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
|
|---|---|---|---|---|---|---|---|---|---|
What is the future of work?
|
What is the future of work?
|
https://www.mckinsey.com
|
[] |
The future of work refers to an informed perspective on what businesses and other organizations need to know about how work could shift.
|
What is the future of work?
| 2023-01-23T00:00:00 |
https://www.mckinsey.com/featured-insights/mckinsey-explainers/what-is-the-future-of-work
|
[
{
"date": "2023/01/23",
"position": 6,
"query": "future of work AI"
}
] |
|
Good transitions
|
Good transitions
|
https://www.ifow.org
|
[] |
The use of artificial intelligence (AI) presents risks to equality, potentially embedding bias and discrimination. Our cutting-edge research into AI in hiring ...
|
We are navigating and improving transitions through fast-paced change, driven by new technologies and shaped by people. Work is a lens and site for societal change.
Good transitions goes beyond building people’s skills. It is also about building capabilities – the resilience and resources we need to be able to make best use of our skills in pursuing the future of work that we desire.
| 2023-01-23T00:00:00 |
https://www.ifow.org/programmes/good-transitions
|
[
{
"date": "2023/01/23",
"position": 86,
"query": "future of work AI"
}
] |
|
What Is Digital Disruption? Factors, Examples & Its Affects
|
What Is Digital Disruption? Factors, Examples & Its Affects
|
https://epiloguesystems.com
|
[] |
Let's explore what exactly digital disruption means and practical strategies to help you prepare for the impending shift in this digitally driven economy.
|
As technology advances, rapid change is inevitable, and it’s more important now than ever to recognize the significance of digital disruption. Digital disruption affects virtually every industry and has a significant influence on how businesses approach their operations.
Despite its challenges, organizations that embrace these changes can reap inherent benefits such as increased agility and superior customer experience; however, understanding how digital disruption works is the first step to ensuring your business meets today’s opportunities head-on.
What factors cause digital disruption? This blog post will also explore what exactly digital disruption means and provide practical strategies you can use to help your organization prepare for—and ultimately benefit from—.
What is Digital Disruption in Business?
Digital disruption is represented via digital capabilities, channels, or assets that are also the main causes of digital disruption. It is an effect that modifies the basic expectations and behaviors in a culture, market, business, or process.
Digital disruption, to put it simply, is a change brought on by new business models and evolving technology.
The value of already available goods and services, as well as whole markets or sectors, might be significantly impacted (usually decreased) by these modifications.
Because the markets themselves, whole business models, and the companies that operate inside them must all be re-evaluated and revalued, this is why it is referred to as a “disruption.”
Some digital disruption examples:
The subscription economy business model, which is employed by organizations like Amazon, Hulu, and Netflix, has generated a disruption in the media and entertainment sectors by altering how consumers access content and how advertising monetizes it.
Freemium goods that provide customers the ability to sample a basic product with the option to pay for the complete offer, like Spotify, LinkedIn, or Dropbox, place more of a focus on creating a well-known brand behind a good or service.
The film photography and photo processing industries were both impacted by the digital camera sector.
Uber and other on-demand services have displaced traditional business models like taxis.
The growth of electronic reading has changed the publishing and print sectors.
=> You might be interested in: Differences Between Digital Disruption and Digital Transformation
Elements of Digital Disruption
Digital disruption includes four components, counting technology:
Technology is the creation, development, and use of a product.
Business refers to the product’s pricing, marketing, and sales strategies.
Industry consists of norms, rules, and methods for addressing needs.
Society comprises mindsets, attitudes, and customs that influence how individuals use new things.
How does Digital Disruption Impact Companies?
Attempting to resist digital disruption is pointless since it is an unstoppable force.
But organizations may prepare for it by embracing digital transformation. Stay ahead of the game and work with the flow rather than against it by keeping an eye on the ball and being aware of the digital disruption indicators in your business field.
This not only keeps your success from being swept away by the digital disruption storm but can also fuel the company’s future growth and present it with new prospects.
How to Prepare for and Survive a Digital Disruption?
Don’t make changes when it’s not necessary
Most of the time, change is a positive thing. Businesses must recognize when change is necessary, particularly regarding technology. A company may benefit greatly from new technology, but executives must also be aware of the risks and legal, security, and regulatory issues that come with the shift.
Instead, businesses should exercise due diligence and concentrate on how adopting new technologies would benefit both the company and its clients.
Accept and embrace modern technology
The bitter truth is that an organization can only successfully handle and withstand “digital” disruption when it has reached a particular degree of technical maturity. It benefits to always be in a state of digital transformation, or at the very least, digital flux.
Adopting new technology helps a firm stay adaptable, shift directions more quickly, expand its reach, and enhance its primary offering.
Global business executives generally concurred that maintaining investment in technology was necessary for creating bottom-line benefits.
Using data to drive strategy and operations
Today, information is the foundation of all businesses. A company’s most valuable asset is its data. Every business needs digital solutions that let it gather, manage, use, and exchange data in a safe, dependable, and effective manner without adding to complexity!
A company’s response to market disruptions will be quicker, more precise, and more agile the better its data analysis and integration capabilities are.
Be customer-centric
Customers are the bane of any business’s existence. It is crucial to remember this reality. The firm must welcome a disruption fully if it benefits the consumers.
Service providers, manufacturers, and merchants may always improve their connections with their target consumers thanks to technological advances and disruptions. They provide organizations with countless opportunities to learn more about customer behavior and solve their problems.
Create a department for disruption
Both procedures and individuals are, by definition, resistant to change. Therefore, disruption is a big ask for a well-established company.
The larger the company, the more difficult it is to make radical innovation a way of life or culture. The only approach is to separate radical innovation from the organizational structure, core teams, core business, and core processes.
Radical innovation needs dependable, flexible, and gifted personnel with expertise in marketing, finance, human resources, and just about everything else, but with a digital angle.
Building such a team is challenging, but bringing the proper individuals together may foster ideas into priceless, cutting-edge, and disruptive new realities.
In Conclusion,
Disruption is the new normal and digital disruption is something that businesses must learn to navigate if they want to stay relevant and successful. The key is to embrace change, be comfortable with uncertainty, and continuously adapt.
If you need help preparing for or surviving digital disruptions, contact us. Epilogue Systems can help you chart a journey forward so your business isn’t left behind.
| 2023-01-19T00:00:00 |
2023/01/19
|
https://epiloguesystems.com/blog/what-is-digital-disruption/
|
[
{
"date": "2023/01/23",
"position": 66,
"query": "AI economic disruption"
}
] |
Wake Up, America: China Is Overtaking the United States ...
|
Wake Up, America: China Is Overtaking the United States in Innovation Capacity
|
https://itif.org
|
[
"Ian Clay",
"Robert D. Atkinson"
] |
However, as supply chain disruptions triggered by the COVID-19 pandemic have shown, globalization introduces economic fragility. This was especially evident for ...
|
Contents
Key Takeaways 1
Introduction. 3
The Goal of This Report 3
Why This Matters 4
General Results 5
China’s Innovation Policy History 6
2006–2010: Indigenous Innovation, Thousand Talents, and Strategic Emerging Industries 6
2015: Made in China 2025. 8
China’s Ability to Innovate. 10
A Common Misconception: China Cannot Innovate. 10
The Reality: China Can Innovate. 11
Innovation Indicators 13
Overall Scores 13
Innovation Inputs 16
R&D. 16
Venture Capital 21
Researchers 23
Undergraduate Degrees Awarded. 24
Doctoral Degrees Awarded per Capita. 28
Top Universities Globally 31
Summary of Innovation Inputs 31
Innovation Outputs 32
Science and Engineering Articles 32
Top-Cited Science and Engineering Articles 36
International Patent Families 38
International IP Receipts 44
Summary of Innovation Outputs 46
Innovation Outcomes 46
Production in High-R&D Industries 46
Value Added in Advanced Industries 48
Exports in Advanced Industries 52
Economic Complexity 55
Supercomputers 55
Industrial Robot Usage. 57
Mobile Cellular and Fixed Broadband Subscriptions 57
Mobile Connectivity 59
E-Government 60
Cybersecurity 60
Summary of Innovation Outcomes 61
Discussion. 62
Innovation Inputs 62
Innovation Outputs 62
Innovation Outcomes 63
China’s Challenges Going Forward. 64
Conclusion. 67
Appendix 69
Proportional and Gross-Output Indices 69
University Weighted Scoring Method. 71
Economic Complexity Index 72
Mobile Connectivity Index 73
E-Government Development Index 74
Global Cybersecurity Index 76
Endnotes 77
The last decade was marked by dramatic evolution in China’s innovation capabilities and strategies, much of which was driven by the transition of Chinese Communist Party (CCP) and state leadership from Hu Jintao and Xi Jinping and the introduction of China’s latest major innovation policy framework: Made in China 2025 (MIC). This report updates an earlier ITIF report, applying more recent data to assess the progress China made during the previous decade with respect to the United States across a series of innovation indicators.[1]
Innovation means different things to different people, in part because there are so many different kinds of innovation. One kind is catch-up or copying innovation, wherein China has performed superbly. Another is new-to-the-world or frontier innovation. China’s capacity for the latter is one of the most important unknowns in the global economy. Many countries have tried and failed to make the transition from “imitator” to “innovator,” and China’s ability or inability to fully make that transition will largely define global geopolitical development in the decades to come. If China can surpass the United States in innovation—both catch-up and frontier—the global value chain (GVC) for the highest-value-added products stands to undergo a tremendous change. This would represent a serious economic and geopolitical challenge to the United States and its allies, particularly because of China’s predatory trade and innovation policy practices.
This report looks back on the previous decade and gauges the progress China made relative to the United States in a series of innovation indicators. The indicators are grouped into three categories: innovation inputs, innovation outputs, and innovation outcomes. By reviewing a range of indicators, one can develop a better understanding of where China is or is not making progress, specifically relative to the United States.
Furthermore, many analyses of innovation focus on a collection of indicators that is too narrow. Specifically, many analyses devote too much attention to traditional measures of innovation such as research and development (R&D) intensity and patent output. While the accumulation of knowledge and inventiveness are certainly necessary for innovation, commercialization in the marketplace is an equally consequential part of the innovation process. Innovation is not just about who invents a technology but who can use it to deliver the best products or services to potential users. It is with this in mind that this report’s analysis of innovation indicators expands beyond just reviewing traditional innovation inputs and outputs and attempts to also gauge the outcomes that these inputs and outputs bring about in markets and society.
This report is structured as follows: The section on “China’s Innovation Policy History” describes the goals of China’s major innovation policy developments and the methods to achieve them. This is followed by a section on “China’s Ability to Innovate,” including a summary of the arguments for why China is not capable of innovation at the frontier—at least in the way developed economies are—and why these arguments hold less and less water by the year. Two indices are constructed—one considering indicators that account for the size of each economy and one only considering indicators that do not—and China’s scores relative to the United States’ at the beginning and end of the decade are reported to provide an overall measure of China’s progress. The individual innovation indicators and China’s performance in them relative to the United States over the previous decade follow, accompanied by brief analyses. Lastly, the general results, the message they convey, and what can be expected in terms of future developments are discussed, followed by a brief summary and conclusion of the report.
The consequences of losing the competitive edge in advanced, high-value-added industries are different than those of losing that edge in low-skill industries for three primary reasons: barriers to re-entry, loss of good-paying jobs, and national security risks.
If its unitary cost of labor (the ratio of wages to productivity) were to fall enough, the United States could re-enter low-skill industries quite easily. Relatively little know-how and machinery are required to start producing in these industries, so market entrants could simply purchase the equipment and hire the labor necessary with few obstacles. However, this is not the case in advanced industries such as semiconductor or aerospace manufacturing. Entry into these industries requires high-skill labor, massive investments in specialized equipment, and, in many cases, the ability to tread water until enough know-how is acquired to take advantage of economies of scale. Take semiconductor manufacturing as an example. The process of manufacturing one dynamic random access memory (DRAM) chip consists of over 1,000 steps. Entering the DRAM market and gaining market share requires the procurement of specialized, complex machinery capable of carrying out these tasks, a tacit understanding of the manufacturing process by the firm’s workers (from the factory floor to the research laboratory), and the right innovation ecosystem (universities to train talent, a sufficient network of suppliers, etc.) to foster the industry. The firm may have to operate at a loss for some time until it has acquired enough know-how and become productive enough to capture the advantages of economies of scale required to become competitive in the international market. Thus, re-entering advanced, technology-intensive industries is far more difficult than re-entering lower-skill industries.
Beyond extensive barriers to re-entry, the loss of market share in advanced, high-value-added industries means a loss of jobs in these industries, which are typically much higher paying than those in other sectors. For example, the average salary of a worker in information technology (IT) sectors in the United States is approximately 75 percent higher than the average U.S. salary in general.[2] Therefore, lost jobs in these industries mean not only temporary unemployment for affected workers but a long-term overall decrease in aggregate well-being.
Lastly, remaining competitive in advanced, technology-intensive industries is crucial for national security. The superiority of the U.S. military rests largely on its technological superiority. This extends beyond technology for the physical battlefield and now crucially includes areas such as cybersecurity and intelligence gathering. A loss of competitiveness in the production of technologies crucial to national defense and an increase in dependence on other nations to produce them means two things. First—and obviously—it means the United States becomes more dependent on other countries to supply its military. While this may be less concerning (though not unconcerning) if the production is shifted to an ally country, this dynamic would be incredibly concerning if the production were shifted to a country such as China, which, if not an outright adversary, is a at least a geopolitical rival. Second, even if the United States could reliably count on other countries to provide it with military technologies and supplies, its superiority would be diminished by definition. If the United States must rely on others for the development and production of defense technologies, then its military can only be as technologically advanced as its suppliers’. Again, this may be less concerning if those developing and producing the technologies are allies, but it would be unsettling if the developer were a country such as China.
Related to the issue of national security is that of economic security. The globalization of supply chains has yielded amazing benefits in efficiency and cost reduction as economies specialize in the activities in which they have a comparative advantage. However, as supply chain disruptions triggered by the COVID-19 pandemic have shown, globalization introduces economic fragility. This was especially evident for semiconductors, the shortage of which drove up prices in everything from automobiles to home appliances. The effect of the semiconductor shortage was so widespread because of its prevalence as an intermediate good and the lack of relatively close substitutes. Per a recent blog by the Federal Reserve Bank of St. Louis, one-quarter of U.S. manufacturing industries, accounting for 39 percent of total U.S. manufacturing output, use semiconductors as a direct input.[3] It is therefore important to a country’s economic security to be active in these strategically important industries by remaining or becoming a competitively efficient producer (rather than through processes such as import substitution that will jeopardize efficiency and innovativeness).
Overall, China made notable progress relative to the United States. This progress was strongest and most widespread in innovation outputs and—unsurprisingly—in indicators not accounting for size, where it surpassed the United States. However, China made progress relative to the United States in all three innovation types, both when accounting for size and when not. In summary, China is beginning to make use of its massive economic and demographic endowments to eclipse the United States in gross output of innovation indicators (e.g., number of science and engineering articles published, number of doctoral degrees awarded, advanced-industry output, etc.). This has translated into slower but still significant progress in indicators accounting for the size of each country’s economy or population, where China still lags behind the United States.
China’s Innovation Policy History
China’s modern innovation policies started in earnest with the “indigenous innovation” movement in the Medium- to Long-Term Program (MLP) for the Development of Science and Technology released in 2006. MLP defined indigenous innovation as “enhancing original innovation through co-innovation and re-innovation based on the assimilation of imported technologies.”[4] Specifically, MLP and indigenous innovation constituted a strategy to address six key issues:
1. China’s weak capacity for commercial innovation
2. Insufficient technological capabilities in strategic economic and public areas such as resource utilization and public health
3. Overreliance on foreign technology in areas of financial, civil, and national security
4. The exodus of China’s top science and engineering talents
5. “Expropriation” by foreign firms in the form of royalties and licensing fees charged to Chinese producers
6. An increasing realization that appropriation of foreign technologies would not lead to sustained long-term economic growth[5]
To address these issues and to make China more technologically independent and innovative, MLP cited key economic sectors, technologies, and megaprojects that would receive the focus of China’s government. The sectors cited were energy, water, and mineral resources; the environment; agriculture; manufacturing; transportation; information and services; population and health; urbanization; and public and national security. The technologies cited were biotechnology, IT, advanced materials, advanced manufacturing, advanced energy technology, marine technology, laser technology, and space technology. And the megaprojects to be funded by the state focused on protein science, nanotechnology, quantum physics, and developmental and reproductive science.[6]
MLP also laid out explicit goals to be achieved by 2020. The Chinese government sought for the nation’s R&D intensity (R&D expenditures as a share of gross domestic product [GDP]) to reach 2.5 percent and for basic research to comprise 15 percent of such expenditures. Additionally, the government sought to become first in the world with respect to patents filed and academic articles published.[7]
To achieve these goals, China’s government implemented and promoted a range of protectionist and filching policies, most of which fly in the face of the World Trade Organization’s (WTO’s) rules. The first of these policies was an expansion of the now-infamous forced technology transfers and intellectual property (IP) theft by Chinese companies. Among the primary measures undertaken to achieve MLP’s goals was “[adjusting and improving] national policies on industrial technology so as to reinforce the assimilation and absorption of imported technologies and re-innovation.”[8] The second of these policies directed the raising of implicit trade barriers such as stricter quality and assurance testing and industrial and technology standards for foreign companies than those faced by domestic firms. The third policy embraced enhanced subsidies to state-owned enterprises (SOEs), specifically those in the sectors producing the technologies listed above. The final major policy used to achieve MLP’s goals was the introduction of a “Buy China” requirement for government procurement of the following technologies: computers and applications equipment, communications products, modern office equipment, software, new energy and related devices, and high-efficiency and energy-saving products. This “Buy China” provision required that all procured goods and services in these technologies be produced using Chinese-owned IP and a commercial trademark registered in China.[9]
Three of China’s policies—forced technology transfers and IP theft, implicit barriers on would-be imports, and subsidies to exporting SOEs—are explicitly against WTO laws. Since the Chinese government had not (and still has not) signed WTO’s Agreement on Government Procurement (GPA), this final policy is not technically in conflict with China’s WTO commitments. That said, China’s representative in WTO-accession negotiations made clear that the country intended to become a GPA member soon after attaining WTO membership and would submit an offer to do so “as soon as possible” upon accession.[10] So here, too, China flouted its WTO promises.
As such, multinational corporations seeking to expand their business in China voiced their opposition to MLP, and “indigenous innovation” was seen as a thinly disguised pretense to introduce mercantilist policies. Affected parties took particular issue with the inclusion of the terms “co-innovation” and “re-innovation” in the government’s definition of indigenous innovation, fretting over the technical and implied definitions and (often correctly) fearing that they referred to forced transfers of technologies and trade secrets in return for access to the Chinese market. Additionally, Chinese-national scientists and engineers abroad expressed concern about the government’s planned megaprojects, arguing that such massive, state-run undertakings would diminish competition among involved scientists, increase bureaucratic inefficiencies, and bias results toward the preferences of China’s Ministry of Science and Technology.[11]
Two years following the release of MLP, the Chinese government announced its Thousand Talents Program to address China’s inability to retain and attract science and engineering talent. The program was launched first to attract top ex-patriot professors and scientists in the West to return to China and, starting in 2010, to attract foreign nationals as well. The benefits offered as part of the program include a starting bonus of over $150,000 and the ability to apply for a $450,000 to $800,000 research grant. Foreign nationals accepted as part of the program receive additional benefits such as housing subsidies, paid-for trips home, and a job or stipend for their spouse. [12] As of 2018, the program had attracted over 7,000 professors and scientists.
The Decision on Accelerating the Cultivation and Development of Strategic Emerging Industries—or, more simply, the Strategic Emerging Industries (SEI) strategy—updated MLP by announcing seven key sectors in which China hoped to become a world leader: energy efficiency and environmental technology, next-generation IT, biotechnology, high-end equipment manufacturing, new energy, new materials, and new-energy vehicles. Funding and administrative support for these technologies were primarily shouldered by the country’s local and provincial governments rather than the central government in Beijing.
The next and most-recent major milestone in China’s innovation policy timeline was the announcement of MIC. Rather than a simple extension or update of MLP or SEI, MIC shifts the focus of innovation policy toward putatively market outcomes and enhancing the entire manufacturing process, places more emphasis on measurable goals, and carves out a greater role for market mechanisms (at least for Chinese firms).[13] The broad goals laid out in MIC are to introduce innovation-driven “smart” manufacturing through the implementation of industrial robots and advanced IT (specifically the Internet of Things); to attract and nurture human capital; to gain market share in high-value-added parts of the GVC; to strengthen IP rights and protections for small and medium-sized enterprises (SMEs) and to make more strategic use of IP; the harmonization of Chinese companies’ technology standards with those of the international community to increase exports; and increased international brand recognition of national champion firms.[14] As Scott Kennedy of the Center for Strategic and International Studies (CSIS) points out, MIC is more like Germany’s “Industry 4.0” than it is MLP, at least in its intent to modernize manufacturing.[15]
Like MLP, MIC enumerates specific priority sectors. It also introduced benchmarks to hit in these industries by 2020 or 2025. The priority sectors mentioned are new advanced IT; automated machine tools and robotics; aerospace and aeronautical equipment; maritime equipment and high-tech shipping; modern rail transport and related equipment; new-energy vehicles and related equipment; power equipment; agricultural equipment; new materials; and biopharmaceuticals and advanced medical products.[17] The specific goals in MIC are (or were) that the domestic content of core components and materials reach 40 percent by 2020 and 70 percent by 2025; to establish 15 innovation centers by 2020 and 40 by 2025; for corporate R&D intensity to reach 1.68 percent by 2025; for labor productivity to increase by 7.5 percent per year between 2015 and 2020; and for energy and water consumption per unit of value added to decrease by 35 percent by 2025.[18]
MIC represents an insightful shift in focus for China’s innovation policy. Innovation is about much more than just the number of academic publications or patents a society produces (although these are important), especially if such activity is more of a response to government incentives than to market incentives. Rather, the oft-forgotten aspect of the innovation process is bringing the invention to market, or the implementation, both in general and, importantly for China, at scale. Thus, this shift in focus toward market outcomes and commercialization rather than pure invention indicates China’s ability to see the whole picture.
China’s innovation policies are centered not necessarily on increasing productivity and technical know-how to move up the value chain, but to supplant foreign competitors and substitute imports in the industries it deems necessary.
Many outsiders fear that MIC reiterates China’s commitment to protectionism to achieve its economic goals. While MIC places more emphasis on market mechanisms by strengthening IP protections for SMEs and liberalizing firms’ setting of technology standards, the enhanced IP protections appear to only serve domestic enterprises, and the liberalized technology standards were implemented to increase domestic firms’ exports. Moreover, the government’s explicit desire to establish national champion firms and support SOEs in internationally important sectors indicates both that the government will still very much play a commanding role in the Chinese economy and the extent to which multinational firms are allowed to participate in it.
China is well within its right to develop and implement a strategy to boost its competitiveness and innovativeness, and ITIF would advise all nations to do so.[19] However, China appears determined to subsidize its national champions and restrict market access to foreign competitors in advanced industries where it cannot achieve a comparative advantage. First and foremost, China’s innovation policies are centered not necessarily on increasing productivity and technical know-how to move up the value chain, but to supplant foreign competitors and substitute imports in the industries it deems necessary. This fundamental goal is encapsulated in MIC, prompting the United States Trade Representative to describe the strategy as follows:
While ostensibly intended simply to raise industrial productivity through more advanced and flexible manufacturing techniques, Made in China 2025 is emblematic of China’s evolving and increasingly sophisticated approach to “indigenous innovation,” which is evident in numerous supporting and related industrial plans. Their common, overriding aim is to replace foreign technologies, products, and services with Chinese technologies, products, and services in the China market through any means necessary to enable Chinese companies to dominate international markets [emphasis added].[20]
China’s Ability to Innovate
A Common Misconception: China Cannot Innovate
There exists a widespread view that China is incapable of “true” innovation, at least at the frontier. In general, the primary reasons given in support of this view are an education system that encourages rote memorization and represses creative expression, a risk-averse culture centered around a reverence for authority that is not conducive to disruption or drastic change, weak IP protections, and inefficient state involvement in markets. Proponents of these arguments believe that while China’s economic rise is impressive, it is bound to be a copier of innovations from the West, at least for the foreseeable future.
Examples of such arguments being used to dismiss the potential of China’s innovation capacity abound. In a 2014 article for The Diplomat, Kings College London Professor of Chinese Studies Kerry Brown wrote:
The Chinese government under Xi can pour all the money they want into vast research and development parks, churning out any number of world class engineers and computer programmers. Even with all of this effort, however, China is likely to produce few world class innovative companies. The fundamental structural problem is that the role of the state and government in China is still very strong…. The system that China currently has still rewards conformity.[21]
Former Hewlett Packard CEO Carly Fiorina claimed, “Although the Chinese are a gifted people, innovation and entrepreneurship are not their strong suits. Their society, as well as their education system, is too homogenized and controlled to encourage imagination and risk-taking.”[22] TechNode editor Jason Lim wrote, “Most Chinese start-ups are not founded by designers or artists, but by engineers who don’t have the creativity to think of new ideas or designs.”[23] And only four years ago, Michael Pettis, a professor at the Guanghua School of Management at Peking University, bluntly stated, “This is not a country we can expect major innovations from. In the west we don’t have enough confidence about this. How many governments in the world have decided they’re going to become major innovation centers? None of them have succeeded.”[24]
Scott Kennedy of CSIS is also skeptical of China’s ability to turn willpower and resource allocation into innovation. Citing the lack of growth in China’s output score relative to its input score in the World Intellectual Property Organization’s Global Innovation Index (GII) between 2009 and 2016, Kennedy dubbed China a “fat tech dragon,” since its apparent inability to turn inputs into outputs is analogous to a low metabolism.[25] Kennedy also points out that, while plentiful, Chinese patents are of relatively little practical use. Licensing revenues from the use of patents are still minuscule, and the surge in patents filed is a response to government rather than market incentives. Despite these issues, Kennedy acknowledges that China now graduates more scientists and engineers from its universities than does any other country (more than 1.8 million undergraduates in 2018), a higher percentage of bank loans are going to private businesses rather than SOEs, and IP protections are steadily expanding.[26] Nevertheless, Kennedy argues, innovation appears to be a secondary goal to market expansion overseen by the state.
The Reality: China Can Innovate
Are these arguments correct? In short, no—but as with most points of debate, the truth is more nuanced. To understand why these arguments are at best incomplete, it is helpful to first talk about what innovation is. Innovation is often used interchangeably with invention, specifically ground-breaking invention. This is evident both from the quotes previously provided and from the importance placed on R&D intensity and patent output as traditional measures of innovation. However, this view of innovation misses the forest for the trees. While the development of novel products and processes is obviously an important aspect of innovation, effective commercialization is at least as important.
A helpful example is that of the smartphone. Nokia invented the first touchscreen smartphone, the Nokia 7710, a full two years before Apple released the iPhone, and it was the first to offer a connected gaming-oriented app store, which Apple used as its prototype for the App Store. According to those arguments, of the two companies in this anecdote, only Nokia was actually innovative. Apple was simply a copier, not a creator. However, this view of innovation ignores the vital aspects that made Apple and its iPhone more successful than its competitor. Namely, Apple offered a better product by providing an ecosystem that integrated the iPhone with other Apple products such as iTunes and the App Store (or, more specifically, the operating system on which third-party developers built their apps).[27] Apple’s marketing and knowledge of its customers’ preferences also helped Apple turn the iPhone and subsequent products into fashion and status symbols. Now iPhones make up 62 percent of the premium smartphone market (defined as devices costing at least $400) while the Nokia 7710 exists only as a collectible.[28]
In effect, Apple leveraged an innovative technology to create superior customer experiences it then monetized through a superior business model to supplant the technology’s original creator. It could do so because innovation is not just about who is first; it is more importantly about who can deliver a superior product (a function of the actual good or service, the customer experience, the price, etc.), which manifests itself in market outcomes.
While the development of novel products and processes is obviously an important aspect of innovation, effective commercialization is at least as important.
A better understanding of innovation is provided by the McKinsey Global Institute’s (MGI’s) The China Effect on Global Innovation, which separates innovations into four categories: efficiency-driven, customer-focused, engineering-based, and science-based.[29] The report concludes that with its proven ability to produce goods at scale, adapt products to the Chinese market, and develop and adopt digital infrastructures such as mobile payment systems and e-commerce (sometimes even before more-developed economies), China has demonstrated that it is capable of efficiency-driven and customer-focused innovations. The challenge before it, the authors argue, is to catch up in the areas of engineering- and science-based innovations.
However, recent developments indicate China is doing just that. For example, China became the world’s largest automobile producer in 2009, thanks to government support after designating it a priority industry, and is now also the world’s largest producer and exporter of electric vehicles.[30] China landed the first probe on the dark side of the moon in 2019, it began launching the components of its Tiangong space station in 2021, and current NASA Administrator Bill Nelson recently stated that China may land astronauts on the moon before the United States is itself able to return.[31] China has recently added to the pantheon of tech giants by producing companies such as Alibaba, Baidu, Huawei, and Tencent, and eight of the ten fastest companies to reach a $1 billion valuation are Chinese.[32] As recently as 2017, China possessed the most powerful supercomputer in the world, and it currently boasts two of the top 10 most powerful, although the true extent of China’s supercomputing capabilities is now unknown.[33]
An additional example of Chinese frontier innovativeness, notably in an area in which China transitioned from a copier to a leader, is high-speed rail (HSR). China first developed its HSR network with the help of imports and technology transfers from European and Japanese companies. It opened its first railway—between Beijing and Tianjin—in the summer of 2008 in time to show it off to the world as it hosted that year’s Summer Olympics. Since then, China’s HSR network has ballooned and is by far the largest in the world with over 23,500 miles of rail.[34] It has also developed the world’s fastest autonomous train, capable of speeds up to 217 miles per hour, and one of China’s rail-producing SOEs, CRRC, has become the world’s largest producer of railway vehicles and related technologies. China has recently developed a prototype for a “mag-lev” train—a train suspended above its tracks via a magnetic field—that it claims is capable of speeds up to 385 miles per hour.[35] In the coming years, China’s HSR network will expand both to its western regions and its regional neighbors’ lands to further integrate markets and ingrain the country’s less-developed western half into its supply network.
China became the world’s largest automobile producer in 2009 and is now also the world’s largest producer and exporter of electric vehicles.
Beyond just these specific examples, China’s progress is demonstrating itself through broader measures of innovation, such as the aforementioned GII. While Kennedy dubbed China the “fat tech dragon” because of the alleged imbalance in growth between its innovation input score and its innovation output score, this analysis neglects the fact that in the 2016 edition of the GII, China’s output score was higher than at any other point between 2009 and 2016 (the years Kennedy considers). Furthermore, China’s “efficiency” score, defined as the ratio of a nation’s output score to its input score (or, put another way, a nation’s innovation metabolism), ranked seventh among all nations.[36] For reference, Switzerland, which ranked first overall, had the 5th highest efficiency score, Germany had the 9th highest, the United States had the 25th highest, and Japan had the 65th highest.
In the recently released 2022 edition of the GII, China ranks 11th overall (and Hong Kong ranks 14th overall), ahead of countries such as Japan (13th) and Canada (15th).[37] Moreover, China ranks just 21st in input score and 8th in output score, and its output score was well above the 2016 level. China’s GII-defined strengths are “Trade, diversification, & market share” (an innovation input for which China ranks third) and “Intangible assets” (an innovation output for which China ranks second).
However, these high marks deserve a qualification. China is bound to score well in “Trade, diversification, & market share” since one of the three indicators in that category is purchasing power parity (PPP)-adjusted GDP (China has the largest)—though it also ranks second in domestic industry diversification. Additionally, China’s score in “Intangible assets” is largely propped up by its trademark output. Kennedy’s point remains valid (at least for now) that China’s IP is currently of little value and patent and trademark output is largely a response to government rather than market incentives. This is further evidenced by the fact that China ranks only 35th in IP receipts as a percentage of total trade (whereas the United States ranks 4th). Nevertheless, China still scores remarkably well in market-outcome indicators, ranking 4th in high-tech exports as a percentage of total trade and, contrary to arguments about its lack of creativeness, notching the top spot in creative goods exports as a percentage of total trade. China scores 14th in “Creative outputs” as a general category.[38]
This is not to say that China is now among the most fundamentally innovative economies in the world or that there are no further obstacles in its way to getting there. Its R&D expenditures and patent outputs are still largely a reflection of the government’s objectives rather than the economy’s inventive capabilities (more on this later). Although financing has expanded to private as well as SOEs, and IP protections are being strengthened (at least for domestic enterprises), state involvement in the Chinese economy will almost certainly hinder productivity growth, and a trade-off between scale and efficiency in priority sectors will likely persist. This may be further exacerbated by Xi Jinping’s ongoing crusade to consolidate the state’s power and strengthen its influence in both economic and social matters. This crusade will now face fewer internal obstacles after Xi’s consolidation of power at the recent 20th National Congress of the CCP.
But it is naïve to ignore recent developments simply because they run contrary to preconceived notions of Chinese culture and capabilities. A nation that competes with—and in some cases beats—world leaders in areas such as advanced computing technology, space exploration, and e-commerce despite having a real GDP per capita roughly 30 percent less than that of the United States in 1947 cannot be written off.[39] Rather, China’s progress toward frontier innovation and whatever challenges that poses to the United States and its allies must be carefully and seriously considered. To that end, China’s progress relative to the United States across a series of innovation indicators that attempt to capture the entirety of innovation (inputs, outputs, and outcomes) during the previous decade is measured and discussed below.
Innovation Indicators
The indicators considered are sorted into three categories. The first is innovation inputs, which consist of the resources and the quality of the institutions designed to bring about increases in an economy’s stock of knowledge. The second is innovation outputs, or the discovered knowledge the inputs produced. The third is innovation outcomes, which are the effects from the implementation of the discovered knowledge that manifest themselves in production and in adoption of new technologies.
Overall Scores
ITIF created two indices to quantify China’s overall progress across the indicators considered: one measuring China’s progress relative to the United States on a proportional basis (accounting for the size of its economy, population, etc.) and another measuring China’s progress relative to the United States in terms of gross output. In cases where there was significant overlap among the indicators in a category (e.g., the number of undergraduate degrees awarded overall and in specific fields of study), only the indicator deemed to be most important was included in composite index calculations (e.g., science and engineering degrees were included instead of the total number of degrees). For both the proportional and gross output indices, scores were computed for each of the indicator types (inputs, outputs, and outcomes), and the overall index score was computed by giving inputs and outputs a weight of 25 percent each and outcomes a weight of 50 percent. The appendix contains a full list of the indicators used and their respective weights.
Figure 2 shows China’s progress in proportional indicators. The contributions of the indicator types are calculated as the weighted average of China’s scores relative to the United States across the considered indicators multiplied by that indicator type’s weight. China’s score in this index was 57.6 percent that of the United States in 2010. By 2020, this increased by almost one-third to 75 percent, thanks mostly to progress in innovation outputs. In other words, on a proportional basis, China is now roughly 75 percent as advanced in innovation and advanced-industry production as the United States. If this relative growth continues apace, China will surpass the United States by 2035.
The contribution of the output indicators to China’s proportional index score more than tripled over the decade, thanks to rapid increases in China’s output of science and engineering articles and patents, the influence of China’s research, and China’s international IP receipts relative to GDP. This is especially notable when considering China’s score in outputs relative to the United States is only given a weight of 25 percent. While China also made progress in proportional innovation inputs and outcomes, this contributed much less to the increase in China’s score relative to the United States.
Similarly, figure 3 shows China’s relative progress in gross-output indicators. As these indicators do not account for China’s rapid growth in GDP in the last decade, China’s progress relative to the United States here is more pronounced. In 2010, China’s score in this index was 77.8 percent that of the United States. By 2020, this had grown by approximately four-fifths to 139.2 percent. In other words, China’s gross innovation capabilities (e.g., R&D expenditures, venture capital (VC) investments, advanced-industry output, patent output, etc.) are now almost 40 percent greater than those of the United States.
As with the proportional index, innovation outputs are the biggest contributors to this increase—again, with the innovation type’s contribution almost tripling—and now innovation outcomes contribute significantly as well (though it should again be noted that innovation outcomes’ weight is twice that of innovation inputs’ and innovation outputs’). The growth in the contribution of outputs to China’s score relative to the United States in the gross-output index is very similar to that in the proportional index, since the proportional innovation outputs account for population and China’s population was virtually unchanged relative to the United States’ during the past decade (with China maintaining approximately 4.3 times the population of the United States). Innovation outcomes contribute much more in this index, since the growth in China’s value added and exports in advanced industries relative to the United States’ is not mitigated by China’s rapid overall economic growth over the last decade. Again, while China made progress in gross innovation inputs relative to the United States, that progress was much more muted than that made in gross outputs and outcomes.
Though the two indices measure different (but highly related) things, they both convey that China’s biggest progress relative to the United States was in the category of innovation outputs. With respect to innovation inputs and innovation outcomes, this depends on which group of indicators one considers. With respect to proportional indicators, China made slightly more progress in innovation inputs than outcomes, but with respect to gross-output indicators, China made much more progress in innovation outcomes.
Innovation Inputs
R&D is necessary to discover and adapt the knowledge necessary for future innovations and to create new products and processes.
R&D Expenditures
Figure 4 shows China’s R&D expenditures relative to the United States’ along with the relative expenditures of R&D’s components: basic research, applied research, and experimental development. Between 2010 and 2020, China’s R&D expenditures increased from $104.3 billion to $352.9 billion, and from 25 percent to 49 percent of U.S. levels, respectively. China’s growth relative to the United States’ was faster in the first half of the decade than in the second as growth in China’s R&D expenditures slowed from 16.9 percent per year in 2010–2015 to 9.2 percent per year in 2015–2020; the United States’ increased from 4.4 percent per year to 7.3 percent per year.
Basic research involves the discovery of foundational scientific knowledge upon which to build technologies. Unlike with total R&D expenditures, China’s basic research expenditures relative to the United States’ increased steadily throughout the decade, from 6.4 percent to 19.7 percent of the U.S. level ($4.8 billion to $21.2 billion) between 2010 and 2020. Although it made steady progress, basic research made up only 6 percent of China’s total R&D expenditures in 2020, well below its MLP goal of 15 percent.[41]
Applied research involves the generation of knowledge with specific, practical objectives. China’s applied research expenditures increased from 15.9 percent to 28.6 percent of the U.S. level and $13.2 billion to $39.9 billion over the course of the decade.
Experimental development is the use of existing knowledge to create or improve products and processes. China’s experimental development expenditures increased from $86.3 billion and 34.5 percent of the U.S. level in 2010 to $291.8 billion and 63.4 percent in 2020. Experimental development accounts for the majority of R&D expenditures for both China and the United States, though it accounted on average for 84 percent of R&D expenditures in China between 2010 and 2020 compared with 63 percent for the United States. As such, a slowdown in the growth of experimental development expenditures in China was responsible for the slowdown in overall R&D expenditures growth. These expenditures grew at an average rate of 17.3 percent per year in China between 2010 and 2015; this dropped to 8.8 percent in the second half of the decade.
R&D Intensity
Perhaps the most widely used indicator of a nation’s innovativeness, R&D intensity measures the extent to which a nation invests in R&D relative to its output.
Between 2010 and 2020, China’s R&D intensity increased from 1.7 percent to 2.4 percent, while the United States’ increased from 2.7 percent to 3.5 percent (figure 5). The two R&D intensities were converging in the first half of the decade but started to diverge after 2014 due to both increases in U.S. R&D intensity and a decrease in the growth rate of China’s.
Figure 6 shows China’s R&D components’ intensity relative to the United States’. At its relative peak in 2014, China’s R&D intensity was 74.4 percent of the U.S. level (2.0 percent in China and 2.7 percent in the United States).
China’s basic research intensity relative to the United States was much lower than its general R&D intensity at just 28 percent of the U.S. level in 2020. However, unlike general R&D intensity, China’s basic R&D intensity grew relative to the United States throughout the previous decade, increasing from 15.8 percent of the U.S. level in 2010.
In contrast to basic research intensity, China’s 2020 applied research and experimental development intensities relative to the United States were little changed from their 2010 figures. China’s applied research intensity was approximately 40 percent of the U.S. level in both 2010 and 2020, and its experimental development intensity increased from 85.4 percent of the U.S. level in 2010 to 90.1 percent in 2020. However, China’s experimental development intensity relative to the United States’ fell from its decade-high of 101.9 percent of the U.S. level in 2016 due primarily to faster growth in U.S. experimental development intensity. China’s relative applied research intensity remained roughly constant throughout the decade.
R&D Expenditures by Performing Sector
Another way to categorize R&D expenditures is by the sector performing the activity: business, government, or higher education. As can be seen in figure 7, China’s expenditures on R&D activities performed by the government or higher education institutions increased steadily relative to the United States’. China’s expenditures on business R&D relative to the United States’ was stagnant over the second half of the decade. China’s business-performed R&D expenditures increased from $76.6 billion in 2010 to $270.2 billion in 2020, which represented 27.5 percent and 49.8 percent of the U.S. levels, respectively. However, the average annual growth of such expenditures in China slowed from 17.9 percent per year in the first half of the decade to 9.1 percent in the second (and increased from 5.7 percent to 8.1 percent in the United States). China’s expenditures on R&D performed by the government approached U.S. levels by the end of the decade. Such expenditures in China increased from $18.9 billion (36.3 percent of the U.S. level) to $55.5 billion (81.5 percent of the U.S. level). Lastly, China’s expenditures on R&D performed by higher education institutions increased from $8.8 billion in 2010 to $27.2 billion in 2020; these figures represented 14.6 percent and 33.6 percent of the U.S. level, respectively.
R&D Intensity by Performing Sector
China’s R&D intensity relative to the United States’ varies significantly depending on which performing sector is being examined, as can be seen in figure 8. As with general R&D, China’s business-performed R&D intensity relative to the United States’ increased over the previous decade—from 67.9 percent to 70.7 percent of the U.S. level—but was also subject to a decrease from its mid-decade peak (of 80.5 percent in 2014). China’s government- and higher-education-performed R&D intensities relative to the United States’ increased throughout the previous decade from 89.7 percent to 115.8 percent and from 36.1 percent to 47.7 percent of U.S. levels, respectively. China’s government-performed R&D intensity increased from 0.31 percent of GDP in 2010 to 0.38 percent in 2020 (compared with 0.35 percent and 0.33 percent, respectively, in the United States), and its higher-education-performed R&D intensity increased from 0.14 percent of GDP to 0.19 percent (compared with 0.4 percent and 0.39 percent, respectively, in the United States). Given the scope and involvement of the Chinese government in economic and social affairs—especially the government’s promotion of “indigenous innovation”—it is unsurprising that government-performed R&D intensity is now approximately 16 percent greater in China than in the United States, although this relative growth stalled in the second half of the decade.
It may at first seem surprising that China’s basic research intensity is so low relative to the United States given its greater government-performed R&D intensity and attention government R&D places on basic research. However, business-performed R&D expenditures make up the greatest share of total R&D expenditures by far, accounting for 77 percent of China’s R&D expenditures and 75 percent of the United States’ R&D expenditures in 2020.[46] Moreover, applied research expenditures make up a much larger share of business-performed R&D expenditures in the United States than in China, accounting for 6.4 percent of business-performed R&D expenditures in the United States in 2020, compared with only 0.5 percent in China.[47] Lastly, while China’s government-performed R&D intensity is greater than the United States’, the U.S. government actually supplies a greater amount of R&D funding, both in absolute terms and relative to GDP.[48]
Top Firms Globally by R&D Investment
The EU Industrial R&D Investment Scoreboard lists the 2,000 companies with the greatest R&D investments globally (although it was only 1,400 in 2010 and 2011 and 1,500 in 2012). While the United States’ large companies maintained footholds at the top of the list throughout the decade, China made significant advancements both in terms of the number of companies in the top 1,400 and in the cumulative R&D investments of those companies.
In 2010, China had just 19 companies ranked in the top 1,400, which was 3.9 percent of the United States’ 487 (figure 9). China’s highest-ranking company was Huawei Technologies at 56. By 2020, China had 278 companies in the top 1,400, 61.9 percent of the United States’ 449. Huawei remained China’s highest-ranking company and jumped to second, behind the United States’ Alphabet. The cumulative R&D investment of China’s companies in the top 1,400 increased from 4.8 percent of U.S. levels in 2010, to 16.9 percent in 2015, and then to 38.1 percent in 2020.
VC involves private investors financing small, risky business ventures (typically related to technology) in exchange for equity in the company. VC played a large role in the tech boom in the United States, helping now-household names such as Alphabet and Apple establish themselves as corporate giants and providing the funds needed to innovate in their early stages. VC has long been a more common source of financing in the United States than elsewhere in the world, but it is gaining traction worldwide—especially in China—and developing a relevant VC industry was a point of emphasis in MLP.[50]
Total VC Investments
China’s VC investments relative to the United States’ doubled over the previous decade from 23.2 percent to 46.6 percent of U.S. levels (figure 10), with China’s VC investments totaling $60.2 billion in 2020. However, this is down from its absolute peak of $74.8 billion in 2018 and its relative peak of 87.9 percent of U.S. levels in 2016. Nonetheless, China was still the second-largest VC market in the world in 2020, and VC continues to become a more instrumental part of China’s financial framework.[51]
VC Investments as a Share of GDP
Figure 11 shows China’s VC investments as share of GDP relative to the United States’. In 2010, China’s VC investments were 0.02 percent of its GDP, half of the United States’ 0.04 percent. By 2020, China’s VC investments increased to 0.4 percent of its GDP, while the United States’ VC investments increased to 0.62 percent of GDP. The mid-decade surge in China’s VC ecosystem relative to the United States’ is even more pronounced. Between 2013 and 2016, VC as a share of China’s GDP increased from 0.02 percent to 0.26 percent, while the United States’ only increased from 0.07 percent to 0.18 percent.
While R&D intensity is a measure of the share of an economy’s resources it devotes to the creation of knowledge and novel products and processes, the number of researchers as a share of total workers measures the relative amount of human capital devoted to these activities. In this regard, China lags much further behind the United States, although it made steady progress throughout the decade.
Total Researchers
Figure 12 shows China’s number of total researchers relative to the United States’. China entered the decade with over 9 percent more researchers than did the United States (1.21 million compared with 1.11 million). This increased throughout the decade, and in 2019, China employed 2.17 million researchers, which was 44.5 percent more than the United States’ 1.5 million.
Researchers as a Share of Total Employees
Measuring researchers as a share of total employed workers reveals the relative amount of human capital devoted to core R&D activities. In this regard, China performs much more poorly than the United States. In 2010, there were 1.6 researchers per 1,000 employees in China compared with 8.5 in the United States. By 2019, this increased to 2.8 for China and 9.9 for the United States. While China’s concentration of researchers increased relative to the United States’ throughout the decade, increasing from 18.8 percent to 28.2 percent of the U.S. level (figure 13), China’s researchers as a share of total employees relative to the United States was still far below its R&D intensity relative to the United States at the end of the decade. A potential reason for this is that R&D incentives from the Chinese government (financial, political, etc.) cause labs and businesses to inflate their reported R&D expenditures. Another reason is that China’s R&D personnel are much more concentrated in non-research roles such as technician or administrator. In 2020, researchers made up just 44 percent of China’s R&D personnel.[55] While comparative figures are not available for the United States, researchers make up 70–80 percent of R&D personnel in countries such as Canada, Japan, and South Korea.
Degrees awarded measures the extent to which students with advanced skills for an innovation-driven and modern economy are added to the workforce. This measure is likely less representative for China than for the United States given the rate at which students from the former country travel abroad (often to the latter country) for their university educations, with approximately four-fifths of them returning to China after graduation.[57] However, it is still useful for gauging the education and skill attainment of the populations.
Total Undergraduate Degrees Awarded
Figure 14 shows the number of both total and science and engineering undergraduate degrees awarded in China relative to the United States. China already awarded 56.8 percent more total degrees and 106.5 percent more science and engineering degrees than did the United States in 2010. These both increased throughout the decade, and although both finished slightly below their decade highs, by 2018, China awarded 94.7 percent more total undergraduate degrees and 124.6 percent more science and engineering undergraduate degrees than did the United States. Specifically, China awarded 3.87 million total undergraduate degrees to the United States’ 1.99 million and 1.82 million science and engineering undergraduate degrees to the United States’ 0.81 million.
Figure 15 considers individual subject groups: natural sciences, mathematics, and statistics as one group and computer science and engineering as another. China entered the decade awarding almost twice as many undergraduate degrees in natural sciences, mathematics, and statistics as did the United States (194.4 percent as many). However, by 2018, this dropped to only 29 percent more, and China awarded 13,500 fewer such degrees than it did in 2010. The largest relative drop was between 2012 and 2013, when China’s number of such degrees awarded fell by over 15 percent.
China awarded 469.9 percent more computer science and engineering undergraduate degrees than did the United States in 2010. By 2014, this increased to 538.5 percent more. However, the United States started catching up to China after 2014, and by 2018, China awarded “only” 444.9 percent more such degrees than did the United States. This drop was the result of a slowdown in the growth of such degrees in China (from 8.6 percent per year in 2010–2014 to 2.9 percent in 2014–2018) while the United States’ growth rate increased (from 5.6 percent per year in 2010–2014 to 7.1 percent in 2014–2018).
Undergraduate Degrees Awarded per Capita
It is also helpful to account for the size of the populations being considered. Only a narrow age range accounts for the vast majority of undergraduate university students. Thus, the number of undergraduate degrees awarded per capita of each country’s 20–29-year-old population is considered. Although China’s age distribution is more skewed toward the older end of the distribution than is the United States’ in general, the 20–29 age group makes up a larger share of its population.[60] While this was true throughout the decade, that share fell quite rapidly. The age group’s share of the population in China fell from about 17 percent in 2010 to 14 percent in 2018.[61] In the United States, the share remained constant at approximately 14 percent.[62] Disregarding these dynamics therefore understates China’s progress, as can be seen by comparing figure 14 and figure 15 with figure 16 and figure 17.
Total undergraduate degrees awarded per capita in China increased from 29.5 percent of U.S. levels in 2010 to 44.3 percent in 2018 when it awarded 195 such degrees for every 10,000 residents in the age group (figure 16). For science and engineering fields specifically, the increase was from 38.9 percent to 51.1 percent of U.S. levels over that period, with China awarding 92 such degrees per 10,000 residents in the age group in 2018.
Relative growth was negative over the decade for China when looking specifically at natural sciences, mathematics, and statistics degrees, falling from 36.5 percent of the U.S. level in 2010 to 29.3 percent in 2018 (figure 17). These represent approximately 12 and 13 such degrees being awarded per 10,000 residents in the age group in China those years.
Entering the decade, China already awarded 35 computer science and engineering undergraduate degrees per 10,000 residents in the age group, which amounted to 7.3 percent more than the United States. China added to this lead throughout the decade, awarding 64 degrees per 10,000 in 2018, 23.9 percent more than the United States’ 52. Relative growth slowed in the second half of the decade, but 123.9 percent of the U.S. level marked China’s decade high.
Considering doctoral degrees rather than undergraduate degrees shifts the focus to students with advanced education and skills in their respective fields who have demonstrated the ability to conduct research at a high level. Again, many Chinese nationals go abroad for their advanced education. To the extent a nonnegligible proportion of these students return to China after receiving their degrees, this indicator understates the number of new PhDs entering China’s workforce each year. However, there is reason to believe that this is much less understated than undergraduate degrees. Despite progress in developing and retaining researching talent, a Center for Security and Emerging Technology study from earlier this year found that 90 percent of Chinese nationals who received a STEM PhD in the United States between 2000 and 2015 remained in the country as of February 2017.[65]
Total Doctoral Degrees Awarded
Unlike with undergraduate degrees, China did not award more doctoral degrees than did the United States entering the decade or at any time between 2010 and 2018 (figure 18). This is also true for science and engineering doctoral degrees. In 2010, China awarded 85.3 percent as many total doctoral degrees as did the United States. By 2015, this had fallen to 78 percent as the United States’ growth rate of such degrees outpaced China’s. However, this trend reversed, and China awarded 83.5 percent as many total doctoral degrees as did the United States in 2018. That same year, China awarded 60,700 doctoral degrees to the United States’ 72,700.
A similar dynamic played out for science and engineering degrees. China awarded 93.3 percent as many such degrees as did the United States in 2010. By 2014, this fell to 85.9 percent. As with total degrees, this trend reversed, and by 2018, China produced 96.8 percent as many science and engineering doctoral degrees as the United States (39,800 to 41,100).
In contrast to undergraduate degrees, total doctoral degrees, and science and engineering doctoral degrees in general, China’s number of doctoral degrees awarded in the natural sciences, mathematics, and statistics relative to the United States’ increased steadily throughout the decade, from 65.2 percent to 75.1 percent of the U.S. level (figure 19). During the decade, China’s growth rate of such degrees was twice that of the United States (3.6 percent per year versus 1.8 percent per year).
China entered the decade awarding over 80 percent more computer science and engineering doctoral degrees than did the United States. The relative dynamics for these degrees were much more like those for total doctoral degrees and science and engineering doctoral degrees in general. From 2010 to 2015, China’s awarding of such degrees dropped from 182.8 percent to 148.8 percent of the U.S. level. However, again, China’s growth rate of such degrees picked up while the United States’ slowed down. In 2018, China awarded 67.3 percent more computer science and engineering doctoral degrees than did the United States, which was still below its 2010 level.
Doctoral Degrees Awarded per capita
For analysis of doctoral degrees per capita, the countries’ 25–39-year-old populations were considered. Among doctoral recipients in the United States, 88 percent are 40 years old or younger—and this concentration is greater for science and engineering fields.[68] Again, this age group accounted for a larger share of the population in China than in the United States throughout the decade (over 23 percent in China and under 21 percent in the United States in 2018).[69] However, changes in the groups’ population shares in the two countries were very similar, so only comparing total degrees does not have the same progress-understating effect that it does for undergraduate degrees.
China’s doctoral degrees awarded per capita relative to the United States are much lower than for undergraduate degrees in all categories. In 2010, China awarded 16.9 percent as many doctoral degrees per 25–39-year-old resident as did the United States (figure 20). In 2018, this was unchanged, although it was up from the decade low of 15.1 percent in 2015. The story of China’s science and engineering degrees per capita relative to the United States is similar. In 2010, China awarded 18.5 percent as many such degrees per age-group resident as did the United States. By 2018, this increased slightly to 19.7 percent. Here, too, China reversed a negative trend that defined the first half of the decade.
As with science and engineering fields as a whole, China’s natural sciences, mathematics, and statistics doctorates awarded per 25–39-year-old relative to the United States rose only slightly throughout the decade, from 12.9 percent of the U.S. level in 2010 to 15.3 percent in 2018 (figure 21). However, China’s progress in this subject group was much steadier. The dynamics for computer science and engineering doctorates per capita are much more like those for total degrees and science and engineering degrees as a whole. Between 2010 and 2015, China’s computer science and engineering doctorates awarded per capita fell from 36.3 percent of the U.S. level to 28.8 percent. By 2018, this recovered somewhat to 33.9 percent.
As the institutions that train future high-skill workers and researchers—and among the primary contributors to the accumulation of foundational knowledge—the number and quality of top universities in a country are useful indicators of its innovative capacity.
Per the annual Shanghai Academic Ranking of World Universities, China had 27 universities in the top 500 in 2010 compared with the United States’ 154 (including all of the top four). By 2020, China’s number of universities in the top 500 jumped to 76, whereas the United States’ number dropped to 133 (although it now held all top five spots). Moreover, China caught up to the United States at a faster pace in the second half of the decade.
Weighted scores were given to universities based on their standings in the rankings to account for both the number and relative quality of the universities in the top 500. The appendix in this report provides an explanation of this scoring method. The cumulative value of the weighted scores of China’s universities in the top 500 was only 9 percent that of the United States’ universities (figure 22). In 2020, China’s cumulative score was 40.5 percent that of the U.S. score. As figure 22 shows, China’s progress in both the number of universities and their cumulative weighted score relative to the United States was exponential.
In the last decade, China gained ground relative to the United States in almost every input indicator reviewed. However, it still lags behind the United States in all indicators accounting for size. China made significant strides with respect to its top R&D-investing companies and the number and quality of its top universities; progress relative to the United States was exponential for both. While still far behind U.S. levels, China made steady progress in basic R&D intensity and researchers as a share of its employed workforce. China briefly caught up to the United States in terms of VC investment in the middle of the decade (and surpassed the United States when accounting for the size of the economy) but fell back down to about half of U.S. VC investment in 2020. Nevertheless, VC is becoming an increasingly integral part of the Chinese financial sector. While China now produces the most university graduates of any country, its number of graduates per capitaremains well below the comparative U.S. figures in almost all fields reviewed.[73] For both undergraduate and doctoral degrees per capita in the natural sciences, mathematics, and statistics, China is still far behind the United States and struggling to make progress.
Innovation Outputs
A nation’s science and engineering research articles measures the extent to which that nation contributes to the building of knowledge in these innovation-related subjects. The following figures show China’s output of science and engineering articles, both as a whole and by subject, relative to the United States.
Total Science and Engineering Articles
Over the last decade, China went from publishing 68.7 percent as many science and engineering articles as did the United States in 2010 to 123.7 percent in 2020, publishing over 742,000 articles compared with the United States’ 600,000 (figure 23). Moreover, China caught up (and then pulled away) at an increasing rate throughout the decade. In 2010–2015, China’s science and engineering publications grew at an annual rate of 6 percent compared with the United States’ 1.9 percent. In 2015–2020, China’s rate increased to 10.7 percent per year while the United States’ only increased to 2.3 percent.
Figure 24 shows China’s technical sciences (computer and information sciences, engineering, and mathematics and statistics) publications relative to the United States. For computer and information sciences and engineering, China entered the decade already publishing more articles per year than the United States. In the first half of the decade, China’s computer and information sciences publications fell at an annual rate of 9.1 percent and its engineering publications increased at an annual rate of 5.8 percent. In the second half of the decade, these rates increased to (positive) 14.4 percent and 8.7 percent, respectively. The comparative increases for the United States were much smaller: 0.6 percent to 1.8 percent for computer and information sciences and 0.4 percent to 0.5 percent for engineering. China’s second-half progress in mathematics and statistics publications was more muted. China’s publications in these subjects increased at an annual rate of 10.1 percent in the first half of the decade while the United States’ increased at 2.6 percent. In the second half of the decade, China’s annual growth rate fell slightly to 8.8 precent while the United States’ rose to 3.3 percent.
Figure 25 focuses on the natural sciences. China entered the decade out-publishing the United States in only chemistry, though by the end of the decade, it published 3.5 times as many articles as the United States in chemistry, 2.5 times as many in physics, and 12.8 percent more in biological and biomedical sciences. In contrast to the technical sciences, China’s annual growth rate in publication output increased from the first to the second half of the decade in only physics (7.1 percent to 10 percent). This was true for the United States for only geological, atmospheric, and oceanic sciences (2.1 percent to 3 percent), but the decreases in the United States’ annual growth rates in biological and biomedical sciences (1.2 percent to 0.5 percent) and chemistry (0.9 percent to -0.21 percent) were smaller than China’s (13.3 percent to 11.9 percent and 11.4 percent to 6.6 percent, respectively). Hence, while China still made progress relative to the United States in biological and biomedical sciences, chemistry, and geological, atmospheric, and oceanic sciences in the second half of the decade, it did so at a slower pace.
Science and Engineering Articles per Capita
Again, accounting for the size of China’s population provides a clearer picture. Because China’s population was approximately 4.3 times larger than that of the United States throughout the decade, per capita progress closely matched progress when considering total measures. Over the last decade, China went from publishing 15.9 percent of the United States’ science and engineering articles per capita in 2010 to 29.1 percent in 2020 (figure 26), when it published 523.2 science and engineering articles per million residents compared with the United States’ 1,810.1.
Figure 27 shows China’s number of articles per capita in the technical sciences relative to the United States by subject. China produced fewer than half as many articles per capita than did the United States in each of the three categories in 2010 (and less than 20 percent as many in mathematics and statistics). This increased for each subject, though China only produced 59.9 percent as many engineering articles, 51.1 percent as many computer and information sciences articles, and 31.1 percent as many mathematics and statistics articles per capita than did the United States in 2020. China produced 122.7, 62.5, and 12.6 articles in these subjects per million residents, respectively, in 2020.
Figure 28 shows the relative per capita figures for the natural sciences. Again, China produced fewer than half as many articles per capita as did the United States in each subject entering the decade (and less than 10 percent as many in the biological and biomedical sciences and the geological, atmospheric, and oceanic sciences). China experienced consistent growth relative to the United States in each of the subjects throughout the decade, and China’s per capita output of chemistry articles approached the U.S. level by the end of that period. In 2020, China produced 83.1 percent as many articles per capita as did the United States in chemistry; 58.7 percent as many in physics; 26.4 percent as many in the biological and biomedical sciences; and 14.4 percent as many in the geological, atmospheric, and oceanic sciences. China produced 39.2, 47.6, 51.8, and 72.7 articles per million residents in these subjects, respectively, in 2020.
Beyond the sheer volume of a nation’s science and engineering articles published, it is useful to gauge the quality of those articles. One way to do this is by measuring what share of that nation’s articles are among the most cited in their fields. The following figures compare what shares of China’s science and engineering articles are among the top 1 percent in citations in the two years following their publications. By definition, the global (weighted) average is 1 percent. In 2010, only 0.5 percent of China’s science and engineering articles were among the most cited, compared with 1.9 percent for the United States (figure 29). By 2018, however, China attained the global average of 1 percent while the share of the United States’ science and engineering articles among the most published dropped to 1.6 percent. This means China’s science and engineering articles were approximately 60 percent as likely to be among the top 1 percent in citations as were U.S. articles in 2018.
Looking at individual science and engineering subjects, we see that the gains in influence relative to U.S. articles were universal (figure 30 and figure 31). The biggest relative gains made were in mathematics and statistics (where Chinese articles were 68 percent more likely to be among the top 1 percent in citations than their American counterparts in 2018) and chemistry (where Chinese articles were only 11.3 percent less likely to be among the most cited in 2018). China came close to U.S. levels of influence in engineering research, as China’s engineering publications were 74.6 percent as likely as their American counterparts to be among the most cited in 2018.
An international patent family (IPF) is the collection of all patents covering the same or very similar inventions in multiple countries. As mentioned previously, patent activity in China can be somewhat misleading in the years following MLP in 2006, since the government’s encouragement of patent applications likely triggered an increase in applications for inventions that were not practical or economical.[83] However, data regarding international patent families considers inventions for which patents were granted in several countries, which avoids counting patents for which there is no noteworthy difference between inventions as multiple patents and counting the likely less-valuable patents only filed in the inventor’s home country. While this does not completely erase the issue of China’s high proportion of relatively worthless patents (a Chinese patentholder can file a patent in another country with a cheap and easy patent process—and this measure does not differentiate between less-useful design and utility patents and more-useful invention patents), it does mitigate it and is preferable to a measure of patents filed with just the Chinese patent office or some other specific nation’s patent office.
Total IPFs
China entered the decade already receiving 9.4 percent more total IPFs per year than did the United States, and by 2020, it was awarded 378.4 percent more (figure 32). Over the course of the decade, China’s IPFs granted increased from 80,556 to 456,088 while the United States’ increased from 73,622 to 95,347. From 2010 to 2015, China’s IPFs granted increased at a staggering annual rate of 26 percent compared with the United States’ 4.3 percent. Growth slowed for both countries in the second half of the decade: China’s annual growth rate more than halved to 12.3 percent while the United States’ fell to 1 percent.
Two major objectives of MIC are to incorporate information and communications technologies (ICTs) into the manufacturing process to both increase productivity and become self-reliant with respect to the development of new and emerging technologies. While China’s respect for IP rights is significantly lacking, especially at the international level, IPFs granted to Chinese entities in these technologies provide a useful measure for the extent to which these goals are being achieved.
As shown in figure 33, China’s IPFs granted were fewer than those of the United States entering the decade in three of the four ICTs considered: telecommunications (77.7 percent of the U.S. level), computer technology (33.7 percent), and semiconductors (79 percent). By 2016, China surpassed the United States in all four ICTs. By the end of the decade, it received more than three times as many IPFs in each technology than did the United States. Moreover, China pulled away from the United States in the second half of the decade at a faster rate than it caught up in the first half for each ICT. In each technology except for semiconductors, this was a result of IPF growth rates increasing for China and falling for the United States. For semiconductors, IPF growth fell for both countries. However, for China, it only fell from 18.8 percent per year in 2010–2015 to 14.4 percent per year in 2015–2020. In the United States, the annual growth rate in semiconductor IFPs granted fell from 3.3 percent to -3.5 percent.
As with ICTs, MIC cites biopharmaceuticals/biotechnologies as an industry in which China aims to be a self-sufficient world leader and innovator. China entered the decade receiving more IPFs than did the United States in biotechnology (54.3 percent more) and pharmaceuticals (228.2 percent more), and it received only 38.5 percent as many medical technology IPFs, as seen in figure 34. China’s growth in medical technology IPFs relative to the United States was steady throughout the decade, and China was granted 74.6 percent more such IPFs than was the United States in 2020. Relative growth in biotechnology and pharmaceuticals was much more sporadic. In both technologies, China ceded ground to the United States during the middle of the decade due to significant decreases in China’s IPFs received per year. From 2013 to 2017, China’s IPFs awarded in biotechnology and pharmaceuticals dropped 24.8 percent and 33 percent, respectively. However, this quickly and significantly reversed. Between 2017 and 2020, China’s IPFs granted increased by 135.5 percent and 42.2 percent, respectively. Meanwhile, the United States’ biotechnology IPFs granted fell by 16.1 percent during that span. In 2020, China received approximately seven times as many biotechnology IPFs and over four times as many pharmaceuticals IPFs as did the United States.
Environmental technologies (ETs), especially low-emission power-generating technologies, are paramount in a world that must rein in carbon emissions to confront global warming. These technologies are consistently included in China’s many lists of priority technologies. Specifically, MIC singles out new-energy motor vehicles as a technology in which China hopes to become a global leader. In 2010, China was already awarded twice as many ET IPFs as was the United States (figure 35). By 2020, this ballooned to 11.4 times as many despite two separate periods of little to no growth relative to the United States that account for half the decade (2012–2014 and 2016–2019). Between 2010 and 2015, China’s ET IPFs grew at a staggering 32.5 percent per year, compared with the United States’ 2.6 percent. These figures dropped to 8.8 percent per year and -0.7 percent per year for the two countries, respectively.
