Category: Artificial Intelligence

In view of a new law regulating artificial intelligence, the head of OpenAI had threatened to withdraw from the European market. Today, the ChatGPT operator has rowed back.

OpenAI now apparently has no plans to withdraw from the European Union (EU). “We are happy to continue to operate here and of course have no plans to leave Europe,” wrote Sam Altman, co-founder and CEO of ChatGPT, on Twitter today. He thus reversed his threat from Wednesday to turn his back on the European market in view of the planned regulations for artificial intelligence (AI).

EU will not be intimidated

“The current draft of the EU AI law would be over-regulation,” Altman had criticized. Yesterday, however, the head of the Microsoft holding was already more conciliatory. “AI should be regulated,” he said at a discussion event at the Technical University (TU) in Munich. “We have called for this.” There are also approaches in Europe that are quite good.”But we need more clarity.” One should wait and see how AI develops further and only then should the state intervened.

His threat to leave Europe had drawn criticism from EU industry chief Thierry Breton and a number of other legislators. Altman had spent the past week traveling Europe, meeting with top politicians in France, Spain, Poland, Germany and the UK to discuss the future of AI and the progress of ChatGPT. He called his tour a “very productive week of conversations in Europe about how best to regulate AI.”

Responding to Altman’s tweet, Dutch MEP Kim van Sparrentak, who worked closely on drafting the AI ​​​​rules, told Reuters today that she and her colleagues must stand firm against pressure from tech companies. “I hope we will continue to stand firm and ensure that these companies have to comply with clear commitments on transparency, safety and environmental standards,” she said. A voluntary code of conduct is not the European way.”

Artificial Intelligence (AI) Act in its final stages

In view of various AI threats, the EU is planning a so called Artificial Intelligence (AI) Act. The law is intended to primarily regulate the provision and use of AI by private and public actors. Among other things, the law stipulates that companies that develop so called generative AI such as ChatGPT must disclose any copyrighted material used.

EU parliamentarians agreed on the draft law at the beginning of the month. Representatives of the Parliament, the EU Council and the Commission are currently working out the final details. In addition to discussions on regulation, the EU wants to encourage companies to make a voluntary commitment. To this end, the Commission is planning a framework agreement with the Internet group Google and other companies. However, the proposal is still the subject of ongoing discussions.

With the release of ChatGPT, OpenAI has sparked the current hype about generative AI. It simulates human interaction and can create texts based on a few keywords. According to experts, this also increases the risk of disinformation campaigns. OpenAI recently came under criticism for not disclosing the training data for its latest AI model GPT-4. The company justified the non disclosure with the “competitive environment and security aspects”.

A new law on dealing with artificial intelligence is being drafted in the EU. The head of OpenAI has threatened to withdraw from the European market if the rules are not relaxed.

ChatGPT provider OpenAI has threatened a possible withdrawal from Europe in view of the European Union’s (EU) planned regulations for artificial intelligence (AI). “The current draft of the EU AI law would be over-regulation,” said Sam Altman, head of Microsoft subsidiary OpenAI, at an event in London yesterday. Although the group wants to make an effort to comply with new legal regulations, if in doubt the company would be prepared to turn its back on the European market.

Today, Altman was more conciliatory. “AI should be regulated,” he said at a discussion event at the Technical University (TU)in Munich. “We have called for this.” There are also approaches in Europe that are quite good. “But we need more clarity.” One should wait and see how AI develops and only then should the state intervene. Before the visit to Munich, the co-founder of OpenAI made a quick trip to Berlin and met with Chancellor Olaf Scholz (SPD).

Details are currently being negotiated

In view of various AI threats, the EU is planning a so-called Artificial Intelligence (AI) Act. The law is intended to extensively regulate the provision and use of AI by private and public actors. Among other things, the law stipulates that companies that develop so-called generative AI such as ChatGPT must disclose any copyrighted material used.

Representatives of the Parliament, the EU Council and the Commission are currently working out the final details. In addition to discussions on regulation, the EU wants to encourage companies to make a voluntary commitment. To this end, the Commission is planning a frame work agreement with the Internet group Google and other companies. However, the proposal is still the subject of ongoing discussions.

With the release of ChatGPT, OpenAI has sparked the current hype about generative AI. It simulates human interaction and can create texts based on a few keywords. According to experts, this also increases the risk of disinformation campaigns.

Sam Altman, the CEO of OpenAI, the company behind ChatGPT, expressed his belief that the future of artificial intelligence involves finding new methods to create AI models beyond simply training them on existing knowledge.

Altman likened the growth of artificial intelligence to the dawn of agriculture or the development of machines in the industrial era. He emphasized that people will utilize these tools to innovate and shape the future we collectively inhabit.

However, individuals in various industries, particularly those in the arts and entertainment fields, do not share Altman’s optimism regarding the increasing sophistication of AI tools. There are concerns about the use of copyrighted material to train AI models and the proliferation of AI-generated disinformation such as deepfakes.

Altman acknowledged that it was “inevitable” for AI technology to be capable of more nefarious uses and expressed concerns about potential misuse of AI, including deepfakes, especially in the context of global elections.

OpenAI was also under scrutiny for its voice assistant Sky, which some online users noted sounded similar to the voice of Scarlett Johansson. OpenAI clarified that Sky’s voice was not an imitation of Johansson’s and belonged to a different actor hired by the company.

