse/ai-replace-recruiters-future-i-asked-chatgpt-weigh-goldstein-cpa
|
[
{
"date": "2023/03/01",
"position": 16,
"query": "artificial intelligence hiring"
}
] |
|
Once companies start automating their candidate ...
|
The heart of the internet
|
https://www.reddit.com
|
[] |
With the recent development of AI tools the power has shifted back to candidates as they are now able to mass produce cover letters and tailor resumes to ...
|
With the recent development of AI tools the power has shifted back to candidates as they are now able to mass produce cover letters and tailor resumes to each job they apply for with great efficiency and little stress. This is excellent for the candidates but it won't be long before most companies catch on (a lot already have) and start automating their entire screening process with AI tools to prevent you from doing this. If you think finding a job sucks right now, here is my prediction of what we're in for in the next 24 months with AI recruitment at big companies:
You go to a company's website, or somewhere like indeed to look at jobs, 100% of the postings are completely generic crap with no real details obviously written by an AI. Not much different from today's posting but now they seem somehow even more generic.
You apply for a job at a company and the company demands that everything you submit in the application is hand written and not AI generated (despite the fact that they use AI for everything).
You submit your resume and cover letter and it is scanned and summarized by an AI. The company employs a tool that detects if the content you submitted was AI written and shadow bans your application if the AI thinks it was. Unfortunately for you the generic corporate AI detection software has a 40% false positive rate meaning that even if your documents are hand written it's likely they will still get flagged and shadow banned.
If the company's AI accepts your application it sets up a chat session with you where it asks you 50-100 questions about your personality and work ethic. Of course it demands that all of your answers are written by you and not AI generated. It still employees the AI detection software with a 40% false positive rate and scans each of your answers and it ends the conversation if it thinks you are cheating. Sometimes the chatbot crashes or disconnects leaving you with no way to continue the conversation and your application is effectively lost in the corporate ether. Don't bother applying again because you're now shadow banned!
After the chat session the AI reduces all of your answers, your experience, your personality and your skills into 1 or 2 sentences and aggregates them into an email with the other 100 candidates that applied and sends it to a hiring manager. The manager may or may not read the email and if they do they probably just glance over what the AI wrote about your for less than a second. They still end up hiring an internal candidate.
You question if your application even went through, if a human will ever look at it and you lament about the dystopian corporate AI future we are now living in.
Obviously this post is somewhat of an exaggeration and a joke, but I can definitely see some parts of this potentially being a reality soon!
| 2023-03-01T00:00:00 |
https://www.reddit.com/r/recruitinghell/comments/11ynhu6/once_companies_start_automating_their_candidate/
|
[
{
"date": "2023/03/01",
"position": 31,
"query": "artificial intelligence hiring"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.