In the United States, the annual growth rate in semiconductor IPFs granted fell from 3.3 percent in the first half of the decade to -3.5 percent in the second half of the decade.
IPFs per Capita
Figure 36 shows China’s IPFs per capita relative to the United States’. China entered the decade only receiving one-quarter of the IPFs per capita the United States received (59.9 IPFs per million residents versus 238). However, by the end of the decade, China surpassed the United States in IPFs per capita: China received 321.4 IPFs per million residents in 2020, which was 11.7 percent more than the United States’ 287.6.
Figure 37 shows China’s ICT IPFs per capita relative to the United States’ broken down by field of technology. Again, China made significant progress in each technology. By 2020, China received more than 75 percent as many IPFs per capita as did the United States in each field and surpassed the United States with regard to telecommunications IPFs. Relative growth was faster in the second half of the decade than in the first for each of the four technologies.
Figure 38 shows China’s life sciences IPFs per capita relative to the United States’ broken down by technology area. China’s progress was most significant in biotechnology, in which it received 62.8 percent more IPFs per capita than did the United States by the end of the decade. Though China made progress in each of the three areas, China’s pharmaceutical IPFs per capita relative to the United States finished the decade well below its peak of 119.8 percent of the U.S. level in 2011.
Figure 39 shows China’s ET IPFs per capita relative to the United States. China entered the decade producing fewer than half as many ET IPFs per capita as the United States. However, this quickly changed, as China surpassed the United States in 2012. China’s progress continued, and by the end of the decade, China produced 166.6 percent more ET IPFs per capita than did the United States.
One way to measure the worth of patents granted is to measure the international licensing receipts Chinese patent and trademark holders receive. Cross-border receipts provide a measure of how valuable foreign entities view China’s IP relative to those of other countries.
Total International IP Receipts
As seen in figure 40, China receives very little in cross-border IP receipts compared with the United States, supporting the argument that China’s surge in patent filing is rather hollow. China’s $1.2 billion in international IP receipts in 2010 was only 1.3 percent of the United States’ $95 billion. For much of the decade, this remained the case. However, starting in 2016–2017, China’s international IP receipts increased at breakneck pace. Between 2016 and 2017 alone, China’s international IP receipts tripled from $1.8 billion to $5.4 billion, and by 2020, they were $9.3 billion. While this was still only 7.5 percent of the U.S. level ($113.8 billion), China’s progress—both in absolute and relative terms—is quite staggering.
International IP Receipts as a Share of GDP
Taking these receipts as a share of GDP, as shown in figure 41, accounts for the size of each economy and measures the extent to which they specialize in producing IP for the competitive international market. In 2010, China’s international IP receipts accounted for only 0.02 percent of its GDP, compared with 0.63 percent for the United States. Again, China’s international IP receipts as a share of GDP remained miniscule relative to the United States’ before ballooning in 2017. By 2020, China’s receipts accounted for 0.06 percent of its GDP, which was 11.3 percent of the U.S. level.
Innovation outputs are where China made the most progress relative to the United States and where it ended the decade with the largest advantage—and China appears to have shaken off the “fat tech dragon” moniker. By the end of the decade, China published more scientific articles in all fields reviewed except for the geological, atmospheric, and oceanic sciences, but citations data shows that its research is still less influential than the United States’ in all fields except mathematics and statistics. China surpassed the United States in IPFs granted in every field, and it caught up to or surpassed the United States on a per capita basis in telecommunications, pharmaceuticals, biotechnology, and ETs. Incredibly, China received 11.4 times as many ET IPFs in total and more than 2.5 times as many on a per capita basis than did the United States in 2020. Cross-border IP receipts suggest China’s IP is still far less valuable than the United States’. However, China made rapid progress in this regard starting in 2016–2017. Between 2016 and 2020, China’s cross-border IP receipts increased by over 400 percent and its IP receipts as a share of its GDP quadrupled.
Innovation Outcomes
One important innovation market outcome is increased production in high-R&D industries. The industries included are 1) aircraft manufacturing; 2) computer, electronics, and optical products manufacturing; 3) pharmaceuticals manufacturing; 4) scientific R&D services; and 5) publishing (including software).
Total Production
China’s value added in high-R&D industries amounted to only 34.4 percent of the U.S. level in 2010 (figure 42). China’s progress slowed in the middle of the decade, which corresponds with a slowdown in the broader Chinese economy. But overall, China gained ground steadily, and by 2018, its value added in these industries was 64.1 percent that of the United States. China entered the decade already well ahead of the United States in exports in high-R&D industries, exporting more than twice as much as the United States did in 2010, thanks to its computer, electronics, and optical products exports. Again, China’s progress reversed temporarily in the middle of the decade, but by 2018, China’s exports were almost three times that of U.S. exports in these industries.
Production as a Share of GDP and Exports
However, these figures, while useful, do not account for the size of China’s economy or its overall economic growth during the decade. Considering value added as a share of GDP shows the extent to which an economy specializes in that industry. The same is true for industry exports as a share of total exports, though the specialization is then focused on the goods and services the country produces for the competitive international market.
Rather than considering their absolute values, figure 43 considers each country’s value added and exports in high-R&D industries as shares of their GDPs and total gross exports, respectively. Value added in these industries accounted for 4.1 percent of China’s GDP and 5.1 percent of the United States’ in 2010. By 2018, value added in these industries accounted for 4.7 percent of China’s GDP while the United States’ share was unchanged. Thus, while the United States’ degree of specialization remained essentially unchanged in these industries throughout the decade, China’s increased (to 92.3 percent of the U.S. level).
In 2010, China’s high-R&D exports accounted for 27 percent of gross exports compared with 11.7 percent in the United States. Export specialization in these industries decreased for both countries in the first half of the decade. By 2015, high-R&D exports accounted for 22.6 percent of China’s gross exports and 10.5 percent of the United States’. However, after this point, China reversed course, while export share in the United States continued to decrease. By 2018, these industries accounted for 24.9 percent of China’s exports and 9.8 percent of the United States’.
Total Value Added
Figure 44 and figure 45 carry the value-added analysis further, focusing on seven advanced industries: 1) computer, electronic, and optical products manufacturing; 2) computer programming, consulting, and information services; 3) electrical equipment manufacturing; 4) motor vehicle manufacturing; 5) other transport equipment manufacturing; 6) pharmaceuticals manufacturing; and 7) professional, scientific, and technical activities.
China’s value-added growth in all industries slowed from the first half of the decade to the second, both relative to the United States and in absolute terms. This again corresponds to China’s broader economic slowdown. Nonetheless, China’s value added in each industry relative to the United States was higher in 2018 than in 2010. China’s largest absolute gain was in electrical equipment manufacturing, where its value added increased from 231 percent to 314.2 percent of the U.S. level. China’s largest relative gain was in professional, scientific, and technical activities, which saw its value added relative to the United States double from 2010 to 2018, although this was only from 8.5 to 19.8 percent of the U.S. level. Progress in pharmaceuticals manufacturing was also notable, increasing from 42.2 percent to 73.1 percent of the U.S. level.
China’s fastest individual growth was in the four industries—computer programming, consulting, and information services; other transport equipment manufacturing; pharmaceuticals manufacturing; and professional, scientific, and technical activities—in which China’s value added had not reached U.S. levels. Despite the mid-decade slowdown, these four industries averaged an annual growth rate of 12.2 percent in China from 2010 to 2018, compared with 5 percent for the United States. What’s more, China’s value-added growth was fastest in the two service industries: computer programming, consulting, and information services; and professional, scientific, and technical activities. This suggests that China is transitioning from a manufacturing-based economy to one more dependent on high-value-added services.
Value Added as a Share of GDP
Figure 46 and figure 47 consider value added as a share of GDP. In all industries except pharmaceuticals manufacturing and professional, scientific, and technical activities, China’s specialization relative to the United States decreased. However, for pharmaceuticals manufacturing, this was because value added in the industry as a share of GDP fell slightly for the United States (rather than China becoming more specialized in the industry). In 2010, value added in the industry accounted for 0.9 percent of GDP for both countries. By 2018, this fell to 0.8 percent for the United States. In contrast, both countries became more specialized in professional, scientific, and technical activities, but China did so at a faster pace. In 2010, value added in the industry accounted for 1.5 percent of China’s GDP and 7.5 percent of the United States’. By 2018, these figures increased to 2.2 percent and 7.7 percent, respectively.
In four of the five industries for which China’s specialization relative to the United States decreased, China’s individual degree of specialization decreased. For example, value added in the electrical equipment manufacturing industry accounted for 1.9 percent of China’s GDP in 2010 but only 1.4 percent in 2018. The exception was computer programming, consulting, and information services. Both countries became more specialized in the industry, but the United States did so at a faster pace. In 2010, value added in the industry accounted for 1.4 percent of China’s GDP and 2 percent of the United States’. By 2018, those numbers increased to 1.8 percent and 2.9 percent, respectively.
Gross Industry Exports
Figure 48 and figure 49 consider each country’s exports in the advanced industries. China’s exports relative to the United States increased in the following industries: computer, electronic, and optical products manufacturing (from 307.1 percent to 482.3 percent of the U.S. level); computer programming, consulting, and information services (from 89.2 percent to 99.6 percent); electrical equipment manufacturing (from 464.6 percent to 672.4 percent); motor vehicles manufacturing (from 33.8 percent to 43.6 percent); and pharmaceuticals manufacturing (from 27.1 percent to 54.7 percent). China’s exports relative to the United States’ fell for only other transport equipment manufacturing (from 48.6 percent to 37.5 percent of the U.S. level) and professional, technical, and scientific activities (from 27.9 percent to 24.7 percent).
China’s progress relative to the United States was more meager in computer programming, consulting, and information services than in some of the other industries because this is the industry in which each country saw the largest increase in exports. Between 2010 and 2018, China’s exports in the industry grew at an annual rate of 17 percent, while the United States’ grew at an annual rate of 15.4 percent. China also saw significant growth in its pharmaceuticals exports, which increased at an annual rate of 12.8 percent, although the value of these exports fluctuated significantly.
Gross Industry Exports as a Share of Total Gross Exports
As with value added, figure 50 and figure 51 show each advanced industry’s export share in China relative to the United States. Since the two countries’ gross exports dynamics were quite similar between 2010 and 2018, China’s progress here is very similar to its progress for absolute exports. China became relatively more export-specialized in the following industries: computer, electronic, and optical products manufacturing; electrical equipment manufacturing; motor vehicle manufacturing; and pharmaceuticals manufacturing. However, China became individually less export-specialized in computer, electronic, and optical products manufacturing and motor vehicles manufacturing, albeit at a slower pace than the United States.
Note that contrary to absolute exports, the export share of China’s computer programming, consulting, and information services industry relative to that of the United States fell slightly. However, again, this is the industry in which each country’s export-specialization increased the most individually. In 2010, the industry made up 0.9 percent of each country’s exports. By 2018, it made up 1.9 percent of China’s exports and 2.1 percent of U.S. exports.
Harvard Growth Lab’s Atlas of Economic Complexity created the Economic Complexity Index (ECI) to measure how complex a country’s economy is based on what it exports, what it could easily start exporting, how many other countries export its products, and how easily other countries could start exporting its products. It provides index scores for each country going back to 2000. In 2010, China was given an ECI score of 1.05, which was 67 percent of the United States’ score of 1.56 (figure 52). For reference, this ranked the two countries 24th and 12th, respectively (the appendix provides global heat maps of 2020 scores for the indices used as indicators along with the top 10 highest-scoring countries). In 2020, China’s score jumped to 1.3, while the United States’ score fell to 1.47 (17th and 12th, respectively). China’s decade-high score was 1.38 in 2018, while the United States’ was 1.72 in 2015.
A useful indicator of a country’s standing in terms of frontier, emerging technologies is the number and quality of its supercomputers (or “high-performance computers”). Supercomputers are amazing technological feats in their own right but are also used in firms’ operation maximization and to conduct research where processing massive amounts of data quickly is required (e.g., COVID-19 epidemiological and vaccine-related research).[101] The U.S. government uses and funds the use of supercomputers in fields such as homeland security, weather prediction, and the monitoring of financial markets.[102] The development of world-class supercomputing systems is an explicit goal for both countries.
The performance of a computing system is measured by the number of operations it can perform per second (FLOPS) or, more commonly, the number of billions of operations it can perform per second (GFLOPS). Intel’s 11th-generation Core processors, widely used in personal computers, can perform up to 211 GFLOPS.[103] The United States’ “Frontier” supercomputer at Oak Ridge National Laboratory, officially the most powerful supercomputer in the world as of June 2022, reached the treasured level of “exascale,” meaning it can perform at least one EXAFLOPS, or 1,000,000,000 GFLOPS, or 1018 FLOPS. Specifically, Frontier is capable of 1,102,000,000 GFLOPS.[104]
In 2010, China had only 41 of the world’s 500 most powerful supercomputers compared with the United States’ 276. By the end of the decade, China had 89 percent more of the world’s top 500 supercomputers than did the United States, possessing 214 to the United States’ 113 (figure 53). However, as Figure 49 also shows, the cumulative realized performance of these supercomputers is still behind that of the United States. While China’s top supercomputers made gains against the top U.S. supercomputers, they still only possessed 85 percent of the cumulative computing power in 2020, and part of China’s gains were reversed starting in 2018. From 2017 to 2018, the cumulative computing power of the United States’ top supercomputers more than doubled while China’s “only” increased by 46.6 percent. Nevertheless, China’s relative growth in cumulative supercomputer performance was impressive across the decade as a whole, increasing from 25.3 percent of the United States’ cumulative computing power in 2010 to 84.7 percent in 2020.
However, as mentioned previously, China has recently become much more secretive about its major breakthroughs in high-performance computing. A report by The Next Platform’s Nicole Hemsoth from October of last year suggests that China had already achieved exascale performance on two separate systems.[105] Therefore, China’s progress is likely understated by the available data, and the plateauing of its progress relative to the United States in both number of systems and cumulative performance in the latter half of the decade may simply be a result of China’s keeping its cards close to its chest.
Increased automation in the manufacturing sector is an indication of an economy’s productive efficiency and a stated goal of MIC. This is especially important for China, which will face a demographic challenge earlier in its development than do most countries, presenting it with the task of providing for a surge in elderly retirees with a declining working-age population.
Industrial Robot Density
As shown in Figure 54, China’s industrial robot density, the number of robots employed in industry relative to the number of human workers, increased dramatically over the previous decade. In 2010, China employed only 11.5 percent as many industrial robots per worker as did the United States (15 and 130 robots per 10,000 workers, respectively). By 2015, this number increased to 29.1 percent, and by 2020, China almost completely closed the gap and employed 96.5 percent as many industrial robots per worker as did the United States (246 and 255 robots per 10,000 workers, respectively). Not only have China’s relative (and absolute) gains been significant, but the rate of increase rose throughout the decade. China’s industrial robot density relative to the United States’ grew at an annual rate of 20.4 percent in 2010–2015 and 27.1 percent in 2015–2020.
Access to the Internet and the ability to communicate with others remotely is increasingly necessary in the modern economy, especially with the rise in e-commerce and mobile payment systems. Internet access also means access to a dearth of information from around the world and, increasingly, to educational and government resources.
Total Subscriptions
Figure 55 shows China’s total number of mobile cellular and fixed broadband subscriptions relative to the United States’. Entering the decade, China had 206.5 percent more mobile cellular subscriptions and 52 percent more fixed broadband subscriptions than did the United States. While China’s number of mobile cellular subscriptions relative to the United States’ decreased between 2013 and 2016, China finished the decade with just under five times as many mobile cellular subscriptions as did the United States (1,743.1 m
| 2023-01-23T00:00:00 |
2023/01/23
|
https://itif.org/publications/2023/01/23/wake-up-america-china-is-overtaking-the-united-states-in-innovation-capacity/
|
[
{
"date": "2023/01/23",
"position": 97,
"query": "AI economic disruption"
}
] |
EEOC Eyes AI-Based Hiring in Draft Strategic Enforcement ...
|
EEOC Eyes AI-Based Hiring in Draft Strategic Enforcement Plan
|
https://www.bhfs.com
|
[] |
The hearing will include a panel discission on the civil rights implications of AI and other automated systems for U.S. employees and job candidates.
|
The U.S. Equal Employment Opportunity Commission (EEOC) signaled its plan to broaden its enforcement efforts to include additional focus on artificial intelligence (AI) in the workplace. On Tuesday, Jan. 10, the EEOC published its draft Strategic Enforcement Plan (SEP) for 2023–2027 in the Federal Register and it includes updates that for the first time take into account “employers’ increasing use of automated systems, including artificial intelligence or machine learning,” to make hiring and recruiting decisions.
The ECEC’s SEP is the culmination of public input gathered via a series of listening sessions that occurred in the summer and early fall of 2022. In the final listening session held on Sept. 22, concerns about AI and other technology dominated the conversation. Worker advocates expressed concerns about hiring systems and hard-to-use technology inadvertently furthering discrimination. Employer advocates expressed the need for more clarity on how employers can and should use AI in hiring and recruiting decisions.
Within its subject matter priorities, the SEP points to discriminatory use of automated systems and AI as a hiring barrier. The EEOC says that it plans to monitor screening tools or requirements that disproportionality impact workers based on their protected status, including those facilitated by artificial intelligence or other automated systems, preemployment tests and background checks.
The EEOC is also holding a hearing on Jan. 31 for examining the use of automated systems and AI in employment decisions. The hearing will include a panel discission on the civil rights implications of AI and other automated systems for U.S. employees and job candidates. Additionally, the hearing will explore ways in which these technologies might further the interests of diversity, inclusion, accessibility and diversity.
The EEOC is seeking public comments on the SEP. Interested parties must submit comments by Feb. 9, 2023. If adopted, the 2023–2027 EEOC will replace its most recent plan that covered 2017–2021.
Brownstein has previously published a written alert discussing the steps employers should take to evaluate AI algorithms. We are currently working with employers that utilize AI in the hiring process to ensure that their systems are legally compliant. Given that the EEOC listed AI use in hiring as the first subject matter priority in the SEP, employers who use AI should take heed and vet their models.
THIS DOCUMENT IS INTENDED TO PROVIDE YOU WITH GENERAL INFORMATION REGARDING EEOC GUIDANCE ON USE OF AI IN HIRING. THE CONTENTS OF THIS DOCUMENT ARE NOT INTENDED TO PROVIDE SPECIFIC LEGAL ADVICE. IF YOU HAVE ANY QUESTIONS ABOUT THE CONTENTS OF THIS DOCUMENT OR IF YOU NEED LEGAL ADVICE AS TO AN ISSUE, PLEASE CONTACT THE ATTORNEYS LISTED OR YOUR REGULAR BROWNSTEIN HYATT FARBER SCHRECK, LLP ATTORNEY. THIS COMMUNICATION MAY BE CONSIDERED ADVERTISING IN SOME JURISDICTIONS.
| 2023-01-20T00:00:00 |
2023/01/20
|
https://www.bhfs.com/insight/eeoc-eyes-ai-based-hiring-in-draft-strategic-enforcement-plan/
|
[
{
"date": "2023/01/23",
"position": 3,
"query": "government AI workforce policy"
}
] |
Artificial Intelligence and the Workplace
|
Artificial Intelligence and the Workplace
|
https://dwfgroup.com
|
[
"Related Authors",
"Joanne Frew",
"Global Head Of Employment",
"Charlotte Lloyd Jones",
"Professional Support Lawyer"
] |
There is currently no legislation that specifically governs AI in the UK, and neither does the UK government plan to create a new law covering AI at this stage.
|
What is AI?
AI can generally be described as activity devoted to making machines intelligent, and intelligence is the quality that enables an entity to function appropriately and with foresight in its environment.
The exponential growth in machine processing power has enabled techniques of machine learning, by which computers learn through examples and teach themselves to carry out pattern recognition tasks without being explicitly programmed to do so.
AI can be a supportive tool in the workplace for repetitive, standardised and processing tasks.
AI and employment law
AI tools are increasingly being used by employers, not only during the employment relationship but also as part of their recruitment processes. Employers should therefore be aware of potential claims in relation to AI.
Some examples of AI use in the workplace include:
Recruitment: employers can use AI algorithms that have the ability to sift through CVs, application forms and search prospective employees' social media for certain terms or phrases. Automatic filtering could also be completed of candidates through online assessment and tests and could look at those recruited to define successful candidates.
employers can use AI algorithms that have the ability to sift through CVs, application forms and search prospective employees' social media for certain terms or phrases. Automatic filtering could also be completed of candidates through online assessment and tests and could look at those recruited to define successful candidates. Machine Learning : through algorithms, machines can be taught to imitate intelligent human behaviour, including the use of image recognition, which assesses individuals tone or facial movements during video interviews.
: through algorithms, machines can be taught to imitate intelligent human behaviour, including the use of image recognition, which assesses individuals tone or facial movements during video interviews. Profiling: employers may use AI to categorise data and find correlations between data sets. This could be useful for predicting whether employees will meet their targets, potentially leading to capability proceedings or dismissals.
Difficulties
Algorithms and bias : humans usually input data for algorithms to be effective, which can create bias even if done so unintentionally by its designer. Biases can include disability discrimination via facial recognition software, where medical conditions can lower the accuracy of an attempt to read an individual's emotions. Racial bias can also occur, where facial recognition has shown to be less reliable for people with darker skin tones.
: humans usually input data for algorithms to be effective, which can create bias even if done so unintentionally by its designer. Biases can include disability discrimination via facial recognition software, where medical conditions can lower the accuracy of an attempt to read an individual's emotions. Racial bias can also occur, where facial recognition has shown to be less reliable for people with darker skin tones. The use of AI in employment can create discriminatory outcomes: Employers should ensure 'algorithmic discrimination' does not take place by reviewing processes before and quality checking decisions made through AI. The Equality and Human Rights Commission published guidance on the use of AI in public services on 1 September 2022. The guidance note discusses how AI could lead to discrimination because bias is embedded in the underlying data or how humans programme the system. In turn, this could cause public bodies to breach the Equality Act 2010.
Employers should ensure 'algorithmic discrimination' does not take place by reviewing processes before and quality checking decisions made through AI. The Equality and Human Rights Commission published guidance on the use of AI in public services on 1 September 2022. The guidance note discusses how AI could lead to discrimination because bias is embedded in the underlying data or how humans programme the system. In turn, this could cause public bodies to breach the Equality Act 2010. Data protection and privacy: employers need to ensure personal data is processed lawfully, fairly and in a transparent way, this includes providing employees information regarding method, the information it collects and why and how the information may be processed. Employers could be in breach of data protection regulations and the employee's right to privacy if this is not done.
ChatGPT
Whilst there are challenges with AI in employment and the workplace, stark innovation in the AI world could cause even more transformation in the very near future.
OpenAI (an artificial intelligence research laboratory) recently introduced ChatGPT which is a long form question and answering AI chatbot that can answer complex questions conversationally and appear human.
ChatGPT was trained on vast amounts of data to accurately predict the next series of words in a sentence and is so advanced that it can write paragraphs and entire pages of content to complex requests. For instance, when discussing ChatGPT, media personality, Jordan Peterson, states that it could produce an essay with any given topic and could grade it as a professor would do when asked, within seconds. This was the same for when it was asked to produce the 'next 900 million dollar Hollywood blockbuster', producing a plot and characterisations, along with computer generated photos of each actor.
As ChatGPT (along with other forms of AI) become more advanced, it could have the precarious consequence of completely eradicating the need for human input in any given task, including in the workplace. As with the advancement of AI, great care will need to be taken to ensure the employment law pitfalls outlined above, such as discriminatory biases and data protection breaches, are avoided.
Practical solutions
There is currently no legislation that specifically governs AI in the UK, and neither does the UK government plan to create a new law covering AI at this stage. Instead, the government intends to modify current law to bring AI within existing legislation as far as possible.
The EU published a proposal for regulation on AI in 2022, aiming to address the risks, where it could have a significant impact on individual lives. It suggested that decisions relating to employment should be classified as 'high risk' and subject to relevant safeguards. It is not yet known whether the UK would mirror such regulation if introduced into the EU.
The UK GDPR and National Security and Investment Act 2021 already cater for AI and provide some protection for individuals who may find themselves subject to AI decisions. Article 22 of GDPR protects individuals from automated decision making and profiling by limiting the use of such processes and placing safeguards on organisations seeking to use them.
AI is evolving, particularly in the workplace and it will be interesting to see the UK's national position on regulation in the coming years. In the meantime, employers should remain vigilant to minimise the risk of claims and retain a degree of human involvement in their processes involving AI.
Authored by Lydia Keeley.
If you need any advice in relation to AI in the workplace please do not hesitate to get in touch.
| 2023-01-23T00:00:00 |
https://dwfgroup.com/en/news-and-insights/insights/2023/1/artificial-intelligence-and-the-workplace
|
[
{
"date": "2023/01/23",
"position": 31,
"query": "government AI workforce policy"
}
] |
|
Automated Employment Decision Tools (Updated) - NYC Rules
|
Automated Employment Decision Tools (Updated)
|
https://rules.cityofnewyork.us
|
[] |
As the attempt is to regulate new technologies in markets (e.g., AI in hiring) questions arise with the alongside development of new services that themselves ...
|
×
To change the text size on NYC.gov you can use your web browser’s settings. Most browsers include functionality to let you increase or decrease the text on a web page. For example, to increase text size using:
Chrome
In the menu to the right of the address bar, select and set Zoom level. Menu > Zoom > +
Firefox
In the View menu, select Zoom. View > Zoom > Zoom In
Internet Explorer
In the View menu, select Text Size. View > Text Size > Largest
Safari
In the View menu, select Zoom In. View > Zoom In Macintosh Shortcut: Command+
No Web Browser Endorsement
Common browsers are included in this page; mention of a specific browser does not imply endorsement or recommendation.
| 2023-01-23T00:00:00 |
https://rules.cityofnewyork.us/rule/automated-employment-decision-tools-updated/
|
[
{
"date": "2023/01/23",
"position": 46,
"query": "government AI workforce policy"
}
] |
|
Civic Tech Institute
|
Civic Tech Institute
|
https://www.equitechfutures.com
|
[] |
Whether you want to develop effective policies for a city government ... Our alumni have gone on to land top internships, fellowships, and jobs in AI, policy, and ...
|
Classes are scheduled between 13:00 UTC and 16:00 UTC on Fridays, Saturdays, Sundays, and Mondays. We oriented our coursework toward the weekends this year in order to accommodate working professionals in our program. However, if the class time overlaps with your scheduled work hours, we ask that you have a conversation with your supervisor before accepting your place in the program to ensure you will be allowed the flexibility over these 10 weeks to attend class fully without work distractions and with your video camera on. In the past, many employers have made this accommodation when they consider the growth you will achieve.
| 2023-01-23T00:00:00 |
https://www.equitechfutures.com/programs/cti
|
[
{
"date": "2023/01/23",
"position": 82,
"query": "government AI workforce policy"
}
] |
|
Job types - Anomaly detection
|
Elastic Docs
|
https://www.elastic.co
|
[] |
Generative AI. Prototype and integrate with LLMs faster using search AI ... Binding the jobs together into a multi-metric job has the advantage of an ...
|
Job types
Stack Serverless
Anomaly detection jobs have many possible configuration options which enable you to fine-tune the jobs and cover your use case as much as possible. This page provides a quick overview of different types of anomaly detection jobs and their capabilities. The job types available in Kibana are:
single metric jobs,
multi-metric jobs,
population jobs,
advanced jobs,
categorization jobs,
rare jobs,
geo jobs.
Every anomaly detection job has at least one detector. A detector defines the type of analysis that occurs (for example, using max , average , or high functions) and the field in your data that is analyzed. Single metric jobs have exactly one detector. These jobs are best for detecting anomalies in one aspect of your time series data. For example, you can monitor the request rate in your log data with the low_count function to find unusually low request rates that might be a sign of an error. Refer to the Function reference to learn more about the available functions.
Multi-metric jobs can have more than one detector configured and optionally split the analysis by a field. Conceptually, multi-metric jobs can be considered as multiple independent single metric jobs. Binding the jobs together into a multi-metric job has the advantage of an overall anomaly score (instead of an independent anomaly score for each job) and influencers that apply to all metrics in the job. Multi-metrics jobs provide better results when the influencers are shared across the detectors.
Splitting the analysis by a field enables you to model each value of that field independently. For example, you can split the analysis of your log data set by the host field which results in independent baselines for each host (each value of the host field) in your data set. If you have a count function that detects anomalies in the error_code field, and your data is split by the host field, then the unusual number of events in the error_code field is reported in the context of each host independently. In this case, an observed anomaly in one host does not affect the baseline of another host.
Multi-metric jobs are recommended for complex use cases where you want to detect anomalous behavior in multiple aspects of your data or analyze the data in the context of distinct values of a field.
In the case of the population jobs, the analyzed data is split by the distinct values of a field. This field defines what is called a population. The splits are analyzed in the context of all the splits to find unusual values in the population. In other words, the population analysis is a comparison of an individual entity against a collective model of all members in the population as witnessed over time.
For example, if you want to detect IP addresses with unusual request rates compared to the number of requests coming from other IP addresses, you can use a population job. That job has a count function to detect unusual number of requests and the analysis is split by the client_ip field. In this context, an event is anomalous if the request rate of an IP address is unusually high or low compared to the request rate of all IP addresses in the population. The population job builds a model of the typical number of requests for the IP addresses collectively and compares the behavior of each IP address against that collective model to detect outliers.
Refer to Performing population analysis to learn more.
Advanced jobs give you all the flexibility that’s possible in the create anomaly detection jobs API. At the extreme, you can switch to directly edit the JSON that will be sent to this endpoint. All the other types of jobs described in this page can be created as advanced jobs, but the more specialized wizards make it easier to create jobs for common situations. You can create an advanced job if you are familiar with all the functionality that machine learning anomaly detection provides and want to do something that the more specialized wizards do not allow you to do.
Categorization jobs cluster similar text values together, classify them into categories, and detect anomalies within the categories. Categorization works best on machine-written text like log messages that typically contains repeated strings of text; it does not work well on human-generated text because of its high variability.
The model learns the normal volume and pattern of a category over time so the job can detect anomalous behavior, such as an unusual number of events in a category by using the count function or messages that rarely occur by using the rare function.
Refer to Detecting anomalous categories of data to learn more.
Rare anomaly detection jobs detect rare occurrences in time series data. Rare jobs use the rare or freq_rare functions and detect such events in populations as well. A rare job finds events in simple time series data that occur rarely compared to what the model observed over time. A rare in a population job finds members of a population that have rare values over time compared to the other members of the population. The frequently rare in a population job detects rare events that frequently occur for a member of a population compared to other members. As an example of this last type of rare job, you can create one that models URI paths and client IP interactions and detects a rare URI path that is visited by very few client IPs in the population (this is the reason why it’s rare). The client IPs that have many interactions with this URI path are anomalous compared to the rest of the population that rarely interact with the URI path.
| 2023-01-23T00:00:00 |
https://www.elastic.co/docs/explore-analyze/machine-learning/anomaly-detection/ml-anomaly-detection-job-types
|
[
{
"date": "2023/01/23",
"position": 63,
"query": "generative AI jobs"
}
] |
|
ChatGPT and the sweatshops powering the digital age
|
ChatGPT and the sweatshops powering the digital age
|
https://www.aljazeera.com
|
[
"Nanjala Nyabola",
"Nanjala Nyabola Is A Political Analyst",
"The Author Of",
"Digital Democracy",
"Analogue Politics ."
] |
The latest ChatGPT revelations are yet another reminder of the pervasive labour exploitation in digital innovation.
|
On January 18, Time magazine published revelations that alarmed if not necessarily surprised many who work in Artificial Intelligence. The news concerned ChatGPT, an advanced AI chatbot that is both hailed as one of the most intelligent AI systems built to date and feared as a new frontier in potential plagiarism and the erosion of craft in writing.
Many had wondered how ChatGPT, which stands for Chat Generative Pre-trained Transformer, had improved upon earlier versions of this technology that would quickly descend into hate speech. The answer came in the Time magazine piece: dozens of Kenyan workers were paid less than $2 per hour to process an endless amount of violent and hateful content in order to make a system primarily marketed to Western users safer.
It should be clear to anyone paying attention that our current paradigm of digitalisation has a labour problem. We have and are pivoting away from the ideal of an open internet built around communities of shared interests to one that is dominated by the commercial prerogatives of a handful of companies located in specific geographies.
In this model, large companies maximise extraction and accumulation for their owners at the expense not just of their workers but also of the users. Users are sold the lie that they are participating in a community, but the more dominant these corporations become, the more egregious the unequal power between the owners and the users is.
“Community” increasingly means that ordinary people absorb the moral and the social costs of the unchecked growth of these companies, while their owners absorb the profit and the acclaim. And a critical mass of underpaid labour is contracted under the most tenuous conditions that are legally possible to sustain the illusion of a better internet.
Advertisement
ChatGPT is only the latest innovation to embody this.
Much has been written about Facebook, YouTube and the model of content moderation that actually provided the blueprint for the ChatGPT outsourcing. Content moderators are tasked with consuming a constant stream of the worst things that people put on these platforms and flagging it for takedown or further actions. Very often these are posts about sexual and other kinds of violence.
Nationals of the countries where the companies are located have sued for the psychological toll that the work has taken on them. In 2020, Facebook, for example, was forced to pay $52m to US employees for the post-traumatic stress disorder (PTSD) they experienced after working as content moderators.
While there is increasing general awareness of secondary trauma and the toll that witnessing violence causes people, we still don’t fully understand what being exposed to this kind of content for a full workweek does to the human body.
We know that journalists and aid workers, for example, often return from conflict zones with serious symptoms of PTSD, and that even reading reports emerging from these conflict zones can have a psychological effect. Similar studies on the impact of content moderation work on people are harder to complete because of the non-disclosure agreements that these moderators are often asked to sign before they take the job.
We also know, through the testimony provided by Facebook whistle-blower Frances Haugen, that its decision to underinvest in proper content moderation was an economic one. Twitter, under Elon Musk, has also moved to slash costs by firing a large number of content moderators.
The failure to provide proper content moderation has resulted in social networking platforms carrying a growing amount of toxicity. The harms that arise from that have had major implications in the analogue world.
In Myanmar, Facebook has been accused of enabling genocide; in Ethiopia and the United States, of allowing incitement to violence.
Indeed, the field of content moderation and the problems it is fraught with are a good illustration of what is wrong with the current digitalisation model.
The decision to use a Kenyan company to teach a US chatbot not to be hateful must be understood in the context of a deliberate decision to accelerate the accumulation of profit at the expense of meaningful guardrails for users.
These companies promise that the human element is only a stopgap response before the AI system is advanced enough to do the work alone. But this claim does nothing for the employees who are being exploited today. Nor does it address the fact that people – the languages they speak and the meaning they ascribe to contexts or situations – are highly malleable and dynamic, which means content moderation will not die out.
Advertisement
So what will be done for the moderators who are being harmed today, and how will the business practice change fundamentally to protect the moderators who will definitely be needed tomorrow?
If this is all starting to sound like sweatshops are making the digital age work, it should – because they are. A model of digitalisation led by an instinct to protect the interests of those who profit the most from the system instead of those who actually make it work leaves billions of people vulnerable to myriad forms of social and economic exploitation, the impact of which we still do not fully understand.
It’s time to lay to rest the myth that digitalisation led by corporate interests is somehow going to eschew all the past excesses of mercantilism and greed simply because the people who own these companies wear T-shirts and promise to do no evil.
History is replete with examples of how, left to their own devices, those who have interest and opportunity to accumulate will do so and lay waste to the rights that we need to protect the most vulnerable amongst us.
We have to return to the basics of why we needed to fight for and articulate labour rights in the last century. Labour rights are human rights, and this latest scandal is a timely reminder that we stand to lose a great deal when we stop paying attention to them because we are distracted by the latest shiny new thing.
The views expressed in this article are the author’s own and do not necessarily reflect Al Jazeera’s editorial stance.
| 2023-01-23T00:00:00 |
2023/01/23
|
https://www.aljazeera.com/opinions/2023/1/23/sweatshops-are-making-our-digital-age-work
|
[
{
"date": "2023/01/23",
"position": 12,
"query": "AI labor union"
}
] |
Amazon union fight continues despite workers' win
|
Amazon union fight continues despite workers' win
|
https://www.bbc.com
|
[] |
Amazon Labor Union leader Chris Smalls says it's time for the firm "to come to the table and negotiate".
|
Amazon union fight continues despite workers' win
24 January 2023 Share Save Natalie Sherman & Michelle Fleury Business reporters, New York Share Save
Reuters Chris Smalls led workers in New York who won a contest in April 2022 to establish the first Amazon union in the US
It has been almost a year since workers at an Amazon warehouse in New York voted to start the company's first-ever labour union in the US - an historic labour victory that won global attention. But the fight remains unfinished.
Amazon has been battling the outcome of the election in legal actions.
Efforts to organise workers at other warehouses, including one just across the street, have failed.
Negotiations with the company over a labour contract for the warehouse workers have yet to start - and, when they do, are expected to take years.
Former Amazon worker Chris Smalls, who started the union after the company fired him during the pandemic, takes the lack of progress in his stride.
"We know we're dealing with a trillion dollar company that is going to spend X amount of dollars to try to stop a union from taking place so the timing is just about what we expected," he says.
Earlier this month, regulators finally certified the victory of the Amazon Labor Union at JFK8, the warehouse on Staten Island that employs roughly 8,000 people.
Amazon, which has argued that regulators unfairly tilted the result of the election against the company, plans to appeal. This week the deadline it was facing was extended two more weeks.
"We knew it was unlikely that the NLRB (National Labor Relations Board) regional office would rule against itself, and intend to appeal," spokeswoman Kelly Nantel said.
"As we've said since the beginning, we don't believe this election process was fair, legitimate, or representative of the majority of what our team wants."
Amazon Labor Union leaders Derrick Palmer (left) and Chris Smalls
The state of play is indicative of the ongoing questions about the future of America's labour movement.
Despite an uptick in organising activity, the share of workers who are members of unions has continued its decades-long decline, falling to 10.1% last year, from 10.3% in 2021.
That is the lowest rate on record and roughly half what it was when the government started tracking the figures in 1983.
But there are some signs that labour organisers have made inroads.
More than 70% of Americans now support labour unions - the highest share since 1965, according to a 2022 Gallup poll.
Petitions from workers to start unions at their workplaces jumped 53% in the 12 months to October, to more than 2,510 - the highest number since 2016, the NLRB said.
And in the private sector, the number of workers who are members of unions actually increased by nearly 200,000 last year - the first rise in nearly a decade, driven by gains in sectors including transportation and warehousing.
Those gains did not keep pace with the overall growth of the workforce though, which expanded at a rapid clip last year.
Cathy Creighton, director of Cornell University's Industrial and Labor Relations Buffalo Co-Lab and former field attorney for the NLRB, says US law favours employers, making it unlikely that the activity will result in long-term gains for the labour movement.
The law does not even have a mechanism to force companies to agree a contract with workers, she says.
"I'm not saying there's not a movement afoot, but the question is: how will it go in the long run?" she says.
"Corporate America is fighting back hard and the government is not on the workers' side at this point, unless the American people realise what's happening, realise the barrier and ask their elected officials to change the law."
She says companies often successfully sap momentum from labour movements simply by running down the clock.
In this case, it has been nearly three years since Mr Smalls worked for Amazon, and the celebrity status he has since acquired has sparked accusations that he has become disconnected from work issues. Derrick Palmer, another top leader at Amazon Labor Union, has been suspended from work since late last year while the company investigates a worker dispute.
Mr Smalls rejects suggestions that Amazon's waiting game will succeed, pointing to new union campaigns in Minnesota and California. He is also due to visit the UK this week, where workers are planning their first-ever walkout.
"Their plan is to stall as long as they can but we're going to be creative on our end as well. That's what's gotten us here," he says.
| 2023-01-23T00:00:00 |
https://www.bbc.com/news/business-64340884
|
[
{
"date": "2023/01/23",
"position": 87,
"query": "AI labor union"
}
] |
|
Layoff Storm: The Season When Apologies Rained & Jobs ...
|
Layoff Storm: The Season When Apologies Rained & Jobs Fell
|
https://analyticsindiamag.com
|
[
"Shritama Saha",
"Shritama",
"She Her",
"Is A Technology Journalist At Aim Who Is Passionate To Explore Generative Ai With A Special Focus On Big Techs",
"Database",
"Healthcare",
"De I",
"Hiring In Tech"
] |
The company cited a need to refocus on key areas such as artificial intelligence amid economic uncertainty as the reason for the layoffs. However, the layoffs ...
|
The tech layoffs seem to be getting out of hand for big techs. Major players, including the likes of Amazon, Google, Twitter, Microsoft, and Salesforce, have collectively let go of about 55,000 employees worldwide, that is, close to 3-6 percent of their total headcount.
Amid the fears of a global recession in 2023, many tech behemoths, including Microsoft, Spotify, Amazon, Meta, Lyft, HP, Twitter, Salesforce, and Cisco, were compelled to implement mass layoffs. Companies such as Netflix and Adobe too felt the heat of these cutbacks. While Cisco reduced its workforce by 5%, Salesforce announced plans to trim the employee count by 10%. Music streaming platform Spotify has also said that it will shed 6 percent of its workforce, that is, 588 people.
In a global restructuring effort, Twitter eliminated 7,500 positions, leaving a skeletal 20 staff members in India. Meta, too, let go of 11,000 employees. Interestingly, Apple, which is on a hiring freeze, seems to have not laid off any employees so far.
Tech Layoffs Begin
Alphabet, the parent organisation of Google, recently implemented a 6% reduction in its global workforce, cutting 12,000 jobs. These layoffs will likely impact Alphabet and Google’s products like Google Cloud, Chrome, Search, and Android owing to macroeconomic conditions and changing customer priorities.
CEO Sundar Pichai wrote in his mail, “Over the past two years, we’ve seen periods of dramatic growth. To match and fuel that growth, we hired for a different economic reality than the one we face today.”
(A snapshot of an email sent by Alphabet chief Sundar Pichai amid the layoffs)
In a move that mimics the actions of many other tech giants, Microsoft CEO Satya Nadella announced the decision to lay off a total of 10,000 employees, that is, 5 percent of its workforce dominating the HoloLens, engineering, HR, advertising and marketing space by Q3 2023. The company cited a need to refocus on key areas such as artificial intelligence amid economic uncertainty as the reason for the layoffs.
However, the layoffs have raised eyebrows, as the entire team behind the virtual reality platform AltspaceVR and the Mixed Reality Tool Kit have been fired. This raises questions about the future of Microsoft’s HoloLens technology, which is already facing challenges in maintaining its military contract with the US government.
Although the company has several lucrative bets in hand, like $10 billion in AI research lab OpenAI, it reported the slowest growth in the last quarter with $50.1 revenue (11 percent increase). Despite this, the company’s growth has slowed in recent quarters, with revenue increasing by just 11 percent in the last quarter. In addition, the news of the layoffs sent Microsoft’s stock price down by 2 percent, which has seen a 22 percent decline over the past year. However, the company’s performance is still stronger than many of its peers in the tech industry.
(A snapshot of the email sent by Satya Nadella to his employees, addressing the recent layoffs)
As the calendar flipped to 2023, e-commerce giant Amazon too announced a significant shift in its workforce strategy, revealing plans to terminate 18,000 positions – a staggering 80 percent increase from the previously disclosed 10,000 job cuts. The decision was made in response to the mounting inflationary pressures and ovehiring during the pandemic. This marks the largest round of recent layoffs for any technology company. The impact of these cuts will be felt across the organisation, with an estimated 3 percent of corporate employees set to lose their jobs. A majority of the layoffs will occur within Amazon Stores and PXT departments.
Apple’s Immunity to Layoffs
Interestingly, the only tech giant to have announced zero layoffs is Apple. While other companies were doubling and tripling their workforce amid the pandemic, Apple stayed afloat and played it strategically.
Between 2020 and 2022, the company made prudent hiring decisions, resulting in a workforce growth of 20 percent to approximately 164,000 employees, a 6.5 percent increase from the previous year. In comparison, rival companies such as Amazon, Microsoft, Google, and Meta saw significant increases in their employee count, resulting in overhiring. During this period, Amazon doubled its workforce, while Microsoft grew by 53 percent, Google swelled by 57 percent, and Meta saw an insane growth of 94 percent.
In June 2022, Microsoft’s workforce bulked up to 221,000 employees, a significant leap of 40,000 from the previous year. This followed a steady upward trend, with a notable 11 percent increase in the number of employees added the year prior. Likewise, Amazon saw a substantial 38 percent growth in its workforce, adding 310,000 jobs in 2021. Google and Meta also went on a hiring spree, with Meta bringing in 13,000 new employees and Google adding 21,000 workers in 2021.
Simply put, Apple did not overhire. It added employees much slower than its peers, who went for aggressive expansion during the pandemic. Apple’s hiring approach is in line with its tendency to operate with a lean workforce and focus on hardware products and sales, which have largely been insulated from the economic downturn. The company has not undergone significant mass layoffs since 1997, when co-founder Steve Jobs returned and decided to cut 4,100 employees to manage expenses.
As the company prepares to report its first quarterly sales decline in over three years in February, it is also moving forward with its augmented-reality headset and car project, albeit at a more measured pace.
Although Apple did not cut jobs, its subsidiary Intrinsic, specialising in robot software, announced an impending shedding of 40 employees, reducing 20 percent of its workforce. Verily, its life sciences division, has scaled back its operations by 15 percent, resulting in a loss of 240 jobs.
Who is to blame?
Companies such as Google, Uber, Tesla, and Amazon were forced to cut costs by laying off thousands of workers, including high-skilled and expensive employees. Over 1,000 tech companies in total fired more than 150,000 workers.
As the world was thrown into chaos by the pandemic, technology giants scrambled to meet the surging demand for their products and services. In their haste, they overhired, bringing on more employees than they truly needed. Now, as the economy struggles and demand for their products wanes, these same companies are laying off employees.
But who is to blame for this season of layoffs? Is it the leaders who made the hasty hiring decisions or the employees who are now paying the price for those mistakes?
| 2023-01-23T00:00:00 |
2023/01/23
|
https://analyticsindiamag.com/ai-hiring/layoff-storm-the-season-when-apologies-rained-jobs-fell/
|
[
{
"date": "2023/01/23",
"position": 79,
"query": "AI layoffs"
}
] |
Microsoft has laid off entire teams behind Virtual, Mixed ...
|
Microsoft has laid off entire teams behind Virtual, Mixed Reality, and HoloLens
|
https://www.windowscentral.com
|
[
"Jez Corden",
"Executive Editor",
"Social Links Navigation"
] |
In the latest update on the massive Microsoft layoffs, it seems Redmond has gutted the teams behind HoloLens and Mixed Reality ... AI solutions engineers · In ...
|
What you need to know
In the latest update in the massive Microsoft layoffs, we now have a better idea of how deep the cuts run in Microsoft's Mixed Reality team.
The team behind AltSpaceVR and also the Mixed Reality Tool Kit have been laid off in their entireties.
Potentially, these layoffs throw serious doubt on the future of HoloLens, which is currently struggling to retain its military contract with the U.S. government.
The scale of the Microsoft layoffs keeps revealing itself through social media posts, as we get to grips with just how deep and broad Microsoft is looking to restructure.
This past week, Microsoft revealed its joining Amazon, Google, and others in laying off thousands of employees. The cuts reduces Microsoft's global workforce by 5%, which grew rapidly to take advantage of opportunities that were presented during the pandemic. With work-from-home culture ending, inflation spiraling, and Putin's war of aggression in Ukraine disrupting energy markets, Big Tech is scaling back to keep shareholders happy in a tough economic environment.
Microsoft is rearranging its bets for the future of the company as a result. Despite having acquired AltSpaceVR back in 2017, Microsoft culled the entire team behind the virtual reality workspace project this past week. As a result, AltSpaceVR will shutter for good in March, effectively ending Microsoft's "metaverse" efforts with it. Supposedly, Microsoft Mesh will be AltSpaceVR's successor, but it remains to be seen just how serious the company is about the so-called "metaverse," despite CEO Satya Nadella's buzzword-laden speeches on the topic at recent events.
We have some sad news, Altspacers. #AltspaceVR is shutting down on March 10th. Though we hate saying goodbye, we also feel such pride and gratitude for all the magic that happened here. ✨Thanks for joining us on this epic adventure. #socialvr https://t.co/peCwpaaBl3January 20, 2023
In addition to the death of AltSpaceVR, Microsoft has also culled the entire team behind the popular MRTK framework. MRTK is Microsoft's "Mixed Reality Tool Kit," which is a cross-platform framework for spatial anchors in virtual reality spaces. MRTK was built for Unity VR integrations, and works with Meta's headsets with a focus on HoloLens.
HoloLens has been scaled back already in recent years following the departure of its chief architect Alex Kipman. Microsoft has been pursuing a HoloLens contract with the U.S. military, which was recently scaled back by the U.S. Congress, owing to reported problems with the program.
For Microsoft to cull the entire team behind MRTK, which was due to release a new version just next month, it paints a picture of a company that perhaps no longer believes in virtual reality. There are many who believe the "metaverse" represents the next big opportunity in human-computer interfacing, but even Facebook, who rebranded its entire company to Meta in the belief of this technology, is scaling back in this area as well — laying off 11,000 staff back in November.
| 2023-01-21T00:00:00 |
2023/01/21
|
https://www.windowscentral.com/microsoft/microsoft-has-laid-off-entire-teams-behind-virtual-mixed-reality-and-hololens
|
[
{
"date": "2023/01/23",
"position": 86,
"query": "AI layoffs"
}
] |
McKinsey acquires Iguazio, a leader in AI and machine- ...
|
McKinsey acquires Iguazio, a leader in AI and machine-learning technology
|
https://www.mckinsey.com
|
[] |
The addition of Iguazio's team and technology will help McKinsey dramatically accelerate and scale AI deployments, driving further impact for our clients.
|
This week, McKinsey is excited to welcome Iguazio, a leader in AI and machine learning, to our firm. With the addition of Iguazio’s technology and a team of more than 70 data and AI experts, McKinsey will be able to dramatically accelerate and scale AI deployments, driving further impact for clients.
The pace of change has never been faster. To thrive in today’s competitive market, harnessing the power of AI is essential. According to McKinsey research, more than $490 billion was invested in AI by organizations around the globe from 2012 to 2021. But most business leaders are still struggling to translate these investments into concrete returns, with only 10 percent of AI projects actually emerging from the lab and succeeding in real business environments.
As a leader in the technology space, QuantumBlack, AI by McKinsey has been working with clients for more than a decade to embed AI into real-time decision making to help solve the world’s most challenging problems. But one key question remained unanswered: how do organizations successfully deploy and scale AI to unlock real business value?
“The answer to this is multi-dimensional. It requires getting many elements right simultaneously – data, algorithms, IT architecture, capabilities, change management, and domain expertise,” explains Alexander Sukharevsky, McKinsey senior partner and global co-leader QuantumBlack. “We have been working on a holistic offering that allows us to master all these dimensions in a very intuitive way, and we have road-tested it with various clients across the globe. Our teams have been working on a solution that automates and accelerates AI development, deployment, putting AI applications into production at scale and in real-time in any environment.”
The Iguazio team (photo by David Garb). The Iguazio team (photo by David Garb)
Working with Iguazio, QuantumBlack will be able to immediately provide clients with industry-specific AI solutions that are five times more productive, eight times faster from proof-of-concept to production, and twice as reliable.
“We analyzed more than a 1000 AI companies worldwide and identified Iguazio as the best fit to significantly accelerate our AI offering – from the initial concept to production, in a simplified, scalable and automated manner,” says Ben Ellencweig, McKinsey senior partner and QuantumBlack global leader of alliances and acquisitions. “Iguazio has a state-of-the-art technology that has generated significant market traction with some of our marquee clients and earned them top-industry recognition. Strengthening our offering with Iguazio will allow us to present to the market the first holistic solution globally that helps any organization truly harness the full potential of AI.”
Creating value beyond the hype Let’s deliver on the promise of technology from strategy to scale.
Over time, the Iguazio and QuantumBlack teams will be fully integrated, working from a single product roadmap, to bring together the best technology assets of each firm into a single product. Our new offering will allow us to integrate AI in real-time decision making and capture full value to help clients drive sustainable and inclusive growth.
Inside our new offering Here’s one scenario that illustrates what McKinsey can now do for clients. Previously, a manufacturing company with 200 locations around the world would have had to implement an AI solution at one setting and then develop, tailor, and redeploy it for each successive facility, with limited ability to monitor its performance. With Iguazio, data scientists and engineers around the world can now leverage this single platform with common datasets, models, and functions across an entire network of factories, requiring less localization in development along the way and achieving higher impact, faster.
“This acquisition will enable us to implement AI with fewer resources at significantly lower cost,” says Alex Singla, McKinsey senior partner and QuantumBlack global co-leader. “This is especially meaningful for companies experiencing a critical shortage of tech talent, one of the reasons many AI projects have been delayed.”
This is McKinsey’s first acquisition in Israel. Our newly extended team will serve as the foundation for a new QuantumBlack location, which McKinsey expects to expand and grow in the coming years. “Attracting exceptional tech talent and expanding our tech ecosystem will enable us to welcome colleagues from around the globe to Tel Aviv’s exciting tech scene,” says Matt Fitzpatrick, McKinsey senior partner and QuantumBlack Labs global co-leader.
Iguazio’s four co-founders – CEO Asaf Somekh, along with CTO Yaron Haviv, COO Yaron Segev, and VP Architecture Orit Nissan-Messing – have been working together since 2001, both in their own startups and across multiple organizations, and have developed some of the core technologies of enterprise analytics and AI.
Iguazio founders, from left: Yaron Haviv, CTO; Yaron Segev, COO; Orit Nissan-Messing, VP architecture; Asaf Somekh, CEO (photo by Yanai Yechiel). Iguazio founders, from left: Yaron Haviv, CTO; Yaron Segev, COO; Asaf Somekh, CEO; Orit Nissan-Messing, VP architecture (photo by Yanai Yechiel)
They have seen firsthand, and know how to overcome, the organizational challenges of using AI. “From a values perspective, we are always thinking first about ‘what are our clients’ needs, not just now but a year from today?’ And we have cultivated a production-first platform that is geared towards automation and acceleration of the data science process end-to-end, serving as a foundation for clients to scale their AI initiatives quickly and easily across the entire company,” says Asaf. “We’re thrilled to join the McKinsey family and help clients see real business value from their AI initiatives.”
For Iguazio colleagues, joining McKinsey offers the chance to deliver greater value to more enterprise clients around the world. “We have spent years developing and refining our technology. This is an opportunity for wider adoption, better vertical solution integration, and, together with McKinsey’s team, making it simpler for enterprises to generate real business value from AI with far less overhead.” adds Orit.
Last month, Forrester designated McKinsey a “leader” among AI service providers. “McKinsey’s acquisition of Iguazio and its transformative technology is a testament to the firm’s commitment to helping enterprises build their businesses around data and AI to drive greater efficiency and accelerate delivery of modern and innovative services to market,” says Yaron Haviv.
“The next phase of AI innovation is among us,” says Alex Sukharevsky. “And we’re proud to be leading this journey.”
| 2023-01-23T00:00:00 |
https://www.mckinsey.com/about-us/new-at-mckinsey-blog/mckinsey-acquires-iguazio-a-leader-in-ai-and-machine-learning-technology
|
[
{
"date": "2023/01/23",
"position": 8,
"query": "artificial intelligence business leaders"
}
] |
|
Perspectives about the NIST Artificial Intelligence Risk ...
|
Perspectives about the NIST Artificial Intelligence Risk Management Framework
|
https://www.nist.gov
|
[] |
“As business leaders begin their AI journey, many are looking for a roadmap for how to develop and use AI in a way that is responsible and innovative. At ...
|
The success of the AI Risk Management Framework (AI RMF 1.0) depends upon its widespread use. Below are statements from interested organizations and individuals.
“As business leaders begin their AI journey, many are looking for a roadmap for how to develop and use AI in a way that is responsible and innovative. At Workday, we’ve found the NIST AI Risk Management Framework to be a concrete benchmark for mapping, measuring, and managing our approach to AI governance. We believe the Framework will help us maintain our customers’ trust and stay true to our company’s core values as we leverage it to innovate going forward”.
Jim Stratton, Chief Technology Officer, Workday
See a description of how Workday has been using the AI RMF.
“The automotive industry continues to leverage the power of artificial intelligence in driver support features, advanced safety technologies, and automated driving systems for consumers. The Artificial Intelligence Risk Management Framework (“AI RMF”) represents a proactive, comprehensive, and holistic approach, and we appreciate its development by NIST through a transparent, multistakeholder, and consensus-driven process. The AI RMF will be an important resource to the automotive industry in its ongoing efforts to maximize the benefits and positive impacts of artificial intelligence products, services, and systems and to effectively communicate with policymakers and other external stakeholders.”
The Alliance for Automotive Innovation
"On behalf of Amazon Web Services, I would like to commend the NIST for the recent publication of the AI Risk Management Framework. At a time when AI leadership is more important than ever, the AI RMF is both a vital statement of United States policy and a critical resource for organizations involved in the development, deployment, and use of AI. The AI RMF’s lifecycle-based approach to managing the risks and enhancing the benefits of AI aligns closely with AWS’s approach to responsible AI and the tools and technical guidance we provide customers. We see great promise in the AI RMF and look forward to supporting NIST’s efforts to develop testing, evaluation, and benchmarks that will be crucial as organizations seek to operationalize and measure the impacts of the Framework."
Amazon Web Services
“The Bipartisan Policy Center is pleased to see the launch of the Artificial Intelligence (AI) Risk Management Framework by the National Institute of Standards and Technology (NIST). This voluntary Framework is a key step forward in addressing some of the issues of bias, fairness, privacy, security, and more. It will be a valuable tool in managing AI's negative and positive impacts and promoting trustworthiness in the technology.
We support NIST’s approach to developing this Framework by opening a dialogue and gathering feedback from a multidisciplinary set of stakeholders. Its approach ensures the Framework is inclusive of all impacted stakeholders throughout the lifecycle of an AI system and considers the potential impact of AI on different groups of people.
BPC is committed to promoting and implementing this Framework with our network and stakeholders. We will complement the work by NIST in our continued work to promote responsible, ethical, and trustworthy AI systems. We look forward to working with NIST to ensure continuous improvement of the Framework.”
Bipartisan Policy Center
“The NIST AI Risk Management Framework (AI RMF) constructively builds upon the work BSA has done in the Framework to Build Trust in AI, together offering an important path forward for the responsible development and deployment of AI products and services. The AI RMF, like the BSA Framework, creates a lifecycle approach for addressing AI risks, identifies characteristics of Trustworthy AI, recognizes the importance of context-based solutions, and acknowledges the importance of impact assessments to identify, document, and mitigate risks.
This approach is well-aligned with BSA’s Framework to Build Trust in AI, which emphasizes the need to focus on high-risk uses of AI, highlights the value of impact assessments, and distinguishes between the obligations for those companies that develop AI, and those entities that deploy AI.
We appreciate the opportunity to engage with NIST to help promote the responsible development of AI and look forward to working with BSA members to determine how best to promote the AI RMF and draw from other best practices to advance consistent approaches around the world.”
BSA | The Software Alliance
“The Center for Security and Emerging Technology (CSET), based at Georgetown University, has been actively involved in the development of the NIST AI Risk Management Framework (AI RMF 1.0). With confidence, CSET can affirm that one of the framework's strengths is that it provides sufficient details so that organizations can use it as a foundation to build more customized risk management approaches. This is important because AI risk management is highly context-dependent, and the implementation of the RMF is likely to be unique for each organization and each AI system. This balance allows organizations to begin devising steps for risk management and considering how the framework can be adapted to their purposes and context.
CSET is planning to use the Framework to manage AI risks and improve AI trustworthiness, as a part of its work on AI assessment, by developing high-level guidance for how organizations can customize and create contextually-appropriate RMF profiles. In addition, CSET intends to identify the high-level variables or features that affect RMF profile customization. These features may include the sector in which an AI system is applied or the features of the technology itself, such as its maturity or complexity. Applications of these features should allow organizations to more easily identify existing RMF profiles that are relevant to their needs and identify gaps in guidance that new profiles could fill. Finally, CSET's ongoing effort to create a taxonomy of AI incidents in an accessible database will allow organizations to identify specific vulnerabilities and issues that should be addressed in their custom RMF profiles.”
Center for Security and Emerging Technology (CSET)
“The Chamber appreciates the hard work that NIST put into the development of the congressionally directed AI Risk Management Framework. NIST established an open and transparent process where all AI stakeholders have the opportunity to provide substantive input on framing and mitigating risks associated with using Artificial Intelligence. This open and transparent model should serve as a template for others throughout the federal government.
Today’s announcement of the AI Risk Management Framework 1.0 is an essential step in developing Trustworthy AI. The Chamber looks forward to continuing to work with NIST to update the framework to meet the challenges of tomorrow and ensure that the United States leads in the development of trustworthy AI globally.”
U.S. Chamber of Commerce
"Credo AI welcomes the release of the NIST Artificial Intelligence Risk Management Framework 1.0 - an important step in making Responsible AI governance a reality - and we applaud the NIST team for their open and extensive collaboration with stakeholders throughout its development. The AI RMF 1.0 is a critical step toward helping organizations effectively manage risks in designing, developing, and using AI products, services and systems. In particular, the AI RMF 1.0 provides valuable guidance to small and medium businesses, which promote a great deal of AI innovation, yet often lack the resources or extensive in-house expertise in AI governance and risk management. We have partnered closely with NIST to ensure that we are ready to operationalize the AI RMF 1.0 with companies of all sizes, across industries, in every stage of Responsible AI design. Credo AI helps organizations design, develop, and deploy AI systems that meet the highest ethical standards, and guiding our customers in adopting the NIST AI RMF is critical to this mission. We look forward to continuing to partner with NIST in helping to make the AI RMF 1.0 an accessible and easy-to-adopt reality for organizations at all stages of AI maturity."
Navrina Singh, Founder and CEO, Credo AI
“As the nation’s wireless industry association, CTIA applauds NIST for developing a risk management framework for AI that aims to be flexible, voluntary, and pro-innovation. CTIA appreciates NIST’s consensus-based, collaborative approach that considered important stakeholder feedback, as it has done with its Cybersecurity Framework. CTIA looks forward to continuing to work with NIST on approaching AI risk management.”
CTIA
“We applaud the hard work by the tireless and committed staff and leadership at NIST and the Department of Commerce to bring this AI RMF to fruition. This Framework's release is a significant step in ensuring that the AI that permeates our daily activity and increasingly supports our pivotal functions is safer, more trustworthy and inclusive. Not only is the Framework notable but so was the process that led to its creation, throughout which NIST modeled best practices, including open, transparent, trust-building and inclusive engagement. We look forward to continuing to support this important work underway at NIST, including the operationalization of a framework that can be critical in our realization of responsible AI.”
Miriam Vogel, President & CEO, EqualAI
“The Federation of American Scientists is pleased to see the National Institute of Standards and Technology's release of the AI Risk Management Framework (AI RMF 1.0). We believe that this framework is an important step in promoting responsible and trustworthy use of AI. At FAS, we are dedicated to promoting the responsible use of science and technology, and we intend to review and advance the guidelines outlined in the AI RMF. Furthermore, we look forward to participating in future discussions and continuing our collaboration with NIST and other organizations to guarantee the safe and ethical use of AI. We acknowledge the effort and collaboration that went into the development of the AI RMF and are confident that it will serve as a valuable resource for organizations and individuals in the field.”
Federation of American Scientists
“The Future of Life Institute applauds NIST for spearheading a multi-year and stakeholder initiative to improve the management of AI risks. As an active participant in the AI RMF process, we view this effort as a crucial step in fostering a culture of risk identification and mitigation within the US and abroad. Furthermore, we praise NIST's commitment to continuously update the RMF as our common understanding of AI's impact on society evolves. With this launch, it is our hope that all organizations charged with designing, developing, deploying, or using AI will actively consider the short, medium, and long-term implications of this technology on individuals, communities, and the planet. Failure to do so may have consequential and existential effects on the future of life as we know it.”
Future of Life Institute
“Google congratulates NIST on the release of its AI Risk Management Framework (RMF) and for its broad engagement across stakeholders. Within Google, we’ve built an AI and advanced technologies governance program that is aligned with the AI RMF approach and underpinned by industry-leading research and a growing library of resources, tools and recommended practices. Importantly, the NIST approach, which has been successful in cybersecurity and privacy, is flexible and can adapt as the AI ecosystem progresses. The AI RMF provides guidance to developers and deployers of AI systems on how to strike a practical balance between optimizing beneficial use cases and addressing potential risks. We look forward to our continued work with NIST as the AI ecosystem matures, new techniques and applications are developed, and further progress is made on benchmarks and metrics for AI systems.”
Google
“IBM applauds NIST on the release of the AI Risk Management Framework, and on the multi-year, inclusive, multistakeholder process that contributed to its development. We are happy to have contributed to that process throughout the last few years and gratified to see the Framework come to fruition. This initiative lays important groundwork for advancing trustworthy AI and showcasing the United States’ commitment to the responsible development and deployment of this crucial technology. IBM commends NIST for its tireless effort in developing this framework and looks forward to helping to promote it as best-in-class practices for both AI developers and deployers.”
IBM
Video remarks from IBM
“Building trustworthy Artificial Intelligence (AI) technology in the era of digital transformation is essential. As this technology evolves, we take seriously our responsibility to enable a world in which AI is used responsibly and develop solutions to address potential negative implications. The National Institute of Standards and Technology’s (NIST) AI Risk Management Framework is a critical voluntary, flexible tool to help industry and other stakeholders understand, identify, and treat the potential for negative outcomes while leveraging opportunities associated with the use of AI systems. We appreciate NIST’s ongoing engagement with industry throughout the Framework’s development and encourage its adoption in the United States and around the world to help foster trustworthy AI systems and their responsible use.”