During a panel discussion, Altman and Airbnb co-founder and CEO Brian Chesky, who have been friends for over a decade, highlighted their strong relationship, which was instrumental in Altman’s reinstatement at OpenAI after he was fired.

OpenAI, a prominent AI startup, played a pivotal role in the development of generative AI technologies, including the launch of ChatGPT in 2022, which led to the proliferation of various AI tools such as hyperrealistic videos, humanlike music composition, and conversational chat agents.

Despite concerns about the potential implications of advancements in AI, Altman emphasized that even with the development of artificial general intelligence, these technologies would remain tools and not autonomous beings. He views the development of AI as a gradual evolution rather than a race and acknowledges the responsibility to get it right.

Sam Altman’s role in OpenAI’s Safety and Security Committee has raised concerns about its independence. As a result, Altman will no longer be part of the organization’s Safety and Security Committee, which aims to provide independent oversight of the AI models developed and deployed by the Microsoft-backed startup.

The committee was established in May 2024 to provide safety recommendations for the AI models developed and deployed by the startup backed by Microsoft. Concerns were raised about Altman leading the oversight body, suggesting that members might not be able to impartially assess the safety and security of its AI models.

With the CEO no longer in charge, the committee now includes two OpenAI board members – former NSA chief Paul Nakasone and Quora co-founder Adam D’Angelo – as well as Nicole Seligman, the former executive vice president at Sony, and Zico Kolter, director of the machine learning department at Carnegie Mellon University’s school of computer science.

According to OpenAI’s blog post published on Monday, September 16, “The Safety and Security Committee will receive briefings from company leadership on safety evaluations for major model releases, and will, along with the full board, oversee model launches, including having the authority to postpone a release until safety concerns are addressed.”

Upon the release of its new reasoning-based AI model o1, OpenAI stated that the safety committee had “examined the safety and security criteria used to assess OpenAI o1’s suitability for launch as well as the results of safety evaluations of OpenAI o1.”

The committee also completed its 90-day review of OpenAI’s processes and safeguards and provided the following recommendations to the AI firm:

• Establish independent governance for safety & security
• Enhance security measures
• Maintain transparency about OpenAI’s work
• Collaborate with external organizations
• Unify OpenAI’s safety frameworks for model development and monitoring

Before establishing the safety committee, both current and former employees of OpenAI had expressed concerns that the company was growing too rapidly to operate safely. Jan Leike, a former executive who left OpenAI along with chief scientist Ilya Sutskever, had posted on X that “OpenAI’s safety culture and processes have taken a backseat to shiny products.”

On May 16, 2023, Sam Altman, OpenAI’s charismatic, softly spoken, eternally optimistic billionaire CEO, and I appeared before the US Senate judiciary subcommittee meeting on AI oversight in Washington DC. At the time, AI was at the peak of its popularity, and Altman, then 38, was at the forefront of it all.

Hailing from St Louis, Missouri, Altman was the Stanford dropout who had risen to become the president of the highly successful Y Combinator startup incubator before the age of 30. A few months prior to the hearing, his company’s product ChatGPT had gained widespread attention.

Throughout the summer of 2023, Altman was treated like a celebrity, touring the world, meeting with prime ministers and presidents. US Senator Kyrsten Sinema praised him, saying, “I’ve never met anyone as smart as Sam… He’s an introvert and shy and humble… But… very good at forming relationships with people on the Hill and… can help folks in government understand AI.”

Flattering profiles at the time depicted the youthful Altman as genuine, talented, wealthy, and solely interested in advancing humanity. His frequent assertions that AI could revolutionize the global economy had world leaders eagerly anticipating it.

Gradually, I realized that I, the Senate, and ultimately the American people, had likely been deceived.

Senator Richard Blumenthal had summoned the two of us (and IBM’s Christina Montgomery) to Washington to discuss what should be done about AI, a “dual-use” technology with great promise but also the potential to cause great harm – from floods of misinformation to enabling the spread of new bioweapons. The focus was on AI policy and regulation. We pledged to tell the whole truth and nothing but the truth.

Altman represented one of the leading AI companies, while I was present as a scientist and author known for my skepticism about many things related to AI. I found Altman surprisingly engaging.

There were instances when he evaded questions (most notably Blumenthal’s “What are you most worried about?”, which I pressed Altman to answer more honestly), but overall, he seemed authentic, and I recall conveying this to the senators at the time. We both strongly advocated for AI regulation. However, little by little, I came to realize that I, the Senate, and ultimately the American people, had probably been manipulated.

In reality, I had always harbored some reservations about OpenAI. For example, the company’s publicity campaigns were often exaggerated and even deceptive, such as their elaborate demonstration of a robot “solving” a Rubik’s Cube that was later revealed to have special sensors inside. It received significant media attention, but ultimately led nowhere.

For years, the name OpenAI – which implied a commitment to openness about the science behind the company’s activities – had felt disingenuous, as it had become progressively less transparent over time.

The constant suggestion from the company that AGI (artificial general intelligence, AI that can at least match the cognitive abilities of any human) was just around the corner always seemed like unwarranted hype to me. However, in person, Altman was very impressive; I started to question whether I had been too critical of him before. Looking back, I realized that I had been too lenient.

I began to reconsider my opinion after receiving a tip about a small but revealing incident. During a Senate hearing, Altman portrayed himself as much more altruistic than he actually was. When Senator John Kennedy asked him, “OK. You make a lot of money. Do you?” Altman replied, “I make no… I get paid enough for health insurance. I have no equity in OpenAI,” and continued to elaborate, stating, “I’m doing this because I love it.” The senators were impressed by his response.