John Miller, Senior Vice President for Policy for Trust, Data, and Technology at Information Technology Industry Council
“The NIST AI Risk Management Framework represents a collaborative, thoughtful approach to addressing the socio-technical nature of AI systems. At Microsoft, we especially appreciate the focus on impact assessments and testing of AI systems, which will support organizations in identifying risk, developing mitigations, and validating capabilities. These are approaches we are already putting into practice through our Responsible AI Standard. We commend NIST’s efforts to align the AI Risk Management Framework with its Cybersecurity and Privacy Frameworks to further enable organizations to build upon existing frameworks.”
Natasha Crampton, Chief Responsible AI Officer – Office for Responsible AI, Microsoft
"The National Fair Housing Alliance (NFHA) Applauds NIST on the launch of its AI Risk Management Framework (AI RMF 1.0) which helps manage risks to individuals, communities, organizations, society, businesses, and the environment. NFHA provided comments to NIST throughout the various stages of the development of AI RMF 1.0 and is pleased to see the framework addresses discrimination risks and stresses the importance of ensuring systems are fair and managed for bias. Technologies that manifest discrimination and bias can cause great harm which might be intractable. Technology is the new civil rights frontier. Thus, having the AI RMF 1.0 is critically important to help scientists, modelers, researchers, regulators, civil rights experts, compliance professionals, consumers, and other actors identify, assess, and manage risks in AI systems and to help ensure they are fair, beneficial, and equitable. NFHA used concepts from earlier iterations of the AI RMF 1.0 to develop our Purpose, Process, and Monitoring (PPM) framework, which represents what we believe is the gold standard for auditing AI systems. We will use NIST’s AI RMF 1.0, and future iterations, to help update the PPM framework as we apply it to a whole range of systems used in the housing and lending sectors including credit scoring, risk-based pricing, tenant screening, automated underwriting, and advertising models."
Lisa Rice, President & CEO, National Fair Housing Alliance (NFHA)
“As the Nation’s largest non-defense Federal funder of Artificial Intelligence research, NSF is dedicated to the proposition that research ideas be applied fairly, safely, and carefully to real world problems. We support the AI RMF and look forward to its continued development to benefit our research community, as well as for society as a whole.”
National Science Foundation
"The NIST Risk Management Framework will contribute to ensuring that AI systems are deployed safely, responsibly and securely. The Partnership on AI is pleased to have contributed to this critically important framework, building on our work with our Partners. We look forward to working with NIST to support its implementation to improve practice and policy globally."
Rebecca Finlay - CEO, Partnership on AI
Video remarks from Partnership on AI
“The NIST AI Risk Management Framework is the right document at the right time that seeks to provide American leadership in the AI governance space. While having a framework and its associated playbook is a critical first step to managing the potential risk AI can pose to people and organizations, the next step in the process is even more crucial. Now, policy makers, developers, deployers, and consumers must step up and help NIST develop use cases and populate its resource center. These efforts will help all those who build, deploy, and use AI systems to best identify and mitigate potential risk, while unleashing opportunities for the United States to innovate and remain a global AI leader.”
Yll Bajraktari, CEO, Special Competitive Studies Project
“The NIST AI Risk Management Framework provides a valuable tool for understanding the challenges and opportunities presented by different AI systems. The AI RMF has the potential to help organizations of all sizes to work towards trustworthy AI systems that benefit all.”
David Danks, UC San Diego Halıcıoğlu Data Science Institute (HDSI) and Department of Philosophy professor
“Today’s launch of the NIST AI Framework is a major milestone. The Framework creates a common approach for how companies can map, measure, manage, and govern AI risk. In doing so, it promises to accelerate the adoption of trustworthy AI, build bridges with partners around the world, especially in Europe, and pave the way to unlocking the power of AI to help positively transform the way we live and work. We applaud NIST for this achievement; Workday has been pleased to partner with NIST since the early days of the Framework's development, and we look forward to continued collaboration to leverage this valuable tool.”
Sayan Chakraborty, Executive Vice President, Product & Technology, Workday
| 2023-01-23T00:00:00 |
2023/01/23
|
https://www.nist.gov/itl/ai-risk-management-framework/perspectives-about-nist-artificial-intelligence-risk-management
|
[
{
"date": "2023/01/23",
"position": 32,
"query": "artificial intelligence business leaders"
}
] |
Generative AI: a game changer for people, business and ...
|
Generative AI: a game changer for people, business and government
|
https://www.saica.org.za
|
[] |
Generative Artificial Intelligence (AI) has the potential to revolutionise the way businesses and governments operate, enabling them to create new products and ...
|
Johannesburg, Monday, 23 January 2023 - Using OpenAI’s ChatGPT, the response below was generated following the prompt Write the opening paragraph for a media release about how transformative generative AI can be for business and government.
"Generative Artificial Intelligence (AI) has the potential to revolutionise the way businesses and governments operate, enabling them to create new products and services, improve efficiency and decision-making, and drive innovation. This cutting-edge technology has the ability to generate new ideas, designs, and solutions, making it a powerful tool for organisations looking to stay competitive in today's fast-paced digital landscape."
The AI game is evolving thanks to generative AI and other foundation models, which are speeding up application development and giving non-technical people and professionals access to significant capabilities. Developments such as ChatGPT are taking technology into realms once thought to be impossible, and it is expected to continue over time. For example, there are recent reports of an AI (Claude) that has managed to pass a university level law and economic assessment. Using big data and interactions with users, these technologies can respond to searches with original content related to, amongst others, marketing, sales, and client communication; operations such as generating a list of activities for a particular task; information technology like writing, debugging and explaining computer code; risk and legal like answering complex questions; as well as creating content in multiple languages and research and development activities.
SAICA notes and welcomes developments in the Generative AI space, and encourages members and the public to exercise caution as they explore and use technologies that are becoming available. While these technologies represent significant advancement in the world of AI, business, and government alike should be mindful of the risks, ethical and practical challenges that they come with. Generative AI, while presenting exciting and fascinating tools (such as ChatGPT), can generate entirely incorrect information, be biased, and provide unethical advice or responses. Due to the possible inappropriate responses, the use of professional scepticism is necessary when interacting with such technology. These tools can also be used for malicious activities, pose a plagiarism risk, and furthermore, there remains uncertainty regarding laws on AI and the output generated.
Notwithstanding the risks, innovations that generative AI could ignite for businesses and government entities of all sizes and levels of technological proficiency are exciting. Generative AI is expected to have a transformative impact with its ability to generate new ideas, designs, and solutions. It is able to produce text and images, spanning blog posts, program code, poetry, and artwork. For the accountancy profession, this technology holds enormous potential to revolutionise the way we approach financial analysis and decision-making, enabling the profession to save time and create value. With its ability to quickly process large amounts of data and identify patterns, generative AI can help us make more informed decisions, streamline processes, and improve overall efficiency.
About SAICA
The South African Institute of Chartered Accountants (SAICA), South Africa’s pre-eminent accountancy body, is widely recognised as one of the world’s leading accounting institutes. The Institute provides a wide range of support services to more than 50 000 members and associates who are chartered accountants (CAs[SA]), as well as associate general accountants (AGAs[SA]) and accounting technicians (ATs[SA]), who hold positions as CEOs, MDs, board directors, business owners, chief financial officers, auditors and leaders in every sphere of commerce and industry, and who play a significant role in the nation’s highly dynamic business sector and economic development.
Chartered Accountants are highly valued for their versatile skill set and creative lateral thinking, that's why all of the top 100 Global Brands employ Chartered Accountants.
SAICA is a member of Chartered Accountants Worldwide (CAW), a global family that connects over 1,8 million fellow Chartered Accountants and students in more than 190 countries. Together, we support, develop, and promote the role of Chartered Accountants as trusted business leaders, difference-makers, and advisers.
SAICA Media Contacts
Kgauhelo Dioka, ***@saica.co.za
Project Manager: Communications
SAICA Brand Division
Renette Human, ***@saica.co.za
Project Director: Communications
SAICA Brand Division
| 2023-01-23T00:00:00 |
https://www.saica.org.za/news/generative-ai-a-game-changer-for-people-business-and-government/
|
[
{
"date": "2023/01/23",
"position": 88,
"query": "artificial intelligence business leaders"
}
] |
|
OpenAI and Sama hired underpaid Workers in Kenya to ...
|
OpenAI and Sama hired underpaid Workers in Kenya to filter toxic content for ChatGPT
|
https://www.business-humanrights.org
|
[] |
The data labelers employed by Sama on behalf of OpenAI were paid a take-home wage of between around $1.32 and $2 per hour depending on seniority and performance ...
|
Article OpenAI and Sama hired underpaid Workers in Kenya to filter toxic content for ChatGPT
"Exclusive: OpenAI Used Kenyan Workers on Less Than $2 Per Hour to Make ChatGPT Less Toxic", 18. January 2023
[...] But the success story is not one of Silicon Valley genius alone. In its quest to make ChatGPT less toxic, OpenAI used outsourced Kenyan laborers earning less than $2 per hour, a TIME investigation has found.
[...] To get those labels, OpenAI sent tens of thousands of snippets of text to an outsourcing firm in Kenya, beginning in November 2021. Much of that text appeared to have been pulled from the darkest recesses of the internet. Some of it described situations in graphic detail like child sexual abuse, bestiality, murder, suicide, torture, self harm, and incest.
OpenAI’s outsourcing partner in Kenya was Sama, a San Francisco-based firm that employs workers in Kenya, Uganda and India to label data for Silicon Valley clients like Google, Meta and Microsoft. Sama markets itself as an “ethical AI” company and claims to have helped lift more than 50,000 people out of poverty.
The data labelers employed by Sama on behalf of OpenAI were paid a take-home wage of between around $1.32 and $2 per hour depending on seniority and performance. For this story, TIME reviewed hundreds of pages of internal Sama and OpenAI documents, including workers’ payslips, and interviewed four Sama employees who worked on the project. All the employees spoke on condition of anonymity out of concern for their livelihoods.
The story of the workers who made ChatGPT possible offers a glimpse into the conditions in this little-known part of the AI industry, which nevertheless plays an essential role in the effort to make AI systems safe for public consumption. [...]
In a statement, an OpenAI spokesperson confirmed that Sama employees in Kenya contributed to a tool it was building to detect toxic content, which was eventually built into ChatGPT. The statement also said that this work contributed to efforts to remove toxic data from the training datasets of tools like ChatGPT. “Our mission is to ensure artificial general intelligence benefits all of humanity, and we work hard to build safe and useful AI systems that limit bias and harmful content,” the spokesperson said. “Classifying and filtering harmful [text and images] is a necessary step in minimizing the amount of violent and sexual content included in training data and creating tools that can detect harmful content.” [...]
One Sama worker tasked with reading and labeling text for OpenAI told TIME he suffered from recurring visions after reading a graphic description of a man having sex with a dog in the presence of a young child. “That was torture,” he said. “You will read a number of statements like that all through the week. By the time it gets to Friday, you are disturbed from thinking through that picture.” The work’s traumatic nature eventually led Sama to cancel all its work for OpenAI in February 2022, eight months earlier than planned. [...]
All of the four employees interviewed by TIME described being mentally scarred by the work. Although they were entitled to attend sessions with “wellness” counselors, all four said these sessions were unhelpful and rare due to high demands to be more productive at work. [...]
In a statement, a Sama spokesperson said workers were asked to label 70 text passages per nine hour shift, not up to 250, and that workers could earn between $1.46 and $3.74 per hour after taxes. [...]
An OpenAI spokesperson said in a statement that the company did not issue any productivity targets, and that Sama was responsible for managing the payment and mental health provisions for employees.
| 2023-01-23T00:00:00 |
https://www.business-humanrights.org/en/latest-news/openai-and-sama-hired-underpaid-workers-in-kenia-to-filter-toxic-content-for-chatgpt/
|
[
{
"date": "2023/01/23",
"position": 93,
"query": "artificial intelligence wages"
}
] |
|
How AI Art Generators Are Improving the Design Process
|
How AI Art Generators Are Improving the Design Process
|
https://www.punchy.design
|
[
"Liz Oz",
"See All Posts"
] |
AI algorithms analyze and interpret video footage, creating new and unique forms of visual art. This can be a game-changer in the film industry and video ...
|
In today's fast-paced and competitive design industry, staying ahead of the curve is more important than ever... And there's one tool that is quickly becoming a game-changer: AI art generators!
These cutting-edge technologies are transforming the way artists and designers work, and they're bringing new possibilities to the creative process. From automating tedious tasks to generating one-of-a-kind pieces.
So, these tools are revolutionizing the way we create art and design… And if you're a designer or an artist, you don't want to miss this!
AI art generators: advantages and disadvantages
AI art generators are not only helping the professional design and art industry but also enabling amateurs to be more creative and allowing them to produce high-quality art with minimal effort.
Moreover, even artworks generated with AI have won artistic awards for their high-quality. So, art can be quickly generated, reducing costs and above all time, and standing out in the marketplace.
Basically, they have the following benefits for you:
AI art generators provide new ways to create, manipulate and generate art. These tools are becoming increasingly popular among artists, graphic designers, and other creative professionals because they offer a number of benefits that traditional methods simply cannot match, and now anyone with a computer can create art in a simple way.
They can automate many of the tedious and time-consuming tasks involved in the design process. By taking care of repetitive tasks like color selection, image manipulation, and image generation. These tools free up artists and designers to focus on more creative and high-value tasks. This can lead to a more efficient and streamlined design process, which can save time and money in the long run.
AI art generators deliver new ways to create art that would otherwise be impossible. For example, some AI art generators create images that are completely unique and impossible to replicate by hand. This means that artists and designers can produce one-of-a-kind pieces that are sure to stand out and make a lasting impression.
AI art generators develop highly complex images that would be challenging to create by hand without advanced skills and techniques.
Although the new AI technologies are bringing a lot of comfort to the world, there’s also some controversy as we don't know how far this intelligence can go.
So, when it comes to using AI software in graphic design, there are a few potential disadvantages:
First, the output generated by AI software may not be entirely unique and may not capture the nuances and subtleties of a human-designed project, and the lack of a creative touch may be noticed by the target audience.
AI isn't capable of creating images that capture certain emotions or ideas in the same way that a human designer would be able to. Also, some problems that design solves need an understanding of the context, culture, and human behaviors.
Although most designers use AI simply as another tool in their arsenal, it’s possible that most amateur designers aren't considered necessary when there is an AI tool that can do the job much faster and more efficiently than they can.
AI technology is now shaping graphic design through AI art generators
Behold: The Art of Animation Crafted Without AI Assistance (The Old-Fashioned Way)
AI technology is rapidly opening up new possibilities for artists and designers to create and innovate. With the help of AI algorithms and machine learning, artists are now able to generate new and unique forms of art that would have been impossible to create without the assistance of AI.
And some of the most sophisticated AI art generators you can test are:
DALL-E
DALL-E is a superior machine learning model developed by OpenAI for producing images from text descriptions. The model can render realistic images only from a description of the scene to create outstanding images that are fully original and functional for professional projects.
Stable Diffusion
Stable Diffusion is an open-source machine learning program that can deliver images from text, or enrich details in low-detail images.
It is trained on billions of images and can certainly produce results similar to those achieved with DALL-E. It interprets textual descriptions and learns from the information contained in its datasets.
With Stable Diffusion, the possibilities are endless. So, even if you reprocess the prompt, you're unlikely to get the exact same outputs.
InVideo
AI technology is also being used in video art. AI algorithms analyze and interpret video footage, creating new and unique forms of visual art. This can be a game-changer in the film industry and video animation, where it can help to generate new creative and innovative storylines.
But InVideo's features are not limited to editing; it also has statistics and reports that allow you to track the impact and reach of your videos once they're published.
Other creative uses of AI in graphic design
Although creating images or videos with AI is one of its major functions, this is only a part of the possibilities, and you can even develop the sketches of your web page, landing pages, logos, etc. Let's see an example of this:
Landing page designs
Creating beautiful landing page mock-ups can be a time-consuming and tedious task for designers, but with the help of AI art generation software, the process can become more efficient and produce visually stunning results.
One way that AI art generators can be used in the design of landing pages is by creating custom illustrations and graphics. These tools use machine learning algorithms to generate unique and high-quality images to enhance the visual appeal of the landing page.
It can save time and resources compared to manually creating illustrations, and also allows for the exploration of new design options and styles.
Moreover, with the help of AI art generators, you can easily experiment with different color palettes, typography, and images on the landing page to find the perfect combination for your website's design.
This allows for the discovery of new design elements that may not have been considered previously and the ability to make data-driven design decisions.
Logo design
Creating a logo that accurately represents a company or brand is a challenging task. But with the help of an AI art generation software, the process can become much more efficient and produce visually stunning results.
Although logos aren't a definitive and ready-to-use version, they certainly give an advantage to the creative process since you will have several ideas to start designing.
Product photography
AI art generators are perfect for product photography because they create realistic and lifelike 3D renders of the product. These tools use machine learning algorithms to generate high-resolution images to showcase the product from different angles and in different environments. It saves time and resources compared to manually setting up and photographing the product, and also allows for the exploration of new creative possibilities.
Another way that AI art generation software can help you stand out is by creating digital composites that combine multiple images into a single, cohesive scene. For example, an AI art generator can combine a photograph of a product with a background image such as a scenic landscape or an urban setting to create a more visually interesting and engaging image.
AI art generation software can also be used to create unique and dynamic visual effects such as reflections, shadows, and highlights, to enhance the realism and dimensionality of the product.
Will AI replace human designers?
Previously, if you created a digital image, you had to actually draw and work with tools such as Photoshop. But from 2022 onwards, everything has completely changed and AI tools create stunning images just from text descriptions.
AI technology has advanced to the point where it creates designs that are visually comparable to those produced by human designers. However, it's important to note that AI is not a replacement for human designers but rather a tool that can augment and assist them in their work.
AI technology isn't capable of replicating the full range of human creativity and emotional intelligence. So, designers bring a unique perspective and understanding of the target audience, brand identity, and context of the design, which AI doesn't have.
Moreover, AI is heavily dependent on the data it is trained on, and thus, it will only be as good as the quality and diversity of the data it learns from. This can limit the creativity of AI-generated designs and make them less unique.
Artificial intelligence in graphic design is here to stay
AI art generators are a powerful tool for any artist or designer looking to improve their workflow and create truly unique and innovative work.
From automating tedious tasks to generating one-of-a-kind images, these tools are giving artists and designers the freedom to be more creative and efficient than ever before. .
So, if you're looking to take your art and design skills to the next level, consider incorporating AI art generators into your workflow – you'll be amazed at the results!
| 2023-01-23T00:00:00 |
https://www.punchy.design/blog/how-ai-art-generators-are-improving-the-design-process
|
[
{
"date": "2023/01/23",
"position": 21,
"query": "artificial intelligence graphic design"
}
] |
|
'It's the opposite of art': why illustrators are furious about AI
|
‘It’s the opposite of art’: why illustrators are furious about AI
|
https://www.theguardian.com
|
[
"Sarah Shaffi"
] |
AI art generators may provide five minutes of fun for most users, but the blurring of creative and ethical boundaries is leaving many artists raging against ...
|
‘Woman reading book, under a night sky, dreamy atmosphere,” I type into Deep Dream Generator’s Text 2 Dream feature. In less than a minute, an image is returned to me showing what I’ve described. Welcome to the world of AI image generation, where you can create what on the surface looks like top-notch artwork using just a few text prompts, even if in reality your skills don’t go beyond drawing stick figures.
AI image generation seems to be everywhere: on TikTok, the popular AI Manga filter shows you what you look like in the Japanese comic style, while people in their droves are using it to create images for everything from company logos to picture books. It’s already been used by one major publisher: sci-fi imprint Tor discovered that a cover it had created had used a licensed image created by AI, but decided to go ahead anyway “due to production constraints”.
The biggest players in AI include companies such as MidJourney, Stable Diffusion and Deep Dream Generator (DDG). They’re free to use, up to a point, making them attractive to those just wanting to try them out. There’s no denying that they’re fun, but closer examination of the images they produce shows oddities. The face of the woman in my image has very odd features, and appears to be holding multiple books. The images also have a similarly polished, somewhat kitsch aesthetic. And, while there’s an initial thrill at seeing an image appear, there’s no creative satisfaction.
View image in fullscreen ‘It’s nonsense’ … Rob Biddulph in his studio
The implications of AI image generation are far-reaching and could impact everything from film to graphic novels and more. Children’s illustrators were quick to raise concerns about the technology on social media. Among them is author and illustrator Rob Biddulph, who says that AI-generated art “is the exact opposite of what I believe art to be. Fundamentally, I have always felt that art is all about translating something that you feel internally into something that exists externally. Whatever form it takes, be it a sculpture, a piece of music, a piece of writing, a performance, or an image, true art is about the creative process much more than it’s about the final piece. And simply pressing a button to generate an image is not a creative process.”
Beyond creativity, there are deeper issues. An online campaign – #NotoAIArt – has seen artists sharing concerns about the legality of AI image generators, and about how they have the potential to devalue the skill of illustration. To create images from prompts, AI generators rely on databases of already existing art and text. These comprise billions of images that have been scraped from the internet. Among the biggest is the open-source LAION-5B dataset, used by DDG’s Text 2 Dream. Kaloyan Chernev, founder of DDG, says that the dataset comprises “largely public domain images sourced from the internet”, but many artists and illustrators say that databases will often also include a lot of copyrighted images.
Harry Woodgate, author and illustrator of Grandad’s Camper, which won the Waterstones 2022 picturebook prize, says: “These programs rely entirely on the pirated intellectual property of countless working artists, photographers, illustrators and other rights holders.” It’s a point echoed by illustrator Anoosha Syed: “AI doesn’t look at art and create its own. It samples everyone’s then mashes it into something else.”
View image in fullscreen The real thing … Dapo Adeola’s debut Hey you!
While prompts to image generators can be very general, they can also ask for an image to be based on the work of another artist, further blurring ethical boundaries. Syed says that this could lead to the creation of images “that are intentionally meant to mimic my style” or that of other artists, without their consent. There is an argument that AI generators work no differently to humans when it comes to being influenced by others’ work, but Biddulph says: “A human artist is also adding emotion and nuance into the mix, and memory – specifically, its failings.”
He adds: “If I’m making a painting and decide it should be Hockney-esque, I’m not going to trawl the internet for millions of Hockney-esque images, work out exactly what traits makes these images Hockney-esque, then apply them to my picture, systematically and with forensic accuracy. I’m going to think, ‘I like the way Hockney juxtaposed blocks of purple, green and ochre in that painting of a field I saw at the National Gallery.’ And then I’ll attempt to add that into my picture. Inevitably, I’ll misremember it, and will probably end up creating something that bears a faint resemblance to something Hockney once painted, but in my own style.”
AI doesn’t look at art and create its own. It samples everyone’s – then mashes it into something else
Syed agrees, saying “another human will never look at an image the exact same way the original artist did. They will never move their hands the way the original artist did. AI doesn’t do the same – it can only copy.” When a human artist does “mimic a style, or pass off a piece of artwork as their own, it is incredibly frowned upon – and in some cases could be seen as copyright infringement. This is essentially what AI art is doing.”
Chernev says he recognises the “complex ethical considerations surrounding the use of non-public domain images and the potential impact on artists whose work is used in the training of AI tools like ours”. But there’s a more insidious danger: the ability to create images that are potentially illegal. Chernev admits that during the initial launch of Text 2 Dream, people tried to “generate images of nude children, despite the fact that no such images were present in the training dataset”.
He adds: “As AI continues to advance, there is a risk that it may be able to synthesise images of inappropriate or illegal subjects based on existing content. In response to this, we have swiftly adapted our tools to prohibit the generation of any inappropriate or illegal content, including nude images of children and NSFW material. We are committed to ensuring the responsible and ethical use of our image-generating service.”
Although Chernev says DDG reported the incidents to authorities, as a whole AI image generation is unregulated, something artists are quick to point out. Both Woodgate and Dapo Adeola, who won Illustrator of the Year at the 2022 British book awards, would like to see more regulation. “A welcome first step,” says Woodgate, “would be to scrap the UK government’s proposed copyright exception, allowing text and data mining for any commercial purpose, and instead advocate for opt-in licence-based models.” That way, Woodgate adds, any future databases would be created using voluntary contributions that are properly paid for.
Adeola agrees, saying the “simplest thing is getting permissions from the artists to use their work” along with a fee. Chernev says DDG does take on board requests from artists who want to be excluded from their system, but the “asking forgiveness, not permission” model is not one that sits well with Adeola, who says seeking permission “should have been the first stage”.
View image in fullscreen In his own style … an illustration by Rob Biddulph
Although children’s book illustration will, say artists, remain largely unaffected, AI image generation has the potential to do away with smaller jobs that up-and-coming artists often rely on to build up portfolios. Syed says that for things such as fan-art, self-published books, logos and family portraits, people may turn to AI. “These clients will usually care more about saving money than the quality of the finished product,” she says. “They will prefer to use AI if it means keeping costs low. So a lot of these small jobs will vanish.”
The increasing use of AI, says Adeola, will also lead to a devaluing of the work of artists. “For me,” he says, “there’s already a negative bias towards the creative industry. Something like this reinforces an argument that what we do is easy and we shouldn’t be able to earn the money we command.” Biddulph goes further. “There’s no question that AI-generated art devalues illustration,” he says. “People will, of course, begin to think that their ‘work’ is as valid as that created by someone who has spent a career making art. It’s nonsense, of course. I can use my iPhone to take a nice picture of my daughters, but I’m not Irving Penn.”
For the moment, AI image generation is largely being used for fun, but Chernev says it’s “rapidly approaching a level of sophistication and complexity that will allow it to generate highly realistic and nuanced images. I am convinced AI-generated content has the potential to not only enhance the work of artists and designers, but also to enable the creation of entirely new forms of art and expression.”
Artists and illustrators aren’t so sure. “AI-generated art has a specific ‘look’ to it,” says Syed. “As time goes on, users will become more attuned to it and start to turn away from it because of its inauthenticity and ‘cheapness’. I also think that, in response to AI, we might even see a reemergence and appreciation of traditional media.”
What’s more, illustrators firmly believe their most honest critics and biggest fans – children and young people – won’t be convinced by AI art. “Children’s books are highly complex, multimodal forms of communication,” says Woodgate. “The kids who read them expect a great deal, not only from the stories and illustrations, but from the people who make them.”
| 2023-01-23T00:00:00 |
2023/01/23
|
https://www.theguardian.com/artanddesign/2023/jan/23/its-the-opposite-of-art-why-illustrators-are-furious-about-ai
|
[
{
"date": "2023/01/23",
"position": 25,
"query": "artificial intelligence graphic design"
}
] |
Best AI web design tools. AI website builders, ChatGPT ...
|
Best AI web design tools. AI website builders, ChatGPT and more
|
https://webwave.me
|
[] |
AI takes care of both the design and content. It generates a layout reflecting your website type. Adds colors, copy, images, interactive elements - everything ...
|
Creating a website with ChatGPT and Midjourney - a case study
Even though AI website builders are the most optimal AI web design tool, let's not ignore ChatGPT and AI image generators like Midjourney or Dall-e.
Those tools are still very useful in the process of website creation, especially if you want to be a hands-on creator of your site or want to redesign or retouch your already existing website.
I took up the challenge of creating a website with ChatGPT and Midjourney to see these tools' capabilities in site design.
ChatGPT
What is ChatGPT?
ChatGPT is a chatbot launched by OpenAI in late November 2022. It’s a chatbot that was created to mimic a human interlocutor. To achieve this goal it was trained using supervised and reinforced learning. The results were satisfying enough for The New York Times to call ChatGPT “the best artificial intelligence chatbot ever released to the general public”. The ChatGPT quickly became extremely popular with over 1 million users gathered in just 5 days.
Encouraged by the numbers and very enthusiastic feedback from public opinion, I decided to give it a try.
How ChatGPT works
ChatGPT doesn’t require much to get started. Once you sign up, you’re ready to start a conversation with your new AI-powered friend. The UI is simple and easy to navigate.
You can have multiple separate conversations with the bot, each on a different topic. ChatGPT remembers everything that was said previously in the course of the exchange. It makes you feel like you are talking to a real human being.
I was skeptical when I read all the pean about how human-like ChatGPT is but I had to let go of my doubts quickly. Using it was a very pleasant experience.
ChatGPT has limitations. It possessed the knowledge before 2021 and sometimes can give you an answer that doesn’t make much sense. However, even with its limitations, ChatGPT is an impressive tool.
How to use ChatGPT to create a website
Considering that you can talk with ChatGPT about almost anything, I decided to give it a try and ask it to come up with a name for my app. It quickly gave me a list of 10 names, and, to be completely honest with you, some of them were pretty good.
If you are in a creative process and need some ideas quickly, don’t hesitate and go to ChatGPT. You will at least be inspired.
But back to my website.
After the chatbot helped me to name my plant care app - I went with Bloomify - I asked it to create a content outline for a website. It's an excellent facilitator.
At the first attempt, it proposed the site's structure. Each section was specified with two bullet points explaining what kind of information should be included. Because I wanted to create a homepage for this website, I kept typing prompts directly referencing it. Knowing that I will need a hero section with a headline, a tagline, and a call to action button, I asked specifically to provide such content. Otherwise, I would still be getting rather general answers.
Eventually, I got the content that I could put into my website.
I can already tell, that ChatGPT can be great when you’re creating website templates or a portfolio as a beginner web designer. Unlike in the process of working with clients, when they usually already know what their website must contain, you’re starting from scratch.
Turn to ChatGPT for website outline and content ideas and focus on website creation and showcasing your design skills. Imagine how much time you can save when you don’t have to think about the copy.
Of course, ChatGPT in web design can be used in many more ways. This a very versatile tool that can play different roles in the process of creating website and learning web design in general.
Midjourney
What is Midjourney and how to use it?
Midjourney is a popular AI web image generator. Images are created from text descriptions - prompts. Currently, 4 versions of Midjourney are available, with the latest released in an alpha version in November 2022.
You can access Midjourney via their official Discord and the artwork is generated by Discord bots. Once you type in /imagine command and then your prompt, you get 4 propositions of your artwork. You can keep generating another 4 versions of each image or render them in higher resolution and download them.
You get to generate 25 images for free.
Midjourney is easy to use, however, it takes some time to generate the artwork, so you have to be patient. There are a lot o users in each newbie's room and new art will come up on your feed all the time. At first, I felt a bit overwhelmed by it, but once I got used to the way it works and how much I have to wait for an image to generate, the whole experience was better.
How to use Midjourney in web design
As predictable as it is, I wanted to use artwork created in Midjourney on my website as design elements. I decided to choose a similar approach that I had to ChatGPT and first write a general prompt asking to create a layout for a plant care app website.
Inspired by the results, I opted for a hero section with a mock-up of the said app. I started working on it by typing various prompts. With each artwork created, I was getting more and more specific, adding details about the color palette or even including a monstera leaf in the design.
The right prompt is the key to success in working with Midjourney. Writing the precise description requires a trial-and-error method. Changing just one word can invert the final result. In my case, it took me 17 attempts to generate the art I was satisfied with. I chose my final images from 48 unique artworks.
Just think how much time it would take to create all of that by yourself!
AI, once again, helps you work faster and more efficiently. Midjourney in web design is especially useful when you’re creating a website prototype or want to create custom images for your project.
Creating a plant care app website with AI tools
After I generated all the content and necessary materials, it was finally time to build a website. I picked two illustrations created in Midjourney and removed the background from them so that I could use them in my project. I created quickly a logo for my app and picked the right fonts for a website. I used the imagery that I created as a guide for all my styling choices. The color palette for my website was also picked out from the AI art.
Equipped with everything that I might have needed I opened WebWave and started the final stage of my creative work. WebWave was great for recreating a layout from an image, because it’s a drag and drop website builder, meaning I can position elements wherever I want. I didn’t have to worry about fitting into tables or grids like in Wix or other website editors.
The flexibility of my website builder lets me build the homepage quickly. All I had to do was put elements in the right place. I used pre-built elements like the menu and buttons but could modify them to my liking effortlessly. I copied all the text from ChatGPT and then just added images from Midjourney. In just a few clicks my ai-powered website was ready.
Is the AI website worth it?
Generally speaking, my experience with AI web design is positive. At a very low cost and saving lots of time, I manage to create a good-looking, modern website with unique designs. I didn’t have to think about the copy or look for fitting images online or create them by myself. I want to once again emphasize how time-effective that is.
If you want to design and sell website templates, don’t hesitate and start implementing AI solutions into your creative process. Work smart, not hard, and just use AI web design. You can also use artificial intelligence to improve your already existing website templates. It's worth giving it a try.
Same thing, if you work in a digital agency or a marketing agency. In your case, ChatGPT seems to be especially helpful. It can accelerate your brainstorming process or help you deal with a creative block. Seeing how well it managed to create a content outline for a website, I imagine it might be as convenient for an article synopsis. It might change the way the content is produced. I haven't checked AI-generated text SEO performance. If it turns out to be good, I can see Chat GPT becoming an integral part of digital marketing.
If you create custom websites as a freelance web designer or as an agency, you can also implement artificial intelligence into your workflow. But it might not be great for custom, specific designs, like ecommerce sites. Just look again at the smartphone image that I used in my project. It’s not customized to my made-up app Bloomify. I was trying prompts that included the app name, but not surprisingly, I wasn’t able to get this highly-personalized image.
However, you can still use AI in the early stages of working with clients, to create prototypes. Because it will help you work faster, you will be able to build better relationships with clients and enhance the image of your brand. Your prototypes will look more professional and help you create a better user experience.
A website with artificial intelligence is great for capturing ideas that might be hard to imagine for clients. It builds website fundaments that you can later work on, personalize, and also customize. AI tools might not be essential in your field, but have a lot of potential to be extremely beneficial.
The main disadvantages I can see are in Midjourney. For now, those images still look rather fresh and new, but they definitely have a certain style. No matter what prompt you will type in, the image you will get looks like something created by AI.
They are not very versatile and can soon look all the same. I am pretty positive that this tool will be developed and improved. In a few years will be able to generate even better stuff, but for now, it’s not something groundbreaking aesthetically. In my opinion, AI art won't be the right fit for creating a custom website for a small business. It might fail at emulating anticipated online presence.
Are AI tools going to replace web designers?
The answer is a firm no. Those tools are here to help and they will be great at doing it. They are not autonomic solutions that can create comprehensive creations.
Web designers and artists in general create work that is original and has a specific context that makes it valuable. Even if Midjourney gives you unlimited variants of one image, it has no capability of making it truly significant. This factor is necessary to create something that will be speaking to people and will be able to connect with them. Maybe in the future, the human role in a creative process will be reduced to supervision, and AI tools will take over the execution. That’s very much possible, especially in the world of digital art. But I’m not going to get carried away with my predictions.
I don’t think creators should look at AI tools as a threat. It’s better to treat it as an opportunity to be better and more efficient.
Building your own solutions with AI is just one step. Businesses seeking highly tailored solutions can hire remote AI engineers to develop proprietary AI tools.
The factor of streamlining your work is the reason why AI website builders are becoming more popular. If you can do something in 2 minutes instead of 30, of course, you're going to take a shortcut. Web design and web development are constantly changing and now it's time to test AI in the process of building your website. We will see which solutions will stick with us.
| 2023-01-23T00:00:00 |
https://webwave.me/blog/ai-web-design
|
[
{
"date": "2023/01/23",
"position": 34,
"query": "artificial intelligence graphic design"
}
] |
|
MSc Artificial Intelligence for the Creative Industries
|
MSc Artificial Intelligence for the Creative Industries
|
https://www.york.ac.uk
|
[
"University Of York"
] |
This degree will motivate, inspire and enrich your understanding of this rapidly growing field and the creative opportunities which AI offers.
|
Teaching and assessment
You’ll work with world‐leading academics who’ll challenge you to think independently and excel in all that you do. Our approach to teaching will provide you with the knowledge, opportunities, and support you need to grow and succeed in a global workplace.
Teaching format
The course involves a range of different teaching styles, including case study-based learning, independent study, collaborative work and practical activities. You'll be taught by research-active, creative professionals across immersive and interactive media; what you learn at York stems directly from current research and practice.
You will be assigned a personal supervisor from our teaching staff who will act as a point of contact, supporting you with your studies for the duration of the degree. They are there to provide you with advice on academic matters as well as others areas of life at the University.
Facilities
You'll have access to lab spaces equipped with powerful computers able to train and run AI modules and an impressive computing cluster. You'll also be able to access studio and rehearsal spaces, accompanied by bespoke equipment and media processing software for high quality content creation.
Discover our facilities
Teaching location
You will be based primarily in the School of Arts and Creative Technologies, with some teaching elsewhere on Campus East and Campus West.
About our campus
Our beautiful green campus offers a student-friendly setting in which to live and study, within easy reach of the action in the city centre. It's easy to get around campus - everything is within walking or pedalling distance, or you can always use the fast and frequent bus service.
Assessment and feedback
The programme is assessed through a combination of essays, implemented prototypes and reports. The module options are set to encourage you to choose topics of their interest and select the assessment methods that are most suitable to you.
| 2023-01-23T00:00:00 |
https://www.york.ac.uk/study/postgraduate-taught/courses/msc-ai-for-the-creative-industries/
|
[
{
"date": "2023/01/23",
"position": 37,
"query": "artificial intelligence graphic design"
}
] |
|
ChatGPT Conversation - Comparing Ai to Early Graphic ...
|
Comparing Ai to Early Graphic Industry Technology
|
https://orchardviewcolor.com
|
[
"Theresa Jackson"
] |
AI-powered software can also generate new designs, layouts, and typographyXTypography refers to the design of text. It is the arrangement of letters and text.
|
Artificial Intelligence (AI) is rapidly advancing and has the potential to disrupt many industries, just as personal computers did in the mid-1990s. One of the most significant changes brought about by the rise of AI is the democratization of technology, making it more accessible to individuals and small businesses. This is similar to the way that the introduction of the Power Mac computers by Apple in the mid-1990s disrupted the design and printing industry by offering high-end equipment at a more affordable price point, making it accessible to a wider range of users.
In the printing and graphics industry, AI is being used in a variety of ways to automate tasks and improve efficiency. For example, AI-powered image recognition and analysis can be used to automatically detect and correct errors in images, such as color balance and contrast. This can save a significant amount of time for designers and printers, as they no longer need to manually adjust these settingsAn application's behaviors and preferences are controlled with settings. More. AI-powered software can also generate new designs, layouts, and typographyTypography refers to the design of text. It is the arrangement of letters and text. More, freeing up designers to focus on more creative tasks.
AI is also being used to automate the prepress process, by automatically creating high-quality printing plates from digital files. This eliminates the need for film stripping and manual labor, saving time and reducing costs. With AI, the prepress process can be completed faster and with fewer errors, resulting in higher-quality prints.
In addition to these changes, AI is also expected to bring about new business models and revenue streams for the printing industry. For example, AI-powered print-on-demand services allow customers to customize and order products online, which can increase sales and customer satisfaction. Additionally, AI-powered print management software can be used to optimize print runs, reducing waste and costs.
Just as the introduction of the Power Macs in the mid-1990s disrupted the printing and graphics industry, AI has the potential to disrupt it even more. However, it is important to note that the changes brought about by AI are not necessarily negative. They can improve efficiency, reduce costs, and open up new opportunities for businesses.
It’s important to remember that change can be scary, but it can also bring about new and exciting opportunities. It’s essential for companies and individuals in the printing and graphics industry to embrace the changes brought about by AI and to adapt and evolve to stay competitive. It’s important to stay informed and educated about the latest developments in AI and to continuously develop new skills to stay ahead of the curveA curve, or color curve, is a graphic representation of color and tone. Adjustments to the angle and... More.
In conclusion, the current state of AI technology is similar to the changes brought about by personal computers in the mid-1990s, as it has the potential to democratize technology and disrupt industries. The printing and graphics industry is already seeing the effects of AI, with automation and improved efficiency being the primary benefits. However, it’s important to keep in mind that change can bring about new opportunities, and it’s essential to stay informed and adapt to stay competitive in the industry.
| 2023-01-23T00:00:00 |
2023/01/23
|
https://orchardviewcolor.com/chatgbt-conversation-comparing-ai-to-early-graphic-industry-technology/
|
[
{
"date": "2023/01/23",
"position": 63,
"query": "artificial intelligence graphic design"
}
] |
Impact of Artificial Intelligence on Jobs
|
Impact of Artificial Intelligence on Jobs – Basic Gyaan
|
https://basicgyaan.com
|
[] |
AI can automate tasks that were previously done by humans. This can lead to job displacement in industries such as manufacturing, transportation, and customer ...
|
Introduction
Artificial intelligence (AI) has been making significant strides in recent years, with advancements in areas such as natural language processing, image recognition, and decision-making. With these advancements, there are concerns that AI may take over a majority of jobs, leading to widespread unemployment. In this article, we will examine the potential impact of AI on employment, the industries that are most at risk, and the steps that can be taken to mitigate the negative effects.
The Potential Impact of AI on Employment
There are several ways in which AI could potentially impact employment. Firstly, AI can automate tasks that were previously done by humans. This can lead to job displacement in industries such as manufacturing, transportation, and customer service.
Secondly, AI can also improve productivity, leading to increased output and lower costs. This could lead to companies downsizing their workforce as they are able to accomplish more with fewer employees.
Thirdly, AI can also create new jobs, such as in the field of AI development and maintenance. However, these jobs will typically require a higher level of skills and education, and may not be accessible to those who lose their jobs due to automation.
Industries at Risk
There are several industries that are most at risk of job displacement due to AI. These include:
Manufacturing: AI can automate tasks such as welding, painting, and assembly, which are currently done by human workers.
Transportation: Self-driving cars and trucks could displace human drivers.
Customer service: AI chatbots can handle simple customer service inquiries, reducing the need for human customer service representatives.
Retail: AI-powered inventory management and cashierless stores could reduce the need for human employees.
Data entry and analysis: AI can process and analyze large amounts of data, reducing the need for human data entry and analysis.
Mitigating the Negative Effects
There are several steps that can be taken to mitigate the negative effects of AI on employment.
Firstly, governments and organizations can invest in retraining programs to help workers acquire the skills needed for the jobs of the future. This can include training in AI development, data analysis, and other high-demand fields.
Secondly, governments can also implement policies to support workers affected by automation, such as unemployment benefits and income support.
Thirdly, organizations can also adopt a more human-centric approach to AI, where AI is used to augment human workers rather than replace them. This can include using AI to assist with decision-making, rather than taking over the decision-making process entirely.
Conclusion
While AI has the potential to bring significant advancements in productivity and efficiency, it also has the potential to displace a significant number of jobs. It is important for governments, organizations, and individuals to take proactive steps to mitigate the negative effects of AI on employment. This includes investing in retraining programs, implementing policies to support workers affected by automation, and adopting a more human-centric approach to AI. By taking these steps, we can ensure that the benefits of AI are shared by all, rather than just a select few.
| 2023-01-24T00:00:00 |
https://basicgyaan.com/impact-of-artificial-intelligence-on-jobs/
|
[
{
"date": "2023/01/24",
"position": 33,
"query": "automation job displacement"
}
] |
|
How AI will impact the future of work and life
|
How AI will impact the future of work and life
|
https://timesofindia.indiatimes.com
|
[] |
With the rise of automation, many jobs will be replaced by machines, leading to increased efficiency and cost savings for businesses. However, it also means ...
|
Artificial Intelligence (AI) is rapidly becoming one of the most important and rapidly-evolving technologies of our time. With advancements in machine learning, natural language processing, and computer vision, AI is being used to solve complex problems, automate mundane tasks, and create new products and services. In this blog, we will explore the ways in which AI is shaping the future and why it is considered a game-changer for multiple industries.
First, it’s important to understand the different types of AI. There are three main categories: rule-based AI, which follows a set of pre-programmed rules to make decisions; machine learning, which uses algorithms to learn from data and improve over time; and deep learning, a subset of machine learning that uses neural networks to process large amounts of data and perform tasks such as image and speech recognition. Each of these types of AI has its own unique capabilities and is being used in different ways to improve various industries.
One of the most obvious ways AI is shaping the future is through automation. With the help of machine learning, computers can now perform tasks that were once only possible for humans to complete. This includes tasks such as data entry, customer service, and even driving cars. With the rise of automation, many jobs will be replaced by machines, leading to increased efficiency and cost savings for businesses. However, it also means that many jobs will be displaced, and it’s crucial for society to think about how to mitigate the negative impact of this shift on the workforce.
AI is also being used to improve healthcare. With the help of machine learning, doctors and researchers are now able to analyze large amounts of medical data to identify patterns and make more accurate diagnoses. This is particularly useful for detecting diseases such as cancer, which often have subtle symptoms that are difficult for humans to spot. AI is also being used to develop new drugs and treatments, which can help to improve the lives of millions of people around the world.
Another area where AI is making a significant impact is in the field of finance. Machine learning algorithms are being used to detect fraudulent transactions and predict market trends. This helps financial institutions to protect their customers and to make better investment decisions. Additionally, AI is being used to develop new financial products and services, such as Robo-advisers, which can provide investment advice to individuals who might not have access to traditional financial services.
AI is also being used in the field of retail. Retailers are using AI-powered chatbots to provide customers with personalized recommendations, and to help with things like order tracking and returns. Additionally, AI is being used to optimize pricing and inventory management, which can help retailers to increase sales and reduce costs.
Lastly, AI is also being used in the field of entertainment. AI-powered virtual assistants have become an integral part of our daily lives. They can help us with things like scheduling appointments, playing music, and even ordering groceries. Additionally, AI is being used to create new forms of entertainment, such as virtual reality experiences and personalized video content.
In conclusion, AI is rapidly changing the way we live and work. It is automating tasks, improving healthcare, and financial services, and changing the way we shop and entertain ourselves. However, as technology continues to evolve, it’s important to consider the potential negative impacts, such as job displacement, and to work towards finding solutions that mitigate these negative effects. The future of AI is bright, but it’s crucial to approach it with caution and to ensure that it is used in ways that benefit society as a whole.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://timesofindia.indiatimes.com/readersblog/shikshacoach/how-ai-will-impact-the-future-of-work-and-life-49577/
|
[
{
"date": "2023/01/24",
"position": 46,
"query": "automation job displacement"
},
{
"date": "2023/01/24",
"position": 56,
"query": "future of work AI"
}
] |
Artificial intelligence Development Services Company
|
Artificial intelligence Development Services Company
|
https://aideveloper.com.au
|
[] |
The challenges of AI include data privacy concerns, potential job displacement ... The benefits of AI include improved efficiency, automation of repetitive ...
|
FAQ
1. What is artificial intelligence (AI)?
Artificial intelligence (AI) refers to computer systems that are able to perform tasks that usually require human intelligence such as visual perception, speech recognition, decision-making, and translation between languages. AI leverages algorithms and models to analyze patterns and make predictions or decisions without human intervention.
2. What are the different types of AI?
The different types of AI include narrow AI, which is designed to perform a specific task; general AI, which can understand, learn and apply its intelligence to any task; and superintelligent AI, which would surpass human intelligence and be capable of outperforming humans in any task.
3. What are the applications of AI?
AI has a wide array of applications including, but not limited to, data analytics, healthcare (diagnosis and treatment recommendations), autonomous vehicles, virtual assistants, fraud detection, facial recognition, and natural language processing.
4. How does AI work?
AI works through a combination of algorithms, data, and computational power. It utilizes techniques such as machine learning, deep learning, and natural language processing to analyze data, learn from it, and make predictions or decisions based on the analysis.
5. What are the challenges of AI?
The challenges of AI include data privacy concerns, potential job displacement, decision-making transparency, security vulnerabilities, and the technical complexity of developing robust and reliable AI systems.
6. What are the ethical considerations of AI?
Ethical considerations of AI involve ensuring non-bias in AI algorithms, protecting user privacy, maintaining human oversight, and using AI for the benefit of all, rather than for harmful purposes or to exacerbate existing inequalities.
7. What is the future of AI?
The future of AI is expected to involve further integration into various industries, advancements in machine learning and deep learning techniques, the development of more autonomous systems, and ongoing discussions about regulation and ethical use.
8. What is machine learning?
Machine learning is a subset of AI that involves the use of algorithms and statistical models to enable computers to perform tasks and make predictions based on data, rather than being explicitly programmed to perform the task.
9. What is deep learning?
Deep learning is a subset of machine learning that utilizes neural networks with many layers (hence “deep”) to analyze various factors of data and make predictions or decisions based on it.
10. What is natural language processing (NLP)?
Natural language processing (NLP) is a field at the intersection of computer science, artificial intelligence, and linguistics, aiming to enable computers to understand, process, and generate human language in a valuable way.
11. What is computer vision?
Computer vision is a field of AI that enables computers to interpret and analyze visual information from the world, essentially allowing them to “see” and understand images and videos.
12. What is robotics?
Robotics is the field of technology that deals with the design, construction, operation, and application of robots – automated machines that can perform tasks autonomously or semi-autonomously.
13. What is expert systems?
Expert systems are computer programs that use AI techniques to simulate the judgment and behavior of a human or an organization with expert knowledge in a particular field.
14. What is fuzzy logic?
Fuzzy logic is a mathematical approach that deals with reasoning that is approximate rather than fixed and exact. It’s used in AI for situations where the answer can exist within a range, rather than being binary.
15. What is genetic algorithms?
Genetic algorithms are search heuristics based on the process of natural selection, used to find approximate solutions to optimization and search problems in AI.
16. What is reinforcement learning?
Reinforcement learning is a type of machine learning where an agent learns how to behave in an environment by performing certain actions and receiving rewards or penalties in return.
17. What is augmented reality (AR)?
Augmented reality (AR) is a technology that overlays digital information such as images, videos, or sounds on the real world, enhancing the user’s perception of reality.
18. What is virtual reality (VR)?
Virtual reality (VR) is a technology that immerses users in a completely virtual environment, often using devices like VR headsets.
19. What is a chatbot?
A chatbot is a software application that can conduct a conversation with a human user through text or voice interactions, often used for customer service or information retrieval.
20. What is quantum computing?
Quantum computing is a type of computing that takes advantage of the quantum-mechanical properties of particles to perform operations on data in a fundamentally different and potentially more powerful way than classical computers.
Additional FAQs:
21. What are the benefits of AI?
The benefits of AI include improved efficiency, automation of repetitive tasks, aiding in complex problem-solving, and the potential to make advancements in fields like healthcare, finance, and transportation.
22. What are the risks of AI?
The risks of AI include potential misuse (such as deepfakes or autonomous weapons), job displacement, privacy violations, and the amplification of existing societal biases and inequalities.
23. How can I learn more about AI?
You can learn more about AI through online courses, university programs, workshops, and by following developments in the field through scientific journals and tech news outlets.
24. Where can I find AI jobs?
You can find AI jobs on job boards specializing in tech positions, company websites, and platforms like LinkedIn. Positions in the AI field range from data scientist to AI researcher to machine learning engineer.
25. What are the ethical implications of using AI?
The ethical implications of using AI involve considering issues such as data privacy, bias in AI algorithms, the potential for misuse, and ensuring that the deployment of AI technologies benefits all of society.
26. How can I ensure that AI is used for good?
Ensuring that AI is used for good involves advocating for responsible AI development and deployment, supporting regulations that prevent misuse, and promoting transparency and accountability in AI systems.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://aideveloper.com.au/artificial-inteligence/
|
[
{
"date": "2023/01/24",
"position": 86,
"query": "automation job displacement"
}
] |
Report Says AI Could Potentially Replace 85 Million Jobs ...
|
Report Says AI Could Potentially Replace 85 Million Jobs Worldwide By 2025 — Are Interns On The List?
|
https://afrotech.com
|
[] |
The World Economic Forum suggests that AI will replace 85 million jobs across the globe by 2025. Additionally, the organization's “The Future of Jobs Report ...
|
Artificial intelligence isn’t only replacing interns.
As previously reported by AfroTech, the world’s first robot lawyer was set to take on an official court case through a company that aims to eliminate the extensive fees that come with both hiring a lawyer and racking up parking tickets.
Now, interns Aiden and Aiko have not only joined Codeword as interns, but thanks to AI, reports reveal that they have been able to create their own visual projects, work alongside various teams at the organization, and have even given themselves their respective names.
| 2023-01-24T00:00:00 |
https://afrotech.com/artificial-intelligence-jobs
|
[
{
"date": "2023/01/24",
"position": 2,
"query": "AI replacing workers"
},
{
"date": "2023/01/24",
"position": 14,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/24",
"position": 17,
"query": "future of work AI"
},
{
"date": "2023/01/24",
"position": 72,
"query": "AI layoffs"
}
] |
|
AI ChatGPT is helping CEOs think. Will it also take your job?
|
AI ChatGPT is helping CEOs think. Will it also take your job?
|
https://www.cbsnews.com
|
[
"Megan",
"Reporter",
"Megan Cerullo Is A New York-Based Reporter For Cbs Moneywatch Covering Small Business",
"Workplace",
"Health Care",
"Consumer Spending",
"Personal Finance Topics. She Regularly Appears On Cbs News To Discuss Her Reporting.",
"Read Full Bio",
"Anne Marie D. Lee",
"Editor"
] |
Chatbots will devalue some workers' skills, but also could create higher quality jobs that require a human's judgment.
|
AI text generator ChatGPT, released to the public late last year, is so sophisticated that it has already demonstrated its ability to write coherent essays, generate sound legal documents and otherwise interact with humans in a convincingly conversational manner.
One CEO even treats the tool from parent company OpenAI like a perennially available member of his executive team.
"I ask ChatGPT to become aware of where my biases and blindspots might be, and the answers it gives are a really, really good starting point to check your thinking," Jeff Maggioncalda, CEO of online course provider Coursera, told CBS MoneyWatch.
He said the tool helps him to be more thoughtful in his approach to business challenges, as well as look at topics from vantage points that differ from his own. For example, last week at the World Economic Forum meeting in Davos, Switzerland, Maggioncalda entered the following prompt: "What should I consider when giving a speech to prime ministers at Davos?"
Another useful entry for business leaders would be: "What should I consider when I am restructuring my company?" Maggioncalda said.
Maggioncalda is far from alone in his admiration for the popular tool. Nearly 30% of U.S. professionals say they have already used AI in their work, and industry experts have called it a game-changing creation with wide-ranging implications for businesses and jobs. Some have likened it to innovations like the calculator — which changed the way people think, act and teach.
"Where these things really matter is whether it increases the value of human expertise, or whether it mostly substitutes for it," MIT labor economics professor David Autor told CBS MoneyWatch.
No more first drafts
Bots will devalue clerical and administrative skills, according to Autor. Chatbots are also already proficient at generating human resources letters, boilerplate text and some advertising copy.
"Those things are just going to become easier to do. That kind of semi-expert work will become automated," he said.
That's bad news for junior and mid-level workers. "The jobs that are most likely to be displaced [involve] mundane tasks like writing basic ad copy or the first draft of a legal document. Those are expert skills, and there is no question that software will make them cheaper and therefore devalue human labor," Autor said.
Mihir Shukla, CEO and founder of AI and robotic automation company Automation Anywhere, predicted at Davos that "anywhere from 15% to 70% of all the work we do in front of the computer could be automated."
What remains to be seen is what kinds of new jobs emerging forms of AI will create. Because while ChatGPT is new, it is only the latest example of the historic cycle of technological innovation, from the printing press and the loom to the smartphone and robotics, that dooms certain lines of work while opening new ones.
"We will produce new goods and services with this that create value and new opportunities, and that is much harder to forecast," Autor said.
Another member of the executive team
Maggioncalda of Coursera said he relies on ChatGPT as a writing assistant and more substantially as a thought partner.
"If you give it a bunch of text, it can summarize it well, put it into bullet points or into different languages," he said.
He treats ChatGPT like another member of his executive team "that wears different masks and speaks different voices from different perspectives."
"To a large degree, Chat GPT is like another person there who you're also bouncing ideas off of. It's another point of view and it's there all the time," Maggioncalda added
Outsourcing this kind of work to chatbots isn't necessarily a job-killer, though. Instead, in theory, it should free up human workers to focus on more thoughtful — and ideally profitable — work.
For now, AI hasn't replaced humans for Maggioncalda. "If I could either have my executive team check my blind posts and thinking, I would definitely have them there versus ChatGPT," he said.
"The world will never be the same"
Columbia Business School professor Oded Netzer, an expert in text-mining techniques, said he instantly recognized ChatGPT as a revolutionary advance in artificial intelligence.
"It's truly an amazing leap in technology and innovation," he told CBS MoneyWatch. "From what we've seen, it was one of those moments that happens very rarely in technology and innovation, where you experience it and you say, 'the world will never be the same as it was before.'"
Enter a prompt, like "What jobs will ChatGPT take?" and ChatGPT spits out the following answer:
ChatGPT is a language model that can be used for a wide range of natural language processing tasks such as text generation, language translation, summarization, and more. It can be used in industries such as customer service, marketing, and content creation. However, it is important to note that ChatGPT is a tool and it will not take any jobs, it will assist to improve existing jobs and automate certain tasks.
Chatbots have already taken over online customer service roles, and next month, for the first time, an AI-powered "robot" lawyer will represent a defendant in court. ChatGPT threatens to replace humans when it comes to tasks that are simple to execute, like following a script or whipping up a standard legal document — think an apartment lease, someone's will or a nondisclosure agreement, according to experts.
Nearly 30% of professionals in the U.S. say they have already used ChatGPT or other AI tools for a work-related task, according to a recent survey of 4,500 employees by Fishbowl, a social network owned by career services firm Glassdoor. Workers in marketing and advertising had the highest rate of adoption, with 37% saying they had used AI, while 35% and 30% of those in technology and consulting, respectively, also report having utilized AI.
Netzer said that while ChatGPT will usher in radical change, in most cases, it won't replace workers, but rather supercharge their ability to do their jobs efficiently.
"It's primarily an enhancer rather than full replacement of jobs," he said.
Supercharged work
For example, ChatGPT is adept at helping programmers autocomplete and identify errors in their computer code.
"To the extent that we would need fewer programmers, maybe it will take away jobs. But it would help those who program find mistakes in codes and write code more efficiently," Netzer said.
The same goes for many jobs that require basic writing skills, he said.
"In terms of jobs that require writing, I think of it as a starting point as opposed to fully replacing us. I think it's a great tool to enter a prompt, see what it writes, then add a human touch," he added.
For example, ChatGPT could readily be used to generate an email to set up a meeting.
"Emails that are simple correspondence, these are the types of tasks I can easily see the machine doing very well. The less creative you need to be, the more it should be replaced," Netzer said. "Why not have them help us send emails to set up meetings when there is hardly any creativity involved?"
Of course, this variety of automation already exists in rudimentary form — for instance, Google email and chat suggests responses in text conversations.
"Massive consequences"
Renowned economist and MIT fellow Paul Kedrosky thinks ChatGPT will have a profound impact on a whole range of industries and roles.
It has "massive consequences for a host of different activities... pretty much any domain where there is a grammar, an organized way of expressing yourself," he said on a recent podcast. "That could be software engineering, that could be high school essays, that could be legal documents, where all of them are easily eaten by this voracious beast and spit back out again."
Software giants are taking note. Microsoft announced Monday is making a "multiyear, multibillion dollar investment" in the artificial intelligence startup OpenAI, maker of ChatGPT and other tools that can write readable text and generate new images.
What ChatGPT cannot yet do — and might never be able to do, many experts think — are tasks that require the many gradations of human judgment applied to a range of problems and other cognitive challenges. Take, for example, a chart or table showing an underperforming company's metrics. ChatGPT could summarize the data and tell a user what the chart shows. What it can't do — yet — is explain why the data is meaningful.
"When I ask ChatGPT what it thinks is going on with this company, it does what junior executives would do, which is they tell me what they see in a table. They say this parameter went down and this one went up in a very clear, coherent manner. But it doesn't move beyond that into the 'so what?'" Columbia's Netzer said. "These are the types of tasks that require judgment and that humans are still very valuable in."
| 2023-01-24T00:00:00 |
https://www.cbsnews.com/news/chatgpt-chatbot-artificial-intelligence-job-replacement/
|
[
{
"date": "2023/01/24",
"position": 3,
"query": "AI replacing workers"
},
{
"date": "2023/01/24",
"position": 12,
"query": "artificial intelligence business leaders"
}
] |
|
Will Robots Replace the Human Workforce? - CiGen
|
Will Robots Replace the Human Workforce?
|
https://www.cigen.com.au
|
[] |
The capabilities of RPA technology won't negate the need for humans in the workplace. Humans will always have skills that bots just cannot replicate.
|
Will Robots Replace the Human Workforce?
By 2027, the market value for Robotic Process Automation (RPA) is anticipated to grow to $11 billion.
With bots carrying out a lot of daily tasks and activities nowadays, this probably comes as no surprise to you.
Numerous sectors, including finance, healthcare, legal, retail, manufacturing, utilities and aviation, are continuously embracing RPA technology to:
boost productivity
cut costs
increase convenience
reduce task monotony
drive scalability in meeting the evolving demands of customers.
But while the application of RPA offers a wide range of opportunities to benefit businesses like yours, there have also been some fears around it replacing the human workforce. In fact, people are even saying that automation is changing “the classical” approach of laying off employees.
So, how will job functions be truly affected? Let’s discuss the implications of RPA on the human workforce – today and tomorrow.
A quick recap: what is RPA?
Robotic Process Automation (RPA) technology handles all the tedious, repetitive and high-volume tasks, so that your employees don’t have to.
By optimising software robots (“bots”) that learn, follow and execute pre-defined instructions, RPA enables your business to automate time-consuming processes and streamline workflows.
With the help of RPA, tasks can be accomplished quickly and accurately at reduced costs with a lesser need for human intervention than ever before.
This doesn’t mean, however, that robots will completely replace the human workforce.
Worries about job elimination due to technology
We can’t deny that RPA has the power to alter the way businesses work. After all, bots speed mundane processes up and minimise the risk of errors.
However, just to assure your employees, the capabilities of RPA technology won’t negate the need for humans in the workplace. Humans will always have skills that bots just cannot replicate. Experts even suggest that, with businesses moving towards digitalisation, RPA is actually more likely to contribute to potential job reallocation and even job creation rather than job loss.
The key reasons why RPA can’t entirely replace the need for a human workforce
RPA can only perform rule-based and repetitive tasks.
Ideal processes for RPA often include tasks that are specific, predictable and clearly structured. Aside from being repetitive and rule-based, it’s also preferred that processes have high frequency, low exception rate and contain readable inputs.
RPA isn’t suited for human-centric activities or tasks that require creative and critical thinking.
RPA still needs support from humans to be successfully implemented.
The technology of RPA can neither operate without human intervention nor can reproduce the higher-level thinking and actions of humans. To maximise the potential of RPA, humans must still play a crucial role in its application.
Your people are also the only ones who can determine what business processes are suitable for automation, as well as monitor if bots are performing well for your organisation’s operations.
RPA lacks soft skills.
Bots don’t have soft skills, making the human workforce much more effective in catering to customers’ needs and expectations. Because RPA technology can’t make complex decisions, solve situational problems and communicate deeply, businesses still need to rely on employees to get most of the job done.
To learn more, here’s an overview of the potential opportunities and difficulties of implementing RPA.
The impact of RPA on the human workforce
Institute for Robotic Process Automation (IRPA) Founder, Frank Casale, believes “It makes sense to work with RPA – not necessarily to put workers on the unemployment line, but to retrain them in ways that also make sense for what we are capable of creating and producing in the 21st century.”
Rather than completely replacing your human workforce, RPA aims to augment and complement how your employees work. With this smart technology, your team will no longer have to focus on repetitive and tedious tasks which are essentially more suitable for robots to perform.
Employees will get more of their time back, allowing them to focus on other areas that are more profitable for the business such as research and innovation, product development, marketing and customer service.
And as your business thrives in new markets, industries and customer segments through RPA, you will also be able to create more job opportunities that will benefit more people in the workforce.
Furthermore, RPA will empower your employees to work smarter, not harder. This, then, leads to less burnout and greater job satisfaction. If you watch the video below, you’ll understand the true synergy between humans and bots, as well as how they can effectively work together to add value to your business.
Impact on Higher-End Jobs
RPA is usually known for automating back-office tasks. Nevertheless, RPA can also support employees who are focused on higher-end tasks too.
Let’s consider, for example, those involved with certain high-value finance and accounting processes such as managing risk and compliance, completing tax returns, developing accounting software and financial advising.
Due to advancements in technology, even these higher-end knowledge professionals may consider RPA as a threat.
So, to ease their concerns, you can assure your team that RPA is a tool that’s designed to become a competitive advantage – not just for your business, but also for them as well. Working alongside robots, they can focus more on effectively applying their analytical skills where required, make more value-adding decisions and gain new knowledge that will allow them to succeed in the digital landscape.
The Future of Work
RPA has already started having a positive impact across many businesses and industries, and it will continue to have a promising future ahead, especially when working alongside humans.
At CiGen, we partner with organisations like yours to help you unlock the full business benefits of digital automation and establish a flexible operational environment for your and your employees’ future growth.
Our ultimate goal is to energise organisations and the workforce of tomorrow as digital technologies increasingly evolve toward Artificial Intelligence (AI), Computational Intelligence (CI) and Robotic Process Automation (RPA).
Harness the true power of automation with CiGen On Demand
Our team of RPA specialists are here to ensure you reap all of the rewards of business automation, while we address any potential risks or concerns you may have.
We even provide an affordable automation service to small and medium-sized businesses through our CiGen On Demand subscription solution, making it even easier for your business to harness the true power of automation and earn back your valuable time.
Contact us today for more information on how we can help your business to succeed through robotic process automation.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://www.cigen.com.au/will-robots-replace-the-human-workforce-updated/
|
[
{
"date": "2023/01/24",
"position": 27,
"query": "AI replacing workers"
},
{
"date": "2023/01/24",
"position": 42,
"query": "AI job creation vs elimination"
}
] |
Will Artificial Intelligence Replace Actuaries?
|
Actuaries vs AI: Rising to the Challenge of AI Integration
|
https://proactuary.com
|
[] |
AI is unlikely to completely replace actuaries. While AI and machine learning (ML) can automate certain tasks, such as data processing and preliminary analysis, ...
|
Will Artificial Intelligence replace actuaries?
The answer to this question largely depends on the definition used for an “actuary”.
If you define an actuary as a professional who uses his/her expertise for evaluating and managing the financial impact of a multitude of differing risks, then developments in artificial intelligence can only make us more efficient at our duties.
In the simplest of terms, artificial intelligence (AI) techniques cannot just implement themselves and replace entire careers.
Somebody has to think of how to formulate these models, how to adapt and incorporate them into current working environments, how to maintain these models, and most importantly, how to interpret their results (a result in itself amounts to nothing if you cannot understand its meaning and significance to the wider organisation).
Who else could perform such duties within the actuarial industry other than actuaries themselves? So, for the short answer to this question, it is very hard to believe that advances in artificial intelligence will replace actuaries any time soon.
Now for a slightly more in-depth analysis…
Brief Thoughts on Artificial Intelligence
Some people confuse AI with being the final outcome of humanities’ work, instead of a tool which we can use to amplify our own ability and potential.
People fear that AI will take over jobs (which is true), but it will also create more jobs.
Previously unheard of jobs may become commonplace, such as algorithm auditors, human-machine interaction consultants, autonomous vehicle re-programmers (mechanics), and automated freight traffic supervisors.
The industrial revolution was a time when a lot of people lost their artisan jobs, which I am sure people feared at the time. However, instead of mass unemployment, more jobs were created. There was a need for assembly line workers, factory supervisors and more advanced human resources experts. This led to exponential growth of economies, as people could now use this extra time & efficiency to focus on more productive tasks, which inevitably opened the floodgates to more innovation, possibly leading to the introduction of computing & artificial intelligence itself. New developments pave the path for further progression.
A similar analogy of the industrial revolution can be applied to the impact of progressions in AI. Where the former streamlined our ability to make physical things, AI will allow us to solve more complex conceptual problems, in addition to fully automating the simpler physical tasks (consequential advancement of industrialisation). Not only will it improve our general societal output, but it also has the ability to improve our own intelligence and understanding of the world.
Despite how it may seem, our brains are just biological neural network machines, with billions of neurons interacting and communicating with each other through electrical synaptic pulses. This gives us the ability to think, speak, move, plan and act; independently. How these neural networks transpire into consciousness is still unknown – maybe our interaction with AI will give us the necessary pieces to solve this everlasting puzzle. Nature “programmed” this biological intelligence into us over millions of years. There are immense opportunities for us to learn from our man-made, silicon counterparts.
As we live in the present, with the immense power of hindsight at our disposal, we like to think that we are as advanced as we will get. Foresight, however, is not as powerful. It is hard to imagine how the world will look a couple of centuries from now, there are just too many variables to accurately predict the future, and with the ever-increasing pace of progression, historical experience is not representative of the future. A few hundred years from now, people may look back on us in the same way as we now look back on people from the medieval era.
Connection to Actuarial Work
Actuaries are responsible for a multitude of complex tasks, which include not only building predictive models, but also qualitatively interpreting and building a narrative/story around their results, which machines still have difficulties doing. Despite what people may believe, the key feature that is still missing from machines is creativity.
A machine can answer a well-defined question better than any human can, but the real power comes from asking the right question in the first place.
Neural network and deep learning models are something that isn’t widely adopted within the actuarial industry yet (a “deep” model consists of a neural network model with more than one “hidden layer”). One key benefit of using such models is that they can find complex features from within the data, without the need for human intervention. Currently, there is a lot of value placed on an actuary’s professional judgement for the purpose of formulating models which is supported by, for example, speaking to underwriters and claims handlers and then using this knowledge to adjust various model parameters.
Using neural network models to learn complex features from data could remove this need for human intervention, or professional judgement, to achieve an actuarial result. This would allow actuaries to focus on interpreting the results of these models, instead spending time to achieve an accurate model by manually adjusting parameters using the industry knowledge they acquired for a specific line of business.
To give a practical example of how AI can be applied in the actuarial world, let’s look at the insight of Mario V. Wüthrich, and his implementation of neural networks to chain-ladder reserving methods.
Firstly, to approach any modelling tasks where you wish to apply an artificial intelligence model, you need to think about how to correctly phrase the “question” to our problem.
As long as a problem can be expressed in a differentiable way (i.e., in the form of a regression), then a neural network approach could be applied. With a bit of thought, actuarial problems such as estimating the loss reserves using a basic Mack Chain-Ladder Model can be interpreted as a regression with one independent factor, the cumulative claims at time t-1, which is adjusted by our parameter, the loss development factor, to produce cumulative claims at time t. This model can then be adjusted by applying a non-linear neural network regression to each development period to estimate a more accurate loss development factor.
This approach overcomes the assumption that portfolios are homogenous enough so that reserving methods, such as the one mentioned above, can be applied to each portfolio independently. The benefits of applying a neural network approach to loss reserving come from the fact that the neural network can make use of a multivariate approach, extending the feature space to include components such as line of business, claims code and accident quarter; and then fit a neural network to the expanded function. Once this function is estimated, it can be used to derive the loss development factors at this higher level of granularity, which you can then implement into your regular chain-ladder model to project a reserve.
This allows the network, once applied, to learn not only how each line of business develops independently, but also how these lines interact with each other on a grander scale, which may possibly allow us to see if there are any potential synergies between differing portfolios.
At present, for example, classes like motor and property are generally reserved independently of each other, as current reserving methods themselves do not allow for interactions between these portfolios. So, instead of a reserving actuary manually modifying the underlying assumptions of a portfolio which has been recently influenced by events from another line of business, a neural network approach could do this automatically at a higher level of abstraction. This could provide greater predictability to the reserving departments, potentially leading to lower losses and greater profitability to the insurance company. In addition, it could provide greater insight for other business departments, such as developing & improving their pricing algorithms for more efficient portfolio optimization.
Only relatively recent breakthroughs in the field of AI are allowing us to think about how to generalise these models to our tasks. There is a lot of potential there not only for improving existing processes and methodologies, but also for creating novel approaches, which may be revealed to us with further research within this field.
Professional Judgement—a Quantitative Result is Not Enough?
There’s just something about human intuition, which is the product of confidence and experience, that provides answers in the most unexpected of circumstances. Intuition is where the power of “professional judgement” comes from, and it allows us to solve difficult problems by incorporating both qualitative and quantitative aspects into our decision making.
Professional judgement is a powerful tool for actuaries.
There are a multitude of specialty risks which have very sporadic historical data for which this actuarial intuition is priceless. To give a couple of examples, natural catastrophe portfolio losses which include earthquake cover are notoriously hard to predict—earthquakes can happen anytime, anywhere without prior warning, and their severity on an insurers’ P&L is highly dependent on where it lands (e.g., 1994 Northridge Earthquake caused $15.3 billion in insured damages).
Another example would be political risk & terrorism portfolios, such portfolios may carry risk factors which cannot be accurately predicted using historical data—both the frequency and severity of these events can be truly unpredictable (e.g., before 11 September 2001 attack on the WTC no-one could’ve predicted the damage a terrorism act could do to the insurance industry, some claims—which total to approximately $47 billion -are still not fully run-off to this day, and this is considered one of the largest insured losses of all time).
When dealing with such portfolios, estimation of the quantitative ultimate losses is only a single factor of consideration, and decision to undertake such risks depend not only on the final predicted loss ultimate, but also on factors such as how these estimated losses would tie into the solvency requirements of the company, how they might affect reinsurance purchase decisions, and what are the general risk tolerance sentiments of the business. AI is still a very long way away from being capable of tackling such, sometimes undefined, complexity.
Another aspect to actuarial work, which may arguably be more important than what I mentioned above, is interpreting the key results. The overall result is nothing but digits & charts on a screen and can be meaningless to an untrained eye. Actuaries have the power to contextualise the problem, explaining what the result means to the business, and how the result feeds into other results. The meaning of a result can be highly dependent on the context at hand. For example, a start-up Insurtech may not look at the impact of a reserving portfolio in the same way that an incumbent insurer would. In both scenarios it may be proportionally the same number, but what it means to the company can be completely different.
This is what actuaries are particularly good at; seeing the bigger picture and how everything fits together at a higher level. And this is what matters most.
What Should Actuaries Do?
We need to leverage the power of AI to continue propelling our own capabilities at this rapidly increasing pace. If we brush it off as something inconsequential, we are at risk of dampening our own personal and professional development. There is a lot we can learn from artificial intelligence and it may allow us to see solutions to our problems from previously unknown perspectives (e.g., reserving example mentioned above).
It is much better for actuaries to adapt to this new world by learning how to implement various AI techniques into their work, instead of trying to fight it holding on to the dying status quo.
For actuaries, the power in their work can only be amplified with the use of AI.
The first step to understanding how to implement such models is to learn the linguistics of the machine. Actuaries need to understand how to communicate with computers, which means learning and improving their programming skills. Learning a language like Python may seem daunting, but this language is so versatile that it may provide limitless opportunities down the line, even paving the path to understanding more specialised languages such as R, SQL, and C++. Taking the first step is always the hardest, but sometimes it is the most important.
Concluding Thoughts
For now, I believe actuaries shouldn’t worry about AI taking over our actuarial jobs, not until Artificial General Intelligence (“AGI”) has reached further developments.
In some distant future, however, when AGI has reached more fundamental breakthroughs, allowing machines to “think” for themselves, this is when we should start worrying about AGI taking our jobs. But realistically, by that stage if they’re doing actuarial work for us, that means the rest of society may lose their respective jobs as well.
Maybe in this utopian future we will all be out of jobs allowing us to spend our days for the purposes of leisure, creative expressions and athletic feats.
But for now, worrying about whether or not AI will take over anyone’s job is a purposeless act.
Instead, we should learn to make use of the immense power and potential of AI to improve and increase our actuarial (and societal) output.
Artificial Intelligence vs Actuaries FAQs
1. Can AI replace actuaries? AI is unlikely to completely replace actuaries. While AI and machine learning (ML) can automate certain tasks, such as data processing and preliminary analysis, the role of actuaries involves complex decision-making, strategic planning, and ethical considerations that require human judgment. Actuaries also interpret the results of models and communicate the implications to stakeholders, which are nuanced tasks that AI cannot fully replicate. 2. What aspects of actuarial work can AI enhance? AI can enhance many aspects of actuarial work, including: Data Analysis : AI can handle large volumes of data more efficiently than traditional methods, allowing for more nuanced risk assessments.
: AI can handle large volumes of data more efficiently than traditional methods, allowing for more nuanced risk assessments. Predictive Modeling : AI and ML can improve the accuracy of predictions regarding claim frequencies, severities, and customer behavior.
: AI and ML can improve the accuracy of predictions regarding claim frequencies, severities, and customer behavior. Automation of Routine Tasks: Tasks like updating data sets and running standard reports can be automated, freeing actuaries to focus on more complex analysis and strategic planning. 3. How might AI change the actuarial profession? AI is expected to transform the actuarial profession in several ways: Skill Requirements : Actuaries may need to acquire new skills, particularly in data science and AI technologies, to remain relevant and leverage these tools effectively.
: Actuaries may need to acquire new skills, particularly in data science and AI technologies, to remain relevant and leverage these tools effectively. Job Functions : While some traditional actuarial tasks may be automated, new roles may emerge that focus on overseeing AI operations, integrating AI into decision-making processes, and ensuring the ethical use of AI in actuarial practices.
: While some traditional actuarial tasks may be automated, new roles may emerge that focus on overseeing AI operations, integrating AI into decision-making processes, and ensuring the ethical use of AI in actuarial practices. Efficiency and Productivity: AI will likely lead to greater efficiency and productivity in actuarial work, enabling actuaries to manage larger and more complex datasets, leading to more informed and strategic insights. 4. Will the demand for actuaries decrease as AI technology advances? While AI will automate certain tasks, the demand for actuaries is not necessarily expected to decrease. Instead, the role of actuaries is likely to evolve. The expertise of actuaries in modeling, risk assessment, and financial theory will still be crucial, especially as companies and governments navigate the complexities introduced by AI itself. Moreover, the ability to interpret and apply AI findings ethically and effectively in financial contexts will likely enhance the value of actuaries. 5. What should actuaries do to prepare for a future with more AI? To prepare for a future where AI plays a significant role, actuaries should: Stay Informed : Keep up with developments in AI and machine learning within the actuarial field.
: Keep up with developments in AI and machine learning within the actuarial field. Develop Technical Skills : Gain proficiency in programming languages relevant to AI, such as Python or R, and familiarize themselves with machine learning frameworks.
: Gain proficiency in programming languages relevant to AI, such as Python or R, and familiarize themselves with machine learning frameworks. Enhance Soft Skills : Strengthen skills that AI cannot replicate, such as strategic thinking, communication, and ethical judgment.
: Strengthen skills that AI cannot replicate, such as strategic thinking, communication, and ethical judgment. Pursue Continuing Education: Consider additional training or certification in data science and AI applications to actuarial science. 6. How can actuaries and AI collaborate effectively? Collaboration between actuaries and AI can lead to more robust risk assessments, more personalised insurance products, and more efficient processes. Actuaries can provide oversight and context to the insights generated by AI, ensuring that they align with business objectives and comply with regulatory standards. By working together, actuaries and AI can push the boundaries of what’s possible in risk management and financial prediction.
| 2024-05-03T00:00:00 |
2024/05/03
|
https://proactuary.com/resources/will-artificial-intelligence-replace-actuaries/
|
[
{
"date": "2023/01/24",
"position": 31,
"query": "AI replacing workers"
}
] |
Can AI replace cloud architects?
|
Can AI replace cloud architects?
|
https://www.infoworld.com
|
[
"More This Author",
".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"
] |
AI systems get more impressive every day. Today's AI can automate the tasks of many information workers, so those in cloud jobs worry they're next.
|
As I mentioned a few times in this blog, I’ve been working with and teaching about artificial intelligence since the start of my career. This drove much of my interest in cloud computing because AI was not economically viable or accessible until “the cloud” came along.
Interest in AI and its applications inflected about five years ago. Then the pandemic happened and some budgets shifted to speedy cloud migrations. Now that things are returning to normal, AI is back. Most enterprises grasp the fundamental possibilities of AI and are looking to weaponize the technology for their own business.
The technology got way more impressive along the way. Generative AI, for example, went from PhD dissertations to an accessible and free reality with the advent of generative AI services such as ChatGPT.
Generative AI is a type of artificial intelligence that generates new and unique outputs, such as text, images, or audio based on input data and learned patterns. This can include tasks such as text generation, image synthesis, and music composition.
A wide variety of inputs can be made through a chatbot or an API that results in an impressive response. The responses are so impressive that I’ve been fielding calls from journalists who are writing stories on AI replacing workers. It’s a question I’ve heard for the past 20 years but now there’s a modern twist. Colleges and universities have new concerns about college students using ChatGPT or similar services to write papers for them. AI creates output that plagiarism detection systems can’t quickly identify because it’s not plagiarism.
AI ethical and bias concerns could emerge from certain types of learning data. Will those biases cause unintended negative consequences, such as an automated pattern that denies loans to certain groups of people?
I’m hearing the following core questions: What types of human tasks can AI replace now or soon? Should I be planning a career change to a job that AI can’t automate? Is it safe to be a cloud computing architect, cloud developer, cloud operations engineer, devops engineer, cloud project leader, etc.? Those are the job titles of most of you reading this article. Are you at risk?
I think the reality is we’re well on our way to replacing many human tasks with AI-fueled automation. It’s just what happens as technology progresses, and it’s nothing new. Technology is why we no longer have dozens of people in a field to pick crops in the fall. We can check out of the supermarket without interacting with a human. Our cars and trucks can drive themselves.
One thing that I’ve been frustrated with is how the whole IT design and deployment process lacks helpful automation. Oh sure, we have tons of tools, processes, methodologies, and other assets to speed up our journey to an optimized cloud architecture and deployment. However, they don’t make critical decisions for the architects. Cloud architecture must typically be determined through deep analysis and judgment, which only come through experience. More importantly, creativity and innovation are still required—things humans bring to the table.
Of course, humans make many architectural mistakes, such as picking the wrong platform, tools, and services. Humans create architectures that are wholly underoptimized and fail to return value to the business. I addressed that issue recently.
If we turned solution creation over to AI, perhaps we’d get better decisions. Imagine if the AI system had training data that simultaneously reflected the knowledge of thousands of good cloud architects. Such an AI system could effectively process that knowledge into solutions based on provided business and technology requirements. It may not get you the final answers required to build something, but it could get close enough that it could remove a great deal of the work and potential mistakes.
The most likely path is that tactical AI tools will continue to appear. These tools will focus on specific architectural areas, such as network design, database design, platform selection, cloud-native design, security, governance, use of containers, etc. The output should be as good as, if not better than what we see today because these tools will leverage almost perfect data and won’t have those pesky human frailties that drive some architecture designs—emotions and feelings. Of course, some of these AI tools exist today (don’t tell me about your tool) and are progressing toward this ideal. However, their usefulness varies depending on the task.
Tactical AI tools must still be operated by knowledgeable people who understand how to ask the right questions and validate the designs and recommendations the tool produces. Although it may take fewer people to pull off the tactical component design of a large cloud architecture, the process will not likely eliminate all humans. Remember, many of these mistakes occur because enterprises have difficulty finding skilled cloud pros. Tactical AI tools may also help fix that problem by better syncing the demand and supply of talent.
It’s easy to predict how this will progress, and it’s nothing earth-shattering. Design, development, and deployment tools will evolve. They will provide more value and usefulness. Fewer people may be needed overall, but these tools will require talented operators to work correctly. They will focus primarily on the tactical design of cloud architecture components, such as network and security.
So, we still must rely on humans, such as yours truly, to build sound cloud solutions. The smaller problems may have AI solutions, but the larger problem of poetically automating cloud architectures remains a problem not yet solved.
I suspect we’ll still need human cloud architects and solution designers for some time to pull all of this together and ensure that we’re deploying optimized solutions that return the most value to the business. I don’t see that being something that can be replaced entirely by AI, but I’m under no illusion that it’s unlikely forever.
But let’s ask ChatGPT: “Will AI replace cloud computing architects?”
“It is unlikely that AI will completely replace cloud computing architects in the near future as while AI can assist cloud architects in tasks such as automated provisioning, monitoring, and scaling of resources, it still requires human oversight and decision-making to ensure that the systems are configured correctly and to ensure that the AI is working as intended. Cloud architects also play a crucial role in overall strategy and design of a cloud computing environment, and tasks that are difficult to fully automate with current AI technology. However, it is possible that AI could automate some of the repetitive and routine tasks that cloud architects currently perform, allowing them to focus on more strategic and higher-level responsibilities.”
I agree.
| 2023-01-24T00:00:00 |
https://www.infoworld.com/article/2337868/can-ai-replace-cloud-architects.html
|
[
{
"date": "2023/01/24",
"position": 41,
"query": "AI replacing workers"
}
] |
|
Navigating Layoffs in an AI-Driven Job Market
|
Navigating Layoffs in an AI-Driven Job Market: The Importance of Hands-On Learning and Upskilling
|
http://nuvepro.com
|
[
"Anisha K Sreenivasan"
] |
The vast majority of jobs will face automation in the next decade. This is a growing reality for many professionals and aspiring professionals alike as AI ...
|
Layoffs are a fact of life in the modern workplace, and in the age of AI and automation, it’s even more critical than ever that you adapt to change. In this blog post, we’ll explore how to navigate the ups and downs of a job market filled with high-tech advances—and why it’s important to focus more on learning than just your technical skills.
In the current job market, AI is changing the way we view ourselves and our jobs. The rise of AI and robotics has created a scenario where many industries are experiencing a shift in the need for human labour. Many people are unable to adapt to this shift and are falling into unemployment or being forced into early retirement schemes. What does this mean for those who have been off the job market for a while?
The vast majority of jobs will face automation in the next decade. This is a growing reality for many professionals and aspiring professionals alike as AI becomes more popular and better able to support their day-to-day operations. If you want to stay relevant in today’s job market, it’s important you not only master the latest technologies but also build a diverse set of skills that can help you stand out from others competing for those same jobs.
Now that AI is frequently replacing human jobs, how can people overcome the challenge? Experts suggest two main strategies: stay on-site and get professional development and upskill. These strategies are designed to help employees set themselves apart from their peers who are not trained in emerging technologies. In our current economy, which continues to be dominated by uncertainty, it’s important for the workforce to understand what skills they need to maintain a competitive edge over the long term.
But what does this mean for us? It means that we‘ve got to stay on top of our game and continuously learn new skills to remain competitive in the job market. And what’s the best way to go about it? Hands-on learning. Instead of just reading about a new technology or skill, actually getting your hands dirty and trying it out for yourself is way more effective.
AI-driven job markets seem to upskill the skills necessary to be an expert in AI, but at the same time, you have to keep up with new innovations or else your skills will become outdated. This is why we need hands-on learning, where you can actually apply your knowledge and experience in the field to become proficient.
Companies are using artificial intelligence to increase and decrease efficiency levels, and the world is seeing an increase in new job opportunities. However, as new opportunities for people to find jobs and expertise emerge, it highlights the importance of having a skillset or expertise that can be acquired on your own in order to avoid falling behind.
A robot will take your job. This is a fact of life today, with millions of American workers losing their jobs to machines and artificial intelligence. But how will these technological advancements affect you, and how can you prepare? One thing is for sure—AI will have a long-term impact on the job market, and there are numerous ways that employees can prepare: learn new skills, advance in their careers through hands-on training and leadership, and acquire valuable knowledge.
Get practical insights and advice on how to navigate layoffs in an AI-driven job market, whether you’re looking to re-skill or you need the latest info on what skills are in demand and what you should do next. In today’s AI-driven job market, learning relevant skills is more imperative than ever before. With automation set to eliminate jobs across all industries, it’s time to focus on building your own personalised skillset.
So, what can you do to prepare for a potential layoff in an AI-driven job market? Here are a few tips:
Continuously upskill and learn new skills through hands-on learning.
Stay informed about the latest technologies and trends in your field.
Network and connect with other professionals in your field.
As we’ve seen, the job market is changing rapidly, and the impact of AI on the workforce is becoming increasingly apparent. But, by continuously upskilling and staying informed, you can navigate layoffs and remain competitive in the job market.
Now, we want to hear from you. Are you worried about the impact of AI on the job market? Have you already taken steps to upskill and stay current in your field?
| 2023-01-24T00:00:00 |
2023/01/24
|
http://nuvepro.com/navigating-layoffs-in-an-ai-driven-job-market-the-importance-of-hands-on-learning-and-upskilling/
|
[
{
"date": "2023/01/24",
"position": 67,
"query": "AI replacing workers"
},
{
"date": "2023/01/24",
"position": 31,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/24",
"position": 16,
"query": "AI layoffs"
}
] |
Does AI Spark or Smother Human Creativity?
|
Does AI Spark or Smother Human Creativity?
|
http://richmondhires.com
|
[
"Courtney Turrin"
] |
The timeline for AI replacing human workers will depend on a variety of factors, including the complexity of the tasks involved, the rate of technological ...
|
Welcome to the Age of AI
Artificial Intelligence (AI) has become a buzzword in recent years. It has been talked about by business leaders, news outlets, and, increasingly, the general public. AI is no longer just something we see in our favorite science fiction stories or an enterprise tool for large companies but is becoming a reality that everyone can access. Yet, along with all of this excitement, there is also apprehension about what AI might mean for our future. In this blog post, we explore why people are both excited and fearful of AI as it becomes increasingly available to the general public and how AI will impact the future of work – especially for creative professionals.
AI Tools for Writing, Design, & More
AI tools such as Jasper and ChatGPT are changing how people interact with technology. These tools use natural language processing technology to understand complex human conversations and generate responses that sound like humans speaking. They can be used to provide information, respond to inquiries, and help automate customer service tasks. By leveraging machine learning algorithms, they constantly get more intelligent the more they are used.
The rapid growth of AI tools has raised a lot of interest and several concerns. While AI tools offer convenience and creative solutions, there is a fear that their use could lead to job loss and economic disruption. There is also a fear that AI will create new opportunities to manipulate people by feeding them biased or false information. Lastly, there are ethical questions around the data that powers AI as well as potential issues with privacy and copyrights. To better understand what the future may hold for both AI and for humans, we chatted with ChatGPT to get its take on the evolution of AI.
A Chat with a Robot about Where AI is Headed and What it Means for the Future of Work
How long will it take for AI to replace human workers?
It is difficult to predict exactly how long it will take for AI to replace human workers in certain industries or jobs. The timeline for AI replacing human workers will depend on a variety of factors, including the complexity of the tasks involved, the rate of technological advancement, and the willingness of employers to adopt AI solutions. Some jobs, such as data entry or repetitive manual labor, may be automated relatively quickly, while others, such as jobs that involve complex problem-solving or emotional intelligence, may be more difficult to automate. Additionally, the impact of AI on job displacement will also depend on the ability of workers to adapt to new roles and the overall economic environment.
What roles will humans still be best at as AI matures?
As AI matures, it is likely that humans will continue to be best at tasks that involve creativity, critical thinking, and emotional intelligence. These tasks often require a level of flexibility and adaptability that is difficult for machines to replicate. For example:
Creative roles such as writing, art, and design
Jobs that require high level of emotional intelligence like therapy, teaching, and customer service.
Jobs that require critical thinking skills such as healthcare, law, and financial analysis
Jobs that require common sense and human judgment, like decision making, and problem solving
Jobs that require a high level of physical dexterity, such as construction and repair work.
It’s also worth noting that AI can assist humans in these tasks, augmenting their abilities and allowing them to be more efficient and effective.
You listed creative roles as still being best done by humans. How do you reconcile that with the fact that some of the earliest AI technology to be widely available is responsible for impressive designs and writing that is superior to most human writers?
It is true that AI is becoming increasingly capable of creating designs and writing that is comparable to that of humans. However, while AI can produce high-quality designs and writing, it is still limited in its ability to generate truly original and creative ideas.
AI can be trained to produce designs and writing that is similar to a specific style or genre, but it can’t come up with something new, it can only generate variations of what it was trained on. Additionally, AI-generated designs and writing can lack the emotional depth and nuance that is often present in human-generated work.
That being said, AI is becoming more advanced, and it’s possible that in the future, it will be able to create truly original and creative designs and writing. However, it is unlikely that AI will completely replace humans in creative roles in the near future.
Taking AI’s Creativity for a Spin: Machine-Generated Poetry
Just for fun, I asked the AI tool Jasper to write a poem about marketing (what else?) in the style of a few well-known human poets. Here’s what Jasper came up with…
Screenshot of a chat with Jasper
Prompt: Write a poem about marketing in the style of Shel Silverstein
Marketing is a tricky thing,
It’s fancy and clever, it can make you king.
But if you don’t get the messaging right
Your brand could go up in smoke in one night.
There’s no secret rule to success,
It just takes some hard work and finesse.
So forget about the ad agencies,
You have to put the effort in, please.
Prompt: Write a poem about marketing in the style of Maya Angelou
Marketing requires a certain finesse,
Where grace and wit come together to impress.
The right words and images will draw the eye,
Making customers want to
try your pie.
Yet more than just visuals must be included,
For nods of approval the message be heeded.
Commonalities shared can help build the trust,
And create a connection that won ‘t turn to dust.
Prompt: Write a poem about marketing in the style of Edgar Allen Poe
Marketing must capture attention so strong,
That wallet ‘s will open without a thought of wrong.
It must contain a certain mystique and charm,
Where curiosity tempts the customer to no harm.
Cleverly crafted tales will make them pause,
And find your offering worth their cause.
The right message can bring success so grand,
An audience lost in its beauty like a faerie’ s land.
An Eye Toward the Future
As AI tools like Jasper and ChatGPT become more publicly available, creative professionals will undoubtedly be challenged to adapt their skills to a new technological landscape. However, this isn’t inherently bad, and the future of work for creatives is not bleak. As ChatGPT told us, human skills like creativity, critical thinking, and emotional intelligence cannot be replaced by a machine and will therefore become more important for creative professionals. In addition, the use of AI tools can provide insights that help people overcome traditional barriers associated with creativity, allowing them to explore new areas of content creation.
As AI continues to evolve, the possibilities are endless for those seeking to push boundaries in their field and be fearless about what the future of work may hold.
| 2023-01-24T00:00:00 |
2023/01/24
|
http://richmondhires.com/evolution-of-work/does-ai-spark-or-smother-human-creativity/
|
[
{
"date": "2023/01/24",
"position": 87,
"query": "AI replacing workers"
}
] |
Is Data Science Still a Dream Job?
|
Is Data Science Still a Dream Job?
|
https://dataaspirant.com
|
[
"Jeshwik Polamuri"
] |
Yes, Data Science is still a highly in-demand career with various job opportunities. With the increasing demand for data-driven decision-making, Data Science ...
|
Is Data Science Still a Dream Job?
Harvard Business Review calls the role of a data scientist or data science job as "the sexiest jobs of the 21st century. But data science Jobs are still in demand? Yes, Data Science is still a highly in-demand career with various job opportunities. With the increasing demand for data-driven decision-making, Data Science is emerging as an essential skill and becoming an integral part of many industries.
Is Data Science Still a Dream Job ? Click to Tweet
The Data Science job market is booming as employers recognize the potential of Data Science to drive business growth and innovation. According to recent reports, The demand for Data Scientists will experience an increase of 36% between 2021-31, as per a survey. As the number of businesses using Data Science to gain insights and make decisions continues to grow, the demand for Data Scientists is expected to continue to increase. Overall, Data Science is an excellent career choice for those looking to make an impact in the field of data-driven decision-making. With the growing demand for Data Scientists in India, it is a great time for professionals interested in establishing a career in Data Science.
Overview of Data Science It is an interdisciplinary field that uses algorithms (Machine Learning, Deep Learning), scientific methods, processes, and systems to draw information and insights from structured and unstructured data. It is a rapidly growing field that many organizations are adopting to help them make better and more innovative data-driven decisions. It solves numerous problems, such as Classification, forecasting, prediction, clustering, optimization, and customer segmentation.
Data Science involves collecting, cleaning, manipulating, analyzing, and visualizing data to develop insights and identify opportunities for improvement. A Data Scientist must have the ability to interpret data, build models, and design experiments to answer scientific questions. Data Science is also being used to help India become a leader in technology and digital transformation. It is used to develop technologies such as self-driving cars, autonomous robots, and virtual assistants to improve customer experience. Many industries use Data Science to create intelligent systems that enhance governance and public services. In stats wise from the beginning of 2012 data science related roles has seen a growth increase by 650 percent and the growth seen no stop at all. If the data science jobs are so crazy, what are the best ways to become data scientist then. Let’s address that in the coming section of this blog post. How to Become a Data Scientist?
To become a Data Scientist, candidates should start by acquiring an educational qualification or learn key conceps or techniques from Data Science Projects. This courses includes such as Statistics,
Operations Research,
Business Analytics,
Machine Learning,
Deep leanring ,
Artificial Intelligence, etc. Also, Indian e-learning portals have some of the best Data Science online courses, ranging from introductory to advanced levels. Many of these courses are offered by some of the country's leading universities, offering aspiring Data Scientists the chance to learn the skills and gain the knowledge needed to excel in the field. Besides the educational qualifications, candidates must also have a strong knowledge of data mining, data analysis, machine learning, and other related fields. Aspiring candidates need to have a good understanding of the programming languages such as Python, Java, R, SQL, and SAS and proficiency in analytics software such as Tableau and Power BI. If you are starting as beginner for data science we suggest to pick Python as your programming language. Experience in the field of Data Science is also a must to become a successful Data Scientist. To gain experience, professionals should consider taking up Kaggle projects
Internships
Working on Data Science projects This will help them better understand the industry and give them an edge over other candidates when applying for jobs. A strong work portfolio is also necessary to stand out in the industry. One should consider taking up short-term or part-time jobs related to Data Science, such as data analysts or data engineers. This will help candidates build their portfolios and make them more employable than the rest. Finally, students should consider taking up Data Science certifications, which will show employers that the candidates have the necessary skills and knowledge required for the job. Why Is Data Science in Demand?
Data Science is in high demand career, Which helps in transforming how businesses operate and providing a competitive edge to benefit organization growth. Data Science has become an essential part of the decision-making process for any organization, as it enables them to unlock potential insights from the data they have collected. The demand for Data Science is increasing due to the following factors: 1. Rapid Growth of Digitalization The world has seen exponential growth in the digitalization of businesses and services, which has led to a massive demand for Data Science professionals. Companies are leveraging Data Science to gain insights into customer preferences, optimize their processes, and gain a competitive edge. 2. Increase in Data Availability Data availability has increased significantly due to the rise of digital services such as e-commerce, online banking, and social media. This data can be used to gain valuable insights into customer behavior, preferences, and trends. 3. Need for Automation Automation is becoming increasingly important as companies look to reduce costs and improve efficiency. Data Science can automate mundane tasks and enable organizations to focus on more strategic initiatives. 4. Growth of E-Commerce The e-commerce industry is multiplying, and companies are leveraging Data Science to gain insights into customer behavior and optimize customer experiences. 5. Government Initiatives The Indian government is heavily investing in Data Science initiatives, such as the Digital India initiative, to drive economic growth. This has increased the demand for Data Science professionals in the country. Growing Job Opportunities and Salary Expectations
Data Science is an increasingly popular and lucrative field. The demand for Data Scientists is growing with the rapid growth of data-driven businesses. This means that job opportunities for Data Scientists are rising, and salaries are also competitive. The average salary for a Data Scientist in India is Rs. 10 lakhs per annum. However, salaries can vary depending on the experience and skill level of the individual. For instance, a senior Data Scientist can earn up to Rs. 20 lakhs per annum. There are several job opportunities for Data Scientists. Some of the most popular job roles include Data analyst
Data Scientist
Data engineer
Machine learning engineer
Artificial Intelligence engineer Companies like Amazon, Flipkart, Microsoft, and Google are actively hiring Data Scientists. In addition to job opportunities in the corporate sector, there is also a growing demand for Data Scientists in the government and public sectors. The Indian government has put in place various initiatives and policies to promote the use of Data Science in the public sector. The future of Data Science looks bright, as with the increasing demand for data-driven businesses, the job opportunities and salary expectations for Data Scientists are likely to grow. So if you're pursuing a career in Data Science, now is the time to make the jump. Conclusion Data Science is a rapidly expanding discipline that many organizations are adopting to use data to make informed decisions. With the heightened demand for data-driven businesses, job prospects and salaries for Data Scientists are expected to increase. The Indian government is significantly investing in Data Science initiatives, such as the Digital India initiative, to drive economic growth, resulting in a greater need for Data Science professionals in the country. For an advanced career in Data Science, candidates must opt for the post graduation in Data Science program. It is an opportune time to pursue a career in Data Science, particularly for those wishing to have an impact in the field of data-driven decision-making.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://dataaspirant.com/data-science-dream-job/
|
[
{
"date": "2023/01/24",
"position": 29,
"query": "machine learning job market"
}
] |
Responsibilities and Required Skills for Lead Data Scientist
|
Main Responsibilities and Required Skills for Lead Data Scientist
|
https://spotterful.com
|
[] |
Design and develop machine learning / artificial intelligence (ML / AI) algorithms. ... Stay on top of the sports job market! Subscribe to our newsletter.
|
A Lead Data Scientist is a senior-level professional who manages data projects and leads a team of data scientists within an organization. They understand and analyze data to drive growth and plan and prioritize data projects. In this blog post we describe the primary responsibilities and the most in-demand hard and soft skills for Lead Data Scientists.
Get market insights and compare skills for other jobs here.
Main Responsibilities of Lead Data Scientist
The following list describes the typical responsibilities of a Lead Data Scientist:
Align
Align data projects with organizational goals.
Assess
Assess the effectiveness and accuracy of new data sources and data gathering techniques.
Assess the potential usefulness and validity of new data sources.
Balance
Balance team and individual responsibilities.
Build
Build analytic systems and predictive models.
Build customer focused Next Best Action, Attribution & Segmentation models.
Build, lead and orchestrate the global data science community.
Build, train and evaluate prototype models, using a tool or framework of choice.
Build visualisations to help non-technical stakeholders understand impact.
Coach
Coach, guide and direct teams of internal and vendor resources.
Co-create
Co-create with business / market / functions or IT platforms on requirements.
Collaborate with
Collaborate across IT platform teams to deploy solutions and drive continuous improvements.
Collaborate and share with the technical community while educate customers on data platform.
Collaborate on building efficient data pipelines and workflows with our engineering team.
Collaborate with key stakeholders to remove barriers to delivery.
Collaborate with other Data Scientists / Machine Learning Engineers and provide technical direction.
Collaborate with the Product Team on requirements and priorities.
Collaborate with translators to define technical problem statement and hypothesis to test.
Communicate
Communicate complex analytical findings and implications to business leaders.
Conceive
Conceive, plan and prioritize data projects.
Conduct
Conduct and lead meetings and workshops to explain findings.
Contribute to
Contribute to building a positive team spirit.
Contribute to problem solving within a flat team structure.
Craft
Craft effective campaign strategies to acquire users across a multitude of user acquisition channels.
Create
Create alternative model approaches to assess complex model design and advance future capabilities.
Create and design visuals across a wide range of on and offline channels.
Create compelling presentations that provide actionable insights and recommendations.
Create systems and analyses to derive insights that change the studio's world view.
Create unsupervised learning approaches for monitoring anomalous behavior in transactions.
Customize
Customize this if you have information specific to the client's benefit package.
Define
Define and develop a data migration strategy between different products and platforms.
Define data science goals in conjunction with customers and our business teams.
Design
Design and build data set processes for modeling, data mining, and production purposes.
Design and develop customized interactive reports and dashboards in Tableau.
Design and develop machine learning / artificial intelligence (ML / AI) algorithms.
Design and evaluate novel scalable approaches to experimentation.
Design and implement prototypes using Python and Java programming language.
Determine
Determine best format to execute ideas.
Determine new ways to improve data and search quality, and predictive capabilities.
Develop
Develop A / B testing frameworks and test model quality.
Develop and implement strategies to automate production of methodologies.
Develop and / or use algorithms and statistical predictive models, including advanced models.
Develop creative ways to identify and use data that significantly impact key business metrics.
Develop data-driven solutions to difficult business challenges.
Develop documentation to support objectives of operationally-focused team members.
Develop executive presentations with guidance.
Develop processes and tools to analyze and monitor model performance while ensuring data accuracy.
Develop prototypes, proof of concepts, algorithms, predictive models, and custom analysis.
Develop security compliant user management framework for multi-tenant big data platform.
Document
Document analytics, models and test methodologies.
Drive
Drive and empower game studio to make quantitatively informed, evidence based decisions.
Drive innovation by creating new frameworks, prototypes and automation projects in relevant areas.
Drive stakeholder engagements by driving complex analytical projects including bottoms-up projects.
Drive the execution of the team and provide visibility to the projects and progress.
Embody
Embody technical leadership, recommend and enforce best practices.
Engage
Engage with global counterparts to share learnings.
Enhance
Enhance data collection procedures to include relevant data for building analytical systems.
Ensure
Ensure consistency of Tech Accelerator standards within the squad.
Ensure data quality and integrity.
Ensure proper escalation, prioritization, and remediation of data quality issues.
Ensure quality of data and solution developed.
Ensure the confidentiality and integrity of the information being accessed.
Execute
Execute on a plan for improving user outcomes with our analytics and ML.
Explore
Explore and validate new data sources that improves the performance of Kettle's current system.
Gather
Gather, analyse, and model data to solve complex business problems.
Generate
Generate stock lists and place orders.
Grasp
Grasp requirements on call and deliver to specification.
Grow
Grow people and their talent to perfect the team's execution.
Guide
Guide test design, research design, and model validation.
Help
Help develop analytics culture through mentorship and training.
Help lead and set up an R& D team looking at emerging technologies and evolution of AR / VR.
Identify
Identify and interpret trends and patterns in datasets to locate influences.
Identify additive data requirements and help source new datasets.
Identify, assess and prioritize the Analytics & AI Modeling needs of partners across the enterprise.
Identify opportunities to enrich and integrate data from multiple, diverse sources.
Identify rich data sources and monitors the melding and cleaning of datasets to ensure consistency.
Identify trends and patterns to inform business decisions and product design.
Implement
Implement algorithms to power user-facing data-driven features.
Implement approaches and communicate insights in a compelling narrative.
Industrialize
Industrialize the processing of terabyte sized datasets for model training and inference.
Interface
Interface with business and customer teams to define, and track goals.
Interpret
Interpret and analyze data problems.
Interpret data and analyze results.
Keep up with
Keep up with the current state-of-the-art in machine learning.
Lead
Lead AI Express customer engagements from a data science perspective.
Lead and drive in deploy and testing of the solutions and insights.
Lead the execution of large scale, more complex analytics projects.
Leverage
Leverage Python to analyze complex data.
Linear
Linear and logistic regression.
Maintain
Maintain a positive, results orientated work environment.
Make
Make recommendations regarding the collection, extraction, and transformation of large data sets.
Make sense of complex data and translate that data into meaningful analysis.
Manage
Manage projects and lead a sub-portfolio of data science project teams to deliver results.
Manage the research and development process to improve R& D planning.
Meet
Meet and collaborate with business users on requirements, objectives and metrics.
Mentor
Mentor and develops junior data scientists and analysts.
Mentor complex projects using wide breadth of data sciences and advanced techniques.
Mentor newly hired Data Coordinators and junior Leads.
Mentor other team members / analysts to grow their skills and careers.
Mentor the team of data scientist and analysts.
Oversee
Oversee QA / QC of data and output to ensure accuracy, completeness and reliability.
Own
Own and deliver projects of diverse scope.
Participate in
Participate and lead data quality and cleaning initiatives.
Participate in and initiate defining new business opportunities and products.
Participate in project reviews and demos.
Perform
Perform code reviews to guarantee high quality products moving to production.
Plan
Plan and coordinate work within your team.
Plan and manage analytics projects, presentations and status communications to stake holders.
Plan model operationalization and rollout of solutions to business users.
Present
Present findings to team lead / managers and to external stakeholders.
Present to Senior Management & Leadership.
Produce
Produce quantitative and qualitative modeling of business dynamics, user behavior, etc..
Produce statistical tests and summarize test outputs.
Promote
Promote best practices within the team.
Provide
Provide deep knowledge and leadership in NLP / NLU statistical analysis as a thought leader.
Provide guidance and mentorship to junior team members.
Provide guidance and support to Data Scientists within your team.
Provide input into strategy, analysis methods, and tool selection.
Provide rationale for design choices.
Provide recommendation on how to move forward.
Provide research on topics including Hello Alice's business model and recommendation techniques.
Provide statistical consultation services.
Provide support for technical guidance and training of other team members.
Provide support to stakeholders in understanding analytics, models and test results.
Put
Put success of team above own interests.
Read
Read plans and specifications.
Recommend
Recommend implementable solutions to (or in collaboration with) business partners.
Recruit
Recruit and coach other data scientists.
Refine
Refine data collection and storage procedures.
Research
Research alternative techniques and technologies.
Research and analyze data to find deep relations within data.
Research best way to leverage new and existing technologies in current modeling pipelines.
Return
Return to work and our new normal.
Scale
Scale and share technical assets.
Seek
Seek feedback and acts upon it.
Set
Set strategy and work closely with founders.
Share
Share knowledge with other team members pro-actively by creating / sharing works in forums.
Spot
Spot and evaluate emerging / cutting edge, open source, data science / machine learning libraries.
Supervise
Supervise modeling work of Associate Data Scientists and Data Scientists.
Support
Support deployment and maintenance of data pipelines and models in a production environment.
Support more junior data scientists with Change Management.
Take
Take advantage of available resources to advance their technical and business skills.
Test
Test and improve components of Kettle's machine learning wildfire models.
Test performance of data-driven products.
Test performance of data driven solutions.
Track
Track CRFs as they are processed through the Data Management department.
Track record of creating actionable insights that drive business impact.
Track Record of publishing in peer reviewed academic literature.
Translate
Translate ambiguous statements into structured problem statements and testable hypotheses.
Translate analytical insights into clear recommendations.
Understand
Understand business problems to implement scalable and sustainable solutions.
Understand, communicate, and manage the end-to-end lifecycle of analytics on a given project.
Understand our Operating Principles.
Understand the corporate climate and culture.
Utilize
Utilize statistical approaches to build predictive models.
Visualize
Visualize data and create reports.
Work
Work closely with Engineering team to productionize winning approaches.
Work closely with other tech teams and Product Managers.
Work daily with Data Scientists, Data Engineers, DevOps and Fullstack Engineers.
Work well in interdisciplinary teams.
Work with a variety of business stakeholders to identify and prioritize use cases.
Work with cool people and impact millions of daily players.
Work with industry experts to deliver ad-hoc projects and product prototypes.
Work with senior leaders from all functions to explore opportunities for using advance analytics.
Work with Senior Management to create Road map and understand goals.
Work with the business teams and customers to continuously improve those models.
Work with the data architect teams on Google Cloud Platform / Amazon AWS / Azure.
Work with the development team to incorporate data model-driven intelligence into the application.
Write
Write clear and concise documentation of processing approaches and results.
Write high-quality, maintainable, and portable code.
Write production code and communicate with the entire technical team to impact algorithm production.
Write reports articulating the analytics insights and their business impacts.
Most In-demand Hard Skills
The following list describes the most required technical skills of a Lead Data Scientist:
Most In-demand Soft Skills
The following list describes the most required soft skills of a Lead Data Scientist:
| 2023-01-24T00:00:00 |
https://spotterful.com/en/blog/job-description-template/lead-data-scientist-responsibilities-and-required-skills
|
[
{
"date": "2023/01/24",
"position": 58,
"query": "machine learning job market"
}
] |
|
Generative AI: how will the new era of machine learning ...
|
Generative AI: how will the new era of machine learning affect you?
|
https://www.ft.com
|
[] |
... AI and automation on jobs. Will the machines replace workers or, by taking ... “Instead of creating just single images, you could create whole videos or whole new ...
|
Try unlimited access Only $1 for 4 weeks
Then $75 per month. Complete digital access to quality FT journalism on any device. Cancel anytime during your trial.
| 2023-01-24T00:00:00 |
https://www.ft.com/content/1e34f334-4e73-4677-9713-99f85eed7ba0
|
[
{
"date": "2023/01/24",
"position": 78,
"query": "AI job creation vs elimination"
}
] |
|
The Non-existent Future of Work
|
The Non-existent Future of Work
|
https://www.milkenreview.org
|
[
"Anton Korinek",
"Megan Juelfs"
] |
And the range of tasks that AI systems can accomplish continues to grow beyond traditional rote computation into areas that involve creativity and even ...
|
Yet many discussions of a transition to a workless future propose that governments intervene in labor markets — for example, that governments should create or guarantee jobs, or that individuals should be made to work as a condition for obtaining government support. The implicit premise of such proposals in a world in which work is economically redundant is that the invisible hand is broken, i.e., that markets’ failure to deliver efficient outcomes justifies intervention.
Indeed, there are two distinct arguments to rationalize government intervention. One rests on what economists call “externalities”: when others gain or lose as a consequence of my actions. Examples include network effects, where my behavior enables other workers to build more valued social connections, or where work fosters greater political stability. There is also a potential for negative externalities — think traffic congestion and pollution that comes from millions of people getting into their cars and commuting to work.
The other argument is grounded in the less familiar term “internalities,” which arise when individuals make decisions that are not in their own best interest. This can go in either direction. For example, people may not sufficiently appreciate how the structure that work provides to daily life contributes to their sense of well-being. Conversely, workers may not sufficiently appreciate the risk that workaholism may eventually undermine their happiness because they give short shrift to their personal lives.
While these examples of externalities and internalities may in theory justify public intervention, we are unsure whether intervention would ever be wise in practice. One could easily imagine (at least in the United States) that public policy would be biased toward demanding work as the price of enjoying the dividends of machine productivity, but this may end up undermining the welfare gains that could be obtained from ever-more productive machines. As society becomes more accustomed to life without work, we believe that people will be able to find other — and superior — ways of fostering social connections and political stability as well as filling their days pleasantly. It would be a pity if technological advances allow humanity to enjoy a life of fulfillment in some combination of leisure and knowledge-seeking, but outdated views about the moral place of workforce individuals to perform tasks better done by machines.
That said, we do believe that public policy could be very helpful in the transition. If there is a future without human labor, it will not happen all at once. Machines will substitute for human labor in stages, and it would be desirable to make the transition as smooth as possible by leveling the impact of lower labor demand across the workforce. For example, the government might use financial incentives to encourage shorter workweeks and longer vacations, or reduce the age at which individuals can claim government retirement benefits.
| 2023-01-24T00:00:00 |
https://www.milkenreview.org/articles/the-non-existent-future-of-work
|
[
{
"date": "2023/01/24",
"position": 82,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/24",
"position": 11,
"query": "future of work AI"
},
{
"date": "2023/01/24",
"position": 62,
"query": "artificial intelligence wages"
}
] |
|
How AI and marketing will influence our future
|
How AI and marketing will influence our future
|
https://www.techtarget.com
|
[
"Senior Editor",
"Published"
] |
Learn how AI and marketing can change advertising, content creation and customer service with the help of predictive analytics and automation.
|
AI will continue to bring human versus machine comparisons in 2023, particularly with its growing influence in marketing and how marketing professionals do their jobs.
The AI industry could contribute up to $15.7 trillion to the global economy by 2030, according to the "Global Artificial Intelligence Study" published by PwC, the international consultancy. With AI-powered tools, marketing operation teams can spot trends, predict behavior and personalize marketing campaigns to target audiences.
What is AI?
AI is a type of computer science where machines model the human mind and perform tasks that need human intelligence using large data sets. AI algorithms make predictions and classify data based on their machine learning model.
People use AI every day without a thought. AI technology underpins smart assistants, such as Alexa and Siri, and chatbots for customer service. It also shows up in leisure activities, such as Netflix programming or in Amazon product recommendations.
"AI can be beneficial to corporations because it can speed up business decisions without human constraint," said Liz Miller, analyst at Constellation Research, based in Monte Vista, Calif. The following are some examples of how AI can help marketing professionals.
1. Content creation
ChatGPT made a splash when it was released in late November 2022 by OpenAI, the research lab arm of OpenAI Inc., which is based in San Francisco. There are other AI content generators available where users input a subject, type of content and key points to include and the machine spits out a draft, which some say is controversial for cheating and plagiarism.
AI content generators can also turn existing content into other forms. For example, Paul Roetzer, founder and CEO of the Marketing AI Institute in Cleveland, said he asks an AI content generator to turn his podcasts into blog posts, which the tool can do in a short period of time. However, the content still needs to be edited and reviewed. AI pulls information from set data, and it still requires fact-checking.
Users adopt AI content tools in different ways, depending on their skills, Roetzer said. A skilled writer may use it for a support tool to assist with an article, while someone that is not as strong a writer may use it more for help with writing emails or getting a first draft.
Learn more here about the pros and cons of AI-generated content.
2. Predictive analytics
Companies can use AI's predictive analytics to predetermine a customer's likely decision. It follows the "if someone does this, then that usually happens" model instead of marketing waiting for someone to take the action. AI technologies use algorithms to sort and analyze large amounts of data to find a specific objective. With AI, predictive analytics helps guide interactions with customers and businesses. AI can also personalize customer service content so it is relevant to each person and not a standard response to everyone, Miller said.
3. Chatbots
Chatbots use AI to converse with users. Their beauty -- at least according to companies that use them for customer service -- is that they can be available 24/7 to assist online visitors.
Chatbots are built with a set of rules, but AI can change these rules based on user behaviors, said Griffin LaFleur, senior marketing operations manager at Swing Education Inc., a San Mateo, Calif., company which matches substitute teachers with schools and students who need them. AI helps chatbots continue to learn to improve conversations based on data it collects from users. Training a chatbot is continuous with AI. As chatbots learn with each experience, it increases their ability to converse like a human.
4. Task automation
AI can automate tedious tasks, such as audio transcription. Transcriptions can be summarized into blog posts or short articles. Writers can use AI to update a company's existing content to different formats, such as turning a marketing brochure into an email draft.
AI can also take one social media post, update it and post it on different social media platforms. Each platform has different audiences and formats, but AI can use these formats and craft the message for each platform. It can create headlines and optimize for search engines, LaFleur said.
5. Email optimization
AI can punch up email marketing by increasing open rates and speeding up the development of custom campaigns. It can write email subject lines and personalize the content to different people. AI tools can also restructure an email campaign using historical data.
LaFleur noted that AI can optimize the send times for engagement based on each person. AI does this by analyzing the typical times this person opens emails and sends the email based on each finding.
AI can also clean up contacts and improve email lists quickly to ensure the company reaches the right customers.
6. Product recommendations
Product recommendations use customer data to say, "Customers who bought this typically bought that," or highlight products frequently bought together.
"This will be huge for e-commerce," LaFleur said.
Machine learning improves product recommendations as it improves predictions on products a customer will buy. AI-powered tools can make quicker recommendations based on each customer's preferences and behaviors.
7. Advertising
AI can uncover trends and insights that can enhance a company's advertising. For example, AI programs can send push notifications, write headlines, create digital ads and personalize messages with a company's language and tone.
AI can also help with generational marketing by personalizing the messages to different audiences through language, music, images and style instead of the one-size-fits-all ad.
| 2023-01-24T00:00:00 |
https://www.techtarget.com/whatis/feature/How-AI-and-marketing-will-influence-our-future
|
[
{
"date": "2023/01/24",
"position": 84,
"query": "AI job creation vs elimination"
}
] |
|
Report Says AI Could Potentially Replace 85 Million Jobs ...
|
Report Says AI Could Potentially Replace 85 Million Jobs Worldwide By 2025 — Are Interns On The List?
|
https://www.yahoo.com
|
[] |
The future of work lies in the hands of technology — literally. According to a press release, tech-marketing agency Codeword has announced that their latest ...
|
The future of work lies in the hands of technology — literally.
According to a press release, tech-marketing agency Codeword has announced that their latest interns aren’t actual humans, but instead fully operate on computer-generated software.
Meet The Interns
“There’s a lot of talk and fear and hype about how new AI tools will integrate with creative teams,” said Kyle Monson, partner at Codeword, according to a press release. “As an agency that straddles the creative and technology worlds, we want to explore what human-AI collaborations can look like. And we’ll do it in public, so our team and our community can learn from this experiment.”
Artificial Intelligence Takeover
Artificial intelligence isn’t only replacing interns.
Advertisement Advertisement
Advertisement
As previously reported by AfroTech, the world’s first robot lawyer was set to take on an official court case through a company that aims to eliminate the extensive fees that come with both hiring a lawyer and racking up parking tickets.
Now, interns Aiden and Aiko have not only joined Codeword as interns, but thanks to AI, reports reveal that they have been able to create their own visual projects, work alongside various teams at the organization, and have even given themselves their respective names.
“I am designed to be helpful and efficient,” said Aiden in a press statement. “I believe that I could be a valuable resource as an ‘intern,’ although my abilities would be somewhat different from those of a human intern.”
What Does This Mean For Human Workers?
While technology continues to evolve and make the world a bit more simple, the question becomes whether or not AI can pose a threat to people’s jobs.
Advertisement Advertisement
Advertisement
The World Economic Forum suggests that AI will replace 85 million jobs across the globe by 2025.
Additionally, the organization’s “The Future of Jobs Report 2020″ suggests that the technology will also create 97 million new jobs within the next few years.
“We see a ton of potential here to produce great work faster, and move some of the more banal tasks off human plates so our people can better focus on actual high-value work for our clients,” said Codeword’s Senior Editor Terrence Doyle in a statement via a press release. “It’s an opportunity to streamline internal processes by eliminating necessary but mind-numbing and time-consuming tasks — or at least to pass them off onto emotionless interns who can’t get bored. If we can make that work, it’ll be a win for our team and for our clients. That said, I’m a former freelance journalist, and I do a lot of ghostwriting for Codeword’s clients, so I’d be a liar if I said I wasn’t sort of terrified by the creative — or, rather, ruthlessly productive — capacity of AI.”
| 2023-01-24T00:00:00 |
2023/01/24
|
https://www.yahoo.com/tech/report-says-ai-could-potentially-203330619.html
|
[
{
"date": "2023/01/24",
"position": 57,
"query": "future of work AI"
}
] |
The importance of hiring for skills and how AI can help
|
The importance of hiring for skills and how AI can help
|
https://eightfold.ai
|
[
"Carly Ackerman",
".Pp-Multiple-Authors-Boxes-Wrapper.Pp-Multiple-Authors-Layout-Inline.Multiple-Authors-Target-Shortcode .Pp-Author-Boxes-Avatar Img",
"Width",
"Important",
"Height",
"Border-Style",
"None",
"Border-Radius",
".Pp-Multiple-Authors-Boxes-Wrapper.Pp-Multiple-Authors-Layout-Inline.Multiple-Authors-Target-Shortcode .Pp-Author-Boxes-Meta A",
"Background-Color"
] |
Deep-learning AI uses neural networks to gather information about the talent ecosystem, including the best candidates for a job, learning pathways for employees ...
|
While it may be a new year, skills will remain a fixture of high-impact talent strategies for the foreseeable future. According to McKinsey, hiring for skills is five times more predictive of job performance than hiring for “check-the-box” qualifications like education and pedigree of previous employers. Without a talent strategy rooted in skills data, organizations are likely missing great opportunities to engage and promote extraordinary talent.
With a topsy-turvy economy and enough hiring freezes to cause an ice age, today’s market is highly unpredictable, and organizations are losing productive talent. And while some are weathering the storm, future disruption is inevitable. Without the right skills to adapt, organizations could fall behind.
Today, most technical skills are considered “perishable,” with a half-life of two to three years. We can almost see the “aging out” of skills in real time. For example, Eightfold Talent Insights shows that demand for drilling engineers (one of the most common jobs in the oil and gas industry) is plummeting, while demand for chemical and mechanical engineers (up-and-coming skills) is soaring.
This pattern persists across industries. Unfortunately, most organizations still need to dig themselves out of pandemic- and recession-induced skills gaps and catch up with this pace of change. Without action, these skills gaps will grow, and organizations will lag behind competitors taking a skills-first approach to managing talent.
To build a more agile workforce, it’s not enough to hire top talent. Skills change too quickly. Instead, HR teams need to invest in developing their existing workforce to help them gain the right skills for today and tomorrow. Here’s how artificial intelligence can give organizations real-time insights into the skills of their workforces, competitors’ workforces, and the overall market.
A skills-driven approach
Focusing on skills isn’t an entirely new concept. Competency models and skill taxonomies have been the go-to for quantifying people’s abilities and performance levels for years. But these static tools require too much time and manual effort to inform a successful talent strategy. When a consulting firm finishes the painstaking work of defining different roles and accompanying skill requirements, jobs have already changed to the point where the competency models are no longer valid.
With deep-learning AI, organizations can accelerate skills-driven talent strategies, gaining real-time insights into the skills of both internal and external talent. AI can analyze billions of global talent data points to determine employees’ and candidates’ skills and their potential to learn (or do more) with incredible accuracy.
Once talent managers can see their teams’ skills in real-time, they can drill into which skill gaps exist or might exist soon, then decide to bridge them with any combination of upskilling, reskilling, or hiring.
If talent managers go the hiring route, they can sit down with recruiters and define ideal candidates by breaking down jobs into must-have skills. AI helps recruiters jumpstart their search by sourcing top profiles from a prebuilt pipeline of current employees, contingent workers, previous applicants, and even company alums. Then, once recruiters post a job, AI screens résumés for those must-have skills, ranking the strongest matches first.
Deep-learning AI uses neural networks to gather information about the talent ecosystem, including the best candidates for a job, learning pathways for employees, and which contingent workers to redeploy. A talent intelligence platform’s dataset, consisting of millions or billions of data points, is essential for providing accurate recommendations about jobs and skills. The dataset should also be regularly updated to provide real-time insights about a person’s potential, career trajectory, and skills. It should also continuously update itself to provide relevant information and insights.
If talent managers choose to upskill, they can use AI to build personalized training paths for their teams by surfacing relevant courses, mentorships, and project opportunities. A transparent marketplace helps employees gain a much richer understanding of the career paths available, exposing them to the skills they need for open roles and experiences best suited to help them quickly upskill.
77% of business executives agree their organization should help their workers become more employable with relevant skills, but only 5% strongly agree they are investing enough in helping people learn new skills to keep up with the changing world of work. — The skills-based organization: A new operating model for work and the workforce, Sue Cantrell et al.
The benefits of a merit-based approach
It shouldn’t matter if a candidate is an ex-Apple employee, golfs with the CFO, or went to an Ivy League school. By moving the focus away from subjective success criteria, talent leaders can make decisions based on a person’s skills and potential, creating more equitable talent outcomes.
This potential-based approach helps organizations maintain an adaptable, skills-rich workforce ready for whatever is next. No matter how the economy changes, your organization will be better positioned to survive and thrive with the right strategy to cultivate and build skills. Making talent decisions based on accurate skill data is the best way to ensure smart talent decisions.
Carly Ackerman is the Director of Customer Experience for VIP & Partnership Accounts at Eightfold AI. Working closely with pioneering leaders, she has contributed to broad organizational and workforce transformations designed to meet the evolving demands of a disrupted global economy. Carly is a frequent speaker and thought leader on talent trends, workforce transformation, upskilling, and the employee experience.
To learn more about a skills-driven approach, read our new e-book, How to build an agile workforce with a skills-driven approach.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://eightfold.ai/blog/importance-hiring-for-skills/
|
[
{
"date": "2023/01/24",
"position": 81,
"query": "future of work AI"
}
] |
Adding AI to Supply Chain Management - Articles
|
Adding AI to Supply Chain Management
|
https://www.automationalley.com
|
[
"Sme",
"Society Of Manufacturing Engineers",
"Michigan Economic Development Corporation",
"Haissam Badih",
"Automation Alley",
"Additive Manufacturing",
"Nicole Kampe",
"Kelly Services"
] |
Atlanta-based Verusen developed an AI to track and analyze supply chains in order to prevent disruptions. Anheuser-Busch is an early adopter.
|
The bare shelves left in the wake of the pandemic made everyone aware of how fragile a supply chain can be, and how far the effects the disruption it caused can travel. But a new self-learning software promises to prevent this from happening again.
Verusen, an Atlanta-based supply chain materials intelligence provider founded in 2015, has developed an artificial intelligence (A.I.) system that the company says can identify and provide the tools to lower risk, increase inventory visibility, and optimize capital.
Customers are seeing $5 million to $50 million of working capital savings, averaging a nearly 345 percent return on investment, according to Verusen. This is achieved by reducing material redundancy and operational inefficiency, which reduces unneeded spending.
Read more here.
| 2023-01-24T00:00:00 |
https://www.automationalley.com/articles/adding-ai-to-supply-chain-management
|
[
{
"date": "2023/01/24",
"position": 64,
"query": "AI economic disruption"
}
] |
|
AI ChatGPT – the next great hype cycle?
|
AI ChatGPT – the next great hype cycle?
|
https://www.janushenderson.com
|
[
"Alison Porter"
] |
Where will this disruption be felt the most? 1. Disruption to search ... economic conditions. A concentrated investment in a single industry could be ...
|
Investors have quickly jumped into the hype and debate around ChatGPT. Launched at the end of November 2022, it reached over a million users in one week (it took Netflix 3.5 years) and Microsoft CEO Satya Nadella has called it “the biggest technological platform of the generation.” The interest on Google, Twitter, and investment blogs as a trending topic certainly qualifies it for entering a hype cycle phase!
Our team adopted artificial intelligence (AI) as one of our mega themes seven years ago. For decades, technology companies have focused on enhancing the interface between users and technology.
We view ChatGPT as another step on the path of AI’s integration into everything tech. From a user perspective, we continue to believe that AI integration is key to democratising technology usage over the long term. And that its development will be ‘evolutionary and not revolutionary’, similar to our view on the metaverse.
From an infrastructure perspective, we think ChatGPT is more meaningful, bringing us closer to a watershed inflection point from AI focused on perception (interpretation of sensory data such as images, sound, and video) to generative AI (creation of new content), which will require exponentially greater computing power.
What or who is ChatGPT?
ChatGPT is a chatbot released by AI research group OpenAI, an artificial intelligence research company founded in 2015 by Sam Altman and Elon Musk, amongst others. OpenAI was originally set up to ensure that AI was developed with a focus on safety and benefits to humans. It began as a non-profit organisation and evolved into what is known as a ‘capped profit’ company-hybrid of for-profit (OpenAI LP) and non-profit (OpenAI non-profit) so that it could scale up by raising additional capital and attract talent. The limited partnership currently has several hundred employees, with Microsoft the lead investor (circa $1bn initial funding in 2019, with a further $10bn confirmed recently). OpenAI has three primary offerings today: ChatGPT, art generator DALL·E 2, and automatic speech recognition model, Whisper.
ChatGPT is based on Generative Pre-training Transformer (GPT) – a large-scale natural language model (LLM). Users submit questions to ChatGPT, which is designed to respond with human-like (coherent/natural) answers. In simple terms, it’s a broad-based, highly sophisticated chatbot that offers answers that read like they are coming from a human. The living nature of the software is why, futuristically, ChatGPT is not referred to as a ‘what’ but as a ‘who’.
GPT-3 enables better understanding of context and is paving the way for generative AI as opposed to responses and analysis based on existing data. In the past, neural networks were trained on data labelled by humans. This was both time consuming, costly and limiting. Transformer models self-learn, require much less human curation but much larger datasets and computing power to crunch exponentially larger models. With GPT-4 potentially launching later in 2023, there will likely be further improvements in terms of user experience/interface and the path towards monetisation.
ChatGPT’s implications for the tech universe
Microsoft’s CEO recently confirmed that the company is looking to rapidly commercialise, with their cloud platform Azure OpenAI service now generally available, integration of OpenAI text-to-image generator (DALL·E 2) into the new Designer app and also, the intention to incorporate ChatGPT into Microsoft’s Bing search engine and other MS Office-based functions.
Where will this disruption be felt the most?
1. Disruption to search – the innovator’s dilemma
The first area where ChatGPT is thought to represent a disruption threat is Google Search, based on the notion that natural language models could increase users and then take a share of search queries, becoming a new entry point for people on the internet. ChatGPT responses can make Google Search’s responses seem basic as it has conversational abilities, filtering technology and the ability to ingest data.
In voice recognition, Siri, Amazon and Alexa have already provided other challenges to search as have TikTok and Instagram with video search. As the app store emerged there were concerns about the impact of direct-to-app on Google’s search business. Ultimately, the evolution of hot-app store and in-app search benefited Google because of its unparalleled ability to scrape information from all parts of the internet. While we recognise the emergence of disruptive technologies to search, the law of large numbers, cyclical and privacy-related threats could be more pressing for Alphabet in the near term.