However, Altman wasn’t completely truthful. While he didn’t own any stock in OpenAI, he did own stock in Y Combinator, which in turn owned stock in OpenAI. This meant that Sam had an indirect stake in OpenAI, a fact acknowledged on OpenAI’s website. If that indirect stake were worth just 0.1% of the company’s value, which seems plausible, it would be worth nearly $100m.

This omission served as a warning sign. When the topic resurfaced, he could have rectified it, but he chose not to. People were drawn to his selfless image. (He even reinforced this image in an article with Fortune, claiming that he didn’t need equity with OpenAI because he had “enough money”.) Not long after that, I discovered that OpenAI had made a deal with a chip company in which Altman owned a stake. The selfless persona he projected began to seem insincere.

In hindsight, the discussion about money wasn’t the only thing from our time in the Senate that felt less than candid. The more significant issue was OpenAI’s stance on AI regulation. Publicly, Altman expressed support for it, but the reality was far more complex.

On one hand, perhaps a small part of Altman genuinely desired AI regulation. He often quoted Oppenheimer and acknowledged the serious risks that AI poses to humanity, likening it to nuclear weaponry. In his own words at the Senate (albeit after some prompting from me), he said, “Look, we have tried to be very clear about the magnitude of the risks here… My worst fears are that we cause significant – we, the field, the technology, the industry – cause significant harm to the world.”

However, behind closed doors, Altman’s lobbyists continued to push for weaker regulation of AI, or no regulation at all.

Presumably, Altman wouldn’t want to be remembered poorly. Yet behind closed doors, his lobbyists persistently lobbied for weaker regulation or none at all.

A month after the Senate hearing, it was revealed that OpenAI was working to soften the EU’s AI act. When Altman was dismissed by OpenAI in November 2023 for being “not consistently candid” with its board, I wasn’t entirely surprised.

At the time, few people supported the board’s decision to dismiss Altman. A large number of supporters rallied behind him, treating him like a saint. The well-known journalist Kara Swisher (known to be quite friendly with Altman) blocked me on Twitter simply for suggesting that the board might have been justified.

Altman handled the media adeptly. Five days later, with the support of OpenAI’s major investor, Microsoft, and a petition from employees backing him, he was reinstated.

However, much has changed since then. In recent months, concerns about Altman’s honesty have gone from being considered rebellious to being fashionable. Journalist Edward Zitron wrote that Altman was “a false prophet – a seedy grifter that uses his remarkable ability to impress and manipulate Silicon Valley’s elite.”

Ellen Huet of Bloomberg News, on the podcast Foundering, reached the conclusion that “when [Altman] says something, you cannot be sure that he actually means it.”

Paris Marx has cautioned against “Sam Altman’s self-serving vision.” AI pioneer Geoffrey Hinton recently questioned Altman’s motives. I myself wrote an essay called the Sam Altman Playbook, analyzing how he had managed to deceive so many people for so long, using a combination of hype and apparent humility.

Many factors have contributed to this loss of faith. For some, the tipping point was Altman’s interactions earlier this year with Scarlett Johansson, who explicitly asked him not to create a chatbot with her voice.

Altman proceeded to use a different voice actor, but one who was obviously similar to her in voice, and tweeted “Her” (a reference to a movie in which Johansson provided the voice for an AI). Johansson was furious.

The ScarJo incident highlighted a larger problem: major corporations like OpenAI claim that their models cannot function without being trained on all of the world’s intellectual property, but they have not fairly compensated many of the creators, such as artists and writers. Justine Bateman described this as “the largest theft in the history of the United States.”

Although OpenAI has repeatedly emphasized the importance of developing safety measures for AI, several key staff members focused on safety have recently left, stating that the company did not fulfill its promises. Jan Leike, a former OpenAI safety researcher, criticized the company for prioritizing flashy advancements over safety, a sentiment echoed by another former employee, William Saunders.

Co-founder Ilya Sutskever departed and launched a new venture called Safe Superintelligence, while former OpenAI employee Daniel Kokotajlo also expressed concerns that safety commitments were being disregarded. While social media has had negative impacts on society, the inadvertent development of problematic AI by OpenAI could be even more detrimental, as noted by Altman himself.

The disregard for safety exhibited by OpenAI is compounded by the company’s apparent efforts to silence its employees. In May, journalist Kelsey Piper uncovered documents revealing that the company could reclaim vested stock from former employees who did not agree to refrain from speaking negatively about the company, a practice that many industry insiders found alarming.

Subsequently, numerous former OpenAI employees signed a letter at righttowarn.ai requesting whistleblower protections, prompting the company to retract its decision to enforce these contracts.

Even the company’s board members felt deceived. In May, former OpenAI board member Helen Toner stated on the Ted AI Show podcast, “For years, Sam made it really difficult for the board… by withholding information, misrepresenting company events, and in some cases, outright lying to the board.”

By late May, negative publicity about OpenAI and its CEO had accumulated to the point where venture capitalist Matt Turck posted a cartoon on X: “days since the last easily avoidable OpenAI controversy: 0.”

There is a lot at stake. The way that AI is currently developing will have long-term implications. Altman’s decisions could significantly impact all of humanity, not just individual users, in enduring ways. OpenAI has acknowledged that its tools have been utilized by Russia and China to create disinformation, presumably to influence elections.