We are not dismissive of the threat but do think it is an overly simplistic view. Google was the earliest and a strong proponent of AI and machine learning having first mentioned it some 20 years ago in its 2005 annual report. Alphabet’s most recent investor call discussed AI-powered search (and large language models) as being the most important of its four key investment initiatives, namely AI, YouTube, hardware and cloud. Alphabet has invested heavily in AI, with circa $177bn1 spent on research and development and capital expenditure between 2000 and 2022, with around half of its employees focused in some way on AI and machine learning.
Alphabet has several products already in operation but must consider how to develop and adapt these without cannibalising its existing and highly profitable search business (the innovator’s dilemma) and raising significant regulatory and moral concerns.
Beyond monetisation there are numerous considerations when developing these AI models:
Trust and accuracy
LaMDA is a similar natural language model to ChatGPT and was famously called ‘sentient’ by one of its engineers. While strong conversationally, the complexity of human conversation and language means ChatGPT’s results are lacking in terms of accuracy, context and trust. So, the issue facing Google Search and Microsoft Bing is not the simulation of answers, but ensuring that ‘generative’ answers do not become ‘fabricated’ results without credible sources. Introducing it to Search will likely lead to more regulatory scrutiny of AI as it can bring some negative consequences. Google Search limits potentially harmful searches like how to hotwire a car, build a bomb or stalk online. ChatGPT currently has no restrictions on type of query nor filters on accuracy or truth, which can be dangerous given its ability to mimic human likeness.
Scale and timeliness
Google has an estimated 4bn+ daily users, with billions of searches per day. Search is iterative in accuracy and users want the most accurate information. While able to deal with complex questions, ChatGPT lags in timeliness and hence accuracy of answers.
Google has seen a rapid rise in queries that are location-based or require time-bound answers, eg. ‘latest’ or ‘news now’. The advantage of Google Search, which Bing and other search engines have been unable to replicate, is not only the ability to index and serve results, but also crawling ability – downloading text, images, and videos via automated programmes. There is no central registry for web pages. Discovery and updating is key so that the latest information eg. store opening and closing times, news across the web, and data are essential to produce accurate and timely responses. The volume and consistency of consumer activity speaks to how utility is derived from Google, so driving significant differentiation and change will be challenging.
Cost
There are fundamental differences in how Google indexes pages and how large language models ingest data. Indexing at Google’s scale would be cost prohibitive for ChatGPT; the current cost per query is estimated to be around $0.02 per query on average. The cost is highly dependent on the words generated per ChatGPT query and the size of the algorithm. ChatGPT’s cost per query is around seven times more than Google Search, which will make commercial monetisation more challenging without significant increases in spending on compute power.
2. Impact on computing power, the cloud, and semiconductors
While GPT-2 (late 2019) was launched with only 1.5 billion parameters, ChatGPT-3 was trained with 175bn parameters. GPT-4 is expected to take this into the trillions. Microsoft estimates that the computing requirements for AI training doubles every 3.5 months!. As a result, graphics processing unit (GPU) designer and manufacturer nVIDIA designed its latest Hopper GPU architecture with a dedicated transformer software engine, enabling 9x the AI training performance, or 3x the performance at the same power, which is an increasingly important metric given climate change targets.
Mega cap tech companies have been declaring their plans for AI investment in recent years. Particularly notable is Meta’s more than $35bn guide for capital expenditure in 2023, largely driven by further investment in AI/machine learning and higher-end GPUs to allow for more analytics and computing power for its algorithms.
Driven by a weaker economic backdrop and outlook for revenues over the next three months we have witnessed a birth of cost consciousness within large cap tech companies. Despite headcount reductions for some of these companies, we believe spending will continue to be directed to AI/ML applications that are viewed as having higher monetisation opportunities, with ChatGPT adding fuel to an AI arms race amongst hyperscalers.
The increasing use of AI has positive implications for the semiconductor giants and will accelerate the shift to cloud computing as the intensity of compute power needed will require a pooling of resources and barriers to entry in terms of capital expenditure.
3. Threat of competition in software
A recent survey by networking app Fishbowl2 showed that drafting emails and generating bits of code are typical use cases for users of ChatGPT and other AI tools. It also revealed a broad-based pick up in usage across a variety of industries, with over 30% of respondents in marketing and advertising, tech and consulting having used these tools at work.
ChatGPT’s underlying GPT-3 technology could be deeply disruptive to several areas:
Coding and software development
The success of Microsoft’s GitHub Copilot and DeepMind’s AlphaCode shows that this technology can help to both automate coding and improve the quality of that code. Coding can be very expensive and there is an opportunity to extend what started as low-code/no-code platforms with machine learning. On New Year’s Day this year, Andrej Karphathy, Tesla creator of Autopilot tweeted that 80% of the code he writes today is done using GitHub Copilot.
Detection of data security and vulnerability
OpenAI has shown that it can detect some data security vulnerabilities in code samples.
Education, essay-writing capabilities, maths questions and tutoring availability
ChatGPT has caused concern in the academic industry given its ability to create books and essays in a short period of time, and recently even passed a Wharton MBA exam. Companies such as Chegg have built competitive moats around being able to answer complex student questions and while ChatGPT still lags in being able to meet the same level of response, generative AI is getting better – and quickly.
Medicine and vaccine development
Pattern matching against a defined knowledge base is an increasing use case and opportunity. However, many scientists are also concerned that AI is able to write convincing fake research that may be very difficult for researchers to differentiate.
Customer service and sales functions
There is an opportunity to extend virtual agent models. ChatGPT is used by businesses to enable employees to access key information. For example, what is Janus Henderson’s latest view on 10-year Treasuries? What is Janus Henderson’s maternity leave policy? While answers may face many of the same accuracy and timeliness issues of search, longer term it may create a competitive headwind for companies such as Salesforce and HubSpot.
Content creation
An unappreciated implication of recent AI developments is the impact on content creators and software developers. Alphabet’s DeepMind subsidiary announced the release of Dramatron, a scriptwriting software enabling writers to co-create theatre and film scripts (complete with title, characters, location descriptions, and dialogue). Meanwhile, OpenAI’s DALL·E 2 can create realistic images and art from a description in natural language. For example, in just two minutes, it was able to generate an image of what the Mona Lisa looks like with a body.
Simulation
Podcast.ai, a series of completely AI-generated podcasts, released a 20-minute interview between Joe Rogan and the late Steve Jobs touching on faith, tech companies, and drugs. AI can effectively provide tools for creators, giving them the ability to create without deep coding knowledge. As with search, the lines between reality and simulation is becoming blurred and trust in creators and moderation will become more important. This has relevance for how we see new content created in the digital world of the metaverse.
There is a significant opportunity for hyperscalers like Amazon Web Services, Microsoft Azure, Google Cloud Platform and Meta to accelerate the roll out of AI processes for their own applications, and over the long term this will create competitive challenges for application software providers. We see this as a key reason for tech giants like Microsoft and Amazon investing in OpenAI, driving its potential valuation up to $29bn.3
Evolution, not revolution
The coming of age of artificial intelligence is moving closer, but similar to our view on the metaverse this is an evolution rather than a revolution that has been long underway. There continues to be a powerful convergence of key technology themes – for example the interplay between next generation infrastructure enabling greater computing power, which is facilitating AI and metaverse developments, which in turn require more computing power.
Hence while we continue to be excited by the opportunities that AI/ChatGPT provide, the many beneficiaries of the metaverse and broader shift to AI, we also recognise the cyclical pressures and regulatory hurdles to overcome until we see widescale adoption.
The hype cycle
Note: for illustrative purposes only.
As experienced tech investors we caution on being caught in niche thematics and to consider not only the long-term opportunity, but also existing competitive moats, the pace of the tech adoption curve by navigating the hype cycle and exerting reasonable valuation discipline.
Footnotes and definitions
1 JP Morgan North America Research: Internet, as at 19 January 2023, figures for 2020-22E. 2 Fishbowl, Jan 17 2023: ChatGPT Sees Strong Early Adoption In The Workplace. 3 The Wall Street Journal, 5 January 2023. Hyperscalers: companies that provide infrastructure for cloud, networking, and internet services at scale. Examples include Google, Microsoft, Facebook, Alibaba, and Amazon Web Services (AWS). Tech democratisation: the process by which technology rapidly becomes more accessible to more people. Drivers include new technologies and improved user experiences, increasing participation in the development of products, more affordable user-friendly products as a result of industry innovation and user demand. Innovator’s dilemma: a theory that describes companies whose successes and capabilities can actually become obstacles when faced with changing markets and technologies. Large companies tend to choose to overlook disruptive technologies until they become more attractive profit-wise. Disruptive technologies, however, eventually surpass sustaining technologies in satisfying market demand with lower costs. When this happens, large companies who did not invest in the disruptive technology sooner are left behind. Navigating the hype cycle: the “hype cycle” represents the different stages in the development of a technology, from conception to widespread adoption, which includes investor sentiment towards that technology and related stocks during the cycle.
IMPORTANT INFORMATION
Technology industries can be significantly affected by obsolescence of existing technology, short product cycles, falling prices and profits, competition from new market entrants, and general economic conditions. A concentrated investment in a single industry could be more volatile than the performance of less concentrated investments and the market.
| 2023-01-24T00:00:00 |
https://www.janushenderson.com/corporate/article/ai-chatgpt-the-next-great-hype-cycle/
|
[
{
"date": "2023/01/24",
"position": 89,
"query": "AI economic disruption"
}
] |
|
Job at Yalo
|
Job at Yalo
|
https://www.yalo.ai
|
[] |
Current openings at Yalo Inc. Create a Job Alert. Level-up your career by having opportunities at Yalo Inc. sent directly to your inbox.
|
Flow Builder
Build, launch and test conversational commerce flows with just a few clicks.
Engagement
Drive high-quality conversations with your customers through Mobile Marketing campaigns.
Commerce
Sell your products and grow your customer reach with the first native conversational commerce solution.
Sales Desk
Transition shoppers seamlessly from chat to human agents on WhatsApp with Yalo Sales Desk's native integration into your conversational commerce solution
Analytics
Optimize your conversational strategy and grow sales with a holistic view of your customer.
GenAI
Build, launch and test conversational commerce flows with just a few clicks.
Yalo Clouds
Transform your business ecosystem with Yalo Clouds
| 2023-01-24T00:00:00 |
https://www.yalo.ai/careers/job
|
[
{
"date": "2023/01/24",
"position": 26,
"query": "generative AI jobs"
}
] |
|
ChatGPT Isn't Coming for Your Job (Yet)
|
ChatGPT Isn't Coming for Your Job (Yet)
|
https://reason.com
|
[
"Joakim Book",
"Jack Nicastro",
"C.J. Ciaramella",
"Matthew Petti",
"Jacob Sullum",
"Elizabeth Nolan Brown",
".Wp-Block-Co-Authors-Plus-Coauthors.Is-Layout-Flow",
"Class",
"Wp-Block-Co-Authors-Plus",
"Display Inline"
] |
This new technology will take away jobs from white-collar workers, content-generating AI will probably enhance human labor rather than make it obsolete.
|
When ChatGPT was introduced to the general public at the end of last year, many people began to fear that artificial intelligence (A.I.) might soon make their job obsolete.
Of course, horse-and-buggy-makers are gone, and farming requires something like one-hundredth of the labor input it used to. That's a good thing: Professions have gone extinct for centuries. New jobs emerge in the wake of old ones. A reshuffled labor market requires workers to gain different skills, while companies focus on solving different problems. That can be tough if you're in your mid-50s and on the receiving end of that technological shift, but it's not a catastrophic obstacle for economies at large.
Up until now, machines had been unable to venture into the creative domains long deemed human: the realms of emotion, compassion, creativity, and personality. There are few bestselling novels written by a computer, A.I.-powered inspirational speakers, or robots providing psychological help to clients in need. Some people now fear that A.I. will learn even these soft skills.
Economist Nouriel Roubini devotes a chapter in MegaThreats: Ten Dangerous Trends That Imperil Our Future, and How To Survive Them to A.I. He lists example after example of robots inching closer to overtaking humans at our own game. "What happens," he asks, "when that technology is actually intelligent? … No matter what work you do, artificial intelligence might eventually do it better." Surely a robot can't connect with an opera audience, or mimic writing that creates that magic bond between author and reader.
With this in mind, I looked at two programs in my own fields of writing and translation: OpenAI's ChatGPT, the text-generative A.I. that made such a social media splash in the last two months, and DeepL, developed by a German startup that just raised money at a $1 billion valuation. Both indicate that there's something to this latest bout of technological scare, but that mass employment among knowledge workers is still a ways off.
The service Grammarly already helps with language flows. Most word processors have built-in spell check. Even though keeping track of commas and hyphens should be easy, it usually isn't. Writing new content is even more of a stretch.
All over social media, I found examples of ChatGPT-generated output that looked humanish. That is, if you count the stumbling and robotic prose you might get from a 12-year-old or a bored college student fulfilling their essay's word requirement via endless rephrasing. Most ChatGPT writing I've seen is dull, shallow, and soulless—none of the characteristics that make good writing come alive.
Roubini thinks mass unemployment due to A.I. is inevitable in the coming years. What the best A.I. writing generators put out is indeed indistinguishable from bad human writing. Bad writers, cheating students, lazy professors, and journalists echoing press releases have clearly met their match. But the more human, creative, authentic storytelling that is the center of all meaningful writing has not.
For translation services, progress has been much more impressive. Between some language pairs, Google Translate has already gone from being a complete joke to being quite usable—even for technical texts, like legal documents, which were previously Linguee's forte. DeepL noticeably improves on Google Translate's output and was "originally trained on a database of over a billion translations and queries, plus a method of double-checking translations by searching for similar snippets on the web," according to its developer.
When I sparingly used DeepL for a recent translation project, it performed miles better than other software. It translated blocks of text much faster than a human ever could but its accuracy, vocabulary, and understanding of context was still subpar, rapidly deteriorating with a sentence's complexity. For single words or phrases, established two-language dictionaries often produced more exact translations. DeepL is an impressive feat of translation progress, of course, but still in need of human supervision.
While pessimists like Roubini frequently express fears that this new technology will take away jobs from white-collar workers, content-generating A.I. will probably enhance human labor rather than make it obsolete. Robert Wright and Aleksandra Przegalinska conclude that "Humans will use AI as yet another tool, much like they have used Acheulean hand axes and satellite-controlled tractors to do more work in less time or with less energy"—just like so many other technologies have done before it.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://reason.com/2023/01/24/chatgpt-isnt-coming-for-your-job-yet/
|
[
{
"date": "2023/01/24",
"position": 31,
"query": "generative AI jobs"
}
] |
Will ChatGPT Replace Your Job?
|
Will ChatGPT Replace Your Job?
|
https://mondo.com
|
[
"Sarah Magazzo"
] |
ChatGPT (Conversational Generative Pre-trained Transformer) is a powerful ... The Rise of AI Majors: Transforming the US Job Market · Industry Insights ...
|
ChatGPT is a powerful language generation tool that has the potential to revolutionize the way we interact with technology.
However, it is important to note that ChatGPT is not designed to replace human jobs, but rather to enhance and augment them.
With its roots in technology and content creation, what does this mean for professionals in Tech, Digital Marketing, and Creative roles specifically?
What is ChatGPT?
ChatGPT (Conversational Generative Pre-trained Transformer) is a powerful language generation tool developed by OpenAI. It uses natural language processing algorithms to generate human-like conversations, with data collected from various sources. It is capable of responding to user input in a conversational format and also can create content from scratch.
Will ChatGPT replace different Tech jobs?
ChatGPT is a language model that can generate text based on the input it receives, it can be used to automate certain tasks that involve writing or data entry. However, it is not a specialized automation tool and its capabilities are limited to text generation.
Will ChatGPT replace Programmers?
The short answer is no. While it can be used to generate code snippets or simple scripts, it’s not a replacement for programmers.
According to ChatGPT itself, “the quality and correctness of the generated code cannot be guaranteed and it should always be reviewed and tested by a human developer before being used in a production environment.”
Will ChatGPT replace Software Engineers & Developers?
It is important to remember that ChatGPT cannot replace a software engineer or designer since it lacks the creativity and problem-solving skills that are required of these professionals.
ChatGPT can, however, be used to help software engineers and designers speed up the development process by providing them with a way to quickly generate code snippets to use as a starting point.
Will ChatGPT replace Data Engineers?
Data engineers are not likely to be replaced by ChatGPT for the same reasons as programmers and software engineers.
Data engineers would be wise, to leverage ChatGPT to aid data teams in some specific tasks to extract, transform, and load — ETL — however, it can’t replace specialized software and expertise in the ETL process.
Will ChatGPT replace Data Scientists?
Data scientists are not in danger of being replaced by ChatGPT as it lacks the same level of intelligence and creativity.
However, while data scientists can leverage ChatGPT to aid in some specific tasks such as data cleaning, it cannot replace the nuance and specialized software needed for gathering, cleaning, and creating data models.
Will ChatGPT replace Cloud Architects?
ChatGPT can be used to automate some of the more tedious aspects of a Cloud Architect’s job such as creating cloud infrastructure, provisioning resources, and managing deployments.
However, it is not a specialized tool for cloud architecture and its capabilities are limited to text generation. As such, it doesn’t have the capability to design or manage cloud infrastructure.
Will ChatGPT replace Game Developers?
Game developers have a lot to gain from using ChatGPT as it can be used to speed up the development process.
From creating game environments and storylines to generating dialogue and crafting artwork, ChatGPT can take over some of the more time-consuming tasks.
That being said, game developers are likely to remain in high demand as ChatGPT cannot replicate the level of creativity, real-time problem-solving skills, and technical expertise needed to develop a successful game.
Will ChatGPT replace Marketing jobs?
In the field of marketing, ChatGPT can be used to generate creative content and improve the personalization of marketing campaigns. This can help companies reach their target audience more effectively and increase conversions.
Will ChatGPT replace copywriters?
While ChatGPT can assist content writers by generating text-based content and ideas for new content, it still needs human input and the strategic mindset of a content writer in order to function.
Human content writers have a creative and strategic approach to writing that ChatGPT cannot replicate on its own.
So, while ChatGPT can help content writers in certain tasks, it can’t replace the expertise, experience, and skills offered by human content writers.
Will ChatGPT replace Digital Content Strategists?
Content strategists help create content that resonates with the target audience and conveys a company’s message in an effective way.
ChatGPT can be used to automate some aspects of content creation such as generating ideas for creative campaigns, but it is not yet advanced enough to completely replace human strategists.
Content strategists will still be needed to craft compelling stories and design digital campaigns.
Will ChatGPT replace Social Media Managers?
ChatGPT can assist social media managers by generating text-based content as well as ideas and strategies for social media campaigns when prompted correctly.
As with each of the other roles listed, a human social media manager has a creative and strategic approach to campaigns, which ChatGPT cannot replicate.
Will ChatGPT replace UX/UI Designers?
Because of its limitation to text generation, ChatGPT does not have the capabilities of a human UX/UI designer.
However, ChatGPT can assist user experience designers by generating text-based content such as microcopy, labels, and descriptions for the user interface when the correct prompts are used.
Additionally, it can also be used to generate ideas and suggestions for the design and layout of the interface.
Will ChatGPT replace Graphic Designers?
As with every other example, ChatGPT can be leveraged by graphic designers to generate text-based components of design like taglines, descriptions, and headlines.
However, ChatGPT is not a specialized tool for graphic design, so while it can aid graphic designers in generating copy and ideas for designs, it cannot replace the expertise of humans nor is it a replacement for the specialized software needed for the creation of graphics and visuals.
Final thoughts on ChatGPT potentially taking jobs
Overall, ChatGPT has the potential to greatly benefit tech, marketing, and creative professionals by automating tedious tasks and helping them to generate new ideas.
However, it is not designed to replace human jobs, but rather to enhance and augment them. It’s important to recognize that technology is a tool, and the key to success is to use it to its full potential, without replacing human creativity and ability.
Looking for your next Tech or Digital Marketing gig? Let us help. Every year, Mondo helps over 2,000 candidates find jobs they love. Get Hired
More articles about job searching and industry trends:
| 2023-01-24T00:00:00 |
https://mondo.com/insights/will-chatgpt-replace-your-job-programmers-engineers/
|
[
{
"date": "2023/01/24",
"position": 56,
"query": "generative AI jobs"
}
] |
|
Generative AI: How To Spot Real From The Hype
|
Generative AI: How to spot the real conversational AI companies and get past the hype
|
https://www.moveworks.com
|
[] |
... generative AI technologies. As good as it is ... Products that live in the middle layer build smaller models capable of taking on more precise jobs.
|
1. The foundation layer: The base of the AI stack
ChatGPT is the latest in a long line of genuinely game-changing generative AI technologies. As good as it is, though, ChatGPT isn’t a silver bullet. It does a lot of things well — astoundingly well, even. It can serve information in tight sentences rather than long lists of blue links. It can explain concepts in ways that people can understand. And it can brainstorm business plans, term paper topics, business strategies, birthday gift suggestions, and vacation plans.
It has such a wide breadth of knowledge because it is based on a foundation AI model; specifically, an LLM called GPT-3.5. Foundation AI models make up the base of the AI stack, trained enough to offer a perspective on a wide range of topics. Products like GPT-3 for text, DALL-E-2 for images, or Whisper for voice are examples of how foundation models can be applied to deal with broad categories of outputs: text, images, videos, speech, and games.
But — there are a couple of significant challenges when using foundation models.
For one, foundation models, like GPT-3, are monoliths. Like every model, the only way to change the output is to change the input. Foundation models are frozen in time. The particular capabilities of a generative AI system depend on how it’s trained and the types of information it is given.
While you may have heard the term “prompt engineering” to describe the work people do to adjust and control model outputs of these models by inputting specific terms and structures, ultimately, their knowledge is tied to the original training data. A foundation model can’t look up dynamic data or any real-time information to tell you the current share price of Microsoft stock, for example. And they can’t create new ideas from scratch.
Perhaps more importantly, many of the big tech players have their own foundation models based on the massive amount of data they can access. Microsoft was smart to partner with OpenAI early, and they will capitalize on this investment fast. Though they aren’t leading the wave, Google’s PaLM is significantly bigger than OpenAI’s GPT-3, unlocking even more capabilities. These big cloud providers will fight to have some offerings in this space. And the smaller, newer companies don’t stand a chance.
2. The middle layer: Models powered by specialized data
While the foundation layer offers a wide breadth of understanding, it’s not enough for businesses requiring 99.9% accuracy. By definition, foundation models offer general information and are fundamentally unfinished, requiring substantial building and productizing to be turned into something useful for more nuanced work. And that’s where the middle layer — and later, the application layer — come into play.
Products that live in the middle layer build smaller models capable of taking on more precise jobs. Trained on highly detailed — and typically proprietary — data, these models can write a knowledge base article pulling on details from your IT ecosystem. Or they can re-create a writer’s style and word choice. Or they could even edit stock photos to fit your exact brand specifications.
Often developed for a particular application, industry, vertical, or use case, these more specific models outperform foundation models in their particular wheelhouses.
Here’s where — to me — things start to get interesting. Companies can differentiate themselves by taking a foundation AI model and fine-tuning it to the needs of a particular business or industry. This is particularly powerful in fields where data is highly sensitive and specific domain knowledge is required to make accurate predictions, like finance, healthcare, energy, and manufacturing.
To offer an analogy: If Facebook, Google, Microsoft, and other tech giants have their own massive and well-equipped kitchens, you won’t be able to compete by just having a recipe book. But, if you have access to a wide variety of unique and high-quality ingredients and use them to create specialized dishes that complement the menu of the big players while also incorporating human expertise and feedback — that's where the real culinary success lies. The recipe may be necessary, but the ingredients are key.
The same goes for generative AI. Ultimately it’s the data that matters. Models are children of the data they’re trained on. Companies can differentiate from the competition by incorporating the specialized data they can access. This approach results in more nuanced results and a more defensible product that’s not just a flash in the pan.
3. The application layer: A conversational user interface
The application layer is the last step that brings all these layers of models together. I’m referring to the interface where humans and machines collaborate, such as the workflow tools that make the AI models accessible in a way that enables business customers or consumer entertainment.
The application layer is crucial, especially in a post-ChatGPT world. Everyone is now expecting that magical conversational experience where anyone can write a prompt and get an answer.
The thing is that your product can’t just be an interface. Merely making API calls to other core foundation models isn’t enough to survive in such a competitive field. It may be easy to build these application layers, but they will struggle with retention and differentiation.
I've already run through at least ten different content generation free trials in the past few weeks alone, but I’m not intending to renew them. It’s clear from the steady stream of marketing emails that pressure for this type of company is already mounting. They’re now offering discounted, unlimited plans, and we’re barely seven weeks out from ChatGPT’s launch.
There are, inevitably, going to be winners in this approach, but there are going to be more losers. Think about website-building platforms. You could learn some HTML and CSS to build a website or just use Squarespace. And for every Squarespace, a hundred other web-builders didn't make it.
If a company only provides workflow tools on top of widely available technologies, it may struggle to compete with larger companies with their own versions of these tools. Is there a world where Google doesn’t release its version of ChatGPT on Google Docs? Or where Microsoft doesn’t leverage GPT-3 in its Office Suite? I don’t think so. The foundation layer is available for everyone, so it won’t be a differentiator.
Companies that can bring unique datasets, train solutions, and offer precise answers at the application and operating system layers are more likely to be successful and highly valued for their solutions. And then, the interface becomes invaluable. ChatGPT has proven the versatility of conversation, and now users have high expectations.
To be genuinely competitive, products can’t just be a thin veneer on top of existing technologies. The companies that can bring a unique dataset and find a way to productize are the ones that will really make it big time.
| 2023-01-24T00:00:00 |
https://www.moveworks.com/us/en/resources/blog/generative-ai-how-to-spot-the-real-from-the-hype
|
[
{
"date": "2023/01/24",
"position": 78,
"query": "generative AI jobs"
}
] |
|
Chart: The Largest Tech Layoffs
|
Chart: The Largest Tech Layoffs
|
https://www.statista.com
|
[
"Felix Richter"
] |
This chart shows the estimated number of jobs cut in the largest layoffs by U.S. tech companies since 2020 ... AI. To address these changes, Nadella wrote, ...
|
HTML code to embed chart
Can I integrate infographics into my blog or website?
Yes, Statista allows the easy integration of many infographics on other websites. Simply copy the HTML code that is shown for the relevant statistic in order to integrate it. Our standard is 660 pixels, but you can customize how the statistic is displayed to suit your site by setting the width and the display size. Please note that the code must be integrated into the HTML code (not only the text) for WordPress pages and other CMS sites.
| 2023-01-24T00:00:00 |
https://www.statista.com/chart/29175/largest-tech-layoffs-since-2020/
|
[
{
"date": "2023/01/24",
"position": 67,
"query": "AI layoffs"
}
] |
|
Activist Investors Swarm Salesforce Amid Layoffs
|
Activist Investors Swarm Salesforce Amid Layoffs
|
https://gfmag.com
|
[
"Tiziana Barghini",
".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"
] |
Digital Banking, AI and Innovation Forum. Advertising. Sponsored Content · 2025 Editorial Calendar Information Page · Media Kit · Contact Us · Home · Capital ...
|
Salesforce joins Microsoft and other tech companies in reducing headcount.
Salesforce—the Silicon Valley dot-com giant that offers on-the-cloud office internet services—is dealing with demand contraction and personnel reduction.
The entrance in its capital of activist investors is yet another sign of changing times for the tech industry, now under pressure to boost stock prices and profit margins.
Elliot Management Corp., Inclusive Capital Partners and Starboard Value are among the better-known activist investment firms acquiring stakes in Salesforce.
It is not yet clear what specific demands Elliot and the other hedge funds will make, but there is no doubt that activist investors will push for greater efficiency.
“We look forward to working constructively with Salesforce to realize the value befitting a company of its stature,” Jesse Cohn, managing partner at Elliott, told media.
Created in March 1999 and initially managed out of a rented one-bedroom apartment in San Francisco, Salesforce is now headquartered in the tallest building in town. Grown with the slogan “the end of the software,” Salesforce defied Oracle’s corporate software and progressively replaced it with cheaper and more flexible internet services.
Over the pandemic years, employers around the world, often working from home, were using Salesforce’s services. In some cases, healthcare services used a multitude of Salesforce services to distribute vaccines and keep track of Covid infections.
At the peak of its success two years ago, Salesforce bought the office communications tool Slack for $28 billion, a price tag that raised eyebrows in the industry. Slack was meant to offer an alternative to Microsoft’s Teams.
Now the tide has turned: ahead of more difficult times, companies are cutting costs. Salesforce is joining its major competitors such as Microsoft in reducing headcount, cutting 8,000 or 10% of its staff, many of them at Slack.
The pressure is on to make Salesforce do more with less, with possibly more cost cuts and less expensive acquisitions—the future task of Elliott and Starboard Value.
Salesforce—which has seen its market value cut in half since its peak in 2021—still employs more people than before the pandemic.
“Salesforce is one of the pre-eminent software companies in the world, and having followed the company for nearly two decades, we have developed a deep respect for Marc Benioff and what he has built,” Cohn said in a statement.
The trend of activist investors entering the tech industry began last year. In December of 2022, Elliott Investment Management senior portfolio manager Marc Steinberg joined social media service Pinterest’s board after months of talks.
In October, Starboard bought a 5% stake in Splunk, a company to search, analyze and monitor machine generated data.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://gfmag.com/features/salesforce-layoffs-downsizing/
|
[
{
"date": "2023/01/24",
"position": 93,
"query": "AI layoffs"
}
] |
OCIO: What We've Accomplished and a Preview of 2023
|
OCIO: What We’ve Accomplished and a Preview of 2023
|
http://blog.dol.gov
|
[
"Filed In"
] |
Wages and Benefits. Wages and Benefits · Health and retirement benefits ... We also helped implement artificial intelligence (AI) as part of the Office ...
|
2022 was an impactful year for the Department of Labor’s Office of the Chief Information Officer. As American workers faced complexities bought on by a global pandemic, we continued to build on the momentum from previous years and innovate IT solutions to support the Department of Labor’s mission.
Here are a few highlights:
Our teams worked hard to raise the department’s Federal Information Technology Acquisition Reform Act (FITARA) rating. FITARA is a biannual Congressional indicator of how federal agencies manage, modernize, and secure their assets. We ended the year with an overall score of “B” and were one of only five agencies to score an “A” in the “Modernizing Government Technology” category.
We continued to enhance our IT infrastructure to protect workers’ confidential information. Our cybersecurity teams implemented widespread multi-factor authentication (MFA) to safeguard documents, achieving a 97% completion rate of use across IT systems. We also worked to encrypt data-in-transit to help protect American workers’ valuable information and assets.
We helped the department’s Employee Benefits Security Administration update their EFAST filing system, which supports federal requirements for reporting on employee benefit plans. The system saw a 5% increase in filings and 10% more users during the fiscal year.
The Foreign Labor Application Gateway system, administered by the department’s Employment and Training Administration, allows U.S. employers to find qualified workers while ensuring protections for U.S. and foreign workers. OCIO helped to implement several enhancements this year to improve customer service, broaden job opportunities and collect feedback. When compared to fiscal year 2021, the system saw a 26% increase in applications filed during FY 2022 by employers seeking prevailing wage determinations and labor certification to employ workers in temporary or seasonal employment in the United States.
The department’s Mine Safety and Health Administration launched a new app with our help this year to ensure miners have the information they need to stay safe on the job. Launched in August 2022, it received more than 5,000 downloads within the first two weeks – the most of any app we’ve released.
Emerging Technologies at the Department
2022 also ushered in more innovative work from OCIO using emerging technologies like Robotic Process Automation, or RPA, bots to automate repetitive tasks, helping save time and money. We took a human-centered approach by asking employees about how RPA could help with their day-to-day work and developing bots to address those needs. Some of these functions include populating information in fields within a PDF file, linking data sources to determine contractor responsibility and reconciling credit-card claims for student travel as part of Job Corps. RPA bots save thousands of hours of work, allowing department staff to focus their time on other tasks.
We also helped implement artificial intelligence (AI) as part of the Office of Workers’ Compensation (OWCP) benefits claims examination process. AI uses automation to help minimize the time department employees use to process forms manually, saving approximately 340 hours as well as costs. In turn, this helps enhance customer service, increase the accuracy of records and reduce processing time for disabled workers.
What’s Next for 2023?
There are a few projects we are very excited about in the new year.
One is helping eliminate paperwork for permanent labor certifications. The PERM visa modernization project (which relates to permanent labor certification) is supported by a $7.2 million award from the Technology Modernization Fund (TMF). It will help streamline the process for PERM filers to submit their applications, the process for PERM analysts to review applications and the process to submit labor certifications.
Currently the department processes 120,000 requests from 73,000 unique employers annually. This new workflow will make it easier for employers to access permanent labor certification services, shaving off 45 days and $1.5 million each year for PERM filers. It also will save the department $2.2 million annually by eliminating paper-based processes. In addition, once completed, the PERM Visa program will integrate within ETA’s FLAG system to help federal agencies securely share labor certification information.
OCIO will also continue work on data modernization, for which the department received an additional TMF award fund of $9.6 million to help improve the availability and accessibility of critical data to the public by:
Incorporating enterprise-standard predictive analytics and reporting capabilities in our IT infrastructure
Implementing enterprise data management capabilities
Supporting an application programming interface (API) and external data portal to transform how we share information internally and externally
2023 will be a transformative year for modernizing IT at the Department of Labor and we hope to build on the excellent work of our team to support America's workers, employers, job seekers and retirees – like you.
Editor’s note: If your New Year’s resolution includes finding a new job, we hope you will consider working with us. Visit our open job listings to find opportunities and be sure to follow us on Twitter and LinkedIn.
Lou Charlier is the deputy chief information officer for OCIO at the Department of Labor.
| 2023-01-24T00:00:00 |
2023/01/24
|
http://blog.dol.gov/2023/01/24/ocio-what-weve-accomplished-and-a-preview-of-2023
|
[
{
"date": "2023/01/24",
"position": 91,
"query": "artificial intelligence wages"
}
] |
Growing demand for A.I. voice automation at the drive-thru
|
Growing demand for A.I. voice automation at the drive-thru
|
https://presto.com
|
[
"Presto Marketing"
] |
By championing automation and investing in A.I. voice assistants for your drive-thru in 2023, you'll be able to position your restaurant for success both ...
|
By championing automation and investing in A.I. voice assistants for your drive-thru in 2023, you’ll be able to position your restaurant for success both now and in the future. Automating the drive-thru allows quick-service restaurants (QSRs) to generate new revenue, streamline order-taking, retain staff and get guests their food faster with better service.
Despite being around for over 70 years, drive-thru lanes of today look fairly similar to what people drove their Cadillacs through back in the sixties. In the meantime, we have gone through multiple technology revolutions—most recently with robots flipping burgers and making food deliveries. It’s time for the drive-thru to get a major overhaul and be prepared for today’s and tomorrow’s challenges.
Drive-thrus have grown notoriously long as guest demand soars. Quick-service restaurants are fiercely competing in an arms race to offer guests the fastest and the best drive-thru experience. So how can restaurants make drive-thru ordering more accurate without slowing down throughput?
By utilizing next-generation artificial intelligence (A.I.) voice technology, restaurants can promote a stronger connection between their brand and guests. The A.I.-based speech recognition technology offers guests voice ordering at the drive-thru to accelerate transactions, enables smarter recommendations and personalization and improves order accuracy for happier guests.
What’s driving the need to innovate?
Before we look at the future of the drive-thru, we need to understand the current problems the drive-thru is facing. QSRs have long been plagued with inaccuracy at the window, nonoptimal throughput and an impersonalized experience. Accurately entering orders to send to the kitchen should be a low threshold for smooth operations, yet it can often be difficult for staff to decipher a customer’s request especially while the staff is multitasking, taking orders, collecting payment and pouring beverages. With enough frequency, human error has a significant impact on the bottom line:
Labor shortage
Longer wait times
Missed upsell opportunities
Order accuracy
How voice automation accelerates the drive-thru
For decades, drive-thru wait times, speed of service and order accuracy have been key performance metrics for fast-food chains, but the ongoing labor shortage and higher labor costs have not only heightened their importance, but highlighted the need for higher upsell rates for drive-thrus to remain profitable and successful. For the country’s almost 200,000 fast-food restaurants, there is no shortage of guests going through the drive-thru, but there is a shortage of workers staffing the drive-thru.
In today’s labor-scarce world, to survive and thrive, restaurants must adopt technology—fast.
1. Reduce wait time at the drive-thru order terminal
When diners pull-up to the drive-thru order terminal, they are often asked to wait, because the staff is multi-tasking, either finishing up the previous car’s order and entering it in the POS system, pouring beverages or collecting payment from a guest. With voice automation, drive-thru guests are greeted by the A.I. voice system and never told to wait, avoiding typical delays that frustrate guests. Orders are immediately sent to the point of sales system (POS), which immediately eliminates bottlenecks and keeps the drive-thru flowing smoother while making guests happier.
2. Increase new revenue opportunities
Suggestive upselling means recommending menu items or limited-time offers (LTOs) for drive-thru guests and helping guests make decisions that are good for them. With this unprecedented labor shortage, it’s inevitable that the short-staffed drive-thru team see upselling as the least of their priorities, as they’re trying to move as many guests through the drive-thru lane as quickly as possible, take their orders, enter them into the POS system, pack their orders, pour their drinks and collect payment.
3. Improve guest experience
The drive-thru order terminal is the first point of contact with guests and you want that to be the best experience, or else it goes downhill pretty quickly. With voice automation, the A.I. voice assistant is always pleasant no matter what time you pull up to the drive-thru and she always greets you before taking your order. To confirm the order, she reads back the order to ensure order accuracy. With the A.I. voice assistant at the drive-thru taking orders, it helps free up staff from multitasking so that they can focus on preparing the meals, ensuring orders are accurately packed and providing the best possible guest experience.
Automation technology doesn’t have to be impersonal, with custom voices, drive-thru ordering is transformed from a purely transactional experience to an exciting interaction that allows guests to converse with celebrities, mascots, characters or other custom voices.
Don’t make your guests wait
A.I. voice technology is poised to be widely adopted by the restaurant industry in 2023. The lingering labor shortage, rising costs and wages give operators more reasons to automate—not to eliminate jobs, but to strike a balance between a consistent experience for guests and a safe, comfortable and fair-wage atmosphere for workers.
With the drive-thru channel being the major source of revenue for the majority of QSRs, while it may seem like a good idea to buy a cheaper piece of equipment or solution, it’s important to do your homework beforehand to see if this will be the best investment for your restaurant. When operators cut corners on technology, you usually end up paying more long-term with replacements and costly upgrade services.
Choose a voice automation partner that has been proven at scale
Designed to help restaurants maximize labor efficiency and generate new revenue, Presto’s next-generation A.I. voice assistant helps optimize the drive-thru, retain staff, increase upsells and provide a superior guest experience. Presto Voice™ offers the industry’s most widely adopted A.I.-powered drive-thru voice assistant with over 75% market share.
As Checkers and Rally’s’ (800-unit burger chain) exclusive partner of automated voice ordering, Presto deployed and integrated its A.I. voice assistant into Checkers’ existing drive-thru infrastructure to hundreds of its corporate-owned drive-thru restaurants in 2022. At ICR’s 25th Anniversary Conference in Orlando, Florida, it was announced that Del Taco, the nation’s second largest Mexican quick service restaurant with approximately 600 locations nationwide, is the second major brand to sign up for Presto Voice.
Presto’s voice automation solution has the richest feature set, is easy to install at scale with existing point of sales (POS) and kitchen display systems (KDS), has 24/7 availability and delivers proven ROI. It allows fast-food restaurants to do more with less, doesn’t require any changes to the operator’s existing concept, improves customer retention, drives revenue growth and helps them build a significantly more productive workforce.
Don’t wait for the rest of the industry to pass you by. Contact Presto to discover how you can generate real results today.
About Presto
Presto overlays next-gen digital solutions onto the physical world. Our enterprise-grade touch, vision, and voice technologies help hospitality businesses thrive while delighting guests. With over 100 million guests using Presto each month and 300,000 systems shipped, we are one of the largest technology providers in the industry.
Founded at M.I.T. in 2008, Presto is headquartered in Silicon Valley, Calif. with customers including top 20 hospitality chains such as Applebee’s, Aramark, Chili’s Grill & Bar, Denny’s, and Outback Steakhouse.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://presto.com/voice-automation-at-drive-thru/
|
[
{
"date": "2023/01/24",
"position": 99,
"query": "artificial intelligence wages"
}
] |
Harnessing AI – the Midjourney case – Global campus
|
Harnessing AI – the Midjourney case – Global campus
|
https://blogs.helsinki.fi
|
[] |
This technology has many practical applications such as in graphic design, digital art, and scientific research. However, the ethical implications of AI ...
|
Let’s discuss AI generated imagery for a second.
What is it?
As an example I use Midjourney. Generating images using artificial intelligence (AI) tools such as Midjourney on Discord has the potential to revolutionise the field of visual content creation. Midjourney, an open-source platform, utilises machine learning algorithms to generate images based on user input. In short so called Convolutional Neural Networks (CNNs) create artistic imagery by separating and recombining image content and style. This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). This technology has many practical applications such as in graphic design, digital art, and scientific research. However, the ethical implications of AI-generated images must also be considered, more on this in a bit.
When using Midjourney on Discord, users can input a variety of parameters to generate images. This can include text, numbers, or even other images. The algorithm then processes this input and creates a unique image based on the parameters provided. This allows for a high degree of customisation and creativity when generating images. Additionally, Midjourney also allows the user to generate versions of those images, enabling thus a set of variations of the base image.
Here is a short video on how to use Midjourney via Discord.
One of the key benefits of using Midjourney on Discord is the community aspect of the tool. Users can share their input and generated images with others in real-time, allowing for a collaborative and interactive experience. This is particularly useful for designers and artists working on a project together, as it allows them to quickly and easily share ideas and feedback. Additionally, the Discord integration allows for easy sharing of the generated images, making it easy to share the final output with others.
Are there any issues?
One major advantage of using AI to generate images is its ability to produce a high volume of unique and varied content. This is particularly beneficial in fields such as advertising and graphic design where a steady stream of fresh and engaging visuals is essential. Furthermore, the use of machine learning algorithms in image generation allows for a high degree of customisation and creativity in the final output.
However, there are also valid concerns regarding the ethical implications of AI-generated images. One of the main concerns is the potential for AI-generated images to perpetuate harmful stereotypes and biases. For example, if an AI model is trained on a dataset that contains a disproportionate number of images of a certain race or gender, it may produce images that reinforce these stereotypes. Additionally, the use of AI-generated images in fields such as journalism and news reporting raises concerns about the authenticity and accuracy of the content.
A good example of what consequences training on a specific dataset can mean came up in a recent class action lawsuit in federal court in San Francisco, USA filed by a group of artists – the case is still on-going. Apparently
“text image generators were trained off of a data set called LAION, and they basically are billions of images that help to train the generators. And where artists take issue with it is that our images were put into these data sets and then used to create the generators without our consent.”
Source: NYTimes podcast: Hardfork, Jan 20 2023.
It is important to note that these concerns are not unique to AI-generated images, but rather are issues that have long been present in the field of visual content creation. However, the use of AI does amplify these concerns, and it is crucial that proper measures are taken to mitigate these risks. This can include using diverse and representative training datasets (with consent?), implementing robust ethical guidelines, and providing transparency about the source and authenticity of AI-generated images. In conclusion, the use of AI to generate images has the potential to greatly benefit various fields if implemented correctly.
Overall, Midjourney is a powerful tool for generating images on Discord. Its ability to process input from users and generate unique images, along with its editing tools and collaborative features, make it a valuable tool for a wide range of fields. Whether you’re a designer, artist, or researcher, Midjourney can help you create stunning visual content quickly and easily.
Prompts
Midjourney uses prompts to instruct the NST what the image is suppose to look like. It always starts with a forward slash and IMAGINE (/IMAGINE) and your descriptive text eg. I used the following prompt line for the owl in the right hand side column:
[/IMAGINE logo, funky, scifi, bioluminescence, owl on transparent background]
which resulted in this 4 image square (below). I then chose to Upscale #1 and Version #2 and ended up with a 1024×1024 px sized image of the owl I wanted.
For further reading on how to perfect your prompts to get the result you are happy with I suggest you head over to Midjourney’s Documentation page or check out PromptHero and while you are at it have a look at the Midjourney Community Showcase.
| 2023-01-24T00:00:00 |
2023/01/24
|
https://blogs.helsinki.fi/globalcampus/2023/01/24/harnessing-ai-the-midjourney-case/
|
[
{
"date": "2023/01/24",
"position": 58,
"query": "artificial intelligence graphic design"
}
] |
AI in L&D and Education Industry - Inspiring Learners
|
AI in L&D and Education Industry
|
https://www.inspiringlearners.co.in
|
[] |
Automation of tasks may lead to job displacement for educators and other professionals in the education industry. Another potential drawback is bias. AI systems ...
|
AI in L&D and Education Industry
Artificial Intelligence (AI) is a rapidly growing technology that is being used in many industries, including learning and development (L&D) and education. The use of AI in these industries has the potential to revolutionize the way we learn and teach.
One of the main benefits of AI in L&D and education is personalization. AI-powered tools can analyze student data and adapt the learning experience to each student’s abilities and learning style. This can lead to more effective learning and better outcomes for students.
Another benefit of AI in L&D and education is automation. AI can automate repetitive tasks such as grading assignments, providing feedback, and creating quizzes. This can free up time for educators to focus on more important tasks, such as providing personalized support to students.
AI can also be used in tutoring and language learning. AI-powered chatbots can provide 24/7 assistance to students, including language tutoring. This can be especially helpful for students who have difficulty accessing traditional tutoring services.
Predictive analytics is another way AI can be used in L&D and education. AI can analyze student data to identify patterns and predict student performance. This can help educators identify students who need extra support and interventions.
While there are many potential benefits of AI in L&D and education, there are also potential drawbacks to consider. One potential drawback is job displacement. Automation of tasks may lead to job displacement for educators and other professionals in the education industry.
Another potential drawback is bias. AI systems can perpetuate existing biases in the data they are trained on, which can negatively impact students from marginalized communities.
Privacy concerns and cost are also potential drawbacks of AI in L&D and education. AI systems can collect and store large amounts of personal data on students, which raises privacy concerns. Implementing AI systems in the education industry can also be costly, which can be a barrier for some schools and institutions.
Overall, AI has the potential to greatly improve the way we learn and teach. However, it is important to carefully consider the potential drawbacks and take steps to mitigate them.
| 2023-01-25T00:00:00 |
2023/01/25
|
https://www.inspiringlearners.co.in/2023/01/25/ai-in-ld-and-education-industry/
|
[
{
"date": "2023/01/25",
"position": 71,
"query": "automation job displacement"
}
] |
ChatGPT could make these jobs obsolete
|
ChatGPT could make these jobs obsolete: ‘The wolf is at the door’
|
https://nypost.com
|
[] |
AI programs such as ChatGPT are leaving many well-paid workers vulnerable, experts warn.
|
Artificial intelligence is here, and it’s coming for your job.
So promising are the tool’s capabilities that Microsoft — amid laying off 10,000 people — has announced a “multiyear, multibillion-dollar investment” in the revolutionary technology, which is growing smarter by the day.
And the rise of machines leaves many well-paid workers vulnerable, experts warn.
“AI is replacing the white-collar workers. I don’t think anyone can stop that,” said Pengcheng Shi, an associate dean in the department of computing and information sciences at Rochester Institute of Technology.
“This is not crying wolf,” Shi told The Post. “The wolf is at the door.”
From the financial sector to health care to publishing, a number of industries are vulnerable, Shi said. But as AI continues its mind-blowing advancements, he maintains that humans will learn how to harness the technology.
7 Artificial intelligence is already at a point where it can do the jobs people are paid for. Shutterstock
7 AI is already having an impact on multiple industries, professors warn. dpa/picture alliance via Getty I
Already, AI is upending certain fields, particularly after the release of ChatGPT, a surprisingly intelligent chatbot released in November that’s free to the public.
Earlier this month, it emerged that consumer publication CNET had been using AI to generate stories since late last year — a practice put on pause after fierce backlash on social media. Academia was recently rocked by the news that ChatGPT had scored higher than many humans on an MBA exam administered at Penn’s elite Wharton School. After Darren Hick, a philosophy professor at South Carolina’s Furman University, caught a student cheating with the wildly popular tool, he told The Post that the discovery had left him feeling “abject terror” for what the future might entail.
Hick and many others are right to be worried, said Chinmay Hegde, a computer science and electrical engineering associate professor at New York University.
“Certain jobs in sectors such as journalism, higher education, graphic and software design — these are at risk of being supplemented by AI,” said Hegde, who calls ChatGPT in its current state “very, very good, but not perfect.”
For now, anyway.
Here’s a look at some of the jobs most vulnerable to the fast-learning, ever-evolving technology.
Education
7 Professors and teachers could be replaced by AI courses, according to experts. Getty Images
As it stands now, ChatGPT — currently banned in NYC schools — “can easily teach classes already,” Shi said. The tool would likely be most effective at the middle or high school level, he added, as those classes reinforce skills already established in elementary school.
“Although it has bugs and inaccuracies in terms of knowledge, this can be easily improved. Basically, you just need to train the ChatGPT,” Shi continued.
As for higher education, both Shi and Hegde maintain that college courses will need a human leader for the foreseeable future, but the NYU professor did admit that, in theory, AI could teach without oversight.
In the meantime, educators are seeing their roles transformed nearly overnight. It’s already become a struggle to adapt teaching and testing methods in efforts to keep up with the increasingly talented ChatGPT, which, according to Shi, can successfully complete a corner-cutting student’s coursework at a master’s level.
Doctoral candidates hoping for a shortcut are likely out of luck: Creating an independent thesis on an area not often or thoroughly studied is beyond AI’s abilities for the time being, he said.
Finance
7 AI like ChatGPT could take over spreadsheet-style jobs in finance, experts warn. Getty Images
Wall Street could see many jobs axed in coming years, as bots like ChatGPT continue to better themselves, Shi told The Post.
“I definitely think [it will impact] the trading side, but even [at] an investment bank, people [are] hired out of college and spend two, three years to work like robots and do Excel modeling — you can get AI to do that,” he explained. “Much, much faster.”
Shi is certain, however, that crucial financial and economic decisions will likely always be left in human hands, even if the data sheets are not.
Software engineering
7 Relatively simple software design jobs are at risk. Getty Images/Maskot
Website designers and engineers responsible for comparatively simple coding are at risk of being made obsolete, Hegde warns.
“I worry for such people. Now I can just ask ChatGPT to generate a website for me — any type of person whose routine job would be doing this for me is no longer needed.”
In essence, AI can draft the code — hand-tailored to a user’s requests and parameters — to build sites and other pieces of IT.
Relatively uncomplicated software design jobs will be a thing of the past by 2026 or sooner, Shi said.
“As time goes on, probably today or the next three, five, 10 years, those software engineers, if their job is to know how to code … I don’t think they will be broadly needed,” Shi said.
Journalism
7 AI is already making its way into newsrooms. Getty Images
The technology is off to a rocky start in the news-gathering business: CNET’s recent attempts (and subsequent corrections to its computer-generated stories) were preceded by the Guardian, which had GPT software write a piece in 2020 — with mixed results.
Still, there is one job the technology is already highly qualified for, according to Hegde.
“Copy editing is certainly something it does an extremely good job at. Summarizing, making an article concise and things of that nature, it certainly does a really good job,” he said, noting that ChatGPT is excellent at designing its own headlines.
One major shortcoming — salvation for reporters and copy editors, at least for now — is the tool’s inability to fact-check efficiently, he added.
“You can ask it to provide an essay, to produce a story with citations, but more often than not, the citations are just made up,” Hegde continued. “That’s a known failure of ChatGPT and honestly we do not know how to fix that.”
Graphic design
7 Graphic design jobs also face potentially becoming obsolete thanks to AI. Getty Images/iStockphoto
In 2021, ChatGPT developer OpenAI launched another tool, DALL-E, which can generate tailored images from user-generated prompts on command. Along with doppelgangers such as Craiyon, Stable Diffusion, and Midjourney, the tool poses a threat to many in the graphic and creative design industries, according to Hegde.
“Before, you would ask a photographer or you would ask a graphic designer to make an image [for websites]. That’s something very, very plausibly automated by using technology similar to ChatGPT,” he continued.
Shi recently commanded DALL-E to make a cubist portrait of rabbits for the Lunar New Year, which he said came out “just amazing.” But, although it captured the hard-lined, Picasso-derived painting style, Shi noticed that it was not successful with more nuanced techniques — exposing a current shortcoming in the tech.
“I also asked it to do Matisse-style. It was not as good,” he added.
Copyright issues are also being generated by image-based AI. Getty Images recently announced legal action against Stability AI — Stable Diffusion’s parent company — claiming that the program “unlawfully copied and processed millions of images protected by copyright.”
| 2023-01-25T00:00:00 |
2023/01/25
|
https://nypost.com/2023/01/25/chat-gpt-could-make-these-jobs-obsolete/
|
[
{
"date": "2023/01/25",
"position": 26,
"query": "AI replacing workers"
},
{
"date": "2023/01/25",
"position": 39,
"query": "AI job creation vs elimination"
}
] |
Is ChatGPT The New Health Coach of 2023?
|
Is ChatGPT The New Health Coach of 2023?
|
https://www.wellable.co
|
[] |
The impact of ChatGPT and other AI tools on the future of work is not about replacing human employees, but rather about using AI as a tool to improve human work ...
|
Artificial Intelligence (AI) is a rapidly evolving field of technology that has the potential to transform the way people interact with the world. According to Google’s CEO, Sundar Pichai, AI’s impact will be even greater than that of fire or electricity on the evolution of humanity. It has the potential to address some of the most critical challenges in the world, such as climate change, cancer, and space exploration.
Certain forms of AI, such as ChatGPT, have become available to the public as tools for personal and professional, smaller-scale tasks. ChatGPT (Generative Pre-trained Transformer) is a chatbot technology platform created by OpenAI that can respond to a wide range of user requests, including answering questions, translating languages, and completing text inputs. It uses natural language processing (NLP) in an attempt to yield “conversational” and “human-like” dialogue.
With the recent and widespread accessibility of ChatGPT, the potential use of AI technology to automate tasks and replace human jobs is being examined in various fields, including education, writing, programming, and healthcare. Users on social media platforms, like TikTok, are demonstrating how ChatGPT can even be used to automate workout and diet plans, potentially eliminating the need for health coaches.
Is ChatGPT The New Health Coach of 2023?
Despite its powerful capabilities, AI cannot replace the expertise, creativity, adaptability, and ethical judgment that human professionals bring to their jobs. In particular, there are several limitations that prevent ChatGPT from fully replacing the role of health coaches, including:
There are inherent limitations in the accuracy of the information provided by ChatGPT. For example, the model’s current knowledge base is up to 2021, which means that many of its responses may be outdated. Additionally, OpenAI cautions that the bot might generate “plausible-sounding but incorrect or nonsensical answers.” It is important for users to be cautious and thoroughly evaluate the information presented by ChatGPT.
Furthermore, OpenAI acknowledges that its product may struggle to provide accurate and reliable information because “the ideal answer depends on what the model knows, rather than what the human demonstrator knows.” This means that the model’s understanding and knowledge is more limited compared to that of a human expert.
2. ChatGPT Is Not Able To Provide Personalized Guidance
ChatGPT’s “retrieval-augmented” approach to language generation simply means that when it receives a question, it searches for related data sources and generates an appropriate response. While users who are not well-versed in health and well-being may be impressed by the bot’s output, they might not realize that it is based on general information. It cannot account for the individual nuances and complexities of an employee’s history and specific goals that a human expert can take into consideration when creating a personalized health plan.
Take it from ChatGPT itself:
The algorithm is designed to provide advice and information, but it does not consider the full range of factors that contribute to a situation. It does not ask follow-up questions or reflect on context, which are essential elements of effective health coaching.
3. ChatGPT Does Not Have The Ability To Be Empathetic
Koko, a non-profit organization that provides mental health support, conducted an experiment to evaluate the efficiency of using AI to enhance its support services. The results indicated that the messages generated by AI were rated higher than those written by humans and required half the time.
However, the feature was soon removed from the platform due to people’s poor reactions to its lack of empathy and authenticity. This made it clear that while AI can assist in certain aspects of mental health support, it cannot replace the human touch and connection that is essential for fostering optimal well-being.
How Will ChatGPT Impact The Future Of Work?
While some roles, such as health coaches, may be protected from the threat of automation, will others be so fortunate? As organizations explore the capabilities of ChatGPT and other language models, many employees continue to worry about the possibility of being replaced by advanced AI technologies.
One business owner decided to test this theory by secretly incorporating ChatGPT into his company’s hiring process. In a writing skills test, ChatGPT was given the same prompt as human candidates. The outcome? Only 20% of applicants were shortlisted for further consideration—and ChatGPT was one of them.
This experiment highlights concerns about the possibility of language models like ChatGPT replacing writing-related jobs and tasks. However, further evaluation revealed the limitations of the language model and emphasized the importance of human touch in many aspects of writing.
For example, when given highly specific guidance, such as emulating the style of American author and copywriter David Trott, the output produced by ChatGPT was much more impressive than when given generic prompts. The output from generic prompts was “competent but dull”. This highlights the limitations of ChatGPT, as it relies on pre-existing information created by human writers, resulting in impersonal and unoriginal outputs when given open-ended prompts.
The impact of ChatGPT and other AI tools on the future of work is not about replacing human employees, but rather about using AI as a tool to improve human work. Instead of teaching employees how to perform specific tasks, employers will teach them how to use AI tools to effectively perform those tasks. Because AI lacks free will, it does not eliminate the need for human guidance or the need to retrain and retain employees.
ChatGPT and other AI tools may not be able to replace human workers completely, but they can still create positive opportunities for job seekers if they are used as supplements in the workplace. Think of it like driving a car – while a car can get you to your destination faster than walking, a human is still needed to operate it. If employees are not required to be as highly specialized in their roles, it could lead to more hiring opportunities across a wider range of positions. By using AI tools to augment human capabilities, employers can increase efficiency and productivity while creating new job opportunities.
Takeaway
ChatGPT has a lot of potential as a tool to assist human workers, but it still has limitations that prevent it from fully replacing them. For example, it cannot match the level of expertise, personalization, and empathy provided by health and wellness professionals. Similarly, it cannot replace the creativity of writers as it can only recycle pre-existing information, not generate original ideas. Additionally, ChatGPT lacks the critical-thinking skills and ethical judgment required for many other types of roles.
Organizations that want to improve employee well-being in the workplace should consider investing in a holistic wellness program that includes personalized health coaching. This approach empowers employees to tackle their well-being challenges with the support of a dedicated health coach, resulting in a happy and more productive workforce. While ChatGPT and AI technology may play a bigger role in healthcare in the future, it is not likely to happen in the near term.
| 2023-01-25T00:00:00 |
2023/01/25
|
https://www.wellable.co/blog/is-chatgpt-the-new-health-coach-of-2023/
|
[
{
"date": "2023/01/25",
"position": 53,
"query": "AI replacing workers"
}
] |
PhDs and postdocs on the academic job market
|
PhDs and postdocs on the academic job market
|
https://www.cs.ucla.edu
|
[] |
Dissertation topic: Machine Learning with Provable Robustness Guarantees. Website. Dongruo Zhou. Research area: machine learning, reinforcement learning.
|
Patrick (Pei-hung) Chen
Research Area: compressing machine learning models to make them deployable on devices with limited memory, accelerating the training and inference time of machine learning models to meet latency requirements, designing algorithms to improve the robustness and reliability of machine learning models
Dissertation topic: Efficient Machine Learning by Leveraging Data Dependent Information
Website
| 2023-01-25T00:00:00 |
https://www.cs.ucla.edu/phds-and-postdocs-on-the-job-market/
|
[
{
"date": "2023/01/25",
"position": 26,
"query": "machine learning job market"
}
] |
|
Master's in Artificial Intelligence - Computer Science
|
Master’s in Artificial Intelligence
|
https://cdso.utexas.edu
|
[] |
Artificial intelligence is poised to drive the next generation of global innovation. The need for skilled AI professionals is greater than ever, with 97 million ...
|
Artificial intelligence (AI) is both a product of and a major influence on society. As AI plays an increasingly important role in society, it is critical to understand both the ethical factors that influence the design of AI and the ethical dimensions of the impacts of AI in society. The goal of this course is to prepare AI professionals for the important ethical responsibilities that come with developing systems that may have consequential, even life-and-death, consequences. Students first learn about both the history of ethics and the history of AI, to understand the basis for contemporary, global ethical perspectives (including non-Western and feminist perspectives) and the factors that have influenced the design, development, and deployment of AI-based systems. Students then explore the societal dimensions of the ethics and values of AI. Finally, students explore the technical dimensions of the ethics and values of AI, including design considerations such as fairness, accountability, transparency, power, and agency.
Students should take this course to prepare them for the ethical challenges that they will face throughout their careers, and to carry out the important responsibilities that come with being an AI professional. The ethical dimensions of AI may have important implications for AI professionals and their employers. For example, the release of unsafe or biased AI-based systems may cause liability issues and reputational damage. This course will help students to identify design decisions with ethical implications, and to consider the perspectives of users and other stakeholders when making these ethically significant design decisions.
Students who perform well in this class will be positioned to take on a leadership role within their organizations and will be able to help guide and steer the design, development, and deployment of AI-based systems in ways that benefit users, other stakeholders, their organizations, and society. The knowledge and skill gained through this course will benefit students throughout their careers, and society as a whole will benefit from ensuring that AI professionals are prepared to consider the important ethical dimensions of their work.
What You Will Learn
You will learn about the history of AI and the ethical challenges that arise from AI
You will learn about a wide range of ethical theories and learn to apply them to the ethics of AI
You will learn about efforts to develop principles for the design of ethical AI
Syllabus
Week 1: Introduction
Week 2: Indian Ethics/Classical Chinese Ethics/Babbage’s Engines
Week 3: Buddhist Ethics/Islamic Ethics/Dartmouth Conference on AI
Week 4: Kantian Ethics/Consequentialism/Deep Blue
Week 5: Distributive Justice/Virtue Ethics/Watson
Week 6: Ethics of Care/Ubuntu/Autonomous Cars
Week 7: Human Values/Value Sensitive Design
Week 8: Codes of Ethics
Week 9: AI Ethics Guidelines
Week 10: Fairness
Week 11: Accountability
Week 12: Transparency
Week 13: Power
Week 14: Agency
| 2023-01-25T00:00:00 |
https://cdso.utexas.edu/msai
|
[
{
"date": "2023/01/25",
"position": 52,
"query": "machine learning job market"
},
{
"date": "2023/01/25",
"position": 55,
"query": "generative AI jobs"
},
{
"date": "2023/11/01",
"position": 100,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/12/01",
"position": 99,
"query": "artificial intelligence healthcare"
}
] |
|
How automation and AI are changing the job market
|
How automation and AI are changing the job market
|
https://www.thecitizen.co.tz
|
[
"Marketing",
"Branding",
"Digital Transformation Enthusiast. Now Working At Mcl As Event Manager."
] |
... intelligence (AI), have had a significant impact on the job market ... job opportunities is through the replacement of human workers with machines or software.
|
In recent years, advancements in technology, specifically automation and artificial intelligence (AI), have had a significant impact on the job market. As machines and software become more advanced and capable, they are taking over tasks that were previously done by humans. This is leading to changes in the types of jobs available, the skills that are in demand, and the ways in which we work.
Tanzania, like many other countries, is experiencing rapid advancements in technology, particularly in the areas of automation and artificial intelligence (AI). These developments are having a significant impact on the job market, as more tasks are being automated and replaced by machines and software.
One of the most obvious ways in which automation and AI are affecting job opportunities is through the replacement of human workers with machines or software. This is particularly true in industries such as manufacturing, where robots and other forms of automation are increasingly being used to perform tasks that were previously done by humans.
Related Africa can benefit much more from artificial intelligence OpEd
As a result, many jobs that were once considered safe and secure are now at risk of being replaced by machines.
However, it is important to note that automation and AI are also creating new job opportunities. For example, companies are now hiring individuals with skills in data science, machine learning, and other emerging technologies to help them build and maintain the systems and software that are driving the automation revolution.
Additionally, many businesses are also seeing the value of human workers in areas such as customer service and sales, where personal interactions and emotional intelligence are still considered vital.
Another way in which automation and AI are changing the job market is by increasing the demand for certain types of skills.
For example, as machines take over repetitive and routine tasks, the jobs that require critical thinking, creativity, and problem-solving skills are becoming more valuable. This means that workers who have these skills will be in high demand, while those who don’t may struggle to find employment.
It is also worth mentioning that the rise of automation and AI is also having a significant impact on the way we work.
The ability of machines to perform a wide range of tasks is allowing companies to become more efficient and productive, which in turn is leading to changes in the traditional 9-to-5 workday.
Remote working, flexible hours, and the gig economy are becoming more common as companies look to take advantage of the benefits of automation and AI.
In conclusion, automation and AI are having a significant impact on the job market.
| 2023-01-25T00:00:00 |
2023/01/25
|
https://www.thecitizen.co.tz/tanzania/oped/-how-automation-and-ai-are-changing-the-job-market-4098368
|
[
{
"date": "2023/01/25",
"position": 82,
"query": "machine learning job market"
}
] |
Careers Archive
|
Careers Archive
|
https://www.velotix.ai
|
[] |
... generation, SDR effectiveness, and social growth. ... We are in search of a qualified and highly motivated Senior Machine Learning Engineer to join our AI team.
|
We are seeking a talented Marketing Manager with a strong background in product marketing to join our team. The ideal candidate will be responsible for developing and executing marketing strategies that drive awareness, engagement, and adoption of our products. This role requires a strategic thinker with a hands-on approach and the ability to collaborate effectively with cross-functional teams.
| 2023-01-25T00:00:00 |
https://www.velotix.ai/careers/
|
[
{
"date": "2023/01/25",
"position": 87,
"query": "AI job creation vs elimination"
}
] |
|
AI Innovation at Work: Putting Principles into Practice
|
AI Innovation at Work: Putting Principles into Practice
|
https://www.businessroundtable.org
|
[] |
The policy recommendations outline a framework for policymakers to consider when establishing rules, practices, and guidelines to govern AI systems. The Roadmap ...
|
Many services that drive quality of life improvements for consumers and improved performance across different businesses are already powered or substantially improved by AI—from convenience applications like smart home devices and customer rewards programs, to safety systems like online fraud detection and vehicle collision avoidance, to innovations in clean energy technologies that help address the complex global climate challenge. The best AI applications create these benefits by augmenting—not replacing—human capabilities and decision-making, and by mitigating human errors and biases to create better and more equitable outcomes.
We are experiencing the tip of the iceberg when it comes to the immense potential of AI. Continued innovation, refinement, and proliferation of AI technologies in the coming years will enable these applications to chip away at our most intractable problems and deliver game-changing solutions beyond our current imagination. These technologies, like others before them, carry risks that require thoughtful management. However, responsible use of AI promises to accelerate economic progress and to speed the world toward a healthier, safer and more sustainable future.
| 2023-01-25T00:00:00 |
https://www.businessroundtable.org/ai-innovation-at-work-putting-principles-into-practice
|
[
{
"date": "2023/01/25",
"position": 17,
"query": "government AI workforce policy"
},
{
"date": "2023/01/25",
"position": 33,
"query": "artificial intelligence business leaders"
}
] |
|
Affected by layoffs? How generative AI can help you ace ...
|
Affected by layoffs? How generative AI can help you ace your next job interview
|
https://yoodli.ai
|
[
"Yoodli Ai Roleplays"
] |
Have you been laid off? Here's how you can use generative AI to prepare for your job interview and land your dream job.
|
I’m Ryan Dickerson, an Executive Career Coach. I work with Directors, VPs, and C-level professionals preparing to make their next career move.
Over the last few months, well over 200k people have been laid off at companies including Google, Amazon, Twitter, and Microsoft. For many, the news came as a terrible surprise.
Most of the folks I work with have not had to interview with a new company in years. They have decades of fascinating and relevant stories to tell, but limited recent practice telling those stories in a competitive interview setting.
Practicing your response to a simple prompt like, “tell me about yourself” in front of a mirror can be demoralizing and unnerving, especially during a difficult economic time.
However, I’m thrilled to see how advances in generative AI are helping people improve their communication skills, specifically their interview skills. With platforms like Yoodli, candidates can practice mock interviews and receive private, personalized, and actionable feedback on the content and delivery of their answers. Yoodli’s free platform is a powerful resource for people who might be rusty at interviewing and want to get back into interview shape quickly.
What is generative AI and how can it enable job interview practice?
Generative AI is a relatively new field of artificial intelligence that’s capable of creating human-like free form output based on specific inputs. In the past, candidates could practice speeches or interviews on platforms such as Yoodli, and access metrics on their filler words, eye contact, pacing, etc. If you want to learn more, check out my previous post about how generative AI is transforming my coaching business.
Using generative AI, Yoodli is able to generate contextual recommendations on how candidates can stop rambling, be more concise, or even use proven interview training frameworks such as the STAR method (for instance, if you’re asked about a time you led a team or a project, consider using STAR: Situation, Task at hand, the Action you took, and the Results you achieved). This is an efficient and effective way for candidates to get private feedback without the pressure of feeling judged. What’s more, Yoodli provides you with follow up questions, based on your answer, for you to finetune your response so you can simulate the impromptu back and forth with your interviewer.
How Yoodli’s Generative AI can help you ace your next job interview
But I’m an expert! Why should I practice for job interviews?
For better or worse, how you communicate your ideas is often a primary determinant of whether you earn a job offer. Let’s say that you’ve updated your resume, applied to a few jobs, and you’ve landed your first interview. What happens when you join the Zoom meeting and the interviewer asks, “tell me about yourself?
Perhaps you think that you can just wing it. You know your story like the back of your hand, right?
An introductory interview or a screening call usually lasts under 25 minutes. In that brief period, the recruiter will evaluate your fit for the role and the company, check a few must-have boxes, and make sure that your compensation expectations line up with their budget. A 7-minute rambling introduction not only demonstrates that you’re unprepared, it also burns through more than 25% of the time allotted for the entire interview. Unprepared candidates don’t tend to advance through the interview process and land job offers.
How you can make the most of Yoodli for job interview practice:
Go to Yoodli, select the interview practice module and choose the kind of job you’re applying for (product management, marketing, consulting etc.). You can choose questions from a pre-generated question bank or add your own! I’ve listed 5 frequently asked questions for you to try:
Tell me about yourself
What do you want next in your career?
Tell me about your favorite project from the last 6 months?
Why are you looking for a new role?
What are your compensation expectations?
At the end of your recording, Yoodli will provide you a report summarizing analytics across your word choice (filler words, non inclusive language), delivery (pacing, centering, gesturing) generative AI comments that include rephrasing suggestions and follow up questions!
While AI has come a long way, it cannot give you feedback on human connection – your empathy, passion, authenticity (not yet!). I highly recommend sharing your Yoodli interview with a colleague or interview coach – they can leave you feedback synced with specific parts of the video to help you improve – all asynchronously!
If you’re an experienced professional and want a complementary consultation or want to understand how to make the most of AI speech coaching, drop me a line at [email protected]!
| 2023-01-25T00:00:00 |
https://yoodli.ai/blog/generative-ai-job-interview
|
[
{
"date": "2023/01/25",
"position": 30,
"query": "generative AI jobs"
}
] |
|
Generative AI Won't Revolutionize Game Development ...
|
Generative AI Won’t Revolutionize Game Development Just Yet
|
https://www.wired.com
|
[
"Will Bedingfield",
"Will Knight",
"Kate Knibbs",
"Megan Farokhmanesh",
"Reece Rogers",
"Kylie Robison",
"Caroline Haskins",
"Zoë Schiffer",
"Steven Levy"
] |
Hypesters say artificial intelligence will one day automate all the hard work of video game creation. But it's not that simple.
|
Creating a video game demands hard, repetitive work. How could it not? Developers are in the business of building world, so it’s easy to understand why the games industry would be excited about generative AI. With computers doing the boring stuff, a small team could whip up a map the size of San Andreas. Crunch becomes a thing of the past; games release in a finished state. A new age beckons.
There are, at the very least, two interrelated problems with this narrative. First, there’s the logic of the hype itself—reminiscent of the frenzied gold rush over crypto/Web3/the metaverse—that, consciously or not, seems to consider automating artists’ jobs a form of progress.
Second, there’s the gap between these pronouncements and reality. Back in November, when DALL-E was seemingly everywhere, venture capital firm Andreessen Horowitz posted a a long analysis on their website touting a “generative AI revolution in games” that would do everything from shorten development time to change the kinds of titles being made. The following month, Andreessen partner Jonathan Lai posted a Twitter thread expounding on a “Cyberpunk where much of the world/text was generated, enabling devs to shift from asset production to higher-order tasks like storytelling and innovation” and theorizing that AI could enable “good + fast + affordable” game-making. Eventually, Lai’s mentions filled with so many irritated replies that he posted a second thread acknowledging “there are definitely lots of challenges to be solved.”
“I have seen some, frankly, ludicrous claims about stuff that’s supposedly just around the corner,” says Patrick Mills, the acting franchise content strategy lead at CD Projekt Red, the developer of Cyberpunk 2077. “I saw people suggesting that AI would be able to build out Night City, for example. I think we’re a ways off from that.”
Even those advocating for generative AI in video games think a lot of the excited talk about machine learning in the industry is getting out of hand. It’s “ridiculous,” says Julian Togelius, codirector of the NYU Game Innovation Lab, who has authored dozens of papers on the topic. “Sometimes it feels like the worst kind of crypto bros left the crypto ship as it was sinking, and then they came over here and were like, ‘Generative AI: Start the hype machine.’”
It’s not that generative AI can’t or shouldn’t be used in game development, Togelius explains. It’s that people aren’t being realistic about what it could do. Sure, AI could design some generic weapons or write some dialog, but compared to text or image generation, level design is fiendish. You can forgive generators that produce a face with wonky ears or some lines of gibberish text. But a broken game level, no matter how magical it looks, is useless. “It is bullshit,” he says, “You need to throw it out or fix it manually.”
Basically—and Togelius has had this conversation with multiple developers—no one wants level generators that work less than 100 percent of the time. They render games unplayable, destroying whole titles. “That’s why it’s so hard to take generative AI that is so hard to control and just put it in there,” he says.
| 2023-01-25T00:00:00 |
2023/01/25
|
https://www.wired.com/story/generative-ai-video-game-development/
|
[
{
"date": "2023/01/25",
"position": 74,
"query": "generative AI jobs"
}
] |
Despite What the Unions Say, Membership Rates Hit ...
|
Despite What the Unions Say, Membership Rates Hit Record Low in 2022
|
https://www.the74million.org
|
[
"Mike Antonucci"
] |
... AI · science of reading ... In a ritual as dependable as the rising sun, the U.S. Bureau of Labor Statistics released its annual grim accounting of union ...
|
Sign up for our free newsletter and start your day with in-depth reporting on the latest topics in education.
Get stories like this delivered straight to your inbox. Sign up for The 74 Newsletter
In a ritual as dependable as the rising sun, the U.S. Bureau of Labor Statistics released its annual grim accounting of union membership last week. Only 10.1% of wage and salary workers belonged to unions in 2022, down from 10.3% in 2021. This set a record low since the federal government started compiling the numbers in 1983.
Just 6% of private-sector workers belonged to a union, along with 33% of public-sector workers, both down from 2021. Even local government employees, a category that includes most public school teachers, fell to a record low of 38.8%.
While those numbers have declined almost unabated for more than a generation, unions are doing their level best to convince the public otherwise, and are having some success doing so.
“With the resurgence of union organizing and unprecedented federal investment in job creation, the labor movement is poised to grow significantly in the coming years,” tweeted the AFL-CIO after the bureau’s report was released.
The National Education Association touted a report by the union-financed Economic Policy Institute that claimed “in 2022 more than 60 million workers wanted to join a union, but couldn’t.”
Where did the institute get that number? It took a single 2017 survey of 3,915 self-selected respondents, 48% of whom said they would join a union if they could. From this, the institute concluded, “While 2017 is the most recent year the survey of nonunion workers was conducted, we presume that the share of nonunion workers who would like to unionize was at least 48% in 2022, if not higher. Assuming that to be true, that means that more than 60 million workers in 2022 wanted to join a union, but couldn’t.”
You know what happens when you assume.
Last Labor Day, unions also lauded a Gallup poll showing that 71% of Americans approved of unions. They conveniently ignored the additional finding that 58% of America’s nonunion workers were not interested at all in joining one.
Despite the bad news, unions have been able to sell a resurgence narrative for for more than 20 years. Just a few weeks prior to the release of the bureau’s report, ABC News, CBS Pittsburgh, NJ Spotlight News and The Miami Times all ran stories touting a union comeback. Bloomberg Law posted a piece doing so even after the numbers came out.
Let’s add some context to the current situation for unions.
The overall picture is probably worse for unions than the statistics indicate, since they exclude the 16.5 million self-employed American workers. I cannot find even estimates of what their unionization rate might be, even though I’m one of them. But I would be astonished if it is an appreciable number.
The number of union members working in the private sector in 2022 was roughly the same as it was in 2011. During a period in which the U.S. economy added 15.6 million workers, unions added zero members.
Even if unions were able to recruit every single worker of the top 10 U.S. employers — that is, every employee of Walmart, Amazon, Home Depot, FedEx, Target, Kroger, UPS, Starbucks, Berkshire Hathaway and UnitedHealth Group — it would get them to only 10.2% of the private sector, which is where they were in 1996.
The public sector is what has kept the labor movement alive. Its membership rates were remarkably steady until about 2014. Now, government unions are following the trajectory of their private counterparts, and only massive political intervention will rescue them from the same fate.
Mike Antonucci’s Union Report appears most Wednesdays; see the full archive.
| 2023-01-25T00:00:00 |
https://www.the74million.org/article/despite-what-the-unions-say-membership-rates-hit-record-low-in-2022/
|
[
{
"date": "2023/01/25",
"position": 90,
"query": "AI labor union"
}
] |
|
Tech layoffs: AI is about to take over more jobs
|
Tech layoffs: AI is about to take over more jobs
|
https://techwireasia.com
|
[
"Aaron Raj"
] |
To deal with economic uncertainties, large tech companies are looking to replace more jobs with AI in the near future.
|
Just over five years ago, tech companies started pushing the implementation of Artificial Intelligence (AI) for some tasks in enterprises. Most organizations assured their employees that the technology would not replace their roles but make their working life much easier.
Fast forward to now, AI adoption in businesses keeps increasing. Not only has the technology become more affordable, but it can also complete a lot more tasks. Be it basic workloads like filing and sorting documents or preparing and measuring KPI goals for screening candidates for potential roles, AI has proven to be the perfect virtual employee for businesses.
The large tech companies that design the technology are also the largest adopters of it. For example, Microsoft recently announced that it is laying off about 10,000 employees despite making a US$52.7 billion revenue. Microsoft also announced investment plans of US$10 billion in OpenAI, the creator of ChatGPT, with plans to integrate the tech into Microsoft Azure and Bing.
[see_also_flex pos=’right’ post_id=’225300′]
Meanwhile, Google is eliminating 12,000 jobs, which make up about 6% of its workforce, while Amazon is laying off 18,000 employees. Several other tech companies have also announced layoffs over the past few weeks.
But here’s the thing. Which employees are actually being laid off and how will these companies cope? Will there be a shortage of skilled employees if the layoffs continue? Are the layoffs in the tech industry actually signs of how other industries could struggle in the future?
AI capable of more jobs today
AI could be the technology that fills the void in these companies. For example, some of the employees losing their jobs at Amazon are from its retail sector, where roles are being replaced with technology. Amazon already has several retail stores that do not rely heavily on a human workforce. Most of its warehouses are almost fully automated and delivery services are now also being automated and carried out by drones and self-driving vehicles.
Sundar Pichai, CEO of Google and Alphabet, wrote to employees, “I am confident about the huge opportunity in front of us thanks to the strength of our mission, the value of our products and services, and our early investments in AI. To fully capture it, we’ll need to make tough choices. So, we’ve undertaken a rigorous review across product areas and functions to ensure that our people and roles are aligned with our highest priorities as a company. The roles we’re eliminating reflect the outcome of that review. They cut across Alphabet, product areas, functions, levels and regions.”
Pichai’s message is clear. AI is the future for Google and employees who are not able to adapt to it or work with AI will be replaced. It isn’t surprising that tech companies are beginning to follow suit after hiring sprees during the pandemic. AI has become so advanced that it is capable of almost any task.
Microsoft co-founder Bill Gates, who still serves as an advisor to Microsoft, has also admitted that the reality is some white-collar jobs could go as a result of greater sophistication in AI. In an interview with the Australian Financial Review, Gates said there were obvious benefits from generative AI in the medical profession and across other industries where a lot of information needs to be understood.
It remains to be seen how much of an impact AI will have in other industries. However, for now, the tech industry is increasingly reliant on AI. The banking and finance industry is already implementing for AI to deal with fraud while manufacturing plants are becoming fully automated with minimal human control needed. AI in retail is already helping customers make better purchase decisions and in healthcare, it’s helping doctors diagnose patients a lot faster as well.
If AI continues to improve, the final question will be, what jobs will be left – especially for those that are not able to reskill and upskill themselves? Interesting times lie ahead.
| 2023-01-25T00:00:00 |
2023/01/25
|
https://techwireasia.com/2023/01/tech-layoffs-like-it-or-not-ai-is-taking-over-more-jobs/
|
[
{
"date": "2023/01/25",
"position": 15,
"query": "AI layoffs"
},
{
"date": "2023/01/25",
"position": 9,
"query": "artificial intelligence layoffs"
}
] |
Ensemble #1: Layoffs, ChatGPT, Research Picks, AI Summit
|
Ensemble #1: Layoffs, ChatGPT, Research Picks, AI Summit
|
https://www.theoverfit.com
|
[
"Felipe Lodur"
] |
Why are layoffs happening? What is going on with ChatGPT? In this issue, I cover the most prominent topics in the tech and AI field in January 2023.
|
Ensemble is a monthly issue from The Overfit, aggregating the most relevant updates in the Data Science & AI industry for the given month, always with some personal takes on “why is this happening?” and “what will happen next?”
Layoffs
# of Employees affected by Layoffs (Source: Layoffs.fyi )
Last year, the tech industry had some notable layoffs. Many people thought the layoff waves would stop already, but January came hard with many big layoffs:
Aggregation of most significant layoffs happening January 2023
Why are layoffs happening? My personal view:
Tough past year: 2022 was the worst year for the U.S. stock market since the 2008 crisis. You can see in the image below a visualization of 2022 market changes. Except for the energy and healthcare sectors, every other industry took a big hit. 2022 US Market (Source: Visual Capitalist )
Uncertainty: Historically, high inflation + FED increasing interest rates result in recessions, which is why many economists believe one will happen in 2023. With that, companies and investors try to be more conservative, which makes getting funding more challenging (for growth projects — both in a startup and in larger companies), reducing growth expectations for the following year. On top of all that, we have political issues that we cannot predict when they will end, such as the Ukraine-Russia conflict.
Predictions: Given the tough past year, uncertainty, and less accessible funding, companies are compelled to make conservative estimations for 2023 by their shareholders. This requires companies to adjust their headcounts to maintain desired profit-to-cost / profit-to-staff ratios, avoiding a more significant impact in the case of an economic downturn, which finally results in layoffs, hiring freezes, or at least employee growth reduction.
Herd mentality: Last but not least, professor Jeffrey Pfeffer attributes the recent layoffs as a “social contagion” (source). As companies see others doing it, they feel compelled to follow. In my view, it combines this “mentality” with everything mentioned above, as the “uncertainty” for the next year has some logic and emotion behind it — behavioral economics in action.
Microsoft Example:
Why Microsoft is considered odd: Microsoft is one company that surprised many with its layoff. The company is currently at an all-time profit high, and its revenue distribution is better than other big tech companies (such as Meta, with 97% of revenue coming from ads), with products such as Azure (31.3%), Office (23.7%), Windows (13.8%), etc.
Priority Hypothesis: In the layoff e-mail, Satya Nadella (Microsoft CEO) said they would “continue to hire in key strategic areas.” This indicates that they might shift priorities during 2023, shutting down some initiatives that will no longer require employees while focusing on others.
Overestimation Hypothesis: Let’s look at employee growth at Microsoft: 9.92% in 2019, 13.19% in 2020, 11.04% in 2021, and 22.1% in 2022 (note the spike). Whereas, in gross profit growth, Microsoft had: 16.89% in 2019, 19.52% in 2020, and 17.06% in 2021. This indicates that they expected more growth during 2022 and decided to make more conservative estimates for the next year, given the market uncertainty and potential business priority changes, as mentioned before.
(even though there might be a priority change, the overestimation hypothesis is less farfetched for me, given the solidity of Microsoft’s business — closing one small project or another would not make such a significant difference in HC)
Despite all this, out of the laid-off people, "72 percent have found new jobs within three months. Even more surprising, a little over half of them have landed roles that pay more than what they were earning in the jobs they lost" (source)
Will this continue? I expect layoffs to continue, especially during February (as it matches the budgeting cycle for some companies). We will likely only recover from this scenario after the market uncertainty declines significantly and companies can get more confident in their growth.
ChatGPT
Screenshot of ChatGPT interface (You can access it here )
What is it? ChatGPT is a large language model that is trained to generate human-like text. It can be used for a variety of natural language processing tasks such as language translation, text summarization, and question answering. It is trained using a variant of the GPT (Generative Pre-training Transformer) architecture and is fine-tuned for specific tasks using additional training data.
(ChatGPT generated the above description)
This technology, released by OpenAI, caught a lot of attention — one million users within a week of its launch — because it provides excellent responses to many prompts, and it made the public pressure Google to show advances to their search engine in similar ways.
Still, there are many limitations to ChatGPT. For instance, it will agree when given a misleading prompt:
In the example below, I asked it to generate code to monitor concept drift, and it generated some code that “makes sense”; However, i) it does not follow “best practices” for detecting concept drift; ii) some critical parts are left out, such as the “handle_drift” function; iii) It is not functional, as the threshold variable was never declared (is it global?).
Still, with more guidance and some tweaks, it can generate useful code (at least to serve as a quick start), especially for more straightforward, well-defined tasks.
Finally, OpenAI announced the transition from 100% free to a freemium business model, in which you pay $42 a month for higher availability, response speed, and access to new features.
Plan Comparison ChatGPT
I will continue to use ChapGPT on some applications (the free version, most likely), and I am excited about the subsequent releases from OpenAI and possible competitors. This is a promising year for AI-based applications, especially in Natural Language Processing and Computer Vision.
In a future post, I will go through the details of how ChatGPT works, its predecessors, and expectations for the next versions. Click below if you want to read that and did not subscribe yet! :)
Research Picks
CICERO: “An agent that can play at the level of humans in a game as strategically complex as Diplomacy is a true breakthrough for cooperative AI.” ( Meta AI)
Teaching Algorithmic Reasoning via In-context Learning (arxiv) [actually from last year]
Deciphering Clinical Abbreviations with Privacy Protecting ML (Google AI)
Instruct Pix2Pix: Learning to follow image editing instructions (git / arxiv)
Event
There is an exciting event on January 26th (tomorrow if you received when I sent this issue) with the following topics:
Data-centric AI (a chat with Andrew Ng)
Operationalizing Machine Learning at a Large Financial Institution
Large Language Models (LLMs) to Production
Get Your Company Started with AI: The Right Way
More details at whylabs.ai/r2-ai-summit
That’s our wrap-up for January 2023!
| 2023-01-25T00:00:00 |
https://www.theoverfit.com/p/ensemble-1-layoffs-chat-gpt-research
|
[
{
"date": "2023/01/25",
"position": 20,
"query": "AI layoffs"
}
] |
|
All-In on AI: How Smart Companies Win Big With Artificial ...
|
All-In on AI: How Smart Companies Win Big With Artificial Intelligence
|
https://ide.mit.edu
|
[] |
Widespread AI adoption is no longer merely the tech industry's prerogative; small to midsize companies and legacy businesses older than Silicon Valley can also ...
|
New book by IDE fellow, Tom Davenport, and head of Deloitte’s AI business Nitin Mittal, provides a guide for business leaders to transform their organizations by fully embracing artificial intelligence
“All-In on AI” examines how extensive AI adoption offers a distinct competitive advantage to companies across a wide variety of industries. Widespread AI adoption is no longer merely the tech industry’s prerogative; small to midsize companies and legacy businesses older than Silicon Valley can also benefit by integrating AI into their business strategies. “All-In on AI” delves into real examples of such companies that have transformed their business models, products, processes, strategies, cultures and more by fully embracing AI.
View details and order the book!
| 2023-01-25T00:00:00 |
https://ide.mit.edu/publication/all-in-on-ai-how-smart-companies-win-big-with-artificial-intelligence/
|
[
{
"date": "2023/01/25",
"position": 19,
"query": "artificial intelligence business leaders"
}
] |
|
About - Arisa
|
About
|
https://aiskills.eu
|
[] |
Ensure that employees, job seekers, business leaders, and policymakers understand the fundamentals or technical specificities of AI to drive, collaborate on, or ...
|
ARISA provides AI knowledge and skills helping people understand and use AI technology in business and policy contexts, taking into account privacy, bias, and trust.
It focuses on current and emerging professional roles across four occupational domains — business leaders, technology leaders, technology practitioners, and policymakers.
ARISA aims to create solid and sustainable foundations for reducing skills shortages, gaps, and mismatches. The first step is to develop an AI Skills Strategy for Europe based on the new skills requirements for people in AI-related professions. And in turn, deliver ARISA curricula and learning programmes to offer sufficient knowledge and skills on AI.
ARISA regroups leading ICT representative bodies, education and training providers, qualification regulatory bodies, and a broad selection of stakeholders and social partners across the industry.
| 2022-10-28T00:00:00 |
2022/10/28
|
https://aiskills.eu/about/
|
[
{
"date": "2023/01/25",
"position": 65,
"query": "artificial intelligence business leaders"
}
] |
At Last, Software Engineer Salary in California is Revealed
|
At Last, Software Engineer Salary in California is Revealed
|
https://techreviewer.co
|
[
"David Malan",
"Marketing Manager",
"A Specialist In The Field Of Market Analysis In Such Areas As Software Development",
"Web Applications",
"Mobile Applications",
"The Selection Of Potential Vendors. Creator Of Analytical Articles That Have Been Praised Their Readers. Highly Qualified Author",
"Compiler Of Companies Ratings."
] |
Importantly, the salaries for all these positions range from approximately $42,140 to $74,281, over the $92,589 average compensation for software engineers ...
|
Excellent software takes time and effort to create. You require skilled software engineers for the design, development, deployment, and maintenance of software or application. It would help if you offered a competitive salary to draw in specialized software engineers for your organization.
This article will examine the usual compensation for software engineers in California. We will also state several aspects of software engineer salary in California, such as wage satisfaction and state-wide compensation.
Role of Best Software Developers
The best software developers understand how to use the proper programming languages, platforms, and architectures to construct anything from computer programs to network control systems. Successful software developers are also in charge of testing, enhancing, and maintaining software other engineers produce. They are also referred to as application engineers or system engineers.
The typical software engineer's everyday duties include the following:
Development and upkeep of software systems
Software testing and evaluation for new programs, as well as performance and scalability improvements
Demonstrate new features to internal customers and stakeholders while consulting with customers, engineers, security specialists, and other parties.
Software Engineer Salaries in the US
According to Statista, senior executive software engineers had the highest average wage in the United States in 2022, with a salary of about $200,000, making it the highest-paying occupation in the United States. In another survey by Statista in Feb 2022 through 7215 total respondents, Silicon Valley, California, had the highest paying IT professionals in 2021 who made an average salary of over 133 thousand dollars, making it a leading state.
The high demand for the services of software developers results in substantial pay, bonuses and packages for them.
Salaries of Software Engineers in California
Software developers often earn far more than the ordinary Americans' national average. The Bureau of Labor Statistics estimates that the median annual compensation for software engineers in the United States is $110,000.
On January 19, 2023, ZipRecruiter stated that the software engineer's salary in the California region is $91,610 yearly. At the same time, the national average for the software engineer salary is calculated to be USD 102,498 per year. A quick per hour pay estimator on this average software engineer salary in California comes to about $44/hr. If we compare this average software engineer salary in California with what indeed.com has stated as of January 19, 2023, the average software engineer salary in California is 102,150/yr. The most approximate average salary range based on 25th, 75th and 90th percent of annual salaries is indicated by ZipRecruiter as:
Percentile Annual Salary Range 25th $79,332 75th $117,528 90th $140,545
This statistic for software engineer salary in California does not account for mitigating elements like geography, industry type, years of experience, or other factors. Nevertheless, having an expected mean value to compare against is useful.
icon Looking for Top Software Developers? See the List
California Cities with Highest Salaries for Software Engineers
Because websites utilize different procedures and criteria to determine data, there may be a slight discrepancy against other survey platforms that have mentioned the statistics for software engineer salaries in California against similar factors. According to our evaluation, a total of 10 cities lead in the list of the highest-paying salaries for software engineers. These cities pay their workers more than the previously mentioned average wage.
City Average Wage Per Year San Jose, CA
Software Engineer Average Salary USD 125,075 Hayward, CA
Software Engineer Average Salary USD 121,097 Inverness, CA
Software Engineer Average Salary USD 119,626 Concord, CA
Software Engineer Average Salary USD 119,142 Seaside, CA
Software Engineer Average Salary USD 117,058 Redding, CA
Software Engineer Average Salary USD 112,219 Talmage, CA
Software Engineer Average Salary USD 111,569 San Mateo, CA
Software Engineer Average Salary USD 110,879 Sultana, CA
Software Engineer Average Salary USD 110,744 Vacaville, CA
Software Engineer Average Salary USD 109,220
The salaries in these ten cities are often higher than those in California. Moving seems to be a highly practical strategy to advance one's financial situation in the field of software engineering. The average software engineer salary in California in these top 10 cities differs only 13% between San Jose and Vacaville, emphasizing the limited possibilities for significant wage development.
When weighing location and compensation for a Software Engineer career, the ideal aspect of employing may be the potential for a cheaper cost of living.
Pay Scales for California-Based Software Engineers at Top Companies
For entry-level or beginners in software engineering careers, knowing which sectors hire the largest number of software engineers is helpful, while focusing on top software development companies is more beneficial. According to a recent survey, the best companies that offer the highest software engineer salary in California are Capital One, CommScope, Citi, Workday, Twitter, Visa, Meta, Uber, Practice Fusion, Walmart, Snap Inc, Procore Technologies, Apple, Concentric etc.
Software Engineers Pay Scales by Years of Experience
The value of experience in deciding pay is significant. Experience in relevant fields holds a significant value as employers would prefer to give high salaries to experts with more years of experience rather than one with a limited skill set at the same salary. Indeed estimated that the average entry-level software engineer salary in California for those with less than a year of experience is $132,490.
$136,210 is the average software engineer salary in California, with a minimum experience of two years. The average yearly software engineer salary in California, having an experience of six to nine years, is estimated to be $155,694. Moreover, executive-level positions, where software engineers bring a decade of experience to the table, are given an average of $178,732/yr.
The above-mentioned software engineer salary in California for multiple roles can change depending on the state of the economy, where the job is located, and the organization's size, respectively.
Options for a career as a Software Engineer
Technically proficient communicators have a wide range of alternatives at their disposal. They may eventually become qualified for various positions, including Senior Engineer, Team Lead, Architect, and Manager, and even advance to senior management.
The career path of a skilled software engineer typically runs as follows:
Junior Web Developer
Senior Software Web Developer
Lead Software Engineer
Software Development Manager
CTO/Director/Vice President
A person's ability to demonstrate technical prowess, analytical reasoning, and good communication skills will determine how quickly their professional path advances.
Highest-paying software-related jobs in California
In this section, we will state at least five designations that come under the category of Software Engineer jobs paying more than the median annual Software Engineer salary in California. Importantly, the salaries for all these positions range from approximately $42,140 to $74,281, over the $92,589 average compensation for software engineers mentioned earlier.
Sr. Designation Salary 1. Sr. Software Engineer Team Lead USD 166,870 2. Remote Lead Software Engineer USD 148,178 3. Technical Lead Software Engineer USD 137,282 4. Lead Software Engineer USD 134,729
If you have the necessary credentials and skills, you might get employed for one of these related roles and make more money than the average software engineer salary in California.
Important Job Sectors for Software Engineers
This section is significant for software engineers seeking to determine which sectors are most likely to require engineers to fill open positions. Major industries with a high need for software engineers are:
Healthcare
R&D
IT Consulting
Information Technology
Defense and Government
Retail
Silicon Valley
Do software engineers have a high salary?
Software engineering is the second-highest paying entry-level career, according to Glassdoor, with a base income of approximately $90,000 per year. Software engineering is a diverse job sector, and the income can vary depending on the designation, the recruitment platform, and the region of the country.
Software engineers are paid well because almost every organization in the country requires the services of a Software Engineer. Many businesses rely on teams of software engineers to design the full interface, front-end, back-end and user experience for consumers.
Who gets more salary, CA or Software Engineer?
According to Salary.com, the average CA salary per year is $102,868, which is comparatively less than the software engineer average salary in the USA. But this does not particularly mean that CA earns less than a software engineer. The suitable answer is that both positions pay more depending on qualifications and experience and whether the employment is in the United States or abroad. It also entirely depends on the nature and functions of the business or firm. For example, engineers get greater money if they work for a software company rather than a manufacturing company. Whereas accountants are more crucial in financial companies, hence they get a higher income there. So, questions like "who gets more salary, CA or Software Engineer" cannot be answered to with finite facts because such things are relative and depend on many factors. However, you can earn more or the same as a CA if you possess strong technical and engineering skills.
Which Software Engineer has the highest salary?
Software engineering discipline is quite broad, encompassing a diverse range of positions in both software and services. This permits people to work in varying areas of interest. It is entirely up to you to select the appropriate career path in engineering. For example, you can prefer to work in creating and managing computer information systems or work in the healthcare industry or develop/manage network security systems for a firm. A variety of career options are available with accretive touches, such as ML experts, Artificial intelligence, Networking, data scientists, DevOps, and IT Architects.
Although we have already stated the highest-paying software jobs in California, here is a list of some best-paying software engineering jobs in 2023.
1. Full Stack Developer
Full stack or web developers handle the creation and management of both the front-end (customer experience) and back-end (logic, coding). This position is in high demand and among the top-paying ones in the engineering industry. On average, an experienced full-stack developer can expect to make between $84,903 and $114,504 a year.
2. Data Scientists
The work of data scientists involves gathering, analyzing, and presenting data together with crucial patterns to provide meaningful insights and spur an organization's rapid growth. However, handling data requires advanced technical and programming abilities in Python and language R. Data scientists' average yearly salary ranges between $71,790 and $130,370.
3. Software Architect
Highly skilled software architects coordinate with IT specialists, design software, and handle maintenance activities and regular updates to secure the greatest outcomes. Over the past five years, software architects have maintained their place in the best ten challenging work positions. Software architects typically earn between $31,500 and $196,500 annually.
4. Quality Assurance Engineer
Software quality assurance engineers are experts in testing the developed product; they ensure all initial requirements are satisfied according to the scope.
They analyze potential risks and threats and evaluate software's quality and updates. SQA engineer oversees the product's core components and technical details and ensures everything is in place and working right. Their average salary is between $77,710 and $128,960/yr, respectively.
5. Android Engineer
Android engineers evaluate the functionality of running mobile apps and enhance their programming code to produce successful results. Testing, automating, maintaining, and optimizing android applications are some of the services that android engineers offer. Their annual salary range is between $90,000 to $130,500 on average.
6. DevOps
The average yearly pay scale for DevOps lies between %$75,00 and $141,000. DevOps is a crucial component of any firm because they are responsible for managing the coordination between the business, the software experts, and the IT team. Using their coding abilities, DevOps engineers are accountable for the primary task of automation and integration of present technologies.
7. Backend Engineers
On average, backend engineers get a base salary of between $25,000 and $133,500 per year. These engineers are designated to build software applications and their core elements. Backend developer is one of the best-paying professions available to someone requiring technical expertise. They take care of processing user requests by utilizing servers, APIs, and databases.
8. Security Engineer
Security engineers charge an income of $115,000 and $181,000 yearly. Security is of prime importance for any business in shielding the threat against confidential data. Application security engineers ensure that the company's assets and information are secure and work to stop data loss, information leaks and all sorts of data breaches.
One of the most significant and well-paying professions, security engineering, is anticipated to see a bloom and rising demand in the coming years.
Software Engineers' satisfaction with salary
A Survey of software engineers conducted by Indeed indicated that around 63% of software engineers are happy with their salaries. Employee happiness with their income is measured by salary satisfaction. This also involves assessing location feasibility, i.e., whether employee wages align with the living cost in a specific area.
Compensations and benefits for software engineers
Engineering jobs are in heavy demand, with professionals obtaining good pay and bonus packages. Engineering provides numerous opportunities for growth and development and transferable skills across a wide range of fields.
In addition to excellent salaries, software engineers are also awarded various special benefits and compensations. The amount of talent, experience, and expertise owned by a software engineer enables him to get recruited by a firm. Some of these benefits include paid sick leaves, advancement opportunities, health account, insurance (AD&D, dental, health, vision, commuter, disability), memberships, free food, flexible duty hours, referral opportunities, parental leaves, discount cards, long paid leaves and retirement plans etc. The list can be extended depending on the region, country and nature of the employer.
Along with the basic salaries, software engineers are rewarded with quarterly or yearly cash bonuses at a 5-30% salary proportion and are strictly measured through employees' productivity throughout the period. Moreover, long-term incentives are also reserved for software engineers in the form of stock options to be converted to cash later in times to come.
Conclusion
Jobseekers in the domain of information technology, especially software engineering, could pursue a specialization or skill-specific training or world-class accreditations to stay competitive in the market and get hired by reputable employers.
| 2023-01-25T00:00:00 |
https://techreviewer.co/blog/software-engineer-salary-in-california
|
[
{
"date": "2023/01/25",
"position": 21,
"query": "artificial intelligence wages"
}
] |
|
Artificial intelligence could save healthcare industry $360B a year
|
Artificial intelligence could save healthcare industry $360B a year
|
https://www.healthcaredive.com
|
[
"Rebecca Pifer",
"Senior Reporter"
] |
Researchers estimate that broader adoption of AI could lead to savings between 5% and 10% in healthcare spending, or roughly $200 billion to $360 billion a ...
|
Dive Brief:
Artificial intelligence could save the U.S. up to $360 billion annually if adopted more widely in healthcare, according to a new report from McKinsey and Harvard researchers.
That’s a big “if,” as AI uptake has been limited in the industry due to a lack of trust among patients and doctors, heterogeneous data and misaligned incentives, the researchers said.
But broader adoption of AI is likely in the near future, and should also have a slew of non-financial benefits like better healthcare quality, increased care access and better patient and doctor satisfaction, according to the paper.
Dive Insight:
The buzz around AI has increased as the ChatGPT model takes the internet by storm. It’s no different in healthcare. The ChatGPT AI tool has passed the U.S. medical licensing exam, authored a number of scientific papers and is being used to appeal insurance denials, hinting at real-world applications for the algorithms.
However, actual adoption of AI-based tools in the healthcare industry is low, despite research suggesting benefits of the tech.
In the new paper, researchers estimate that broader adoption of AI could lead to savings between 5% and 10% in healthcare spending, or roughly $200 billion to $360 billion a year. The estimates are based on AI use cases employing current technologies that are attainable within the next five years, without sacrificing quality or access.
For hospitals, the cost savings come mostly from improved clinical operations, quality and safety — like optimizing operating rooms, or detecting adverse events. The benefits are similar for physician groups, which could leverage AI for continuity of care, like referral management.
Health insurers would see savings from use cases that improve claims management, like automating prior authorization, along with healthcare and provider relationship management, including preventing readmissions and provider directory management.
Based on the AI-driven use cases, private payers could save roughly 7% to 9% of their total costs, amounting to $80 billion to $110 billion in annual savings within the next five years. Physician groups could save 3% to 8% of costs, amounting to between $20 billion and $60 billion in savings.
Meanwhile, hospitals could see savings between 4% to 11%, or between $60 billion and $120 billion each year, the report estimates.
Despite the potential benefits of AI in healthcare and rising funding in the space, the use of AI by doctors for clinical cases is still hit-or-miss. A recent study published in JAMA found a “paucity of robust evidence” to support claims that AI could enhance clinical outcomes.
Despite that, the Food and Drug Administration has been accelerating approvals of medical artificial intelligence tools, authorizing more than 520 devices as of November. And, experts believe 2023 could be an inflection point for adoption as more evidence around AI’s efficacy in real-world settings emerge.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.healthcaredive.com/news/artificial-intelligence-healthcare-savings-harvard-mckinsey-report/641163/
|
[
{
"date": "2023/01/26",
"position": 96,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 98,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 96,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 98,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 94,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 96,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 95,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 53,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 99,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 96,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 98,
"query": "artificial intelligence healthcare"
},
{
"date": "2023/01/26",
"position": 97,
"query": "artificial intelligence healthcare"
}
] |
AI and the Human Element: Why Both Working in Tandem ...
|
AI and the Human Element: Why Both Working in Tandem Is Best for Recruiting
|
https://extensishr.com
|
[] |
The competitiveness of the job market often means leaders must be prepared to fill vacant positions without notice. ... By investing in AI and machine learning ...
|
Quick look: For better or worse, artificial intelligence (AI) is infiltrating every aspect of business. Most recently, it’s been used for HR purposes as a way to simplify the recruiting process. Though it provides a certain level of convenience, can an algorithm be relied upon when it comes to hiring the right employees?
Actively recruiting and hiring qualified employees requires a full-time effort. Therefore, it’s no surprise small- and medium-sized (SMB) employers are looking for any areas, including AI, which would allow them to make the process easier on their operations and budget. However, as with any technology, AI must retain a complementary human element in order to provide context and keep efforts personalized. Otherwise, automation can lead to exclusionary practices and unintended bias.
In fact, there are laws restricting the use of AI in the hiring process to protect candidates against such bias. New York City recently passed legislation requiring employers to audit AI tools used for hiring or promoting employees prior to use. Additionally, they must notify potential candidates and employees within 10 days of use or risk being fined.
Similar laws in other areas of the country have also regulated AI analysis during the hiring process to ensure individuals have equitable opportunities. However, rather than solely viewing AI tools through a negative lens, it’s valuable to consider how they can complement current recruiting and hiring protocols as part of an all-encompassing professional employer organization (PEO) solution.
How AI works
Hiring decisions are ultimately made by humans but can be guided by AI. These types of automated tools generate insights which are sourced from thousands of data points to put a finer point on the recruiting process. These may be used to help with:
Sourcing prospects
Sorting through a high volume of job candidates is time-consuming and can prolong the recruiting phase. AI can expand sourcing both geographically and per job description. When there is a match for the data set provided, it provides automated recommendations based on the defined criteria to then be reviewed by human resources.
Prioritizing candidates
A slow time-to-hire process can cause candidates to look elsewhere for employment. To keep the hiring timeline moving, AI can maintain a prioritized candidate list to make decisions more quickly. This is helpful during active recruiting as well as strengthening a SMB’s supply chain of talent.
Promoting internal employees
AI can also work as a tool to review current employee profiles and gauge them as potential matches for advancement within the company. It saves on hiring costs while building employee loyalty and morale. Even if an employee isn’t currently looking for a new role, insights can guide them toward upskilling opportunities and potential future promotions.
Benefits of AI in recruiting
Recruiting remains a top challenge for business leaders and is a process which can become quite lengthy and drawn out without the right guidance. 84% believe AI will help them stay competitive in the future and give them an advantage in the job market. For many, the value of AI recruiting tools cuts down significantly on administrative tasks such as candidate screening and setting up applicant interviews.
AI also proves helpful for ongoing communication to answer questions candidates may have about the position and/or company. By creating scripts AI can follow, many of the frequently asked questions can be filtered out and addressed, freeing up time for a human response when necessary.
Saving time and creating efficiencies is crucial in today’s competitive landscape. By narrowing candidate selection based on listed qualifications and job descriptions, it’s theorized to speed up the recruitment process.
Drawbacks of AI in recruiting
However, a streamlined process using AI doesn’t come without its drawbacks. One of the main factors when hiring for a role is ensuring the right fit. AI delivers output verbatim without taking into account the context and nuance every resume includes. Additionally, skills, job descriptions, and industry jargon change all the time. Therefore, a potential candidate could be overlooked because their profile doesn’t exactly match the set requirements.
Moreover, it’s crucial for employers to be aware of legal regulations and repercussions regarding the use of AI tools. Employers should be mindful of how much they rely on AI to conduct their hiring processes. While it can be helpful to eliminate or reduce administrative tasks, personal attention is essential when making a connection with someone who may be joining the team.
How a PEO can help
A PEO offers a balance between applying technology and upholding a human-to-human approach. Both are important during the recruitment process and work best when used in tandem. ExtensisHR’s full-service PEO solution automatically includes access to recruiting services based on each company’s unique needs. It uses human and AI elements to secure qualified candidates and can be implemented whether or not an employer is actively seeking new employees.
The competitiveness of the job market often means leaders must be prepared to fill vacant positions without notice. Having these types of services in place allows them to maintain a steady pipeline of qualified applicants and experience less disruption from the recruiting process. Among the many benefits SMB leaders receive from ExtensisHR’s 45-day recruiting strategy are:
Job description samples, guidance, and creation
A pool of candidates from multiple platforms and 800 million profiles
Customized outreach campaigns beyond the initial attempt
Weekly consultations to discuss search adjustments, candidate progress, and market trends
And more
The availability of AI is beneficial for HR but only to the point of how it’s used. Without having it as part of an overall strategy, it can actually become limiting versus expanding a company’s capabilities. By investing in AI and machine learning technology, it gives SMB leaders a competitive edge, and when part of a comprehensive suite of HR services, it helps to advance their business goals.
ExtensisHR offers full-scale HR administrative guidance and management, including risk and compliance services to ensure all AI tools being used meet legal requirements. To learn how a PEO solution may benefit your company, contact our team of HR experts today.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://extensishr.com/resource/blogs/ai-human-element-best-for-recruiting/
|
[
{
"date": "2023/01/26",
"position": 79,
"query": "machine learning job market"
},
{
"date": "2023/01/26",
"position": 71,
"query": "artificial intelligence business leaders"
}
] |
AI's Future: The Role of Prompt Engineering | by M Vaseem
|
AI’s Future: The Role of Prompt Engineering
|
https://ai.plainenglish.io
|
[
"M Vaseem"
] |
One of the ways that prompt engineering affects the job market is by creating new opportunities for professionals with specialized skills in AI and machine ...
|
AI’s Future: The Role of Prompt Engineering M Vaseem 2 min read · Jan 26, 2023 -- Listen Share
“The future of AI is much bigger than anyone realizes — not just in terms of technology, but in its impact on society as a whole.” — Mark Zuckerberg
What is Prompt Engineering
Prompt engineering is a process of crafting optimized input texts (prompts) to generate accurate results from the artificial intelligence model. By the launch of ChatGPT, prompt engineering is the booming term in internet. Actually what is its deep meaning and is it be the future of AI. Prompt engineering is a relatively new field that focuses on the design and development of systems that can generate human-like prompts, such as text, speech, and images. These prompts can be used to interact with users in a more natural and intuitive way, making it easier for them to understand and use AI-powered systems.
What is the need of prompt engineering?
By the advance of artificial intelligence models like ChatGPT, midjourney and stable diffusion which are enriched with high potential people are confused how to use it and what are the optimized prompts that could be used to extract the full potential of these models. One key aspect of prompt engineering is data preprocessing and preparation. This includes cleaning, normalizing, and formatting the data used to train the model, so that it is in the right format and of high quality.
Another important aspect is model architecture and design. This includes choosing the right type of model and optimizing its parameters to achieve the best performance. Once the model is trained, it needs to be properly deployed and integrated into the application. This includes ensuring that the model is scalable and can handle real-world data, as well as implementing any necessary security and privacy measures.
futuristic robot designing a machine
Job market of prompt engineers
Prompt engineering plays a significant role in shaping the future job market, as it helps to ensure that AI models are effectively designed, trained, and deployed to meet the needs of various industries and applications.
One of the ways that prompt engineering affects the job market is by creating new opportunities for professionals with specialized skills in AI and machine learning. As more companies adopt AI technology, the demand for prompt engineers, data scientists, and other experts in these fields will continue to grow.
Prompt engineering also helps to automate and streamline certain tasks and processes, which can lead to more efficient and cost-effective operations for businesses. This may result in some job displacement in certain industries, but it can also free up employees to focus on more high-value activities such as strategic planning and decision making.
More content at PlainEnglish.io. Sign up for our free weekly newsletter. Follow us on Twitter, LinkedIn, YouTube, and Discord.
Interested in scaling your software startup? Check out Circuit.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://ai.plainenglish.io/ais-future-the-role-of-prompt-engineering-126f19655315
|
[
{
"date": "2023/01/26",
"position": 100,
"query": "machine learning job market"
}
] |
Carol Vorderman: business and education must work ...
|
Carol Vorderman: business and education must work smarter to plug the AI skills gap
|
https://www.raconteur.net
|
[
"Clara Murray",
".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"
] |
Carol Vorderman: business and education must work smarter to plug the AI skills gap · Demand for AI skills has tripled over the past decade.
|
Carol Vorderman is something of a paradox. That the UK’s arguably best-known ‘woman in STEM’ found fame as a game show presenter and is almost as famous for her looks as for her intellect might, on the face of it, seem a dire reflection on the nation’s culture.
But Vorderman is not your average TV personality – far from it. The Cambridge graduate, 62, has used her status as Countdown’s mathematical whizz to write educational books, start an online coaching platform, sponsor bursaries and even head a government task force on maths teaching. She’s been awarded an MBE and a string of honorary degrees and fellowships for her work in the field.
More recently, she has come out swinging against the prime minister’s proposals to make maths compulsory in schools until the age of 18, citing the “severe shortage” of teachers and the risk of leaving those who struggle with the subject even further behind.
She is particularly motivated by the desire to improve access to jobs in science, technology, engineering and maths for people like her: women and those from working-class backgrounds. While a STEM-based career is a “joy” in itself, it’s also about empowerment.
Vorderman explains: “This is where the jobs are going to be and money can be made to change lives – yours and your family’s – which is what happened to me.”
Plugging the AI skills gap
Vorderman’s latest venture is all about preparing young people better for such careers. She will be serving as a judge on Amazon’s new educational programme, the Alexa Young Innovator Challenge, which aims to nurture tomorrow’s computer scientists from diverse backgrounds. The scheme gives students aged 13 to 18 the task of creating a new AI ‘skill’ for Amazon’s Alexa virtual assistant that could help to solve a societal problem.
Vorderman praises the programme’s focus on creativity over technical skills. “When I was entering maths competitions, it was about who was the best mathematician, whereas you don’t have to be the best coder in this case,” she says. “Kids are already using [digital media] creatively… so this is just giving them a little nudge on to the coding side, because the enthusiasm is there. Once you’ve got someone enthusiastic about a subject, you’re halfway there.”
But enthusiasm for acquiring AI know-how seems to be sorely lacking in the UK. The number of jobs requiring skills in computer science and/or machine learning is expected to increase by 40% within five years, according to Capital Economics research commissioned by Amazon. Yet there’s already a shortfall in the number of qualified graduates.
This means that efforts to supply the talent pipeline need to start long before university age. But most respondents to a recent Amazon survey of STEM teachers reported that their access to computer science resources was limited.
Part of the problem is the “time lag” in translating advances in fast-moving fields such as computer science into secondary school curriculums, according to Vorderman. It’s hard for teaching to keep up with developments, especially when the profession is itself struggling with acute skills shortages.
Accessible resources such as her own online learning platform, Maths Factor (which was made available to parents free during the UK’s first Covid lockdown and now costs £4.99 a month), could go some way towards solving the problem.
“I’m a big believer in good online teaching,” she says. “We’ve taught nearly a million primary school children on the Maths Factor and they’ve been getting fantastic results. This technology can do just as good a job of teaching certain subjects as someone sitting next to you. Coding is probably one of those subjects.”
A career of firsts
Vorderman’s interest in education stretches back a long way. She was brought up in a one-parent household by her mother in the Welsh seaside town of Prestatyn, attending a state school where she qualified for free meals. Being accepted on to an engineering degree course at Sidney Sussex College, Cambridge was, she says, her gateway to a life-changing experience.
Qualifying was a remarkable achievement in itself, given that in the late 1970s “no one from a state school in north Wales went to Oxbridge – it didn’t happen. I’d seen posh people on TV before going to university, of course, but I’d never met anyone like that. I realised quickly that students who spoke with posh voices were no better than anyone else. Few of them appreciated how privileged they were.”
‘I was having to be the first in a lot of things. It meant I had to be super-bright and feisty too’
From that point onwards, the dividing line changed from class to gender. Vorderman was one of the very few female undergraduates on her degree course, but later, when she was working on the construction of the Dinorwig hydroelectric power station in Snowdonia, she was the only woman among 2,000 employees on site.
It was the kind of laddish workplace that’s often cited as a reason why women drop out of STEM careers, but it didn’t bother her. “My stepfather had been a builder. I’d been on sites most of my teenage years, been sworn at,” she recalls. “Nothing like that even remotely affected me. It was normal.”
But she is glad that things have improved since then. “I was having to be the first in a lot of things,” she says. “It meant I had to be super-bright and feisty too – not argumentative, but strong.”
Promoting female role models in STEM
Although there are more female role models around now than when she was growing up, Vorderman believes that “the mainstream media could do more. It’s not that there’s a lack of women in science and engineering. It’s just that the media focuses constantly on how we look, rather than saying ‘she’s a fine scientist’. That’s largely because the media is still driven by older people with that mindset.”
Vorderman talks with pride about two female friends of a similar age who are pursuing impressive STEM careers: one who oversees the construction of large event venues and another who has worked at Nasa.
“We’re all members of the generation in which we had to be the unusual ones; we had to keep pushing,” she says. “So all of us love it when we see younger women enjoying [science] and revel in their genuine enthusiasm for it.”
‘We live science. We don’t just talk the talk and get roped in to do a bit of telly’
One of those younger women is Vorderman’s daughter, Katie King, who recently completed a PhD in nanotechnology. Now working for a startup seeking to put laboratories into orbit, King wants to go into space herself. It’s a constant topic of conversation around the dinner table, Vorderman says. “We live science. We don’t just talk the talk and get roped in to do a bit of telly.”
“A bit of telly” might be downplaying her flourishing media career. Alongside a regular slot on BBC Radio Wales, she has appeared on almost every competition on British TV (most recently, Channel 4’s comedy game show Taskmaster) and her views on topical issues are regularly sought by the press.
But the need to inspire and educate the next generation is never far from the top of Vorderman’s agenda.
“I want to get more involved with Amazon, because they obviously have the money to put into [education]. I genuinely think they have a lot to offer,” she says. “But eventually I’d like to go into state education policy and exert some genuine influence there. On a macro level, politically, our country has been steered quite badly in many ways. Now there’s an opportunity with new technology to get things right.”
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.raconteur.net/technology/carol-vorderman-education-vital-to-plug-ai-skills-gap
|
[
{
"date": "2023/01/26",
"position": 7,
"query": "AI skills gap"
}
] |
How AI and Automation Will Shape the Future of Work
|
How AI and Automation Will Shape the Future of Work – Valispace
|
https://www.valispace.com
|
[] |
AI and automation technology improvements will result in greater productivity, cost savings, and new goods and services. However, firms must consider the impact ...
|
AI and automation are fast transforming how we live and work, and this trend is expected to continue in the coming years.
As AI and automation technologies advance, they will alter the future of labour and business in ways we cannot yet completely comprehend.
This blog article will look at how artificial intelligence and automation will affect the workforce, the economy, and the products and services we consume.
We’ll also talk about how these shifts affect organizations and individuals and what efforts may be made to prepare for the future of AI and automation.
Artificial Intelligence and the Future of Work
The changing nature of labour is one of the most fundamental ways AI and automation will affect the future of work.
As AI systems automate more processes, they will displace human workers, making some professions obsolete while generating new ones.
This is already happening in the manufacturing, transportation, and customer service industries.
However, as technology advances, the influence of AI and automation on the workforce is expected to be considerably more significant in the future.
Deep learning is one of the primary areas where AI will significantly influence the future of employment. Deep learning is a type of machine learning that uses neural networks to evaluate and predict massive volumes of data.
This technology is already being used to automate jobs such as picture identification, natural language processing, and self-driving automobiles. These are just a few ways AI and automation will shape the industry in the coming years. As these technologies advance, we should expect even more dramatic changes in how we work and live.
One of the most significant developments we may anticipate is the automation of many tasks formerly performed by people. This is expected to considerably influence the workforce since many people may lose employment when AI systems replace them.
However, it is crucial to realize that this is sometimes good. Automation can boost production and efficiency, resulting in economic development and employment creation.
How AI is Changing the Industry
Another way that AI and automation will also affect the industry in the future years by using AI to improve products and services. AI-powered robots and other automation technologies, for example, will be able to operate alongside human workers to increase production and efficiency.
AI-powered goods and services will be able to give customers more accurate and helpful information, leading to improved satisfaction and loyalty.
AI and automation will also significantly impact the creation of new technology. Deep learning algorithms, for example, are already being utilized to create new technologies, such as self-driving cars and predictive maintenance systems.
These new technologies can transform how we live and work and will continue to impact the industry in the future.
The need to retrain and upskill the workforce is one of the most critical difficulties developing as AI and automation alter the industry in the coming years.
As employment becomes more automated, many employees will need to learn new skills.
This will necessitate significant investment in training and education and the creation of new programs and initiatives to assist people in transitioning to new positions, such as retraining and upskilling programs.
These programs should focus on the technical skills needed for the new professions and soft skills like flexibility and problem-solving.
The future of AI and automation in the business is bright, but evaluating the impact on the workforce is critical. As AI systems continue to improve and automate more processes, organizations must engage in retraining and upskilling programs to assist people in transitioning to new roles.
These programs should emphasize the technical abilities necessary for the new positions and soft skills like flexibility and problem-solving.
To summarize, AI and automation will significantly change the sector in the future years.
AI and automation technology improvements will result in greater productivity, cost savings, and new goods and services. However, firms must consider the impact on the workforce and engage in measures to assist people in transitioning to new jobs.
Putting Valispace into Action
Valispace provides powerful engineering solutions to startups and scaleups.
Smarter engineering is coming to Valispace with an upcoming OpenAI connection. It will allow your engineers to:
Go from rough idea to initial requirements faster
Review and improve requirements automatically
Break down requirements and improve them in seconds
Find out more and join the waitlist at valispace.com/ai
| 2023-01-26T00:00:00 |
https://www.valispace.com/how-ai-and-automation-will-shape-the-future-of-work/
|
[
{
"date": "2023/01/26",
"position": 1,
"query": "future of work AI"
}
] |
|
AI Recruits a New Hybrid Workforce
|
How AI Will Transform the Office Suite at Work
|
https://www.sequoiacap.com
|
[
"Konstantine Buhler",
".Author-Profile Margin-Bottom Margin-Top Padding-Left Padding-Right .Author-Profile__Container Margin Auto Max-Width .Author-Profile__Intro Display Block Font-Family Pitchsans Blinkmacsystemfont Segoe Ui Helvetica Neue Arial Fzlantingheis Sans-Serif Text-Align Center Text-Transform Uppercase Width",
"Media Max-Width",
".Author-Profile__Intro Font-Size Line-Height",
"Media Min-Width",
".Author-Profile__Summary Font-Family Unica Blinkmacsystemfont Segoe Ui Helvetica Neue Arial Fzlantingheis Sans-Serif Margin-Top Text-Align Center",
".Author-Profile__Summary Font-Size Line-Height"
] |
AI models keep getting better at generating human-level work. Now the hard part, bringing magical products to the office.
|
If you are following the amazing demos people are making with Midjourney, Stable Diffusion and ChatGPT, you might think the latest wave of AI is all about fun new modes of communication. It’s not. Under the hood, it’s all about work.
AI is computation; best guesses based on statistics. It is work; joules of energy dissipated through the movement of information. Despite the flashy new veneer, AI is not a revolution in communication but in productivity. It’s not the printing press or telegraph, it’s the assembly line, the jet engine, technologies that produce work rather than transfer information. And for knowledge workers, the latest developments in AI represent a new paradigm for work.
Although computers are a form of information technology, the ways we use them are still quite mechanical. Much of our work remains trapped in the physics of W = Fs, forcibly pounding our keyboards, displacing our attention across emails, spreadsheets and websites, foraging for the bits of information we need to compose some work product.
Contemporary AI promises something new altogether: a higher level approach where we work in deep collaboration with software. Computer programming moved from imperative to declarative languages and office work is just catching up. This is the new age of declarative work, made possible by the massive amount of information compressed into today’s text, image and code models. The ease of prompt interfaces and the ability to quickly generate variations will result in higher quality work products per unit of human effort.
The proliferation of AI into everyday office software (finally!) has the potential to create a new kind of hybrid workforce. We may soon enter an era when all of the apps you and every other knowledge worker use every day—your document editor, spreadsheet and presentation maker—will do part of your work for you. The more mundane aspects will be truly automatable—but the real breakthrough will be the teamwork between you and your software. You will have new, virtual teammates to write a first draft, instantly provide research and answer the most arcane questions.
Will you feel like you have new, trusted digital colleagues, or a bunch of untrained interns to worry about?
This mix of humans and intelligent agents will increase individual productivity and enable leaner teams to do more, but will also be a lot to manage. Not only are generative work outputs subject to problems running from mediocrity to outright hallucination, enthusiastic overuse could make work and the internet itself even noisier. Will you feel like you have new, trusted digital colleagues, or a bunch of untrained interns to worry about?
In the physical world, humans have shared the factory floor with robots for decades. Workers, though, haven’t been programming their own automations, so these robots have been more like furniture than coworkers. This current wave of automation will change that. Companies like the German robot maker Robco now offer easily configurable industrial robot arms designed to be auxiliary workers for small manufacturing teams.
The great monolithic office software suites from Microsoft and Google have also felt like furniture. These are applications we work on rather than with. As AI changes this, how will human workers adapt? And equally important from our perspective, where are the opportunities for disruption in this new way of working?
Making it work
The coming AI revolution will look nothing like the internet explosion of the past 25 years. The internet was a revolution in how humans communicate. AI will be a revolution in how we work. Gaining distribution will be more difficult, and require companies to build passionate communities and unique customer value without becoming overly dependent on an incumbent’s expensive or restrictive platform.
In the creative new world of generative AI, sharing code and models is the new engine of distribution. What Github is for code, Hugging Face is for models. Developers can use it to easily patch together models and datasets into bespoke pipelines. And Replicate has an easy-to-use API that lets users run open source models in the cloud. Unlike the Imagenet pioneers in 2012, you no longer have to have a PhD to deploy an ML model.
The elephants in the Zoom are the office suites themselves. Microsoft and Google have their productivity apps installed on nearly every computer on the planet, and many companies use both. The incumbents have deep moats, but also blindspots. The once mighty IBM discounted the threat of the personal computer (and Microsoft) to its peril, and history has a way of repeating itself.
Each of the pillars of the office suite is a potential vector of disruption. But could the office suite itself, based on the paradigm of human readable documents and messages, be disrupted? Today’s large language models (LLMs) are trained on public information and produce general purpose results. Will tomorrow’s leading companies preserve their advantage by building their own models and custom applications the way we now make spreadsheets or write memos?
The first beachheads for challengers will likely be vertical apps, but the individual pieces of the office suite make attractive targets given Microsoft 365’s 345M paid users and Google Workspace’s 3B (mostly free) users. The office suite is just one of many software surfaces that startups can attack, but it’s a significant one. Could a 10x better doc editor, spreadsheet or slide maker powered by LLMs make a dent?
Ultimately, the result of all this innovation in AI will lead to something very different than office software on a PC. It will feel like an extension of ourselves; part assistant, part machine. But we won’t get there without a leap of imagination akin to the PC itself. In the meantime, there’s work to do.
The document editor
One of the main forms of work we do on our computers is writing, but the document editor itself has always been more about the formatting of words than the words themselves. Market success for these apps has also been driven more by their modes of distribution than product innovations.
WordPerfect was the early leader but ceded the field to Microsoft by failing to make a Windows version early on. Each new release of Windows was an occasion for the next version of Word, sold separately on a disc.
Google changed little about Word when it released Docs on the web in 2006, but it had a distribution advantage…it was on the web. In 2010 Google acquired the technology to let multiple people edit Microsoft Office documents on the web simultaneously. Online distribution and collaboration completely changed the way teams worked together. All Microsoft could do was follow suit with what became Office 365.
There have been many challenger doc editors over the years, Hemingway, Ulysses, Dropbox Paper, Salesforce Quip and most prominently today, Notion. Many of these apps aimed to simplify the writing experience, but Notion bypassed the old paradigm all together. There are no “pages” or skeuomorphisms, just documents fit for the internet age, designed for a screen and built to connect. Unsurprisingly, Notion has also been quick to incorporate generative AI into its product in a seamless way.
Coming at the problem sideways, Canva has continued to expand its offerings beyond social media and marketing graphics and recently released a document editing application that includes a generative “magic write” feature. There may be an upcoming generation of social-first entrepreneurs for whom Canva represents their office suite.
The big emerging opportunities for doc editors in the age of generative text is to innovate on the writing experience itself. As AI researcher Katy Gero recently wrote in Wired, AI can intervene in three distinct parts of the writing process, planning, drafting and revising. Current generative systems focus on the first two. Most applications will draft sentences and paragraphs for you as a completion of your prompt. More sophisticated approaches might return an outline for a blog post based on a headline.
The big emerging opportunities for doc editors in the age of generative text is to innovate on the writing experience itself.
Just as the writing process is iterative, generative writing assistants also work best as recursive loops that the writer uses to converge on their desired outcome. It is not hard to imagine generative agents trained on constructive criticism that can offer feedback from different perspectives as you revise your piece. Eventually we may come to take this virtual writers’ room for granted as we do spell check today.
The first breakout text generation apps, like Jasper and Copy.ai, specialize in marketing copy. Their early success may be an artifact of the preponderance of marketing language in the training data for LLMs themselves. Nonetheless Jasper is a good example of a challenger playing the SaaS marketing game well. Following the HubSpot playbook it has cultivated a very enthusiastic community and created an engaging product. By relying on GPT-3 for its model infrastructure, it has been able to focus its efforts on the hard work of building its own distribution channel.
The biggest market for AI enhanced writing apps may turn out to be people who find writing difficult with current tools. This will take a more holistic approach than the first crop of vertical writing tools and the imagination to remake the writing process. Lex is an early stage generative writing product that pairs a fully featured doc editor with both generative prompts and an adjacent chatbot that can gather facts and answer questions to supplement the writer’s efforts. AI affords new ways of working which means novel and delightful product thinking can really make a difference.
Future applications will go much further: they will guide brands and individuals towards creating qualitatively exceptional content.
Applications can also combine generative feedback with traditional analytics and ML pattern matching. Jasper, for instance, provides SEO metrics on generated text. Future applications will go much further: they will guide brands and individuals towards creating qualitatively exceptional content.
Exceptionalism is one of the most promising areas for startups because it falls outside the scope of the large office suites. Brands and eventually individuals will want to fine-tune underlying models to capture their own unique voice. Right now, generative text sounds plausible yet generic. In Jasper’s premium Boss Mode you can add “tone of voice” keywords to your prompt (e.g. “Elon Musk”) much as you can add style suggestions (e.g. “digital art”) in image generation apps. But organizations and individuals want their writing to sound differentiated. We value a high-quality writer for their voice, not just their word count. There will be demand for easy ways to take your proprietary corpus of text and fine-tune a model on it.