More advanced forms of AI, if developed, could pose even more serious risks. Despite the impact of social media on polarizing society and subtly influencing people’s beliefs, major AI companies could exacerbate these issues.

Moreover, generative AI, popularized by OpenAI, is having a substantial environmental impact in terms of electricity usage, emissions, and water consumption. As Bloomberg recently stated, “AI is already wreaking havoc on global power systems.” This impact could grow significantly as models continue to expand in size, which is the objective of all major players.

To a large extent, governments are relying on Altman’s assurances that AI will ultimately be beneficial, despite the lack of evidence so far, to justify the environmental costs.

I genuinely believe that if we continue on the current path, we will not achieve an AI that we can trust.

Meanwhile, OpenAI has taken a leading role, and Altman sits on the homeland security safety board. His counsel should be viewed with skepticism.

Altman may have briefly attempted to attract investors for a $7 trillion investment in infrastructure related to generative AI, which might end up being a significant waste of resources that could be better utilized elsewhere if, as many suspect, generative AI is not the right path to AGI [artificial general intelligence].

Overestimating current AI could potentially lead to conflicts. For example, the US-China “chip war” concerning export controls, where the US is restricting the export of crucial GPU chips designed by Nvidia and manufactured in Taiwan, is affecting China’s AI progress and escalating tensions between the two nations.

The chip battle is largely based on the belief that AI will continue to advance exponentially, despite data indicating that current approaches may have reached a point of diminishing returns.

Altman may have initially had good intentions. Perhaps he genuinely aimed to protect the world from AI threats and guide AI for positive purposes. However, greed might have taken over, as is often the case.

Unfortunately, many other AI companies appear to be following the same path of hype and cutting corners as Altman. Anthropic, formed by a group of OpenAI ex-employees concerned about the lack of focus on AI safety, seems to be increasingly competing directly with its parent company.

The billion-dollar startup Perplexity also appears to be a lesson in greed, using data it should not be using. Meanwhile, Microsoft shifted from advocating “responsible AI” to rapidly releasing products with significant issues, pressuring Google to do the same. Money and power are corrupting AI, much like they corrupted social media.

We cannot rely on large privately held AI startups to self-govern in ethical and transparent ways. If we cannot trust them to govern themselves, we certainly should not allow them to govern the world.

I sincerely believe that we will not achieve trustworthy AI if we continue on the current path. Apart from the corrupting influence of power and money, there is also a significant technical issue: large language models, the fundamental technique of generative AI, are unlikely to be safe. They are inherently stubborn and opaque – essentially “black boxes” that we can never fully control.

The statistical techniques behind these models can achieve remarkable feats, such as accelerating computer programming and creating believable interactive characters resembling deceased loved ones or historical figures. However, such black boxes have never been reliable and are therefore an unsuitable basis for AI that we can entrust with our lives and infrastructure.

Nonetheless, I do not advocate for abandoning AI. Developing better AI for fields like medicine, material science, and climate science could truly revolutionize the world. Generative AI may not be the solution, but a future form of AI yet to be developed might be.

Ironically, the biggest threat to AI today could be the AI companies themselves; their unethical behavior and exaggerated promises are turning many people away. Many are ready for the government to take a more active role. According to a June survey by the Artificial Intelligence Policy Institute, 80% of American voters prefer “regulation of AI that mandates safety measures and government oversight of AI labs instead of allowing AI companies to self-regulate.”

To achieve trustworthy AI, I have long advocated for an international effort similar to Cern’s high-energy physics consortium. The time for that is now. Such an initiative, focused on AI safety and reliability rather than profit, and on developing a new set of AI techniques that belong to humanity rather than just a few greedy companies, could be transformative.

Furthermore, citizens need to voice their opinions and demand AI that benefits the majority, not just a select few. One thing I can guarantee is that we will not achieve the promised potential of AI if we leave everything in the hands of Silicon Valley. Tech leaders have been misleading for decades. Why should we expect Sam Altman, last seen driving a $4 million Koenigsegg supercar around Napa Valley, to be any different?

When did OpenAI start?

OpenAI embarked on its groundbreaking journey on December 11, 2015, as a response to the potential dominance of AI by large tech companies.

Who are the current owners of OpenAI?

During its early stages, OpenAI received substantial support from influential figures in the industry, including contributions from Elon Musk and Peter Thiel.

As the company evolved, Elon Musk decided to step down from the board in 2018 to avoid potential conflicts with his other ventures like Tesla and SpaceX.

Due to its ambitious goals and financial requirements, OpenAI transitioned from a nonprofit to a “capped-profit” for-profit entity in 2019, with a significant $1 billion investment from Microsoft.

Ownership of OpenAI is divided among Microsoft (49%), other stakeholders (49%), and the original OpenAI non-profit foundation, which maintains its autonomy.

Other stakeholders in OpenAI include a16z, Sequoia, Tigers Global, and Founders Fund.

OpenAI Inc. functions as the overarching non-profit umbrella, while its for-profit activities are managed by OpenAI LP.

Is OpenAI a publicly traded company?

Despite its significant presence in the AI field, OpenAI is a private company and is not subject to the strict regulations and quarterly pressures faced by public companies.

However, there is considerable demand for OpenAI stock, so a public offering cannot be ruled out in the future.

Conflicts within the OpenAI Board

Elon Musk Sues OpenAI for ‘Placing Profit Above Humanity’

In late February 2024, Elon Musk, who co-founded OpenAI in 2015, filed a lawsuit against OpenAI, alleging that the company had shifted its focus from creating artificial intelligence for the benefit of humanity to pursuing profit.

Musk claims that OpenAI, which was established as a not-for-profit organization with the goal of developing artificial general intelligence, has become a closed-source subsidiary of Microsoft, focusing on maximizing profits for the company.

Musk’s lawsuit seeks to compel OpenAI to adhere to its founding agreement and return to its mission of developing AGI for the benefit of humanity.

In response to Musk’s claims, OpenAI released an open letter stating that Musk had been involved in discussions about creating a for-profit entity in 2017 and had sought majority equity and control over the board and CEO position.

Elon Musk decided to leave OpenAI and started his own AGI competitor named xAI within Tesla.

Sam Altman’s Unexpected Departure from OpenAI

On November 17, 2023, Sam Altman was unexpectedly removed from his position as CEO of OpenAI.

Mira Murati, the company’s chief technology officer, assumed the role of interim CEO, and Emmett Shear, the former CEO of Twitch, was appointed as the new CEO.

Microsoft CEO Satya Nadella offered Altman a position to lead an internal AI division at Microsoft, which Altman accepted, and OpenAI’s president Greg Brockman also transitioned to a role at Microsoft.

However, just four days later, Sam Altman resumed his position as CEO of OpenAI, despite having accepted a role at Microsoft.

OpenAI’s founder and CEO, Sam Altman, recently saw his net worth reach $2 billion according to the Bloomberg Billionaire Index. However, this figure does not reflect any financial gains from the AI company he leads.

This marks the first time the index has assessed the wealth of the 38-year-old, who has become synonymous with artificial intelligence as the CEO of OpenAI, which was recently valued at $86 billion.

According to a report by Bloomberg, Altman has consistently stated that he does not hold any equity in the organization. The report also indicated that a significant portion of his observable wealth comes from a network of venture capital funds and investments in startups.

Moreover, his wealth is expected to increase with the upcoming initial public offering of Reddit, where he stands as one of the largest shareholders.

In related news, Tesla’s CEO, Elon Musk, has filed a lawsuit against OpenAI and Sam Altman, accusing them of violating contractual agreements made when Musk helped establish the ChatGPT developer in 2015.

A lawsuit submitted on Thursday in San Francisco claims that Altman, along with OpenAI’s co-founder Greg Brockman, originally approached Musk to develop an open-source model.

The lawsuit further stated that the open-source initiative promised to advance artificial intelligence technology for the “benefit of humanity.”

In the legal filing, Musk alleged that the focus on profit by the Microsoft-backed company violates that agreement.

It is important to mention that Musk co-founded OpenAI in 2015 but resigned from its board in 2018. Subsequently, in October 2022, Musk acquired Twitter for $44 billion.

OpenAI’s ChatGPT became the fastest-growing software application globally within six months of its launch in November 2022.

Moreover, ChatGPT triggered the development of competing chatbots from companies such as Microsoft, Alphabet, and various startups that capitalized on the excitement to secure billions in funding.

Since ChatGPT’s introduction, many companies have started utilizing its capabilities for diverse tasks. This includes document summarization, coding, and igniting a competitive race among major tech firms to release their own generative AI products.

Although OpenAI is currently valued at $157 billion, it still faces challenges ahead

Recently, OpenAI completed the most lucrative funding round in Silicon Valley’s history. The next step is to successfully navigate a highly competitive AI landscape.

Even though Sam Altman’s company has solidified its leading position in the generative AI boom by achieving a new $157 billion valuation after securing $6.6 billion in fresh capital from prominent investors, its top position is not assured.

Since the launch of ChatGPT in late 2022, it has become evident that their mission to create large language models that can rival human intelligence will involve substantial costs necessitating extensive resources.

Though Altman’s company now casts a significant influence over the industry with its new valuation of $157 billion, numerous competitors are vying for capital and resources, making the startup’s path to profitability more complex.

Thus, while OpenAI has a moment to commend, the situation will soon reveal how strong its competitive advantage is and whether a severe wave of consolidation is imminent in Silicon Valley’s booming industry.

While OpenAI’s recent valuation and capital influx represent enormous amounts that any founder in Silicon Valley would envy, indications suggest that Altman remains somewhat apprehensive.

As per a Financial Times report about the fundraising, Altman’s nearly nine-year-old venture urged its new investors—a group led by Thrive Capital, which includes Nvidia, SoftBank, and Microsoft—to refrain from funding rival companies, of which there are many.

Anthropic and Mistral, both valued in the billions, are aiming to challenge OpenAI. Additionally, Musk’s xAI and Safe Superintelligence (SSI), a startup founded in June by Ilya Sutskever, a former chief scientist at OpenAI who previously attempted a coup against his ex-boss, are also in the mix.

“For the main model developers, these mega-funding rounds are becoming standard as the expenses for training the largest models are soaring into the hundreds of millions of dollars,” remarked Nathan Benaich, founder and partner at Air Street Capital, an investment firm.

Several significant factors indicate that OpenAI cannot afford to be complacent.

For starters, the expenses associated with delivering groundbreaking advancements in generative AI are projected to escalate. Dario Amodei, CEO of Anthropic, noted earlier this year that he anticipates training expenses for AI models could exceed $10 billion by 2026 and potentially reach $100 billion afterward.

OpenAI itself might face training costs surpassing $3 billion annually, as previously estimated by The Information. Training GPT-4o, for instance, costs around $100 million, but this figure is expected to increase based on the complexity of future AI models.