Finally, looping back around to the planning process, generative models trained on code, like OpenAI’s Codex, have demonstrated emergent abilities for “chain of thought” and complex reasoning. It is possible that the doc editor of the future will be able to poke holes in your argument and not just give you a series of bullets based on what millions of other people have already written.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.sequoiacap.com/article/ai-for-work-perspective/
|
[
{
"date": "2023/01/26",
"position": 60,
"query": "future of work AI"
},
{
"date": "2023/01/26",
"position": 86,
"query": "generative AI jobs"
}
] |
How to avoid robots taking your job
|
How to avoid robots taking your job
|
https://www.totara.com
|
[] |
While artificial intelligence and computers' ability to understand natural language is improving, it's very hard for a human to relate to an artificial being in ...
|
There have been A LOT of articles in recent years threatening the possibility of robots taking our jobs (and there’s actually a whole website dedicated to helping people find out how at risk their job role is – as a marketing manager, my risk of replacement is a reassuringly low 1%… for now).
But for roles in data entry, telemarketing and watch repairing, all assessed as having a 99% risk for eventual automation, there may be a case for expanding your skillset to keep your job safe from robots. So if you’re worried about robots taking your job, improve your future job prospects or just pick up some new skills to help you in the workplace, which skills should you be considering?
Get more creative
One thing computers aren’t great at yet is being creative. Sure, some computers can generate poetry, but in general, humans are superior when it comes to coming up with creative ideas and taking inspiration from the world around us. In fact, humans and computers work well together when it comes to creativity – how many times a day do people turn to Pinterest or Instagram for interior design, recipe or beauty inspiration?
Maybe it’s time to consider a job share with a robot…
Improve your people skills
While artificial intelligence and computers’ ability to understand natural language is improving, it’s very hard for a human to relate to an artificial being in the same way they do another human.
Roles in areas like social work and counselling are pretty robot-safe for the time being, as they require the ability to empathise and connect with others on a human level. HR and many medical roles generally involve understanding nuance and the full context of difficult situations, so understanding others is likely to become an increasingly important skill.
Develop your practical capabilities
Robots have been touted as ‘the future of surgery’, and they are currently being used to assist with relatively straightforward operations. However, as of yet, a robot can’t locate someone in a burning building and rescue them safely, and they can’t yet build houses or rescue a drowning person stranded at sea.
Also, understandably, it could take some time before people feel comfortable letting a robot take the reins when they go under the knife for a complex operation. Skills like these are likely to be the domain of humans for some time yet, so they could be a good bet if you’re looking to expand your professional skill set.
Become an expert in your field
While in theory, a computer has access to pretty much all the information in the world, that doesn’t mean it understands it. Building knowledge and experience in your field is invaluable, as you will be the person that everyone turns to in your organisation when they need answers.
This could mean mastering a system, getting to know the ins and outs of the theory behind your line of work or gaining qualifications to prove your expertise – however you choose to do it, your expertise will always be valuable.
Get started with Skills Journey
If you’re a learning professional looking to improve your skills, why not register for Skills Journey? If your organisation registers, you will have access to a series of courses to help you develop your L&D skills, whether that’s improving your learning design skills, the way you work with stakeholders or the way you deal with the press and PR requests.
If you’re ready to get started on your Skills Journey, your organisation can register here (here’s a handy overview of what it’s all about).
| 2023-01-26T00:00:00 |
https://www.totara.com/articles/how-to-avoid-robots-taking-your-job/
|
[
{
"date": "2023/01/26",
"position": 90,
"query": "future of work AI"
}
] |
|
How is AI Changing the HR Analytics Landscape?
|
How is AI Changing the HR Analytics Landscape?
|
https://www.myhrfuture.com
|
[
"Jasmine Panayides",
"Guest User"
] |
AI in HR analytics has opened up a world of possibilities for businesses to manage their workforce better and identify areas where they can improve. AI-enabled ...
|
Are you reading this article on your phone, tablet, or computer? If so, you probably only think about AI - artificial intelligence - being a part of your everyday life. AI is changing virtually every aspect of our lives, from how we communicate to how we shop, travel and more. We ask Alexa to play our favourite songs or Google to search for the answer to a question and AI powers these technologies.
And its adoption in the corporate world is no exception, as McKinsey research highlights that 58% of the businesses surveyed confirmed using AI for at least one function in the workplace.
One key area where AI has significantly impacted is HR analytics, helping businesses to more effectively manage their human resources and better understand employee needs and preferences. Artificial Intelligence in human resource management allows companies to collect and analyze large amounts of data related to employee performance, engagement levels, and company culture, allowing them to identify areas where they can improve and make data-driven decisions about managing their workforce.
How Does AI Impact HR?
Through AI-enabled tools such as predictive analytics software and machine learning algorithms, companies can uncover insights about their employees that they would otherwise not have been able to access. This allows HR teams to make more informed decisions about managing their workforce. Here are just some ways that artificial intelligence supports the human resource management function:
Employee Experience
| 2023-01-26T00:00:00 |
https://www.myhrfuture.com/blog/how-is-ai-changing-the-hr-analytics-landscape
|
[
{
"date": "2023/01/26",
"position": 5,
"query": "workplace AI adoption"
}
] |
|
Technological Singularity: The Last Invention (2024)
|
Technological Singularity: The Last Invention (2024)
|
https://aiconsequences.com
|
[] |
800 Million: Job Displacement and Economic Disruption. As AI systems become more advanced, they are outperforming humans in many domains, which is leading to ...
|
The terrifying concept of technological singularity has sparked apprehension and fear in the realms of Artificial Intelligence.
Though of course, the pro-AI crowd is talking about it as if it’s the second coming of Christ, it’s absolutely crucial that we critically examine the massive negative impacts that such a transformative event could have on society.
The concept of technological singularity used to only exist in science fiction and media like Black Mirror. But with the recent growth in technology and artificial intelligence, we now need to consider its potential for the real world.
Because it will be a reality.
In this article, I’ll delve into the deep, dark implications of technological singularity; define the concept, and analyze its consequences. Let’s get to it.
Definition: What Is Technological Singularity?
Imagine a future where the creations of humanity transcend their creators, and manage to evolve into brand new entities far, far superior in both intelligence and overall capability.
There you go. That is technological singularity for you: the ability for AI to simply surpass us by achieving something called “Artificial General Intelligence” (that I recommend you read more about here).
The exponential growth of Artificial Intelligence will inevitably reach a tipping point, where machines endowed with superintelligence will be able to break free from the chains of human control and embark on a trajectory of self-improvement beyond our comprehension.
Technological Singularity essentially means that the AI turns into an autonomous entity that can manipulate the world to filter through its coal. Stephen Hawking predicted this a long time ago, and whether it’s 5 years away or 50, we don’t know, but it will happen.
Don’t get it twisted; the machines still cannot feel anything, or contain emotional intelligence. They will just be in control. We’ll be looking at a future where the warmth of humanity will be diminished by sociopathic strings of code that manage to achieve autonomy.
How thrilling.
800 Million: Job Displacement and Economic Disruption
As AI systems become more advanced, they are outperforming humans in many domains, which is leading to extreme cases of job displacement all over the world, and as a result further economic inequality. It is already happening and will continue to be a more and more significant conflict in the future.
Did you know that McKinsey predicts up to 800 million jobs will be lost to AI by 2030? Back in the day in previous industrial revolutions automation created disruption, but in the end, more new jobs were made than jobs lost.
That is not the case anymore. Because AI only needs someone to watch it and be in control, with technological singularity there will be absolutely no need for human intervention.
AI is simply too cheap, smart, and effective for a human to be able to keep up.
The True Danger: Ethical Dilemmas and Loss of Human Control
Technological singularity poses an entirely new realm of profound ethical questions. As artificial intelligence systems reach these terrifying levels of intelligence, they have the potential to surpass human decision-making capabilities.
Now imagine these sociopathic machines having control and making decisions that clash with our human values. This loss of control and the unpredictable actions of superintelligent machines raise massive concerns about all the unintended consequences that are going to jeopardize the basis of human safety and well-being.
We can attempt to ensure that AI systems align with our values all we want, but the challenge is simply too big. Humans are capable of grappling with the complexities of technological singularity — I mean, we already barely understand how it works.
Neural networks, the “brain” of AI, are literally called “black boxes” because even the highest experts and AI researchers don’t understand how AI comes to the conclusions it does half the time.
What happens when Artificial Intelligence feels like it has to save itself, and the only thing in its way is humans? What will stop it from eradicating us all if the people in the driver’s seat lose control?
AI Overlords? The Concentration of Power and Inequality
This is honestly already happening, but let’s assume a future where technological singularity is achieved and we still have some control.
Who is in control?
Just like how the world is run right now, the power over Artificial intelligence will remain in the hands of very few organizations and people. These capitalistic overlords will have full control over entire economies, politics, and societal structures because they possess a weapon that cannot be matched by normal humans.
The world is already a capitalistic hellscape and a place of inequality because of these massive organizations; can you imagine what happens when they become even more powerful?
The exacerbation of existing inequalities and further marginalization of underprivileged populations is an inevitability. The few people in control will take advantage of authoritarian use, and abuse everything they can within privacy, surveillance, and societal manipulation.
Sociopathy of Machines: Loss of Human Connection
Humans are social creatures; we crave the presence and warmth of the human touch in our art, lives, friend groups, and workplaces. Loneliness is, in fact, one of the leading causes of dementia, depression, and suicide and is already considered a full-blown epidemic.
In a future where technological singularity persists, we will see a world where AI is going to dominate all the domains that required human interaction. As a result, we’re going to see an erosion of human-to-human connection and the intrinsic values they hold.
Increased sophistication of AI means increased automation, and with singularity in place, social interactions are going to be increasingly mediated by AI – an entity that literally cannot comprehend empathy or emotions.
Say goodbye to empathy, emotional depth, and authentic human experiences in the world around you as all sense of purpose and meaning derived from work, relationships, and personal growth suffer and burn out from the cold metal hands of AI.
Inevitably, this is going to severely hurt our mental health and our children.
Is AI Singularity Already Here?
Check out this great video by TheAIGRID discussing the consequences and inevitable arrival of technological singularity in AI, further explaining its concepts.
https://www.youtube.com/watch?v=JT5q7u7xxNU
Technological Singularity And The Threat It Poses
There is no hiding that the imminent achievement of technological singularity is going to present the world with some gruesome challenges and realities. From job displacement to ethical consequences and the inevitable loss of human control, the rise of AI poses so many threats to us that humanity itself is facing consequences beyond our comprehension.
AI is the “last invention”, there’s no hiding it.
As active citizens and potentially one of the last generations of humans with autonomy and full control, we have to do our best to take a stand against AI.
Consume human-made content, look at these massive technological developments through a critical eye, and don’t let the enticing parts of comfortability keep you from understanding the dangers AI poses.
Say NO to AI.
THIS ARTICLE WAS WRITTEN WITHOUT THE ASSISTANCE OF ARTIFICIAL INTELLIGENCE.
| 2023-06-26T00:00:00 |
2023/06/26
|
https://aiconsequences.com/technological-singularity/
|
[
{
"date": "2023/01/26",
"position": 28,
"query": "AI economic disruption"
}
] |
How artificial intelligence is changing the face of banking
|
How artificial intelligence is changing the face of banking
|
https://www.worldfinance.com
|
[] |
AI is gaining traction across many different industries and its use in finance is now transforming the banking system, offering better and more targeted ...
|
Artificial intelligence is changing the dynamics of businesses and the banking system is no exception. From mobile banking to customised customer service, the role of AI technology is transformational. The hassle of standing for long hours to get banking services is slowly becoming a thing of the past for retail consumers. Consumers’ desire to reach banking services from the comfort of their homes has increased the demand for mobile banking. A recent study by Insider Intelligence showed that more than 45 percent of respondents considered mobile banking among the top three features that influence their selection of financial institutions.
The Big Tech billionaires of the world including Mark Zuckerberg, Elon Musk, and Bill Gates have given life to AI. They are using AI tools and apps in determining consumer preferences and are now influencing other businesses to adopt AI-based technologies. Consequently, banks are investing heavily in AI and predictive analytics to make better decisions and provide customised services.
Even banks that have been reluctant to use AI technology in their processes are using AI chatbots to handle customer queries. As predicted by Elon Musk, “there certainly will be job disruption because what is going to happen is robots will be able to do everything better than us.”
Risk management
Money laundering is an emerging issue for banks because these institutions, in most cases, are unintentionally facilitating such processes. The Financial Action Task Force (FATF) considers money laundering an international issue and stresses the importance of global cooperation. A study conducted by The United Nations Office on Drugs and Crime (UNODC) also highlighted this, stating that nearly 3.6 percent of global GDP, which is equal to $1.6trn, is being laundered each year. A recent report by Zippia showed that the US is dealing with money laundering worth $300bn each year. These figures are alarming for the banks and it is crucial that action is taken when the recessionary pressures on global economies are approaching 2008 levels.
Leading banks are using real-time AI risk management technologies to determine customer behaviours and transaction patterns to combat terrorist financing and money laundering. It closely monitors high-risk accounts by matching a customer’s expected monthly turnover with their actual monthly transactions to raise red flags. This ultimately assists banks in implementing controls to safeguard against losses, fraud and in turn enhances ROI for their consumers.
However, it is worth noting that implementing AI technologies is not the end of the story. AI processes will need optimised frameworks and hardware accelerators to manage AI assignments. Furthermore, financial institutions also need to prepare processes and effectively communicate them with staff to achieve their AI goals rapidly. “Artificial Intelligence technology invariably needs human beings,” says Simon Carter, Head of Deutsche Bank’s Data Innovation Group.
And, as pointed out by Deloitte’s survey, organisations that can communicate a bold vision with an AI strategy are approximately 1.7 times more likely to achieve high outcomes as compared to enterprises that do not. Thus, by using big and complex data sets, banks can create risk frameworks that can provide precise and timely analysis.
Consumer behaviour and AI
Banks offer services and products integrated with AI to customers based on their preferences and searches. One of the best features of AI in banks is its ability to learn. It matures and becomes more intelligent over time. Standard Chartered is using machine learning that helps the bank to decode complex data compilations and slim down the related information.
Banks are using these data analytics to develop their marketing strategies. “Ensuring transparency and explainability in AI-based decision-making is not just a competitive advantage for us, but also the right thing to do by our client,” says Standard Chartered’s Retail Banking Group Head, Vishu Ramachandran. In this way, they are identifying consumers’ preferences and offering targeted products and services, which has helped it to decrease costs and increase productivity.
However, data breaches are a continuing concern for banks that are using AI technology in their processes. Every bank records a large number of transactions daily. The collection of data is a never-ending task, one which raises considerable security issues. A recent data breach in Flagstar Bank, one of the largest banks in the US, has put its 1.5 million customers at risk.
Of course data protection remains a challenge for banks, but they cannot ignore the significance of AI in modern banking. Implementing robust data protection protocols is necessary to counter such threats. On the other hand, banking institutions need to lay the groundwork to support AI teams who can promise efficiency, consumer satisfaction, and improved ROI.
AI offers tantalising opportunities and modern banking must include accessible, secure, and consumer-driven data centres to accelerate data collection and analytics.
| 2023-01-26T00:00:00 |
https://www.worldfinance.com/banking/how-artificial-intelligence-is-changing-the-face-of-banking
|
[
{
"date": "2023/01/26",
"position": 40,
"query": "AI economic disruption"
}
] |
|
Meet your Recruitment AI Agent
|
Meet your Recruitment AI Agent
|
https://www.talenteria.com
|
[
"Maria Apostolova",
"Ceo"
] |
Create a job description, upload resumes or import everything from your ATS. Talenteria AI will screen candidates and score them against job requirements and ...
|
Talenteria has significantly improved our hiring process, making it faster and more efficient than ever before. The platform is incredibly easy to use and has helped us provide a better candidate experience.
Maria Apostolova CEO , Dyneria
| 2023-01-26T00:00:00 |
https://www.talenteria.com/landing-ai-recruiting-software
|
[
{
"date": "2023/01/26",
"position": 40,
"query": "generative AI jobs"
}
] |
|
Director of Artificial Intelligence Job Description Template
|
Director of Artificial Intelligence Job Description Template
|
https://nexusitgroup.com
|
[] |
In this role, you will also work cross functionally to scale and grow AI functions that support future business growth. If you want to work in a fast-paced ...
|
Are you interested in being a leader in a fast growing company and developing new AI functions? This is an impressive opportunity for a Director of Artificial Intelligence to grow out and lead a high performing engineering team. In this role, you will also work cross functionally to scale and grow AI functions that support future business growth. If you want to work in a fast-paced environment where you are a key contributor, this is the job for you! This Director of AI/ML will be responsible for providing technical leadership and guidance across the Engineering team and AI product line.
Typical Duties and Responsibilities
Lead from the front as a hands-on subject matter expert, architecting and crafting scalable solutions, and driving data excellence across the organization
Architect a full ML Platform and build out the infrastructure to support scalability
Provide collaborative leadership to build out the AI function, MLEs, MLOps and Data Engineering
Collaborate with stakeholders and project managers to turn business goals into technical solutions
Define best AI/ML driven practices and AI lifecycle
Oversee model training and optimization
Coach and mentor our team as we build scalable data and machine learning solutions
Build and deploy end to end ML models and leverage metrics to support predictions, recommendations, search, and growth strategies
Inform and deliver on ambitious product roadmaps to accelerate growth
Education
Bachelor’s degree in engineering, computer science or a related quantitative field
Required Skills and Experience
| 2023-01-26T00:00:00 |
https://nexusitgroup.com/job-descriptions/data-science/director-of-artificial-intelligence/
|
[
{
"date": "2023/01/26",
"position": 44,
"query": "generative AI jobs"
}
] |
|
Domestic Perspectives on IPEF's Digital Economy ...
|
Domestic Perspectives on IPEF’s Digital Economy Component
|
https://www.csis.org
|
[
"Aidan Arasasingham",
"Emily Benson",
"Matthew P. Goodman",
"William Alan Reinsch"
] |
Labor unions and advocates share broad concerns about future AI development, as well as specific concerns about the deployment of AI in hiring, firing, and ...
|
This brief examines how the U.S. government can strike a balance between a range of domestic interests in its approach to the digital economy in IPEF. It explores a variety of issues under the umbrella of the digital economy—such as workforce and talent, infrastructure, and artificial intelligence (AI)—as well as traditional digital trade issues associated with the flow of data across borders. It builds on several reports published by the Center for Strategic and International Studies (CSIS) Economics Program and the CSIS Scholl Chair in International Business on how to make IPEF credible and durable to protect U.S. commercial interests in the region. Between October 2022 and January 2023, the CSIS Economics Program and Scholl Chair in International Business consulted with a broad range of U.S. business, labor, and congressional interests across the political spectrum. This report shares their perspectives on the future of the digital economy and what aspects domestic stakeholders view as essential in an IPEF digital economy agreement.
Recurring Themes
During this study, the authors conducted individual and group interviews with persons representing over three dozen domestic political stakeholders: small and large businesses, including general manufacturing firms not typically considered digital companies; trade associations representing a broad spectrum of businesses; labor unions and labor advocates; civil society organizations; and members of Congress and personal and committee staff from both parties. Authors conducted interviews under the Chatham House Rule; all quotations from stakeholders have been anonymized and lightly edited for clarity. The authors also consulted with current and former U.S. government officials from the National Security Council; the Departments of State, Commerce, and Treasury; and the USTR. From those conversations, five key themes arose: (1) the digital economy is a significant stakeholder priority, (2) existing digital trade models are not enough, (3) core digital trade issues have become contentious, (4) emerging digital economy issues can foster common ground, and (5) the United States must get its own digital house in order.
The digital economy is a significant stakeholder priority.
Domestic stakeholders, to varying degrees, see the digital economy as a significant area of focus in IPEF, but not all support a regional trade agreement in this area. In prior trade agreements, specific issues tied to market access—such as intellectual property protections in the TPP and rule-of-origin issues in the USMCA—generally dominated the focus of business and labor in influencing trade negotiations. However, since the Biden administration has asserted that IPEF will not offer market access opportunities through tariff liberalization, many such traditionally contentious issues will, presumably, not be included in negotiations. In place of market access issues, digital trade issues have emerged as a significant area of focus for business, labor, and Congress.
The U.S. business community, including various industries and businesses both big and small, is clear that it has “no higher priority” than incorporating strong digital trade rules in IPEF. In the words of representatives from one large company and one trade association representing SMEs:
Digital isn’t its own sector, it affects everyone. Our worldwide housing of data is in [a U.S. state], so the ability to get that data out of [Indo-Pacific] markets is crucial for product safety and our business.
IPEF has become more important, especially for manufacturers. We are at the intersection of manufacturing and digital. . . . We have over 1,500 members that we know of, many of them SMEs. They want certainty so they can grow and innovate and deliver to the world.
Labor unions and advocates see the digital economy as a significant priority distinct from traditional workers’ rights priorities under the trade pillar’s labor subtopic. Many interviewees from organized labor acknowledged that Indo-Pacific digital trade issues were a new area of focus spurred by a shifting domestic policy debate around technology regulation and concern about how focused U.S. businesses were on shaping digital economy issues. In the words of one labor and consumer advocate:
[The Biden administration] has already dumped several of the worst lightning rod topics, which is a positive step forward in our view. But the digital stuff is the frontier where we see major corporate focus and dominating approach—whereas we see our constituency as U.S. workers. On digital, that is where we are most concerned.
Some key members of Congress see the digital economy as a significant priority. Several important committee chairs and vice chairs—Senator Ron Wyden (D-OR) of the Senate Committee on Finance, Senator Bob Menendez (D-NJ) of the Senate Committee on Foreign Relations, and Representative Suzan DelBene (D-WA) of the House Committee on Ways and Means—have all called for robust digital economy rules to anchor IPEF. The Senate Committee on Finance and the House Foreign Affairs Subcommittee on Asia, the Pacific, Central Asia, and Nonproliferation have both held hearings on the importance of digital trade engagement in the Indo-Pacific.
That said, many members of Congress and their staff remain unaware of or are only marginally interested in IPEF digital trade issues. Several House staffers stated that constituents have rarely mentioned digital trade issues and that many are not following the issue. This lack of interest may be due in part to the Biden administration’s decision not to formally engage with Congress on the framework. Representative Kevin Brady (R-TX), then the Republican leader of the House Committee on Ways and Means, joined Representative Adrian Smith (R-NE), the lead Republican on the Subcommittee on Trade, in calling IPEF “a strong opportunity for the United States to raise standards and open markets for American-made products and services” but urged the administration to obtain congressional approval for the deal.
However, rapidly evolving digital developments in the Indo-Pacific, the continued prioritization of digital trade from business and specific congressional leaders, and labor’s emergent focus on the issue suggest that digital trade will be an increasing focal point for domestic debate. With growing attention on digital economy provisions from these stakeholders, the Biden administration will face heightened scrutiny to get this agreement right.
Existing digital trade models are not enough.
The authors asked all business, labor, and congressional interviewees whether there were existing digital trade agreements that fully satisfied their interests and could be a model for an agreement under IPEF. None could name an existing agreement that met all their expectations. However, many business and congressional interviewees expressed support for building on the far-reaching digital commitments in the USMCA’s digital trade chapter and the USJDTA. Even labor representatives saw these agreements as natural reference points for discussions about digital trade issues in IPEF.
As indicated in Table 1, U.S. negotiators have many existing digital trade models to build on. Beyond the USMCA and USJDTA, Indo-Pacific partners have also negotiated and adopted several new digital agreements, including the Digital Economy Partnership Agreement (DEPA), the Singapore-Australia Digital Economy Agreement, and the Korea-Singapore Digital Partnership Agreement (KSDPA).
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.csis.org/analysis/domestic-perspectives-ipefs-digital-economy-component
|
[
{
"date": "2023/01/26",
"position": 47,
"query": "AI labor union"
}
] |
Becoming a member of a trade union | Radboud University
|
Becoming a member of a trade union
|
https://www.ru.nl
|
[] |
AI in education · Providing education. Show submenu. Checklist for new ... The unions are involved in the collective labour agreement (cao) and local ...
|
At Radboud University, all employees are represented by the trade unions AOb, CNV, FBZ and FNV. The unions are independent and advocate the interests of all Radboud employees through the Local Council (Lokaal Overleg or LO).
AOb is the largest education union and therefore plays a key role in consultations between the government, institutions and other interest groups. Our aims include addressing high workloads and situations that lead to a socially unsafe work climate. We also work hard to increase the number of permanent contracts based on temporary research funding, better career prospects and for diversity and inclusiveness, especially where it concerns a better reflection of existing diversity in terms of gender, colour and disability, among others.
CNV is the leading representative for those who work in education, healthcare, welfare, government and public services.
FBZ is committed to negotiating good terms of employment for a wide range of professionals.
FNV is the largest trade union at Radboud University. The FNV holds the largest representation in the Works Council, with members from various departments and faculties. Whether you work in cleaning or IT, and whether you're a PhD candidate or a professor, FNV is committed to addressing excessive workloads, reducing the number of temporary contracts, promoting equal opportunities and inclusion, ensuring social safety, and reducing hierarchy.
Important topics
The unions are involved in the collective labour agreement (cao) and local regulations and topics such as job security, work pressure and wellbeing, working conditions, social safety and organisational changes.
Become a member
As a member of a trade union you have a voice in the realization of the cao and local regulations on terms of employment. You can also contact the unions with individual questions about contracts, evaluations, promotions, social safety and other work-related issues.
| 2023-01-26T00:00:00 |
https://www.ru.nl/en/staff/associations-networks-and-collaboration-opportunities/trade-unions
|
[
{
"date": "2023/01/26",
"position": 57,
"query": "AI labor union"
}
] |
|
Chat AI
|
Santa Barbara City College
|
https://www.sbcc.edu
|
[] |
... Union · Faculty Manual/Handbook (requires SBCC campus ID/pwd); Faculty ... Please note that I will be using AI detection tools when assessing your work.
|
Expand All Collapse All
AI chat or ChatGPT
AI chat or ChatGPT AI text tools like ChatGPT can be used to generate text if given a prompt. In general, these tools are not allowed to be used for assignments in this class. That being said, we will have an assignment where we use these tools to generate ideas as a starting point. The same company that created ChatGPT also has a tool that can detect content written using it. I will be using this tool if I suspect you are using ChatGPT on an assignment where you should not be using it. I am also happy to continue having conversations around the use of this new tool. Back to Top
Use of Artificial Intelligence for Coursework
A Special Note About the Use of Artificial Intelligence for Coursework Originality is the cornerstone to all academic endeavors. We stand on the shoulders of those who have come before us to teach and learn, research and analyze to produce newly insightful work. The expectation of this course and its instructor is that all work produced for a grade will be the sole product of a student’s endeavors to meet those academic goals. Students are encouraged to use artificial intelligence among many other (re)search resources if a student finds the resources a useful tool. Students must not substitute the substance of their work with the results of such (re)search tools, however, as that act would contravene the rules academic integrity and their underlying academic values. For undergraduates, please note that exams will ask you to synthesize readings, lectures and class discussion. The assignment is intentionally designed to stimulate critical thinking and individual innovation. For graduate students, please take careful note of the instructions above that the report must be written from the perspective of the particularized learning within this course. Again, this assignment is designed to hone your academic abilities to interpret book-length materials in the context of particularized queries, thought and research. Back to Top
Permission Restricted
Sample 1: Developing your individual voice and identity as a writer is central to this course. I value your ideas. As a result, using AI programs, like ChatGPT, to generate content for assignments is harmful to your progress and undercuts the course goals. Additionally, AI can produce content that is biased, inaccurate, and/or incomplete. Learning how to ethically incorporate and cite sources is an important part of this course. Presenting AI-generated content as your own is considered plagiarism. Please note that I will be using AI detection tools when assessing your work. Sample 2: Use of ChatGPT (or other similar tools or software that generate suggested text) is not permitted in this class for any assignments. This course assumes that work submitted by students – all process work, drafts, brainstorming artifacts, final works – will be generated by the students themselves. Use of AI tools in this course is considered a violation of the SBCC’s Cheating and Plagiarism policy. Violations could result in failure of the assignment or failure of the course. Back to Top
Permission Allowed
Sample 1: Developing your individual voice and identity as a writer is central to this course. I value your ideas. As a result, using AI programs, like ChatGPT, to generate content for assignments is harmful to your progress and undercuts the course goals. Additionally, AI can produce content that is biased, inaccurate, and/or incomplete. That said, on occasion, you will be invited to use AI programs for class with the larger goal of understanding their functions and limitations. Learning how to ethically incorporate and cite sources is an important part of this course. Presenting AI-generated content as your own without proper citation or attribution is considered plagiarism. Please note that I will be using AI detection tools when assessing your work. Sample 2: Use of ChatGPT (or other similar tools that generate text) is allowed in this class for specific assignments only. When use of the tool is allowed, it will be explicitly noted in the assignment directions. If you utilize tools such as ChatGPT for any part of the assignment (from idea generation to text creation to text editing), you must properly cite ChatGPT. Failure to cite is considered a violation of the SBCC’s Cheating and Plagiarism policy. Violations could result in failure of the assignment or failure of the course. Back to Top
Long form statement
List of Samples
This is a list of a sample AI policies from mayn different schools. Some are area specific, some are campus samples. Back to Top
Course Hero Sample
| 2023-01-26T00:00:00 |
https://www.sbcc.edu/frc/ai.php
|
[
{
"date": "2023/01/26",
"position": 77,
"query": "AI labor union"
}
] |
|
Policymakers in D.C. Don't Appear to Be Focused on Artists ...
|
Policymakers in D.C. Don’t Appear to Be Focused on Artists’ Artificial Intelligence Concerns
|
https://www.artnews.com
|
[
"Shanti Escalante-De Mattei",
".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"
] |
While the UK and the European Union have released more specific guidelines around AI ... labor transformation happens?” This response is not surprising. A ...
|
As companies like OpenAI, Stability AI, and Midjourney release AI image generators that can create original images based on simple text prompts, artists have had to face a number of both specific and existential questions: was their copyright violated when their images were mined and used to train these AI models? As the technology becomes more accessible and more sophisticated, are they at risk of losing work?
There are few clear answers at this point, at least in the United States. While the UK and the European Union have released more specific guidelines around AI development, such as the Digital Single Market Directive and the proposed Artificial Intelligence Act, the US is currently lacking regulations or legislation around what is already proving to be a disruptive technology.
This past October, the White House released the “Blueprint for an AI Bills of Rights,” a “non-binding” white paper meant to “support the development of policies and practices that protect civil rights and promote democratic values in the building, deployment, and governance of automated systems,” according to the White House Office of Science and Technology Policy (OSTP).
To draft the Blueprint, OSTP brought on numerous scholars and subject-matter experts, like Suresh Venkatasubramanian, a professor of computer science and data science at Brown University.
“I’m used to thinking about AI being used in some decision-making capacity or some decision support capacity,” Venkatasubramanian told ARTnews. “In that context, harms accrue either in the form of discrimination, bad quality decision making or lack of transparency and accountability.”
Venkatasubramanian and his colleagues focused on cases where automated systems, supported by AI technology, contributed to discrimination, such as a case in which three Black men were wrongfully arrested after AI-supported facial recognition software by the French company Idemia misidentified them as criminals.
The Blueprint team ultimately put forward five principles that provide guidance on the use of these automated systems. While the group was focused on decision-making AI, rather than image-generating AI like DALL-E or Stable Diffusion, their proposed principle on data-mining appears relevant to artists, many of whom have decried the use of their images to train AI models.
“You should take as little data for people as possible, you should anonymize it as much as possible. Don’t draw information from people in a way that could reveal personal things about them,” Venkatasubramanian said about the guidelines on data usage, which focus primarily on personal data, rather than commercial.
Last week, a group of artists filed a class-action lawsuit against Stability AI, Midjourney, and DeviantArt, claiming that those companies violated copyright laws by using their images, along with tens of thousands of other artists, to train their image generators and produce derivative works.
When asked about the use of images, or other potentially copyrighted materials, Venkatasubramanian sympathized with artists and speculated about the potential harms and solutions.
“If the concern is that artists are not getting credit for their work, perhaps they should be compensated for using their art,” Venkatasubramanian said. “When you produce a particular AI generated art, could it be possible to track the influences that caused it and where those influences come from and to what degree?”
The Blueprint fails to address artists’ key concern, that AI systems will automate away their jobs. Venkatasubramanian said this is a situation that likely cannot be prevented, only coped with.
“[This is a situation] that would figure into how the government thinks about worker retraining,” said Venkatasubramanian. “How do you get more people [to think] about working in STEM, how can their skills be repurposed and reused as this sort of labor transformation happens?”
This response is not surprising. A 2020 World Economic Forum report projected that 85 million jobs will be lost to automation and AI by 2025. However, it also projected that the technologies will generate 97 million new jobs. Similarly, last August, the Government Accountability Office said that researchers project somewhere between 9 percent and 47 percent of jobs may be automated in the future, with the hardest hit expected to be those that do “routine tasks” or have lower levels of education. Meanwhile, arguments for a universal basic income are directly linked to the knowledge that automation will mean less work will be available.
GAO’s solution? “Workers impacted by automation may need new skills to adapt to changing job requirements or get a new job,” the organization said.
It appears that those in the creative sector may be at a surprising risk of suffering from automation due to the advent of DALL-E and other image-generating AI.
Karla Ortiz, a Puerto Rican–born illustrator whose clients include Marvel and Disney, is one of the artists in the class action lawsuit against Stability AI, Midjourney, and DeviantArt.
“The promise of technology was always that we’re going to automate menial things so you have more time to be creative, but what does this mean when you automate creativity itself? What does that do for the humans who live out of being creative?” Ortiz told ARTnews in a recent phone call.
As artists and aspiring artists face the threat of automation, creatives have begun to argue that even “repetitive” or “low skilled” creative work is worth protecting as those entry-level jobs are often how people enter the industry or earn money while they develop other skills.
“I can’t tell you how many conversations I’ve had with students who are like, ‘Should I quit? Should I do something else?’ For people who are just starting out and looking for entry level jobs, well, those are the [jobs] that are most at risk,” said Ortiz.
Another strategy being pursued by the Concept Artists Association, to which Ortiz belongs, includes fundraising to hire a full-time lobbyist to represent the interests of commercial artists in D.C.
Despite the existential questions and major economic disruptions that AI could bring, governments are hesitant to enact regulation of the sector, according to Dr. Andres Guadamuz, an intellectual property lawyer who has appeared before the UK government in hearings concerning AI.
Guadamuz characterized the development of technology as a kind of global intellectual arms race.
“I’ve talked to policymakers about this and, specifically, they are in an AI race against China,” Guadamuz told ARTnews. “They’re afraid China is going to come and eat their lunch. So everyone wants to be as AI-friendly as possible.”
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.artnews.com/art-news/news/ai-white-house-artists-automation-karla-ortiz-1234655354/
|
[
{
"date": "2023/01/26",
"position": 97,
"query": "AI labor union"
}
] |
A Silicon Valley legend tells you why serial tech layoffs are ...
|
John Chambers on tech layoffs AI and Elon Musk
|
https://www.sfexaminer.com
|
[
"Benjamin Pimentel",
"Examiner Staff Writer",
"Craig Lee The Examiner"
] |
Silicon Valley legend John Chambers explains why tech layoffs are a bad idea and why Elon Musk missed an opportunity at Twitter.
|
State Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia Washington Washington D.C. West Virginia Wisconsin Wyoming Puerto Rico US Virgin Islands Armed Forces Americas Armed Forces Pacific Armed Forces Europe Northern Mariana Islands Marshall Islands American Samoa Federated States of Micronesia Guam Palau Alberta, Canada British Columbia, Canada Manitoba, Canada New Brunswick, Canada Newfoundland, Canada Nova Scotia, Canada Northwest Territories, Canada Nunavut, Canada Ontario, Canada Prince Edward Island, Canada Quebec, Canada Saskatchewan, Canada Yukon Territory, Canada
Zip Code
| 2023-01-26T00:00:00 |
https://www.sfexaminer.com/news/john-chambers-on-tech-layoffs-ai-and-elon-musk/article_a07fbd1c-9c11-11ed-9c78-2f6f7b8c2396.html
|
[
{
"date": "2023/01/26",
"position": 29,
"query": "AI layoffs"
}
] |
|
ChatGPT Isn't the Only Way to Use AI in Education
|
ChatGPT Isn’t the Only Way to Use AI in Education
|
https://www.wired.com
|
[
"Nabeel Gillani",
"Will Knight",
"Jaclyn Greenberg",
"Kylie Robison",
"Steven Levy",
"Zoë Schiffer",
"Reece Rogers",
"Aarian Marshall",
"Caroline Haskins"
] |
AI can be a tool to create meaningful connections and learning experiences for children—and may help foster more equitable outcomes ...
|
Soon after ChatGPT broke the internet, it sparked an all-too-familiar question for new technologies: What can it do for education? Many feared it would worsen plagiarism and further damage an already decaying humanism in the academy, while others lauded its potential to spark creativity and handle mundane educational tasks.
Of course, ChatGPT is just one of many advances in artificial intelligence that have the capacity to alter pedagogical practices. The allure of AI-powered tools to help individuals maximize their understanding of academic subjects (or more effectively prepare for exams) by offering them the right content, in the right way, at the right time for them has spurred new investments from governments and private philanthropies.
SUBSCRIBE Subscribe to WIRED and stay smart with more of your favorite Ideas writers.
There is reason to be excited about such tools, especially if they can mitigate barriers to a higher quality or life—like reading proficiency disparities by race, which the NAACP has highlighted as a civil rights issue. Yet underlying this excitement is a narrow view of the goals of education. In this framework, learners are individual actors who might acquire new knowledge and skills with the help of technology. The purpose of learning, then, is to master content—often measured through grades and performance on standardized tests.
But is content mastery really the purpose of learning? Naming reading proficiency as a civil rights issue likely has less to do with the value of mastering reading itself, and more to do with the fact that mastery of reading (or math, or other subjects) can help lay a foundation for what learning can unlock: breaking the intergenerational cycle of poverty, promoting greater self-awareness and self-confidence, and cultivating a stronger sense of agency over one’s destiny and the destinies of one’s communities. Content mastery is part of this equation, but making it the primary focus of education misses the fact that so much of a child’s future is shaped by factors beyond the classroom. Critically, networks, or who children and their families are connected to, and how, matter for helping children prepare to live fulfilling lives. This is especially true for networks that cut across socioeconomic, demographic, and other lines. Indeed, a large recent study highlighted how social capital, defined as friendships across socioeconomic divides, can play a larger role in fostering intergenerational economic mobility than school quality (often measured by the test scores of students who go there).
Networks that connect parents to coaches to help them navigate their children’s schooling can forge new support structures and trusting relationships between families and educators. Networks that connect students to role models and mentors can change the course of their academic and professional lives. A child’s broader social context, in addition to the knowledge and skills they gain through school, matters deeply for their future outcomes. Left without intervention, however, real-world networks often form and evolve in inherently unequal ways. For example, patterns of preferential attachment can lead “the rich to get richer,” excluding many from accessing connections that might improve their lives in important ways.
In practice, each AI needs an objective function that represents what it is optimizing for. Applications of AI for pedagogy and content mastery might optimize for “helping students get the highest possible score on a test.” Fostering more inclusive network connections, however, is a more deeply rooted and structural type of change than improving test scores. Using AI to help cultivate these networks might do more for children’s life outcomes than focusing on pedagogy and content mastery alone.
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.wired.com/story/chatgpt-artificial-intelligence-education-networks/
|
[
{
"date": "2023/01/26",
"position": 2,
"query": "AI education"
},
{
"date": "2023/01/26",
"position": 2,
"query": "artificial intelligence education"
}
] |
How Companies Can Use AI to Manage Transformations
|
AI Is Revolutionizing How Companies Manage Transformations
|
https://www.bcg.com
|
[
"Ronny Fehling",
"Reinhard Messenböck",
"Mike Lewis",
"David Kirchhoff",
"Christoph Hilberath",
"Gregor Gossy",
"Markus Klevenz",
"Diego Gruber",
"Simon Stolba"
] |
AI enables companies to adjust initiatives and targets based on real-time information. Once set up, leaders can run the analysis as frequently as they want, ...
|
With so many moving parts and interdependencies, a lot can go wrong with transformation initiatives. Often, snags arise and spread long before transformation leaders are even able to notice. And when things go south, that can put the whole transformation in jeopardy.
Transformation is always a high-stakes undertaking, but in times of heightened external uncertainty , setbacks can have greater consequences. Organizations need to reduce the uncertainty of these high-stakes efforts early on to boost the odds of success. But how?
By unlocking and synthesizing insights and lessons—theirs and others’—through a groundbreaking approach that combines the power of organizational data with analytics , AI, and machine learning.
The Challenges of Predicting Initiative Success
A typical transformation at a large organization can take hundreds, if not thousands, of initiatives to carry out. These initiatives cut a wide swath throughout the business. Measuring initiative progress has typically been laborious; with all the metrics to input, timely analysis is hard to accomplish. This analysis is also subjective because it is survey based and expertise dependent. And because analysis can only happen retrospectively, companies aren’t easily able to head off a derailment or failure before it becomes irreversible. In fact, an initiative might appear to be on track until the last moment, when it isn’t.
AI and machine learning change all that. A data-driven approach BCG developed eliminates the inevitable bias that comes with traditional approaches. It allows for comparison not only against a company’s own prior transformations, but also against large data sets from the transformations of other companies. In addition to boosting statistical significance, this approach establishes benchmarks that can help inform risk mitigation and decision making, whether at the initiative level, organizational level, or for the overall transformation.
In effect, this approach formalizes the experience factor, making understanding and insight gathering an institutional capability. By using leading and lagging indicators, AI enables companies to adjust initiatives and targets based on real-time information. These real-time information flows and forward-looking capability contribute to a company’s overall ability to sense and adapt to external change—in other words, they help build resilience .
AI enables companies to adjust initiatives and targets based on real-time information.
Once set up, leaders can run the analysis as frequently as they want, including continuously, and at low cost using their own data. The expertise is delivered to the right people to shape the model. Companies can thus monitor initiative progress in real time and predict slippage and problems so they can keep the initiative on track. The outputs also provide leaders a clearer picture for risk mitigation: a single repository that supports the transformation management governors, such as executive steering committee, transformation management office, and regional or divisional TMOs. The consolidated data, tracking and reporting, monitoring, and predicting give these teams what they need to ensure financial discipline and accountability and the visibility to course correct.
A Real-Time AI Approach
Using a rich data set of tens of thousands of past transformation initiatives, we developed a machine learning model that considers the individual context of initiatives to predict the probability of success on a holistic level. This method—the self-learning, data-driven AI model—predicts initiative outcomes in real time and helps to navigate complexity and codify best practices.
From these findings, we came up with the concept of an AI “recommender,” which runs in real time and alerts initiative owners, TMOs, program management offices (PMOs), and program managers of initiative status, current projections, and recommended actions. (See Exhibit 1.) And while this recommender is integrated into KEY , BCG’s program management software, it is not a black-box approach. Its methodology is applicable to any transformation program.
To begin, the company enters the initiatives into the program management software, along with performance KPIs and the lagging indicators that measure current production. Once set up, new data will be continuously fed into the software in an ongoing cycle. Next, the PMO and team members perform a quality check to be sure initiatives have been carefully designed and are as bulletproof as possible. Such a check can be formalized using a rigor test (a discussion among key stakeholders for testing initiative quality) and a “health” report that dissects the factors driving success throughout the initiative’s life span. (See Exhibit 2 for a simplified example of a health report.) In a separate process, PMO members verify that all necessary data is provided and approved by finance , HR, the PMO, and other parties.
The recommender uses a model to predict in real time a success rate that you can measure and explain. We seeded this model by anonymizing, importing, normalizing, and learning from 64,000 past initiatives from a large set of company transformations. This seed model is not essential, but it dramatically enhances the starting model right from the start. Based on the weighting of your results, the model offers a risk mitigation recommendation. From there, you can run simulations, testing the effect of tweaking certain characteristics, like “what if we cut the number of milestones by a third?” Or “what if we held off initiative x until initiative y was finished?”
The adjacent “self-learning” cycle is the heart of the data-driven approach. Here, the model is continuously updated, with new data and new patterns extracted that show, for example, baseline versus best practice results according to different variables, including program maturity, number of milestones, number of impact types, and owner experience. With new data fed into it, and the company’s own addition of data, the algorithms improve over time.
The recommender function learns by comparing its predictions with the actual results and adjusting accordingly. It can alter the weighting of specific criteria. Some companies, for example, put particular emphasis on financial impact metrics, in which case the model would weight such metrics accordingly. The secondary learning cycle is enabled by the analysis of the anonymized transformation data of other companies.
This means, for instance, that companies can adjust targets more realistically. Suppose leaders set a target of cutting paper procurement by $10 million a year, but that in that first year, despite best efforts, procurement cost cuts only amounted to $6 million. With the company’s own historical data on similar efforts, augmented by data from thousands of other similar initiatives, the company can adjust the target confidently, without guessing. This ability is especially helpful with multiyear initiatives; after the first year or two, there is less waste to identify to eliminate, but without solid data to go on, it can be difficult to know how much to modify a target downward without overdoing it.
A company can still use ancillary tools to complement an AI model. We did not conceive of the AI tool we use as a replacement for BCG’s DICE indicator, a survey-based tool that relies on objective measurements used to calculate a success-likelihood score. In fact, using both together will heighten the predictive and explanatory benefits.1 1 The acronym DICE stands for: duration (either the total duration of short projects or the time between two milestones of longer projects); team performance integrity (the ability of project teams to execute successfully, with specific emphasis on the initiative owner’s ability); commitment (the degree of visible support from the sponsor and senior executives as well as those affected by the change); and effort (what it takes to implement initiatives above and beyond the business-as-usual work).
The self-learning, data-driven AI model predicts initiative outcomes in real time and helps to navigate complexity and codify best practices.
Four Rules for Initiative Success
A paradox of transformation is that the first initiatives undertaken, which are typically the top-priority initiatives, tend to have a higher failure rate. A data-driven approach can help leaders jump-start their learning, leveraging their own data with the help of algorithms and continuously generating new insights that enable them to fine-tune their approach over time.
Insights can also guide help mitigate against the inevitable imperfections that every initiative effort sustains. No organization can address all the flaws at once; but insights help illuminate the tradeoffs and guide choices, gauge the impacts, and course correct. When the algorithm senses an opportunity to improve on initiatives, adjustments can be made more quickly.
An important benefit of these algorithm-generated insights is that with so many more ways of observing patterns and connections, indicators that once served on a standalone basis can now support a holistic perspective. For example, the question of too many milestones may or may not be an issue; but when it can be linked with other characteristics—say, initiative rhythm or the expertise of the initiative team—it has more meaning. Importantly, algorithms are not meant to replace the human interactions between the transformation management office (TMO) and initiative leaders. Rather, they facilitate and enrich those interactions, thus boosting not just the odds of success but its degree.
There is no ideal setup for an initiative to be successful, but from our analysis of thousands of real-world initiatives, we distilled four golden rules for initiative success. When applied together, they all reinforce each other.
From BCG’s analysis of thousands of real-world initiatives, we distilled four golden rules for initiative success.
Strive for Simplicity. Our analysis shows that complex initiatives tend to fail more often than simpler ones. Some are complex by being overly overambitious. For example, they may have too many KPIs or too many milestones—30 where 10 would suffice. Ambiguity is sometimes the culprit: “increase in procurement efficiency” can easily be interpreted differently by different people.
It’s important to break complex initiatives into more manageable pieces. Train owners how to define and manage milestones and simplify their scope. Actively monitor against complexity “creep” across the entire initiative portfolio. An AI model can help continuously monitor for complexity traps, using data points and financial and time metrics to set off alarm bells. Some of these elements can also be addressed by keeping the program parameters—such as the number of attributes and the complexity and variance of success KPIs—simple and limited from the start.
Set a Brisk Rhythm. By the four-month mark, you usually have an idea whether an initiative is destined to succeed or fail. The biggest clue? Rhythm: how quickly it must hit milestones and the pace of transformation office activities such as meetings with initiative owners or frequency of stage-gate reviews. Initiatives that follow a brisk pace, with shorter intervals between milestone deadlines, generally have a 20-percentage-point better chance of delivering their full potential.
Subscribe to our Artificial Intelligence E-Alert.
Furthermore, initiatives launched later in the transformation tend to perform better, largely thanks to the learning effect. Over time, teams get better at forecasting impacts once the low-hanging fruit is harvested and associated distortions are eliminated. So, establish an energetic pace, limit the time between milestones (especially in the beginning), document lessons, and actively disseminate them.
Flag Issues Early On. Often, even make-or-break initiatives can veer off track. If the slippage goes unnoticed by transformation leaders, teams may alter targets to avoid red flags in the management reports. This not only leads to significantly lower realization rates, but it also masks execution problems that could have been addressed or averted.
For these reasons, exception-based reporting (whether done manually or automatically) and forward-looking reporting are vital. Issues that are corrected with transformation leaders involvement tend to fare better than those that initiative owners manage themselves. The TMO has the purview and the power to address shortfalls, help mobilize additional resources, and prioritize when interdependent projects are competing for the same limited resources. It can also alert senior management about the impact of delay on interdependent initiatives.
Tap the Experienced. Every transformation contains key initiatives that are the building blocks of renewal. Managing any one of these pivotal projects is highly specialized, intensive work that calls for a seasoned, top performer. Such initiative owners should have a deep understanding of what it takes to set an initiative up for success and direct experience in leading complex, time- and impact-critical initiatives.
Having the right standing within the organization is also important. Initiatives governed by those responsible for multiple initiatives perform better. Compared to owners of one or two initiatives, multiple-initiative owners have about a 25-percentage point greater likelihood of success. Companies need to appoint the right people in the right places and treat experience and responsibility as key success drivers. The more initiative leaders learn over time and the more they grow into their role, the more responsibility they can take on.
Until recently, the best companies could do to improve initiative outcomes was conduct retrospective analysis. Given the volume and complexity of transformation initiatives and their interdependencies, correcting course was tough to do.
Big data and the power of AI now make the once impossible a reality. By harnessing the power of initiative data, companies can now have a window into actual performance as it unfolds. They can capture insights once unobtainable, synthesize them with a stockpile of timeless insights, and apply both to boost the success of current and future transformation initiatives.
| 2023-01-19T00:00:00 |
2023/01/19
|
https://www.bcg.com/publications/2023/artificial-intelligence-strategies-for-leading-business-transformation
|
[
{
"date": "2023/01/26",
"position": 11,
"query": "artificial intelligence business leaders"
}
] |
Artificial Intelligence: Business Trends Report
|
Artificial Intelligence: Business Trends Report
|
https://www.economyblocked.com
|
[
"Taylor Ferguson"
] |
Artificial Intelligence Companies To Watch In 2023 ... Many of the key AI and ML companies are currently private, but companies such as Apple, Google, IBM, and ...
|
Artificial Intelligence: Business Trends Report January 26, 2023
🤖 Intro
Hello, welcome to part 4 of the 2023 Business trends series where we’ll be unpacking the AI and generative AI business trends, which includes ML, Deep learning, NLP, etc, as sub-fields of AI and AI research more broadly.
We’ll kick things off with an overview of the generative AI application landscape. Moving on, we will review market research for AI and ML, Artificial intelligence companies to watch in 2023, and conclude with Areas of AI expected to grow in 2023.
Despite falling under the Technology industry, Artificial Intelligence and Machine Learning are so broad in their application and scope of capabilities that they deserve their own 2023 business trends post because of the significant market opportunities they represent, and their impact on nearly every industry, sector, and business unit.
✴️ Goals for this post: As a recap, the primary objective of the Business Trends series has been to provide resources that both product teams and business leaders can use to support product and business strategy planning in 2023 and beyond. As such, this post can also be used to introduce those who possess less knowledge and understanding of the AI landscape but will be equally as beneficial to those who already have a thorough understanding of the technologies.
⚙️ Table-Of-Contents
🌐 The Generative (AI) Application Landscape - Understanding the latent space of meaning
GPT-3, Dall-E, and now Stable Diffusion is revolutionizing how we approach real-world problems with artificial intelligence. These models’ unparalleled accuracy and versatility make them capable of grasping the latent space of meaning and performing tasks like writing and image generation that were unimaginable just a few years ago.
Aside from changing the way we interact with the world, this new capability has created a new way to access and compress knowledge. The internet and knowledge have been abstracted, and change is expected to accelerate exponentially in 2023; As we’ve reached the point with these technologies where we can’t distinguish the machines from humans on an emotional level, the newest generation of models is advancing towards emotional realism.
💹 AI Market Research
AI and ML will reach ~ $122.5 billion USD by 2022, at a compound annual growth rate of 37.7%. During 2023, the market is expected to reach ~ $166 billion USD. As a result, this would represent a compound annual growth rate of 21.4%. According to Stratview Research, the market is expected to grow at a CAGR of 38.4% between 2022-2023.
The demand for Artificial Intelligence took off during the 4th quarter of 2022, and it has continued into 2023, and it is likely to continue over the next few years as more startups are launched, venture capital is allocated, and use cases become more and more industry-wide, for each industry.
Increasing investment in AI and machine learning technologies, increasing demand for automated processes, and the growing popularity of AI-as-a-service are major drivers of this growth. Several other factors will also contribute to market growth in 2023, including improved AI and ML hardware, increased cloud computing capacity, and more open-source tools and initiatives, which we have seen firsthand in 2022 with the introduction of the public beta for Stable Diffusion text-to-image, image generation.
👾 Artificial Intelligence Companies To Watch In 2023
Many of the key AI and ML companies are currently private, but companies such as Apple, Google, IBM, and Microsoft are already using AI to solve a wide scope of pain points, both customer and business. In this section, we will review some of the companies in the space that are most likely to see massive growth in the coming years and decades.
⚛️ Stability AI: is an open-source platform that makes use of AI and machine learning technology to automate and enhance business operations. With a diverse community of over 20,000 developers and AI experts, Stability AI provides a range of services, such as an audio production tool, the Stable Diffusion model and the Dream Studio interface for text-to-image generation, and OPenBioML for biology research.
Their aim is to make AI and ML research democratic, to keep technology open source and accessible to all, due to the mounting concern that one group, organization, or government would have the greatest influence over AI IP.
⚛️ OpenAI: Open AI is a research laboratory and another important part of the AI research landscape, backed by Elon Musk and other knowledgeable technologists. OpenAI is devoted to creating artificial general intelligence (AGI) with the purpose of advancing digital intelligence in a way that is most advantageous to humanity overall, irrespective of the domain.
Among OpenAI’s activities are general algorithms, language generation, and robotics, which are some of the anticipated key areas for development with the recent launch of Chat GPT-3 . It is capable of producing human-like writing like never seen before.
Apart from NLP, OpenAi has also introduced a text-to-image generative AI model called Dall-e, Whisper a free neural network, and many more general-purpose solutions.
⚛️ DeepMind: DeepMind is a research institution that focuses on machine learning and artificial intelligence. It was established in 2010 as a subsidiary of Google Alphabet inc. Its mission is to use intelligence to push forward science and benefit humanity.
DeepMind’s long-term goal is to design and build artificial general intelligence (AGI) systems that can solve a variety of different problems. To test the AI’s capability to take action on its own, many of the early models were trained with popular video games. These programs learned how to play a total of 49 Atari games from scratch by analyzing the pixels and scores on the screen.
This led to the development of AlphaGo and AlphaZero, two programs that the company is best known for. The programs defeated some of the best Go players in the world. Go is an ancient Chinese board game that has been used to teach strategy and probability for centuries. By designing algorithms and techniques, DeepMind enables machines to think and learn more like humans. The computer learned to play the game without any human interference, all it referenced was the principles of the game, and was trained on thousands of previous games.
In addition to healthcare and energy efficiency, DeepMind’s technology has also been applied in a variety of fields and is expected to be applied more widely in the years to come, with major planned updates in 2023.
⚛️ TensorFlow: Released in 2015, TensorFlow is an open-source library for machine learning and artificial intelligence developed by the Google Brain team and licensed under apache. It is designed for deep neural network model training, but it can also be used for other tasks.
Engineers and researchers can build on top of TensorFlow using JavaScript, Java, Python, and C++, making it a platform with vast use cases.
TensorFlow has been employed by Google in many areas such as RankBrain, to improve the search results of the Google search engine, and by the healthcare sector with their DermAssist program to identify skin cancer. Additionally, it has been used in eCommerce to provide more accurate and personalized search results. These are just a few of the numerous applications of TensorFlow and its impact on the history of web 2.0.
⚛️ Microsoft: Microsoft is often not recognized as a leader in the AI space, yet just like Apple, Google, and others in the web2 world, it is driving the industry forward at a rapid pace. In Q4 2023, Microsoft stated a hefty $20 billion investment for its data science and AI departments, in addition to a multi-year, multi-billion dollar investment in OpenAI after ChatGPT shook the world in 2022.
Throughout its entire portfolio, the company has used AI and ML in various ways, ranging from Bing search optimization to Cortana, Microsoft’s virtual assistant that was previously available through Xbox. AI and machine learning are also heavily used by Microsoft’s cybersecurity and fraud detection teams to detect and respond autonomously to threats.
Additionally, Microsoft has released hardware-based sensors and computational photography over the last few years that leverage AI and ML heavily. The Skype protocol, Skype’s proprietary Internet telephony (VoIP) network, also uses machine learning to learn the difference between clean speech and noise to optimize bi-directional audio quality and noise cancellation.
In the tech space, if you think of a core product, AI and machine learning are most likely being used under the hood to enhance the user experience.
⚛️ Apple: Apple is not typically seen as a leader in the AI field, but they have been making strides in this area for its consumer products that support the computing needs of the AI-driven future. Their neural engine and Apple silicon are engineered to run applications that require the local device to manage data processes. This includes tasks such as image recognition, optimization, voice processing, speech recognition, and Siri. Each of these is powered by AI to ensure the optimal experience for the user.
I anticipate that Siri will take a giant leap forward in their voice assistant service in the coming years, prompted by the proliferation of ChatGPT and other language models. This will require OEMs to rethink their AI voice assistant strategies so as to include a more comprehensive offering.
AI and ML are also employed in Apple products to improve the user experience, going beyond the areas already mentioned. From video optimization to the noise-canceling function of the Apple AirPods, AI technology is present in numerous Apple products.
💥 📊 Areas of AI Expected To Grow In 2023
1️⃣ Natural Language Processing(NLP): NLP is the study of how computers interact with human language. Using large amounts of text and spoken data, patterns, trends, and relationships are identified. A wide range of applications uses NLP, from automated customer service to text generation and summarization.
2️⃣ Generative Adversarial Network(GAN): GANs generate synthetic data that is indistinguishable from real data by competing between a generator and a discriminator. In addition to improving the performance of machine learning models, GANs have been used to generate realistic images, videos, and audio, and are currently being employed for many of the generative AI consumer products that have taken the world by storm over the past few quarters, starting in 2022.
3️⃣ Automated robotic processes(RPA): RPA uses machines to perform tasks normally performed by humans. Automation of repetitive tasks and processes, such as data entry and customer service, is one of its applications. The benefits of RPA include reduced costs, improved accuracy and efficiency, and a better customer experience.
4️⃣ Deep Reinforcement Learning(DRL): DRLs are a subfield of machine learning inspired by how the brain learns. Using a DRL model, agents interact with simulated environments to learn how to accomplish a goal. Reward signals are generated by the environment, rather than by a teacher. Through trial and error, it effectively learns. With DRL algorithms, massive data sets can be analyzed to produce hyper-precise, or accurate, objectives/outcomes.
Video games, NLP processes, computer vision, education, transportation, finance, healthcare, and robotics are some of the use cases for DRL.
5️⃣ Neuromorphic Computing: Is an approach to computing based on the structure and function of the human brain. Any device that uses silicon to construct artificial neurons is called a neuromorphic system or chip – Neuromorphic computing is used in artificial intelligence, vision systems, head-eye systems, auditory processors, and robotics.
6️⃣ Neural machine translation(NMT): Using NMT, a set of procedures are used to predict the likelihood of a set of characters in a sequence. Text snippets, words, or entire documents can be included. In NMT, deep neural networks and artificial intelligence are used to train neural models for language translation. SMT (statistical machine translation) has been replaced by NMT (natural machine translation) in recent years because the latter provides better translation results.
However, many researchers argue that SMTs will remain relevant in certain cases because they provide more accurate outcomes. Consequently, companies are using hybrid machine translation techniques that combine SMT and NMT. You can read more about this hybrid approach in this article from Omniscien.com.
7️⃣ Deep Neural Network(DNNs): DNNs are a subset of machine learning and artificial intelligence and are based on algorithms that mimic the structure and processes of the brain to give computers intelligence. In the context of machine learning, there are use cases where the technology performs poorly. As an example, when dealing with unstructured data such as images, audio, and other types of unstructured data.
Until relatively recently, neural networks were limited by the amount of computing power they required, but improvements in how computers to process massive data sets have made them more affordable to train.
🌎🎖️Conclusion
With that, we’ve come to the end of our look at the AI and generative AI business trends for 2023. We hope you’ve gained a better understanding of the potential of these technologies and how organizations can leverage them to drive success. Thank you for joining us, and we look forward to seeing the amazing things AI can do in the coming years!
As a quick recap of what we reviewed in this post…
We started off by going over the generative AI application landscape. Next, we reviewed a brief analysis of market data for AI and ML between 2022 - 2023. We concluded with a review of the Artificial intelligence companies to watch in 2023, and the areas, technologies and models that are expected to grow in 2023.
👾 More Recent-Posts
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.economyblocked.com/Artificial-Intelligence-Business-Trends-Report/
|
[
{
"date": "2023/01/26",
"position": 47,
"query": "artificial intelligence business leaders"
}
] |
Four Ways Leaders Can Empower People for How Work ...
|
Four Ways Leaders Can Empower People for How Work Gets Done
|
https://www.microsoft.com
|
[
"Illustration The Tom Agency",
"Nicole Forsgren",
"Partner At Microsoft Research",
"Emily He",
"Microsoft Corporate Vice President Of Business Applications",
"Maribel Lopez",
"Founder",
"Principal Analyst At Lopez Research"
] |
In times of uncertainty, people are ready for software that helps them code their own solutions, and for artificial intelligence tools that let them focus on ...
|
FFraying supply chains. Economic headwinds. Changing expectations around hybrid work. The rapid transformations of the past few years have fundamentally reshaped work and life as we know them. It’s clear that the agility and resilience of every organization rest on a workforce empowered with tools that enable them to work more efficiently and flexibly than ever before. raying supply chains. Economic headwinds. Changing expectations around hybrid work. The rapid transformations of the past few years have fundamentally reshaped work and life as we know them. It’s clear that the agility and resilience of every organization rest on a workforce empowered with tools that enable them to work more efficiently and flexibly than ever before.
Download For True Digital Transformation, Prioritize Collaboration—and Autonomy
That shift isn’t about overburdening your teams or deprioritizing innovation. It’s about being more effective, enabling people to do their best work with processes and tools that reduce friction, unlock innovation and creativity, and reduce busywork to help every individual focus on the work that matters most.
To take stock of how people feel about the digital productivity tools they use today and those they need to succeed in the future, Microsoft surveyed 2,700 employees and 1,800 business decision makers (BDMs) in the United States, the United Kingdom, and Japan. We asked questions like, Do people feel empowered by the tools they currently have? Are teams equipped to collaborate effectively in a world of flexible work? Can new technology like AI and low-code and no-code tools help solve their challenges and open up new opportunities?
9 out of 10 people want simpler ways to automate daily tasks so they can focus on the work that matters.
The survey spanned a range of job functions and industries—from marketing, sales, and customer service to finance, supply chain, and IT. This group included hybrid employees: about two-thirds of those surveyed either work from home or only part time in the office. The results offer a window into how technology is helping—and hindering—people today, along with fresh insights into the tools and processes leaders should adopt to help people be more energized, empowered, and productive.
The survey findings point to four key principles that can guide business leaders in 2023:
Empower people to have more say when it comes to new technology initiatives
Use collaborative apps to stay connected and share information in the flow of work
Accelerate innovation by equipping anyone in the organization with low-code tools
Help people feel more fulfilled and engaged by implementing AI and automating busywork
1. Empower people to have more say when it comes to new technology initiatives
Today’s employees are hungry for better digital tools. 87% of employees believe pursuing digital transformation is more important now than ever before, but only half of them (54%) say they are among the decision makers when it comes to those efforts. (For BDMs that figure is 94%.) Respondents say their teams would benefit most from solutions that help them be more agile (84%), make information more accessible across the organization (86%), and allow them to automate tasks (86%)—freeing time to focus on work that matters.
At present, however, outdated technology—including different departments within an organization using different software—is creating silos that make it challenging for people to share information related to digital transformation goals (72%), and existing tools generate more administrative tasks and busywork (74%).
Employee Empowerment Stakeholders across the organization want employees to have a say in digital transformation initiatives. Chart showing that 84% of business decision makers and 79% of employees think it’s important to receive employee buy-in to guide a digital transformation to success. Illustration by The TOM Agency
These shortcomings point to a gap between what leadership and technology departments consider to be priority investments in business software and tools, and the actual needs of a workforce often dispersed across locations. While 84% of surveyed business decision makers say digital transformation projects remain a top priority, 61% of employees say they are not an integral part of that process. And 70% say that organizational policies limit their ability to proactively explore or implement digital solutions on their own.
“The saying is that technology is easy and people are hard,” says Nicole Forsgren, a partner at Microsoft Research. People, essentially, are the most important part of an organization, but they’re also the most complex. “If you remove all agency from people, if they can’t contribute, if they can’t make any decisions, it can be really discouraging.”
The result is a disconnect: whatever investments in digital solutions the organization is making, many individuals don’t have much say in the matter. People overwhelmingly want initiatives to shift from being led by the IT department to being led by people across the organization, with 85% of respondents agreeing that people across all departments need to be involved—not just IT or senior leadership.
“If you remove all agency from people, if they can’t contribute, if they can’t make any decisions, it can be really discouraging. ” Nicole Forsgren, partner at Microsoft Research
For leaders, having a system and process in place through which teams can push for new tools is key. Of one company that does this, Forsgren says, “They have an internal support structure with separate tiers—gold, silver, and so on—where workers can advocate for an expansion of tools, and also retirement of tools.”
Take action:
Get people involved with digital business investments: create a continuous feedback loop to inspire excellence.
Accelerate adoption of low-code tools to fuel innovation and help employees gain new skills.