A portion of the expenses is fueled by the acquisition of powerful chips, referred to as GPUs, primarily sourced from Jensen Huang’s Nvidia, to establish clusters in data centers. These chips are crucial for supplying the computational strength necessary to operate large language models (LLMs).

The competition for talent has been intense in this current wave, as AI laboratories strive to gain an advantage over their rivals, prompting them to present ever more extravagant compensation packages.

“Benaich remarked to BI, “These expenses are set to escalate as firms continue to invest heavily to compete for often slight performance improvements over their rivals. This competition lacks clear historical comparisons, largely due to the staggering capital expenditure requirements and the absence of a straightforward path to profitability.”

Although OpenAI’s newfound capital will assist in financing some of the more costly aspects of its operations, it isn’t exactly in a strong position at this moment. A report from The New York Times last week indicated that the leading AI laboratory globally is poised to finish the year with a $5 billion deficit.

Additionally, OpenAI’s rumored push for exclusivity among its investors may have potential downsides. Benaich characterized this approach as “uncommon” but also as a representation of how OpenAI views its own clout in the market.

“This is also a daring strategy that may attract unwanted scrutiny from regulatory bodies,” he added.

For experts in the industry, this situation poses questions about the long-term sustainability of such practices.

Investors foresee some degree of consolidation approaching.

As OpenAI solidifies its role as the leading player in the industry, investors expect some consolidation among startups focusing on foundational models in the upcoming year.

LLM startups require continuous access to substantial capital, but not everyone can secure the same inflow of funds as OpenAI. With Microsoft acquiring Inflection.ai and Google similarly attracting the founding team of Character.ai, investors anticipate more acquisitions of this nature in the near future.

“This is a competition for capital as well, and ultimately only financial backers like sovereign wealth funds will be capable of providing the necessary capital for these LLM startups,” a European growth-stage venture capitalist mentioned to BI.

When funding becomes scarce, established giants, including major tech companies, might acquire smaller focused companies. These smaller firms have access to a vast array of proprietary data for training their models.

Venture capitalists also predict a more grounded approach to investing in LLM leaders at inflated valuations. “Many other firms are raising funds based on aspiration rather than substance, and I believe we will begin to witness a certain rationalization in that area,” another growth-stage VC informed BI, noting that “the overheated excitement surrounding AI is likely to temper next year.”

“You don’t require 50 foundational model enterprises — it’s more likely that you’ll end up with two or four,” he stated.

He added that those companies which endure will be the ones that effectively cater to consumer needs. “You might see Amazon, Anthropic, OpenAI, Meta, and Google, but I struggle to envision many others existing.”

OpenAI has successfully secured $6.6 billion in a significant funding round that places a valuation of $157 billion on the startup, placing it in a small group of tech startups with extraordinarily high private valuations.

This deal, which roughly doubles OpenAI’s valuation from just this past February, highlights the intense expectations investors have for the generative AI surge that OpenAI catalyzed with the launch of ChatGPT in 2022.

“The new funds will enable us to strengthen our position in leading-edge AI research, enhance our computing power, and continue developing tools that assist people in tackling challenging problems,” OpenAI stated in its announcement regarding the deal on Wednesday.

The funding arrives as the nine-year-old AI startup, helmed by CEO Sam Altman, confronts rising competition from companies like Google, Meta, and other AI startups, and during a time when OpenAI is navigating its own transitions — most famously marked by a boardroom incident last year that saw Altman briefly ousted and then reinstated within five days.

Since that time, the firm has faced a series of significant leadership exits as it tries to shift from its origins as a nonprofit research entity to a producer of commercial products that can take advantage of the booming AI sector. Recently, OpenAI’s chief technology officer Mira Murati unexpectedly stepped down to “create the time and space for my own exploration.” Moreover, as recently reported by Fortune, some insiders have expressed concerns that the company’s focus on safety may have been compromised in the rush to release new products ahead of competitors.

Despite the internal upheaval, investors seemed eager to gain a stake in the startup.

OpenAI did not reveal the identities of its investors, but Thrive Capital confirmed via email to Fortune that they had invested and led this latest funding round. According to Bloomberg, which first shared news of the deal, Khosla Ventures, Altimeter Capital, Fidelity, SoftBank, and the Abu Dhabi-based MGX also joined in, along with AI chip manufacturer Nvidia and Microsoft, which had previously invested $13 billion.

OpenAI has reported that ChatGPT is used by over 250 million individuals weekly

With this funding, OpenAI solidifies its position as one of the most valuable startups globally, following TikTok parent company ByteDance, valued at $225 billion, and SpaceX, led by Elon Musk, with a valuation of $200 billion, according to CB Insights’ rankings of tech company valuations.

On Wednesday, OpenAI announced that more than 250 million people worldwide engage with ChatGPT weekly.

While the company does not share its financial outcomes, the New York Times has indicated that OpenAI’s monthly earnings reached $300 million in August and anticipates generating $11.6 billion in revenue in the coming year.

With a new valuation of $157 billion after funding, investors seem to be assessing the company at 13 times its expected revenue for next year.

In comparison, Google’s parent company, Alphabet, is traded on the stock market at 5.3 times its predicted revenue for next year, while Nvidia is evaluated at approximately 16 times projected revenue.

On Wednesday, OpenAI referenced its foundational principles, emphasizing that it is “making strides toward our goal of ensuring that artificial general intelligence serves the entire human race.”

Artificial general intelligence, or AGI, remains a theoretical concept of an AI system capable of performing tasks as well as or even better than humans.

The potential risks associated with AGI were part of the rationale behind OpenAI’s establishment in 2015, as Altman, Elon Musk, and the other co-founders aimed to create a counterbalance to Google’s DeepMind, which they were concerned would develop AGI driven solely by commercial motives.

Musk, who departed from OpenAI, has criticized the organization for straying from its original purpose, even as he has ventured into his own AI enterprise, xAI.

The valuation of OpenAI has nearly doubled since earlier this year when it arranged a tender offer allowing employees to sell a portion of their shares to private investors, valuing the company at about $80 billion.

How safe is the use of artificial intelligence? The EU states have now agreed on rules. These are intended to ensure that AI systems are safe and comply with fundamental rights. Consumer advocates still see dangers.

For the first time, EU member states have laid down comprehensive rules for the use of artificial intelligence (AI). The decision is intended to ensure that AI systems are safe and respect fundamental rights, the Council of EU states announced. At the same time, innovation should be promoted.

Praise from Buschmann and Habeck

“The EU is well on its way to setting the world’s first binding standard for trustworthy AI,” said Federal Justice Minister Marco Buschmann (FDP). However, he sees room for improvement: for example, in ensuring anonymity in public spaces and transparency in the use of AI systems.

Federal Minister of Economics Robert Habeck (Greens) also welcomed the agreement. Artificial intelligence is “crucial for the competitiveness of the EU”.

Before the new rules actually come into force, the EU states must reach an agreement with the European Parliament.

Ban: AI for evaluating people

The EU Commission proposed the law in April 2021 with the aim of setting global standards. The greater the potential dangers of an application, the higher the requirements should be. High penalties are provided for violations of the rules. Above all, the authority wants to create the basis for users to be able to trust AI applications.

Among other things, the telecommunications ministers agreed on a ban on using AI to evaluate people based on their social behavior or personality traits if this leads to disadvantages. In addition, the regulation should specify how to deal with particularly risky AI systems.

These include biometric recognition systems and systems used in water and electricity supplies. The use of AI in the military sector and for purely research purposes is to be exempted from the rules.

AI already in many areas

Artificial intelligence usually refers to applications based on machine learning, in which software searches through large amounts of data for matches and draws conclusions from them.

They are already being used in many areas. For example, such programs can evaluate CT scans faster and with greater accuracy than humans. Self-driving cars also try to predict the behavior of other road users in this way. And chatbots or automatic playlists from streaming services also work with AI.

Critics: “important questions remain unanswered”, “full of loopholes”

The EU consumer association Beuc complained that the decision of the EU states left too many important questions unanswered, such as facial recognition by private companies in public places. In addition, provisions that classified systems as highly risky had been watered down.

Dutch Green MEP Kim van Sparrentak, on the other hand, criticized the decision. The agreement text lacks “necessary safeguards for fundamental rights” and is “full of loopholes,” vanSparrentak wrote on Twitter.

AI’s potential benefits and risks

The wide range of potential applications of AI also means there is a similarly broad spectrum of possible benefits and risks associated with using such technology. The potential benefits of AI at a societal level, as outlined by the European Parliament, include the following:

AI has the potential to improve healthcare, enhance the safety of cars and other transportation systems, and provide personalized, affordable, and longer-lasting products and services. It can also improve access to information, education, and training. Furthermore, AI can enhance workplace safety by utilizing robots for hazardous job tasks and create new job opportunities as AI-driven industries evolve and transform.

For businesses, AI can facilitate the development of innovative products and services, increase sales, optimize machine maintenance, enhance production output and quality, improve customer service, and conserve energy.

The use of AI in public services can result in cost reductions and provide new opportunities in public transportation, education, energy, and waste management. It can also contribute to improving the sustainability of products.

The utilization of data-based scrutiny can strengthen democracy, prevent disinformation and cyber attacks, and ensure access to high-quality information.

AI is expected to play a larger role in crime prevention and the criminal justice system, as it can process massive datasets more quickly, accurately assess prisoner flight risks, predict and prevent crime or terrorist attacks. In military contexts, AI could be used for defensive and offensive strategies in hacking and phishing, as well as targeting key systems in cyberwarfare.

However, the article also highlighted some of the risks associated with AI. These include issues of liability, such as determining who is accountable for any harm or damage caused by the use of AI. Similarly, in an article on Forbes’ website, futurist Bernard Marr suggested that the major risks of AI at a broad level are:

A lack of transparency, especially in the development of deep learning models (including the ‘Black Box’ issue where AI generates unexpected outputs, and human scientists and developers are unclear about the reasons behind it).