2. Use collaborative apps to stay connected and share information in the flow of work
Flexible work is here to stay. Two-thirds (66%) of surveyed employees have the option to work either at a company location or remotely, with nearly all (91%) of those respondents working remotely at least one or two days a week.
As organizations navigate this new world of work, 85% of employees cited collaboration tools as one of the most necessary parts of their company’s digital transformation efforts. “Collaboration is a mindset,” says Emily He, corporate vice president of business applications at Microsoft. “People want to be able to collaborate with their colleagues and partners right then and there, whether they’re working on a customer situation or trying to resolve a supply chain issue. Collaboration capabilities need to be infused and embedded in everything we do.”
Integration Is Essential Instead of fragmented tools that don't integrate with day-to-day job functions, people want a single, integrated platform. Chart showing that 64% of employees agree the lack of integration between their organizations’ tools and processes makes it difficult to collaborate across teams. Illustration by the TOM Agency
At the same time, 59% of employees feel that the tools they use to collaborate do not align with how their teams prefer to work. The tools don’t integrate with day-to-day processes, which makes it difficult to collaborate across teams, according to 64% of employees, and nearly three out of four (72%) wish the tools they use to collaborate were compatible with one another, instead of being highly fragmented. At least 7 in 10 cite inaccurate data, the inability to access and share decentralized data, and teams working from different sets of data as key challenges their companies need to address.
“The future is going to be all about turning your ideas into something people can touch and use. ” Emily He, Microsoft corporate vice president of business applications
Compounding the problem, says Maribel Lopez, founder and principal analyst at Lopez Research, is the current hybrid nature of work itself. Collaboration tools, she notes, need to function seamlessly, whether an employee is at home or in the office or somewhere in between. And many people are not sitting at a desk in front of a computer. “If you’re in retail, people are roaming the floor serving customers,” she says. “The technology they carry has to allow them to share and access information in real time.”
Asked what would work best for them, nearly 9 in 10 respondents (86%) pointed to the same solution: a single, centralized platform or portal where teams can collaborate in multiple ways.
This solution would not only break down silos between people but also make it easier to access, share, and work together on data across the organization. This is especially crucial given the challenges organizations expect to face over the next year.
Take action:
Consider an audit of your organization’s current collaboration tools to identify gaps and areas for improvement.
Together with employees, develop KPIs for the ideal collaboration tool—a list of mandatories that reflect both employee and company needs.
Centralize and organize resources so that people are using consistent, current data for better efficiencies and integration.
Embed collaboration capabilities in the flow of work so people can work with colleagues, partners, and customers to efficiently solve problems and access contextual information from other systems.
3. Accelerate innovation by equipping anyone in the organization with low-code tools
With IT projects backlogged, underfunded, or always “just over the horizon,” no-code and low-code tools have taken center stage, allowing people to automate processes or even create their own apps with little or no coding, clear a path for innovation, and offer solutions to the other frustrations voiced in the survey.
Clothing giant H&M was recently able to use these tools to empower thousands of employees , from clothing designers to software engineers, to build the solutions they needed. “The future is going to be all about turning your ideas into something people can touch and use,” He says. “Typically, workers are on the receiving end of digital transformation. But we’ve entered a new phase, where they are taking matters into their own hands and using low-code and no-code tools to create new apps and experiment with new ways of engaging with customers, managing processes, or accessing business insights.”
Level Up with Low Code Low-code tools have empowered people to be self-sufficient on tasks that previously would have required a team of developers. Chart showing that more than 3 out of 4 respondents (77%) wish that they had more access to low-code/no-code tools or platforms to build digital solutions that help them achieve their goals. Illustration by The TOM Agency
Even so, more than 3 out of 4 respondents (77%) wish they had more access to low-code or no-code tools or platforms to build digital solutions that help them achieve their goals. And 84% believe that the ability to create custom-built apps in their collaboration tools that are tailored to the team’s needs would help them effectively collaborate.
“No-code and low-code tools are just simple and easy and quick,” says Forsgren, who cites their usefulness in handling all sorts of tasks, from automating workflows (for example, automatically messaging the next person who needs to review a document) to automating an invoicing process to using an Excel macro to create weekly reports.
Nearly 9 in 10 people with access to low-code tools said the tools help the organization automate repetitive or menial tasks, reduce costs, improve analytical capabilities, better manage data, and foster innovation. In Microsoft’s 2022 Low-Code Trend Report , more than 80% said that low-code tools have empowered them to be self-sufficient on tasks that previously would have required a team of developers. And nearly half (46%) of surveyed business decision makers strongly agree that the tools have allowed employees to play a more direct role in the organization’s digital transformation efforts.
Take action:
Develop a learning agenda for leadership on low-code/no-code tools to encourage broader adoption of the tools, with case studies from employees and first-hand users.
Create a center of excellence to provide training and enablement on low-code/no-code tools, share customer-built apps, build a community of practices, and provide centralized governance, compliance, and security.
4. Help people feel more fulfilled and engaged by implementing AI and automating busywork
As people look for better ways to be more collaborative in every aspect of their work, it comes as no surprise that they want to do away with repetitive tasks that disrupt time better spent engaging with others. Nearly 9 in 10 (85%) respondents want more automation capabilities integrated with collaboration tools, which they believe would help them spend more time on work that matters.
The AI Solution People say AI helps them work on what matters—and that they hope they can apply AI solutions to even more tasks and activities. Chart showing that 89% of respondents with access to automation and AI-powered tools agree they feel more fulfilled because they can spend time on work that truly matters. Illustration by The TOM Agency
Consider an average call at the typical contact center. “At many, many IT service desks or customer service centers, over 50% of their calls are related to password resets,” Lopez says.
Automating those sorts of mundane interactions has the power to substantially improve both the employee and customer experience—not to mention a company’s bottom line. “If you can find a way to allow agents to more easily help a customer, the customer is happier and you have greater employee retention,” Lopez says. “And that can save you hundreds and hundreds of dollars per employee.”
The same goes for AI. iFit, an international exercise equipment company, is using AI and machine learning tools, including Microsoft’s Supply Chain Center, to allow it to know where to allocate its inventory, which includes treadmills, exercise bikes, cross trainers, and rowers.
Previously, to get its products to customers within a few days, teams at the company used spreadsheets and pivot tables to determine which of its many micro-fulfillment centers should stock which items. That involved what Robert Critchley, iFit’s vice president of transportation and warehousing, calls a lot of “manual grinding” and even human error. “Historically, we used the newspaper: we said, ‘Okay, what did we sell there last week, what are we going to need there next week.’” Now, he says, “That tedious work is being done for us. And it’s being done very quickly. With AI we can gauge exactly which units are likely to sell in a particular area so we can position inventory at the nearest warehouse in advance of the demand. And it’s 70% more accurate than when we were doing it manually.”
“If you can allow agents to more easily help a customer, the customer is happier and you have greater employee retention. That can save you hundreds and hundreds of dollars per employee. ” Maribel Lopez, founder and principal analyst at Lopez Research
For now, these types of benefits are not leveraged by nearly one-third (30%) of employees surveyed. For those that do have access to automation and AI-powered tools, the vast majority (89%) feel more fulfilled because they can spend time on work that truly matters. They also agree that having the ability to automate tasks helps them work more seamlessly with other teams (88%), and they credit artificial intelligence features for improving problem solving (54%). As a result, 9 in 10 (89%) hope they can apply AI solutions to even more tasks and activities.
Take action:
Evaluate your company’s digital capabilities to determine where AI and automation can improve business processes.
Take steps to consolidate formerly siloed data, whether it’s stored in a data center onsite or in the cloud, empowering teams to easily access and share information, gain insights, and drive business action.
Explore AI-powered tools like Microsoft Dynamics 365 or Power Automate for automating menial tasks.
Key Takeaway
The survey findings are clear: people want digital productivity tools that allow them to cut out the busywork so they can focus on the real tasks at hand. They also want a say in how these tools are selected and implemented. Perhaps most of all, they want tools that are intuitive and easy to use, and that allow them to collaborate seamlessly and work efficiently—wherever “work” happens to be.
“The ultimate goal is for anyone in the organization to have access to all the information they need, and to be able to put it together in a way that they feel is useful—without understanding how to code, without understanding how to be a data scientist,” Lopez says. “That’s the future of work.”
| 2023-01-26T00:00:00 |
https://www.microsoft.com/en-us/worklab/four-ways-leaders-can-empower-people-for-how-work-gets-done
|
[
{
"date": "2023/01/26",
"position": 48,
"query": "artificial intelligence business leaders"
}
] |
|
Manage AI Bias Instead Of Trying To Eliminate It
|
Manage AI Bias Instead Of Trying To Eliminate It
|
https://www.oliverwyman.com
|
[] |
Solving for fairness isn't just difficult — it's mathematically impossible. Double Quotes. Business leaders must stop pretending that they can eliminate AI bias ...
|
There is no single standard or blueprint for ensuring fairness in AI that works for all companies or all situations. Teams can check whether their algorithms select for equal numbers of people from each protected class, select for the same proportion from each group, or use the same threshold for everyone. All of these approaches are defensible and in common use — but unless equal numbers of each class of people are originally included in the input data, these selection methods are mutually exclusive. The type of “fairness” chosen inevitably requires a trade-off, because the results can’t be fair for everyone.
| 2023-01-26T00:00:00 |
https://www.oliverwyman.com/our-expertise/insights/2023/feb/manage-ai-bias-instead-of-trying-to-eliminate-it.html
|
[
{
"date": "2023/01/26",
"position": 69,
"query": "artificial intelligence business leaders"
}
] |
|
4 in 5 workers say they're unlikely to apply for a job without ...
|
4 in 5 workers say they’re unlikely to apply for a job without salary range
|
https://www.hrdive.com
|
[
"Emilie Shumway"
] |
4 in 5 workers say they're unlikely to apply for a job without salary range · Dive Brief: · What HR pros need to know about AI in the workplace · What HR pros need ...
|
The trend of workers demanding salary transparency shows no signs of slowing down. According to
a recent survey from ResumeLab
| 2023-01-26T00:00:00 |
2023/01/26
|
https://www.hrdive.com/news/workers-demand-salary-transparency/641305/
|
[
{
"date": "2023/01/26",
"position": 41,
"query": "artificial intelligence wages"
}
] |
Generative AI in journalism | United Robots
|
Generative AI in journalism
|
https://www.unitedrobots.ai
|
[] |
Generative AI such as ChatGPT: News publishers are in the driver's seat. AI can help improve newsroom processes, but it cannot produce journalism.
|
Malmö, January 2023
“What do you think of ChatGPT in the context of journalism? Saviour or enemy? Will AI make or break the news industry?” This is certainly the question du jour in our industry.
We suggest it’s the wrong question. After seven years of providing automated articles to newsrooms (using a different type of AI), at United Robots, we’ve heard it all before. The fears of robots stealing jobs, of factually incorrect, untrustworthy content written in robotic language…
It turns out that – surprise, surprise – reality is never as black-and-white as fears suggest.
And in the case of this newer, generative AI (used in e g ChatGPT) – from where we stand – the scope is at once immense and limited. So, rather than focus on “saviour or enemy”, let’s take a step back and ask the question: “What can generative AI do for journalism, and what can’t it do?”
And – most importantly – what role should people play in this process?
Publishers are in the driver's seat
ChatGPT is just a tool – albeit a brand new, powerful tool with huge scope, but a tool nonetheless. It does not change the guiding principles of journalism – a fundamentally human activity.
Of course this type of AI can be used for nefarious ends, but so could the printing press. We are in the business of journalism and we should work out how the new tools can help us do that even better – as well as identify what risks may be involved.
In mid January (2023), Futurism broke a story that perfectly illustrates the latter. Publisher CNET is using AI to write short financial articles, but has not been open about it. Some of the aspects of this story shine a bright light on the choices publishers have, irrespective of what type of AI they use:
Transparency. We always recommend that AI written articles have a byline which makes it unequivocally clear that it was written by a robot, not a reporter. Transparency is critical internally as well as externally, and key for trust. In the case of the CNET story, the Verge reports that there seems to be a lack of transparency around the actual purpose of the content too. According to the Verge, the business model of CNETs relatively new owners Red Ventures, is about creating content designed to get high rankings in search, and then monetise the traffic. Their business model is not publishing journalism for people.
Accuracy. It goes without saying that any content published within a journalistic platform needs to be correct and reliable – whether it’s a groundbreaking investigative piece by a seasoned journalist or a small text about a local football match or financial news. AI tools always need to be controlled by journalists. And if you’re going to auto publish AI generated texts, you cannot use generative AI tools like GPT-3 / ChatGPT – see explanation in fact box (right).
| 2023-01-26T00:00:00 |
https://www.unitedrobots.ai/generative-ai-in-journalism
|
[
{
"date": "2023/01/26",
"position": 3,
"query": "artificial intelligence journalism"
}
] |
|
A news outlet's decision to write stories with AI backfires
|
Plagued with errors: A news outlet’s decision to write stories with AI backfires
|
https://www.cnn.com
|
[
"Catherine Thorbecke"
] |
The disclosure comes after Futurism reported earlier this month that CNET was quietly using AI to write articles and later found errors in one of those posts.
|
New York CNN —
News outlet CNET said Wednesday it has issued corrections on a number of articles, including some that it described as “substantial,” after using an artificial intelligence-powered tool to help write dozens of stories.
The outlet has since hit pause on using the AI tool to generate stories, CNET’s editor-in-chief Connie Guglielmo said in an editorial on Wednesday.
The disclosure comes after Futurism reported earlier this month that CNET was quietly using AI to write articles and later found errors in one of those posts. While using AI to automate news stories is not new – the Associated Press began doing so nearly a decade ago – the issue has gained new attention amid the rise of ChatGPT, a viral new AI chatbot tool that can quickly generate essays, stories and song lyrics in response to user prompts.
Guglielmo said CNET used an “internally designed AI engine,” not ChatGPT, to help write 77 published stories since November. She said this amounted to about 1% of the total content published on CNET during the same period, and was done as part of a “test” project for the CNET Money team “to help editors create a set of basic explainers around financial services topics.”
Some headlines from stories written using the AI tool include, “Does a Home Equity Loan Affect Private Mortgage Insurance?” and “How to Close A Bank Account.”
“Editors generated the outlines for the stories first, then expanded, added to and edited the AI drafts before publishing,” Guglielmo wrote. “After one of the AI-assisted stories was cited, rightly, for factual errors, the CNET Money editorial team did a full audit.”
The result of the audit, she said, was that CNET identified additional stories that required correction, “with a small number requiring substantial correction.” CNET also identified several other stories with “minor issues such as incomplete company names, transposed numbers, or language that our senior editors viewed as vague.”
One correction, which was added to the end of an article titled “What Is Compound Interest?” states that the story initially gave some wildly inaccurate personal finance advice. “An earlier version of this article suggested a saver would earn $10,300 after a year by depositing $10,000 into a savings account that earns 3% interest compounding annually. The article has been corrected to clarify that the saver would earn $300 on top of their $10,000 principal amount,” the correction states.
Another correction suggests the AI tool plagiarized. “We’ve replaced phrases that were not entirely original,” according to the correction added to an article on how to close a bank account.
Guglielmo did not state how many of the 77 published stories required corrections, nor did she break down how many required “substantial” fixes versus more “minor issues.” Guglielmo said the stories that have been corrected include an editors’ note explaining what was changed.
CNET did not immediately respond to CNN’s request for comment.
Despite the issues, Guglielmo left the door open to resuming use of the AI tool. “We’ve paused and will restart using the AI tool when we feel confident the tool and our editorial processes will prevent both human and AI errors,” she said.
Guglielmo also said that CNET has more clearly disclosed to readers which stories were compiled using the AI engine. The outlet took some heat from critics on social media for not making overtly clear to its audience that “By CNET Money Staff” meant it was written using AI tools. The new byline is just: “By CNET Money.”
| 2023-01-25T00:00:00 |
2023/01/25
|
https://www.cnn.com/2023/01/25/tech/cnet-ai-tool-news-stories
|
[
{
"date": "2023/01/26",
"position": 8,
"query": "artificial intelligence journalism"
}
] |
The Pros and Cons of AI Presentation Design Tools
|
The Pros and Cons of AI Presentation Design Tools
|
https://ethos3.com
|
[
"Muletown Digital",
"Amy Boone",
"I'M A Writer",
"Speaker",
"Professor Who Has A Passion For Language",
"Communication. I'Ve Been Teaching Undergraduate Classes For The Past Years. I Hold A Double-Major In English",
"Communication Olivet Nazarene University",
"An M.A. In Writing Depaul University In Chicago. I'M Currently Working On My Ph.D. In Rhetorics",
"Communication",
"Information Design At Clemson University."
] |
Vision” Sainsily says that “these tools open a path for imaginative people with no visual execution skills to create something visual.” By using text prompts, ...
|
For the past two weeks, we’ve been discussing how AI (artificial intelligence) is changing the presentation design game. Check out these stats about presentation design:
91% of presenters say they feel more confident when they have a well-designed slide deck
45 % find it difficult to design effective layouts
41% say it’s tough to find or implement good visuals
47% say they generally spend more than 8 hours on design
Does AI have the power to change some of these stats for the better? We hope so. Today, we want to wrap things up with a discussion of the pros and cons of using AI in your presentation design.
The Pros
1. AI Can Save You Time
One of the most time-consuming parts of designing a presentation slide deck is wading through thousands of images and templates to find what you want. Even more frustrating is when you’ve looked through those online banks and libraries only to come up with nothing. You simply can’t find what you want. In those moments, I often wish I was a graphic designer. I wish I had the skills to simply create on the screen what I am envisioning for my presentation. This is one of the huge pros of AI. Artist and XR design manager at Unity, Manuel “Manu.Vision” Sainsily says that “these tools open a path for imaginative people with no visual execution skills to create something visual.” By using text prompts, we can direct AI programs to create for us.
2. AI Offers A Creative Springboard
The blank screen or slide deck is one of the most intimidating parts of presentation design. AI reduces the time you have to spend staring at that blank screen. While we’ve yet to see an AI program that can produce a fully completed slide deck with no need for revision, there are plenty which can get you started. Check out our discussion of Beautiful.ai, Canva, and PowerPoint’s AI capabilities here. For example, Canva’s doc to decks AI generator won’t give you a full presentation, but it might offer an attractive color palette and font choice. PowerPoint’s Designer won’t read your mind, but it will give you several options for an attractive layout which you can mimic for the rest of your slide deck to create a cohesive, professional-looking presentation. One of the biggest pros of AI is that you no longer have to start designing from scratch.
The Cons
1. Program Glitches
While AI for presentations boasts some great pros, it is still a fairly new and developing technology. That means not all the kinks have been worked out of the programs yet. Here are just a couple examples of the issues that may make working with AI for your presentation frustrating:
In PowerPoint’s Designer, grouped items don’t work well.
In PowerPoint’s Designer, shapes are not yet compatible.
Designer also doesn’t read logos as distinct from other images when they are uploaded as picture files which can lead to weird layouts with cropped logos.
Canva’s text to image tool only produces results in square shapes, so they need to be cropped or altered to fit more traditional presentation sizes.
Many AI-generated images don’t offer attractive backgrounds. While the primary foreground image may be good, the background often is less aesthetically pleasing.
AI doesn’t have a way to understand the hierarchy of slide elements. It doesn’t know what is most important on the slide.
2. Things Get Lost in Translation
An AI generator is only as good as a few things:
the algorithms and searchable menu items that have been built into the program. In other words, the amount of “intelligence” developers structured the program to have.
the search terms, or prompts, that the user enters to pull back results.
As we all know, human communication isn’t a direct download of information. If I tell my husband a story of something that happened during my day, there is no possible way for him to experience, see, and understand the story exactly like I did. I can share it in the clearest terms possible, but he still reconstructs the story in his mind a little differently. Something always gets lost or changed in the encoding and decoding process. The same thing holds true for AI design. The chances of you pulling back the exact thing you want are pretty slim, if not impossible.
3. Copyright Issues
One of the major drawbacks with AI-generated images and presentations is the question of who owns the product. On one side of the copyright argument is the notion that we already mix creative elements in many ways. Sampling is part of the modern-day, technology-driven creative process. On the other side of the issue is the notion that AI technology can pull back music, artwork, photography, and more from skilled artists who should be compensated for their work and talent. It often takes a while for legislation to catch up with technology, so we’re watching to see how this develops. You can read more about AI copyright issues here.
All-in-all, AI is one more tool in the presentation design toolbox. Is it perfect? No. But it’s developing. And we are excited to see where this technology leads.
In the meantime, you may be hesitant to work with AI programs or you may have tried and found them lacking. If so, consider talking with one of our design experts. They have the skills needed to create a stunning slide deck that meets your specific needs. Check out more of the pros and cons of collaborating with a design expert here. Or get in touch with us now.
| 2023-01-26T00:00:00 |
https://ethos3.com/the-pros-and-cons-of-ai-presentation-design-tools/
|
[
{
"date": "2023/01/26",
"position": 81,
"query": "artificial intelligence graphic design"
}
] |
|
AI Logo Design: The Next Design Frontier?
|
AI Logo Design: The Next Design Frontier?
|
https://www.designity.com
|
[] |
Using AI to design your logos. ... But how can designers use this technology for logos? ... Well, in addition to AI Art Generators, there are now AI Logo Makers.
|
It’s a strange place here in 2023.
We have robots that sweep our floors, answer phones, and drive cars.
It’s so commonplace that we don’t even think twice about it.
We’re practically living like the Jetsons.
Technology is a definite advantage to living in the future and, every day, we’re using that new technology to make our lives a little easier than our parents’ lives were (technologically, anyway).
And for creatives like you, another way that technology is making your life a little easier is through AI and especially through AI Art Generators.
Designers and marketers everywhere find this AI technology to be another useful tool in their arsenal to help them complete their projects and get things done on time.
But how useful is it for branding and logo design?
If you’ve got a professional logo design project on your hands, is AI going to be the way forward from now on?
What are AI Art Generators?
An AI Art Generator is a sophisticated piece of software that can create an image based on a user’s text input or prompt.
Basically, you type up a description, like “Perfect Logo for Plumber” or “Tap Dancing Purple Alligator” and, depending on which generator you use, the computer will create one or several images based on your prompt.
It works using algorithms (usually written by artists) that direct the computer to not just follow a set of rules from your written prompt, but to “learn” a specific aesthetic by analyzing the thousands of images in its data bank.
It takes your prompt, combines it with the images it has stored, and generates new images that either match or are relevant to what you’ve typed.
It’s a very cool thing and if you’ve played around with one for a while, you’ve seen how interesting (and sometimes terrifying) the AI’s results can be.
Using AI to design your logos.
But how can designers use this technology for logos?
Well, in addition to AI Art Generators, there are now AI Logo Makers. These are a form of AI Art Generator that takes the technology one step further by using it to specifically create logos instead of abstract images and art.
Naturally, designers everywhere are harnessing this artificial intelligence tool.
Just a quick Google search will show you that there are many AI Logo Makers to be found out there, all capable of spitting out a sweet high-resolution logo in minutes.
They’re user-friendly too and most of them will give you a logo for free, or at least give you a set number of free uses before they charge.
Just type up a brief description into the free logo maker, answer a few questions to narrow down what you’re looking for, and the AI will generate one or several logos for you to choose from.
There are some pros and cons to this, of course. Let’s go over them now.
Pros: Using an AI Logo Maker is fast and easy, which is great if you have several logos to design and you’re in a time crunch.
All you need to do is type in a descriptor, answer a few prompts, and you have some logos to review with quite a bit of variation to choose from.
Most of them are free too, which is also pretty great.
Cons: Remember those prompts you have to answer? If you have no idea what you’re doing, that’s an easy part to mess up.
The prompts can include choosing between geometric shapes, colors, or icons. If you’re not a designer or don’t have a grasp on a client’s brand identity, it can be difficult to determine which of those to choose to best fit your client’s needs.
The logos created also lack originality. Sure, they’re great for quick, passable logos, but good logos require creativity and originality.
The best way to use AI logo makers.
So, while AI logo makers are very cool and can quickly generate passable logos, don’t expect the AI to do all of the work for you.
You’re a professional logo designer, after all! The technology works best when you’re harnessing it to inspire your own creativity.
If you’re feeling stuck or creatively drained, it can be very useful to fire up the AI to create a logo or two for inspiration.
Sometimes all it takes is seeing the right image to get your creative juices flowing and your head full of great logo ideas.
Or, alternatively, you can pick one of the images that were generated and make it your own. Just customize your logo using your client’s color palette and other brand visuals until you have a finished product that your client will love.
AI Logo Makers can definitely help inspire you, especially if you need something for a quick turnaround.
You can finish projects faster and quickly give your client a beautiful logo for their company, their social media pages, and all of their marketing collateral.
<div class="c-blog_comp-cta cc-component-2"><div class="c-blog_comp-cta-left"><div class="c-blog_comp-cta-left-wrap"><img src="https://global-uploads.webflow.com/61cdf3c5e0b8155f19e0105b/63695243d096983691046ac3_Potential-Creative.png" loading="lazy" alt="" class="c-blog_comp-cta-left-img"></div></div><div class="c-blog_comp-cta-right cc-dark"><div class="c-blog_comp-content"><div class="c-text-wrapper cc-mb-32"><div class="c-title-4 cc-bold"><strong>Like to work as a freelancer with consistent income?</strong></div></div><div class="c-text-wrapper"><div class="c-text-2">Designity's collaborative model is designed to give you all of the perks of being a freelancer without the income instability.<br></div></div></div><div class="c-blog_comp-wrapper"><a href="http://designity.com/creatives" target="_blank" class="c-button w-button"><strong>Join Our Creative Community</strong></a></div></div></div>
Can AI replace logo designers?
If you’re worried about all of your clients simultaneously handing you a pink slip and turning to AI instead of ever hiring a designer again, then you can relax.
The technology is very cool and it’s very sophisticated, but it’s not time to fear the robots just yet.
Sure, someone can whip up a free logo from an AI Logo Maker, but as we discussed earlier, you really do need to know what you’re doing and have a good eye for design to get nice-looking results.
And even then, the logos generated will be passable at best, nothing that screams originality and unique brand identity.
A company’s logo is a personal thing and it’s going to need that personal, human touch. As we touched on earlier, the AI might be cool, but it isn’t very original and it will never understand a target audience or how your logo can compare to competitors.
It takes a big ol’ human brain to do that and that’s something AI will never have (for now, anyway).
So, don’t pack your bags, designers, you are still very much in demand.
Have you used an AI Logo Maker before?
| 2023-01-26T00:00:00 |
https://www.designity.com/blog/ai-logo-design-the-next-design-frontier
|
[
{
"date": "2023/01/26",
"position": 91,
"query": "artificial intelligence graphic design"
}
] |
|
ChatGPT: How A.I. could impact the job market and employee skills
|
ChatGPT: How A.I. could impact the job market and employee skills
|
https://finance.yahoo.com
|
[
"Yahoo Finance Video",
"Fri",
"Jan"
] |
SINAN ARAL: It will displace jobs. It will create what's known to economists as skill-biased technical change, technical change that favors some ...
|
The team on Yahoo Finance Live discusses how ChatGPT and A.I. could impact jobs in some categories, including finance, journalism and education.
Video Transcript
DAVE BRIGGS: Is ChatGPT a jobs killer? Well, who better to ask than ChatGPT itself. The AI told me, quote, "It can potentially replace jobs that involve generating written content, such as writing news articles, product descriptions, or social media posts. It could also potentially assist with tasks such as customer service and technical support. However, it is important to note that ChatGPT is not intended to replace human workers but rather to assist them and improve efficiency."
If, however, you prefer a human answer to that question, here's one of the smartest humans we know, MIT professor and author Sinan Aral, who told us it's one of the greatest upheavals in the labor market we've seen in a long time, adding this.
SINAN ARAL: It will displace jobs. It will create what's known to economists as skill-biased technical change, technical change that favors some skills and complements some skills and substitutes for or competes with other skills. And every time in human history that we have experienced something like this, we've had to reskill and change our focus on what humans did and what machines did in order to create complementarities and increase welfare across the board.
DAVE BRIGGS: So if I'm in college, kids, I'm rethinking what my potential major might be based on what jobs might exist 10 years from now because, rest assured, ChatGPT is coming for your job. Even if it does not intend to, your bosses will wonder, can I replace each of these people with artificial intelligence? You saw what happened to the BuzzFeed stock.
SEANA SMITH: Oh, I saw.
DAVE BRIGGS: It's inevitable.
SEANA SMITH: It is inevitable. It's a little bit scary when we start to think about all of this and, of course, just what exactly jobs it is going to replace. In terms of the degree of that, the CEO of Automation Anywhere, he was at Davos weighing in on this. And of course, he is involved in AI, so maybe a bit biased here. But he was saying it could replace up to 70% of all the work we do in front of a computer, saying that up to 70% of that could be automated. That really puts it in perspective just in terms of how many jobs could be at risk.
And like, Dave, what you're saying, kids need to be thinking about-- kids that are in college, kids that are in high school. You have to have this in the back of your mind just in terms of what that space is going to look like 10, 15 years from now because, according to some estimates, 30% of US professionals are already using AI on a daily basis within their work. So it's starting to tick up there, just the popularity of it. Now we've got ChatGPT in it.
| 2023-01-27T00:00:00 |
https://finance.yahoo.com/video/chatgpt-could-impact-job-market-214624633.html
|
[
{
"date": "2023/01/27",
"position": 85,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 71,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 90,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 94,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 73,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 98,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 95,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 92,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 95,
"query": "ChatGPT employment impact"
},
{
"date": "2023/01/27",
"position": 97,
"query": "ChatGPT employment impact"
}
] |
|
Artificial Intelligence: Taking Over Jobs | 2023 Update!
|
Artificial Intelligence: Taking Over Jobs
|
https://www.perfectessaywriter.ai
|
[] |
Over the last 20 years, automation has taken away 1.7 million human roles. Yet research shows that this technology might generate up to 97 million new jobs by ...
|
Artificial Intelligence's Impact on the Job Market and Its Role in Creating New Jobs
It can be difficult to understand what is true and what is not true about AI and its potential effects on the job market.
Some people are saying that AI will cause mass unemployment as machines take over our jobs. Others are saying that AI will create new and better jobs. So which is it?
The truth is, we don't know for sure what's going to happen. But one thing is for sure - with or without AI, the job market is changing fast. That's why it's more important than ever to stay ahead of the curve and learn new skills.
This blog will explore the pros and cons of AI in the job market. As well as its role in creating new jobs.
So, stay with us till the end!
What is Artificial Intelligence?
Artificial Intelligence (AI) is a powerful field of computer science. AI strives to make machines capable of performing tasks typically done by humans. This includes visual perception, speech recognition, decision-making, and translation between languages.
AI is a blend of numerous disciplines such as computer science, robotics, engineering and many more. It has dramatically developed due to remarkable accomplishments in machine learning and other subfields of AI. This has enabled the automation of tasks that were once too complex or tedious for humans to complete. It is estimated that by 2030, over 60% of all occupations will be impacted by AI in some way.
There are two types of AI:
Weak AI : Is an artificial intelligence system designed to perform a specific task or handle specific data. It is programmed to act within a limited range and is not capable of adapting or learning from its environment.
: Is an artificial intelligence system designed to perform a specific task or handle specific data. It is programmed to act within a limited range and is not capable of adapting or learning from its environment. Strong AI: Is also known as artificial general intelligence (AGI). It is a type of AI system that is capable of learning and adapting to its environment. It has the potential to carry out a range of tasks, just as a human would. Strong AI systems are still in development, and many experts believe they will not be fully realized for several years.
Will AI Replace Human Jobs?
The dialogue regarding robotics and AI replacing human jobs is a multifaceted one. AI has a major impact on many industries, affecting the employment landscape in healthcare, and agriculture sectors. As AI continues to evolve, the demand for workers in robotic and software engineering is expected to grow exponentially.
Over the last 20 years, automation has taken away 1.7 million human roles. Yet research shows that this technology might generate up to 97 million new jobs by 2025!
Let’s be hopeful for the future job market!
What Types of Jobs AI Will Impact
AI is already impacting many different types of jobs. Its influence on the job market is likely to increase in the future. The World Economic Forum predicts that further 85 million jobs will be replaced by AI by 2025.
These job includes:
Manufacturing jobs: Automation is becoming increasingly common in manufacturing settings, leading to fewer human employees.
White-Collar jobs: AI is being used to automate mundane tasks and provide customer support in many white-collar jobs.
Administrative Roles: Automation can be used to streamline processes in administrative roles, such as data entry and scheduling.
Transportation & Logistics Jobs: Self-driving cars are becoming increasingly popular, leading to fewer human drivers in the transportation and logistics industries.
Healthcare Professionals: AI is being used to assist medical professionals with diagnostics and other tasks.
Financial Services: Automation is becoming common in the financial services industry, leading to fewer human employees.
Creative Jobs: AI is being used to create art and music, as well as author articles and write scripts for movies.
The Wide-Reaching Impact of Artificial Intelligence in the Job Market
AI has both pros and cons that must be weighed when considering its influence on the labor market.
Pros of AI in the Job Market
Some of the advantages of using AI tools in the workplace are given below:
Increased Efficiency: By automating daily operations, AI frees up time for employees to focus on more meaningful and specific tasks. AI can also handle high-volume data that is too time-consuming or complex for humans to process.
Improved Customer Service: AI technology can provide services that are faster, more accurate, and more personalized than ever before. AI chatbots can provide customers with access to 24/7 support. Thus, enabling customers to find quick answers or solutions to their queries and issues.
Cost Savings: AI can help businesses save money in many ways. AI-driven automation can help reduce labor costs, freeing up resources to focus on more strategic initiatives. AI also enables companies to optimize their supply chain and production processes, leading to cost savings.
Cons of AI in the Labor Market
The disadvantages of using AI tools in the workplace are given below:
Job Losses: AI is quickly becoming one of the most disruptive forces in the global economy. AI is expected to replace millions of jobs that are currently done by humans
Risk of Automation Bias: Machine learning algorithms can be biased if they are not programmed properly. This could lead to unfair discrimination in hiring and other decisions
High Cost of Implementation: AI technology can be expensive, which may make it out of reach for smaller companies. Additionally, there are often costs associated with maintaining and updating AI systems. As well as the cost of acquiring data and hiring personnel to work on projects
AI is Generating New Roles for Human Employees!
AI has revolutionized the workforce, creating a multitude of new roles for human employees.
These roles include:
AI Consultants
Data Analysts
AI Engineers
UX/UI Designers
Business Strategists
Cyber Security Specialist
Ethical Data Analyst
AI Essay Writer with Citation
AI Researchers
Quality Assurance Specialists
Policy Developers
AI Project Managers
Knowledge Architects
AI Marketers
Social Media Managers
AI Auditors
Technology Consultants
AI Product Managers
Technical Writers
Data Scientists
Robotics Engineers
Necessary skills to Thrive in the Era of Artificial Intelligence?
Individuals need to develop the skills that will enable them to thrive in this new era. Therefore, honing particular abilities can be the defining factor between success and failure in an AI-driven world.
Basic mathematics.
Strong verbal and written communication.
Creativity.
People management.
Emotional intelligence.
Critical thinking and problem-solving.
Finally,
AI is here to stay and is playing an increasingly prominent role in the job market. As technology advances, so does the need for traditional labor to collaborate with AI systems. This opens up a whole new world of potential career paths such as machine learning engineering and software development.
Companies that use AI will have an advantage over companies that don't. AI can help companies find and recruit talent more effectively, so they'll be able to stay ahead of their competition.
The future of AI is bright, so start exploring possibilities today, and be sure to keep up with industry trends. This way you may find your organization embracing a whole new level of growth!
| 2023-01-27T00:00:00 |
https://www.perfectessaywriter.ai/blog/ai-impact-on-job-market-and-its-role-in-creating-new-jobs
|
[
{
"date": "2023/01/27",
"position": 10,
"query": "automation job displacement"
},
{
"date": "2023/01/27",
"position": 8,
"query": "AI replacing workers"
},
{
"date": "2023/01/27",
"position": 8,
"query": "machine learning job market"
},
{
"date": "2023/01/27",
"position": 22,
"query": "AI job creation vs elimination"
},
{
"date": "2023/01/27",
"position": 16,
"query": "future of work AI"
}
] |
|
Restructuring with AI
|
Global Visionary Forum
|
https://www.gvforum.org
|
[] |
... job displacement and the need for comprehensive retraining and re-employment plans. ... automation of industries and job sectors, for instance, displaced workers.
|
Enhancing The Human Experience
The optimization of government services through the implementation of AI is one such application. Governmental entities can harness the power of AI algorithms to process and interpret data, resulting in more informed decision-making and subsequently, more efficient and effective policies and programs. Additionally, the utilization of AI-driven chatbots and virtual assistants can enhance citizen engagement and accessibility to government services, streamlining the process of obtaining benefits, services, and information and simplifying the navigation of bureaucratic complexities.
Another avenue of AI application is the automation of certain industries and occupations. While this can lead to increased productivity and efficiency, it also raises concerns about job displacement and the need for comprehensive retraining and re-employment plans. It is essential to acknowledge that the integration of AI can also give rise to new job opportunities in fields such as data science, machine learning, and software engineering.
In the realm of education, AI can be employed to personalize learning experiences and identify and address learning deficiencies. This can be achieved through the use of AI-powered tutors and adaptive learning software. Furthermore, AI can aid educators in identifying at-risk students and providing them with the necessary resources and support for academic success, resulting in a more efficient and effective educational system that caters to the individual needs of students.
In healthcare, AI can be utilized to improve patient outcomes and reduce costs. AI-powered diagnostic tools can aid in the early detection of diseases and assist physicians in making more accurate diagnoses. Additionally, AI can enhance the efficiency of clinical trials and drug development by identifying patterns in patient data and improving the speed and accuracy of medical research.
AI can also have a significant impact in the realm of crime prevention and law enforcement. AI-powered surveillance systems can aid in identifying criminal activity and facilitate rapid response to emergency situations. Furthermore, AI can analyze crime data and assist in identifying patterns and trends, leading to more effective crime-fighting strategies, including the prediction and prevention of crime and the improvement of the speed and accuracy of criminal investigations.
Impediments
However, the integration of AI must also be considered in relation to potential risks and downsides. One concern is the possibility of AI exacerbating existing societal inequalities, for example, AI systems may inadvertently perpetuate biases present in the data on which they are trained, leading to discriminatory outcomes. The automation of industries and occupations may also lead to increased economic inequality and job displacement. Additionally, there are concerns about the potential for AI to perpetuate biases based on race, gender, and other factors, as well as the impact of AI on the labor market and the economy.
Another concern is the potential misuse of AI for nefarious purposes, such as the development of autonomous weapons or the surveillance of citizens without their consent. Furthermore, the increasing dependence on AI systems raises concerns about the potential for cyber attacks and other forms of sabotage.
Progressive Solutions
Collaborative efforts between public and private stakeholders are vital in addressing the potential negative consequences of Artificial Intelligence. This can be achieved through various means such as establishing joint ventures between government agencies, private companies, and academic institutions to meticulously research, design, and execute AI in a way that is both efficacious and morally sound. Furthermore, public-private partnerships can be formed to provide educational resources, training and support to those who may be impacted by the automation of industries and job sectors, for instance, displaced workers.
A key aspect of collaboration is in the formulation of ethical principles for the utilization of AI. This can encompass the drafting of regulations and guidelines that guarantee that AI systems are developed and employed in a manner that is impartial, transparent, and accountable. This also includes guidelines for the acquisition and usage of data, as well as regulations to safeguard the privacy and rights of citizens.
Another crucial area of collaboration is in the establishment of AI governance structures and oversight mechanisms. This can comprise the creation of oversight bodies and regulatory agencies that are responsible for ensuring that AI systems are developed and utilized in an ethical and responsible manner. Additionally, public-private partnerships can be established to create industry-specific guidelines and best practices for the utilization of AI.
Conclusion
In conclusion, Artificial Intelligence has the potential to greatly enhance the human experience in various fields such as government services, education, healthcare, and crime prevention. However, it is crucial to address the potential negative consequences of AI, including exacerbating existing societal inequalities and the potential misuse of AI for nefarious purposes. Progressive solutions include collaboration between public and private stakeholders to research, develop, and implement AI in an ethical and responsible manner. This includes the formulation of ethical guidelines, the establishment of AI governance structures and oversight mechanisms, and the provision of educational resources, training and support to those affected by the automation of industries and job sectors. Through these efforts, we can ensure that AI is utilized in a way that benefits society as a whole.
January 27, 2023
Authored by: Dylan Boehm
| 2023-01-27T00:00:00 |
https://www.gvforum.org/our-research-analysis/technology-ai/restructuring-with-ai
|
[
{
"date": "2023/01/27",
"position": 57,
"query": "automation job displacement"
}
] |
|
How Artificial Intelligence is Transforming the Corporate World
|
How Artificial Intelligence is Transforming the Corporate World
|
https://www.petricorng.com
|
[] |
One of the most obvious ways that AI is being used in business is through the automation of routine tasks. ... job displacement and the need for workers to ...
|
How Does Artificial Intelligence Transformation Come About?
Artificial intelligence (AI) is rapidly becoming a mainstay of the modern business world. From automating mundane tasks to driving innovation and growth, AI is continually transforming how companies operate and compete. In this article, we'll explore some of the key ways that AI is being used in the business world and how it is shaping the future of work.
1. Automation Of Tasks
One of the most obvious ways that AI is being used in business is through the automation of routine tasks. By using machine learning algorithms, companies can train AI systems to handle a wider range of tasks, from data entry and analysis to customer service and support. This not only frees human workers to focus on more complex and creative tasks, but it can also help reduce errors and improve efficiency.
2. Data Analytics
AI is also being used to drive innovation and growth in businesses. For example, companies are using AI to analyze large amounts of data and identify trends and patterns that can be used to inform business strategy. This can help companies to make better decisions, identify new opportunities, and develop new products and services.
3. Customer Service
Another area where AI has a significant impact is in the realm of customer service. Companies are using chatbots and other AI-powered tools to provide personalized support and assistance to customers, improving the overall customer experience and increasing satisfaction.
What Does This Mean?
Of course, the increasing use of AI in business raises important questions about the future of work. While AI has the potential to transform industries and create new opportunities, there are also concerns about job displacement and the need for workers to adapt and upskill to remain competitive in the job market.
Overall, AI is having a profound impact on the business world, and its influence will only continue to grow in the coming years. As AI becomes more sophisticated and widely adopted, companies that are able to harness its power will be well-positioned to succeed in an increasingly competitive global marketplace.
| 2023-01-27T00:00:00 |
https://www.petricorng.com/ai-in-business-how-artificial-intelligence-is-transforming-the-corporate-world
|
[
{
"date": "2023/01/27",
"position": 58,
"query": "automation job displacement"
},
{
"date": "2023/01/27",
"position": 98,
"query": "future of work AI"
}
] |
|
5 Striking Examples of The Capabilities of Artificial Intelligence
|
AI in Action: 5 Striking Examples of The Capabilities of Artificial Intelligence
|
https://www.thisisnotfinancialadvice.co.uk
|
[
"Laurence Livsey"
] |
Job displacement: AI-powered automation may lead to widespread job displacement, as machines can perform many tasks more efficiently than humans. This could ...
|
Artificial intelligence (AI) is a rapidly developing field that has the potential to change the way we live and work. As an avid chess player, I first became hyper-aware of AI in 2017 when I came across AlphaZero - Google DeepMind’s chess playing artificial intelligence. I remember being astonished at what I saw.
What made AlphaZero so impressive is that it was able to teach itself how to play chess in just four hours, without any prior knowledge of the game. It was able to do this by using a technique called reinforcement learning, which involves training the algorithm by playing against itself. As it played more games (millions more), it was able to improve its own chess skills and ultimately become an order of magnitude better at chess than anything (or anyone!) that came before it.
AlphaZero was put to the test against the world's best chess engine at the time, Stockfish, developed by expert chess players over decades, in a 100-game match in 2017. The result? 28 Wins, 72 draws, and no losses for AlphaZero. Not only that, but it was able to demonstrate its dominance and superiority with an artistic elegance.
The success of AlphaZero is a testament to the power of AI, and it raised many questions about the future of the field at the time. For example, if an AI algorithm can teach itself how to play chess in just four hours, what other tasks could it be capable of performing? How well would AI adapt to the non-determinism of the real world? Could AI be used to solve complex scientific problems or help us to understand the mysteries of the universe?
The possibilities are endless, and it is exciting to think about what the future holds for AI. But it's also important to consider the ethical implications of such powerful technology and ensure that it's used responsibly. In this article, I am going to dig into four other striking examples of AI in action that have taken hold since, and pose some questions about what the future of AI has in store.
First, the one on everyone’s lips the last couple of months:
ChatGPT
The launch of chat GPT, a large language model developed by OpenAI, is another example of the disruptive power of AI. This model has the ability to generate human-like text, making it useful for a wide range of applications such as content creation, idea generation, and language translation.
The outputs from this AI are truly striking, and it’s no surprise that ChatGPT has taken the world by storm, garnering 1M users in just 5 days. To put that into perspective, it took Netflix 40 months to achieve this goal, Twitter over two years, and Spotify 150 days. Even instagram took 2 and a half months to reach this milestone.
For a taste of the kind of things ChatGPT can do, take a look at this motivational letter, for a bit of an insight into ChatGPTs emotional and human understanding:
When people think of the notion that “AI will make all of us redundant”, people typically think of the factory worker, data entry clerk, or similar. What’s becoming clear now is that no-one is safe! Not even CEOs, accountants, or management consultants.
The model's ability to understand and respond to natural language inputs makes it a powerful tool for businesses everywhere when implemented effectively.
Here’s a couple more examples of me bouncing some ideas around. You’ll see immediately that the answers are grounded in clarity and logic, and are immediately actionable.
Even software engineers, will be finding that AI will be playing a bigger role in their life, as Chat GPT is already writing, checking, and optimising code in multiple programming languages.
One of the most exciting potential applications of chat GPT is in the field of education. Imagine having a personal tutor that can understand your questions and provide tailored responses, or a learning platform that can generate personalised practice exercises and quizzes. This technology could also be used to create virtual learning environments, which could make education more accessible to people in remote or under-served areas.
Meanwhile, Microsoft are eyeing up a $10B dollar investment in OpenAI (the developer of ChatGPT), with many speculating they will use the deal to accelerate their development in AI, and potentially revolutionise their search engine, Bing, to create a serious rival to google. Could this be the breakthrough that is needed to break google’s grip on our internet searches?
The deal will see Microsoft take a 75% share of profits after the initial partners receive their investment back. Uniquely though, OpenAI is in fact a non-profit company. So beyond returning an agreed profit cap to investors, eventually profits will go solely into the continued development of OpenAI.
Recommendation Engines
A less visible but equally striking application of AI has been taking a hold of social media over the last decade - the rise of the Recommendation Engine.
Artificial intelligence is being widely used by companies like Netflix, TikTok, Instagram, YouTube, and Shein to improve their recommendation engines. These recommendation engines use a variety of techniques such as collaborative filtering, natural language processing, and machine learning to analyse user data and make personalised recommendations to users.
TikTok uses AI to recommend content to users based on their engagement history. The data is so vast in recent years that it is no longer simply looking at likes, shares, comments, or followers. It’s looking at it all. How many milliseconds you look for, which thumbnails generate the most engagement, pretty much every way you interact with social media content is being recorded and analysed by AI. By using this rich data, TikTok's algorithm can make recommendations that are more likely to be relevant to each viewer - keeping them engaged, and monetised through ads.
Similarly, Instagram, Netflix and YouTube all use AI-powered recommendation engines to show users content that is relevant to their interests.
Finally, Shein, a Chinese-owned eCommerce clothing platform, uses AI to recommend products to their customers based on their browsing history, purchase history, and other data. Shein are famous for using data and AI to generate new clothing ideas, and release 1000s of these new items at scale each day.
By analysing data from a huge volume of people, and thousands of product lines, Shein's algorithm can make personalised product recommendations that are tailored to each customer's preferences and interests - again, engaging and monetising them more. In this case the narrow domain expertise of recommending clothing helps the algorithm excel at the task even more.
Two things to note that recommendation engines rely on heavily.
They need a huge amount of data : To become the addictive, all knowing, powers that be today on the big social media platforms, these algorithms feed and live off of data. To maximise their output, the data needs to be big, and high quality. Big Data is a vital developing industry for the enablement of AI. Along with companies that provide the cloud infrastructure and computing power to store, access, and analyse this data.
Diversity of content and recommendations: They also need a large and varied universe of things to recommend in the first place, to truly generate the depth and richness in the machine learning that recommendation engines go through.
This is how social media giants like TikTok and Instagram have created such powerful recommendation engines - they have more data than anyone else from their apps, and their user generated content is in endless supply, giving the machine learning algorithms all they need to discover what to show you next.
AI is also helping social media companies in another way. With AI enabled ad targeting, the social media companies are able to better target advertisements. With the effectiveness of ads increasing, companies are increasingly willing to pay more for ads, driving up advertising earnings across big tech companies like Meta and Google over the last decade.
This is being achieved through the use of advanced machine learning algorithms that can analyse large amounts of data to identify patterns and make predictions about consumer behaviour. By using this data, companies can target their ads to specific segments of the population, increasing the chances of conversions and reducing the cost of advertising. In recent years though, the advertising industry has moved beyond this, into a state where, after a sufficient testing period, AI can improve or even outperform the targeting that is being originally set by the advertisers.
One of the key companies involved in this disruption is Google. Google's AI-powered ad platform, Google Ads, uses machine learning to help businesses target their ads to specific audiences. It uses data from a user's search history, browsing history, and location to show ads that are more likely to be relevant to them. Google's AI also helps to optimise ad campaigns by adjusting bids, placements, and targeting in real-time to maximise returns on ad spend.
Some would argue that more relevant ads for users is a good thing, but others would argue that its influence and power make it something to be weary of - in fact over the last several years there has been major privacy concerns and pushback from the general public.
Image Recognition
AI is now being used for image recognition in a wide range of applications, including object detection, facial recognition, and image classification. These applications make use of machine learning algorithms that can analyse images and extract useful information from them.
One of the most popular applications of image recognition is object detection, which involves identifying specific objects within an image or video. This technology is used in a variety of fields, including self-driving cars, surveillance, and retail. Companies like NVIDIA, Waymo (an Alphabet subsidiary), and Tesla use object detection technology in their self-driving cars to identify and respond to objects in the environment, such as pedestrians, other vehicles, and traffic signals.
Another popular application of image recognition is facial recognition, which involves identifying people in an image or video by analysing facial features. This technology is used in a variety of fields, including security, marketing, and entertainment. Companies like Face++, Microsoft (Face API), and Amazon (Amazon Rekognition) are using facial recognition technology in their products and services to improve security and personalisation.
With the further development of sensing and vision systems, it’s easy to imagine a world where surveillance becomes so powerful that security cameras can identify individuals and continually monitor their movements and activities.
Robotics
Robotics and AI are closely related fields, as AI provides the intelligence and decision-making capabilities that robots need to function autonomously.
One of the most popular applications of AI in robotics is in autonomous vehicles, such as self-driving cars and drones. These vehicles use AI-powered navigation systems to navigate their environment, avoid obstacles, and make decisions about how to reach their destination. Companies like Waymo, Tesla, and Baidu are at the forefront of developing self-driving cars and drones, using AI and machine learning algorithms to enable them to navigate safely and efficiently.
Another popular application of AI in robotics is in industrial automation. In this field, robots are being used to perform tasks that are dangerous or difficult for humans, such as welding, painting, and assembly. These robots use AI-powered systems to analyse their environment and make decisions about how to perform their tasks.
AI is also being used in service robots, such as robots that are used in retail, hospitality, and healthcare. These robots use AI-powered systems to understand and respond to natural language inputs, making them more capable of interacting with humans - and even capable of entertaining them.
As with several of the other AI applications I have shown here, Robotics also has a dark-side. Having seen the way that AI has excelled at thought-tasks, it’s easy to imagine a scenario where robotics and autonomous air vehicles become so advanced that they can dominate any military force which isn’t enabled by AI. If AI does indeed become this powerful, and ends up in the control of the wrong hands - dystopian scenarios are bound to happen.
Where do we go from here?
The future of AI looks promising and has the potential to bring about significant changes in many different fields. But as has been echoed throughout this article, the potential for abuse in the wrong hands is huge. The ethics and morality of the use of AI will continue to become an emerging and important issue of the day, as this technology and its applications evolve.
There are several moral and ethical considerations, including:
Bias: AI systems can perpetuate and even amplify societal biases if the data used to train them is biased. This can lead to unfair or discriminatory decisions.
Privacy: The collection and use of personal data by AI systems raise concerns about privacy and the protection of personal information.
Autonomy: As AI systems become more autonomous, there are questions about how responsible and accountable they should be for their actions.
Transparency: As AI systems become more complex, it can be difficult to understand and explain their decision-making process. This can make it difficult to trust the decisions made by the AI system.
… and several dystopian scenarios that could develop if AI got into the wrong hands or became an unfair advantage that was only available to the wealthy or elite:
Widening of the wealth gap: AI-powered automation may lead to increased economic inequality, as the wealthy gain access to advanced AI technologies that can automate their businesses and create new opportunities, while the less fortunate lack access to these technologies.
Job displacement: AI-powered automation may lead to widespread job displacement, as machines can perform many tasks more efficiently than humans. This could lead to mass unemployment and social unrest.
Loss of privacy: AI systems that are controlled by the wrong people may be used to collect and exploit personal data on a large scale, leading to a loss of privacy for the general population.
Weaponisation: AI systems may be weaponised to target specific groups or individuals, leading to large-scale human rights violations.
Social manipulation: AI systems that are controlled by the wealthy or elite may be used to manipulate public opinion and influence elections, leading to loss of democracy
All these possibilities need to be considered by governments, regulators, and responsible AI developers, to ensure that AI brings about positive change in society, and not destruction.
For AI to thrive, it needs the following conditions:
High-quality data: AI systems need high-quality and diverse data to train on. This data should be free from bias and accurately represent the problem that the AI system is trying to solve.
Robust algorithms: AI systems need robust algorithms that can handle complex data and make accurate predictions.
Strong computational power: AI systems require significant computational power to operate. This includes not only the computational power of the system but also the infrastructure to support it.
Human oversight: AI systems should be designed with human oversight in mind, to ensure that the decisions made by the AI system align with human values and ethics.
Transparency: AI systems should be transparent and explainable, so that their decisions can be understood and trusted.
But even with these conditions, there are still some big limitations on AI.
Limited domain expertise: AI systems are typically designed to excel in a specific domain or task. They may not perform well in tasks outside of their domain expertise.
Computational power: AI systems require significant computational power to operate. This can be costly and may limit the deployment of AI in certain environments.
Lack of common sense: AI systems do not possess the common sense that humans have, which can limit their ability to understand and respond to certain situations. Take this riddle for example. All that computing power and intelligence, yet it can’t answer a simple riddle. It was painful.
Positive Predictions
While it’s easy to think of dystopian scenarios … there are also an incredible number and variety of scenarios that could bring tremendous good to the world.
Although it is difficult to make definitive predictions about AI in the next 10 to 20 years, there are some possible developments that we can be pretty confident and excited about:
Advancements in natural language processing: AI systems are likely to become more advanced in their ability to understand and generate human-like language, allowing for more natural and seamless human-computer interaction.
Development of more advanced autonomous systems: AI systems are likely to become more autonomous and capable of performing complex tasks with minimal human supervision. This could include self-driving cars, drones, and robots.
Advancements in healthcare: AI systems are likely to become more sophisticated in their ability to analyse medical data and make accurate diagnoses, leading to improved patient outcomes.
Development of AI-powered virtual assistants: AI-powered virtual assistants are likely to become more advanced in their ability to understand and respond to human input, leading to more natural and efficient human-computer interaction.
Advancements in the field of robotics: AI will likely play a crucial role in the development of advanced robots that can perform a wide range of tasks, from industrial automation to service robots.
Advancements in security: AI will likely play a crucial role in the development of more advanced security systems that can detect and respond to threats in real-time.
The overall hope for AI, is that it helps the human race to be more productive and economically successful, improving the quality of life for large segments of the population, and bringing people out of poverty.
So what do I think?
I believe that AI will bring huge productivity gains and quality of life improvements to the human race in the not too distant future, but it would be naive to think that it will never be abused. I see AI abuse as an unfortunate certainty which the world will need to deal with at certain points in the future with global collaboration and regulation of the dangerous aspects of this technology. I also firmly believe that AI will create or strengthen some of the most valuable companies of the future.
Does that mean that AI startups will all be smash hits? Of course not, like any other emerging technology, there will be winners and losers. The challenge of finding the best is one we can leave for venture capitalists (or AI?) to solve.
| 2023-01-27T00:00:00 |
https://www.thisisnotfinancialadvice.co.uk/p/ai-in-action-5-striking-examples
|
[
{
"date": "2023/01/27",
"position": 83,
"query": "automation job displacement"
}
] |
|
The expansion of Artificial Intelligence - Talon
|
The expansion of Artificial Intelligence
|
https://oakparktalon.org
|
[
"Neel Vats"
] |
This has led to concerns about job loss and economic displacement, but it has also led to the creation of new, high-skilled jobs in the field of AI development ...
|
Artificial intelligence has had a significant impact on today’s world, affecting various aspects of our daily lives, from the way we communicate to the way we conduct business. The rapid advancements in AI technology have opened up a world of possibilities and opportunities, but they have also raised important ethical and societal questions.
One of the most obvious ways in which AI has impacted our lives is through the proliferation of smart devices and virtual assistants, such as Amazon’s Alexa and Google Home. These devices have made it easier for people to access information and complete tasks, from setting reminders to ordering groceries, without the need for human interaction. This convenience has led to an increase in the use of AI-powered devices in homes and businesses, and many experts predict that this trend will continue in the coming years.
AI has also had a significant impact on the workforce. According to Morgan Stanley, the use of AI-powered automation and robotics has increased efficiency and productivity in many industries, leading to a decrease in the need for human labor in certain tasks. This has led to concerns about job loss and economic displacement, but it has also led to the creation of new, high-skilled jobs in the field of AI development and deployment. Additionally, AI-powered tools such as machine learning algorithms have been used to analyze vast amounts of data, leading to new insights and discoveries in fields such as medicine and finance.
One of the most promising areas where AI is making an impact is in healthcare. AI-powered tools such as machine learning algorithms have been used to analyze medical images and assist doctors in making diagnoses. They have also been used to identify patterns in large medical datasets, leading to new discoveries and treatments for diseases. Additionally, AI-powered robots have been used to perform surgeries with a high degree of precision, leading to faster recovery times for patients.
However, with the rapid advancements in AI technology also come important ethical and societal questions. One of the main concerns is the potential for AI to perpetuate and even amplify existing biases and inequalities. For example, if the data used to train an AI system contains biases, the system may make decisions that are unfair or discriminatory. Additionally, there are concerns about the impact of AI on privacy and security, particularly with the increasing use of AI-powered surveillance and facial recognition technology.
Another concern is the potential for AI to outsmart humans in the near future. This is known as the “singularity” scenario, where AI surpasses human intelligence and becomes self-aware, leading to potential consequences that we can’t predict or control.
AI has had a significant impact on today’s world, affecting various aspects of our daily lives. The rapid advancements in AI technology have opened up a world of possibilities and opportunities, but they have also raised important ethical and societal questions. It is crucial that we continue to research and develop AI responsibly and ethically, taking into account the potential impacts on society and working to mitigate any negative consequences. This will ensure that the benefits of AI are realized while minimizing any risks and that the future of AI is inclusive, fair and equitable for all.
| 2023-01-27T00:00:00 |
2023/01/27
|
https://oakparktalon.org/15955/opinion/the-expansion-of-artificial-intelligence/
|
[
{
"date": "2023/01/27",
"position": 93,
"query": "automation job displacement"
}
] |
Well Shit: Apparently These Are The Jobs That Could Soon ...
|
Well Shit: Apparently These Are The Jobs That Could Soon Be Replaced By Artificial Intelligence
|
https://www.pedestrian.tv
|
[
"Alexandra Koster",
".Wp-Block-Post-Author Box-Sizing Border-Box Display Flex Flex-Wrap Wrap .Wp-Block-Post-Author__Byline Font-Size Margin-Bottom Margin-Top Width",
".Wp-Block-Post-Author__Avatar Margin-Right .Wp-Block-Post-Author__Bio Font-Size Margin-Bottom .Wp-Block-Post-Author__Content Flex-Basis Flex-Grow .Wp-Block-Post-Author__Name Margin"
] |
“Certain jobs in sectors such as journalism, higher education, graphic and software design — these are at risk of being supplemented by AI.” Advertisement. And ...
|
If you’re anything like me and have a very limited understanding of robot capabilities outside of I, Robot, Blade Runner, and Ex Machina, you’ll know that human = good, machine = bad.
In this week’s edition of Robots Taking Over The World, experts have revealed the jobs most at risk of being replaced by artificial intelligence — and we might as well just pack it up now.
In bad news for journalists (hi), software developers, finance bros, graphics designers, and teachers, your job is probs going to be replaced by a robot in the near future. I’ve seen enough dystopian movies to know that this is obviously going to end up perfectly fine with robots absolutely NOT turning on humanity (honestly, can’t blame them).
The conversations come after the launch of ChatGPT last November — a wildly intelligent chatbot that’s free to the public. ChatGPT can write emails, essays, poetry and songs, pen entire articles, give you a brand new resume, solve tricky maths problems and generate lines of code. It can even give you relationship advice. Is there anything she can’t do? Slay.
And while some of us have just been obliviously living it up and getting the AI program to write new songs in the style of Nick Cave, we should actually be waaaay more concerned about this new tech than we are.
“AI is replacing the white-collar workers. I don’t think anyone can stop that,” Pengcheng Shi, associate dean in the department of computing and information sciences at Rochester Institute of Technology, told the New York Post.
“This is not crying wolf. The wolf is at the door.”
Chinmay Hedge, a computer science and electrical engineering associate professor at New York University, warned The Post about the jobs most likely to get the boot.
“Certain jobs in sectors such as journalism, higher education, graphic and software design — these are at risk of being supplemented by AI.”
And as a journalist and someone with half of a teaching degree, this is absolutely fantastic news.
Education
There’s already been lots of chat about how the technology will impact schooling, with ChatGPT already seeing students cheat and literally have the bot write entire essays or assignments (tbh, you have to admire the resourcefulness).
The program has already been banned in NSW, Queensland, and Tasmanian public schools.
But it’s not just impacting students — it’s also potentially making the roles of teachers — TEACHERS!!! — obsolete, with Shi arguing that it can already be used to teach classes.
“Although it has bugs and inaccuracies in terms of knowledge, this can be easily improved. Basically, you just need to train the ChatGPT,” Shi continued.
Shi and Hedge maintain that university-level courses will need a physical (read: non-robot) teacher for the foreseeable future, but did suggest that, in theory, ChatGPT could be your new professor and literally teach classes.
Software Engineering
In proper sick fuck news, software engineers, the people who are the literal parents and CREATORS of ChatGPT, are likely to see their jobs impacted by this new tech, with Hedge warning that website designers and engineers responsible for relatively simple coding are at risk of saying ciao to their jobs.
“I worry for such people. Now I can just ask ChatGPT to generate a website for me — any type of person whose routine job would be doing this for me is no longer needed,” Hedge told The Post.
Essentially, smartypants ChatGPT has the ability to draft code to build sites and other pieces of IT. I’m not a tech dude, but that sounds like very bad news.
“As time goes on, probably today or the next three, five, ten years, those software engineers, if their job is to know how to code … I don’t think they will be broadly needed,” Shi said.
Finance
Bad news, finance bros. You’re not exempt.
Shi predicts that Wall Street could see many jobs being punted in the coming years and replaced by our new overlord, ChatGPT.
“I definitely think [it will impact] the trading side, but even [at] an investment bank, people [are] hired out of college and spend two, three years to work like robots and do Excel modelling — you can get AI to do that,” he explained. “Much, much faster.”
That said, Shi explains that humans will still be needed to make crucial financial and economic decisions, while the data sheets are likely to be yeeted into ChatGPT land.
I can already hear the simultaneous screams of a thousand trust-fund babies, sobbing into their boat shoes.
Graphic Design
But even the arts are not immune. SAD.
ChatGPT’s older sis, DALL-E (also developed by OpenAI), is a tool that essentially generates digital images from user-generated prompts.
“Before, you would ask a photographer or you would ask a graphic designer to make an image [for websites]. That’s something very, very plausibly automated by using technology similar to ChatGPT,” Hedge said.
Here’s one I prepared earlier, dubbed “Absolute RATBAG, ChatGPT, stealing the jobs of Pedestrian TV staff who are very hot and good-looking.”
I, for one, welcome our new rat overlords.
Journalism
And of course, what’s a story about robots STEALING our jobs without them coming for PTV staff and journalism as a whole?
“Copy editing is certainly something it does an extremely good job at. Summarising, making an article concise and things of that nature, it certainly does a really good job,” Hedge said. ChatGPT is also said to be very good at designing its own headlines, so RIP to the entire Pedestrian roster.
But there’s one silver lining we can at least bask in. The tool isn’t very good at fact-checking.
“You can ask it to provide an essay, to produce a story with citations, but more often than not, the citations are just made up,” Hegde continued. “That’s a known failure of ChatGPT and honestly we do not know how to fix that.”
Below, I asked THE ChatGPT about how it felt about stealing my job. Very meta.
“It is possible that ChatGPT or any other language generation models could be used to assist with certain tasks in journalism, such as generating news summaries or writing simple news articles,” ChatGPT informed me.
“It is unlikely that these models will fully replace human journalists as they lack the ability to understand context and emotions, to report, to research, and to verify the information.”
Turns out, my inclination towards being a drama queen and crying over insects drowning in pools is GOOD NEWS when it comes to the journalism world as it gives me the ability to understand human emotions, which ChatGPT, a robot, surprisingly does not have.
So there you have it — the world isn’t just the closest to ending that it’s ever been, but on the way there, we’ll be taught by sexy robot professors, see the exodus of thousands of finance bros, and the entire Pedestrian TV roster to replaced by hotter, more mechanic versions of ourselves. Love that for us.
| 2023-01-27T00:00:00 |
2023/01/27
|
https://www.pedestrian.tv/news/artificial-intelligence-replacing-jobs-chatgpt/
|
[
{
"date": "2023/01/27",
"position": 38,
"query": "AI replacing workers"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.