• Bias and discrimination, particularly when AI systems inadvertently perpetuate or amplify societal biases.
• Privacy concerns, particularly regarding AI’s ability to analyze large amounts of personal data.
• Ethical concerns, especially related to the challenges of instilling moral and ethical values in AI systems.
• Security risks, including the development of AI-driven autonomous weaponry.
• Concentration of power, given the risk of AI development being dominated by a small number of corporations.
• Dependence on AI, including the risk that overreliance on AI leads to a decline in creativity, critical thinking skills, and human intuition.
• Job displacement, as AI has the potential to render some jobs unnecessary, while potentially creating the need for others.
• Economic inequality, and the possibility that AI will disproportionately benefit the wealthy individuals and corporations.
• Legal and regulatory challenges, and the necessity for regulation to keep pace with the rapid pace of innovation.
• An AI arms race, involving companies and nations competing to develop new capabilities at the expense of ethical and regulatory considerations.
• Loss of human connection, and concerns that reliance on AI-driven communication and interactions could lead to reduced empathy, social skills, and human connections.
• Misinformation and manipulation, including the risk that AI-generated content fuels the spread of false information and manipulation of public opinion.
• Unintended consequences, particularly related to the complexity of AI systems and the lack of human oversight leading to undesired outcomes.
• Existential risks, including the emergence of artificial general intelligence (AGI) surpassing human intelligence and posing long-term risks for humanity’s future.
• On the issue of misinformation and manipulation, several observers have suggested that the 2024 elections, particularly the US presidential election, may be the first elections significantly
• influenced by AI in the campaigning process.
• Potential impact on the employment market in the UK

A government-commissioned report by PWC in 2021 discovered that 7 percent of jobs in the UK workforce faced a high risk of automation within the next five years. This figure increased to 30 percent over a 20-year period:

Based on our analysis, it is estimated that approximately 7 percent of current UK jobs could be highly likely (over 70 percent probability) to be automated in the next five years, which could rise to around 18 percent after 10 years and just under 30 percent after 20 years.

These estimates align with previous studies and incorporate feedback from an expert workshop on the automatability of different occupations alongside a detailed examination of OECD and ONS data relating to task composition and required skills for various occupations.

The report highlighted the manufacturing sector as being particularly susceptible to job losses over the next 20 years, with anticipated reductions also in transport and logistics, public administration and defense, and the wholesale and retail sectors. Conversely, the health and social work sector was anticipated to experience the most significant job growth, along with expected gains in the professional and scientific, education, and information and communications sectors.

Jobs in lower-paid clerical and process-oriented roles were identified as being particularly at risk of being lost. On the other hand, the report indicated that there would be increases in jobs within managerial and professional occupations.

The report suggested that the most probable scenario is that the long-term impact of AI on employment levels in the UK would be largely neutral, although the specific impacts within this framework remain uncertain.

Subsequent analyses of AI, especially since the introduction of LLMs such as ChatGPT and Google Bard, have raised questions about whether the impact of AI will predominantly affect lower-paid or manual jobs. A report published by OpenAI in March 2023, the creator of ChatGPT, suggested that higher-paying jobs are more likely to be affected by LLMs. The analysis also indicated that there would be variations depending on the nature of the tasks involved:

The significance of science and critical thinking skills is strongly negatively linked to exposure, indicating that occupations requiring these skills are less likely to be influenced by current LLMs. Conversely, programming and writing skills show a strong positive correlation with exposure, suggesting that occupations involving these skills are more susceptible to LLM influence.

On April 21, 2023, the House of Commons Business, Energy, and Industrial Strategy Committee released a report on post-pandemic economic growth and the UK labor market. This report emphasized the potential impact of AI on productivity within the UK. It mentioned research from Deloitte which found that “by 2035 AI could enhance UK labor market productivity by 25%”, and that “four out of five UK organizations stated that the use of AI tools had heightened their employees’ productivity, improved decision-making, and made their processes more efficient”.

The report also argued that AI and related technologies might have a positive effect on facilitating labor market access for individuals who have experienced difficulty finding and maintaining employment, such as disabled individuals.

Estimates of AI’s impact on the UK and global economy are continually being released as these products evolve. Recent examples include research from McKinsey, which indicated that generative AI could provide value equivalent to the UK’s entire GDP to the global economy in the coming years:

Generative AI’s effect on productivity could add trillions of dollars in value to the global economy. Our latest analysis estimates that generative AI could add the equivalent of $2.6tn to $4.4tn annually across the 63 use cases we analyzed—by comparison, the United Kingdom’s entire GDP in 2021 was $3.1tn.

This impact would raise the overall influence of all artificial intelligence by 15 to 40 percent. This estimate would approximately double if we factor in the impact of integrating generative AI into software currently utilized for tasks beyond those use cases.

Case study: Potential impact on the knowledge and creative industries (House of Lords Communications and Digital Committee report, January 2023)

AI has potential applications across nearly all aspects of human life, making it impossible to discuss them all here. Yet, in January 2023, the House of Lords Communications and Digital Committee examined the potential effect of AI on the creative industries in the UK as part of a broader assessment of the sector, providing an illustrative example.

The committee received testimony indicating that new technologies and the rise of digitized culture will alter the way creative content is created, distributed, and monetized in the next five to ten years.

The committee emphasized the importance of protecting intellectual property (IP) and its significance to the creative industries. It also highlighted the impact of AI technologies, particularly the use of text and data mining by generative AI models to learn and develop content on existing materials.

The committee also brought to attention the proposed reforms to IP law:

The government’s proposed changes to IP law illustrated the tension between developing new technologies and supporting rights holders in the creative industries. In 2021, the Intellectual Property Office (IPO) sought input on the relationship between IP and AI. In 2022, the IPO outlined its conclusions, including “a new copyright and database right exception which allows text and data mining for any purpose”.

The committee expressed concerns that such proposals were “misguided” and did not adequately consider the potential harm to the creative industries. They argued that while AI development was important, it should not be pursued at the expense of the creative industries. As a result, the committee recommended the IPO to immediately pause its proposed changes to the text and data mining regime. The committee also urged the IPO to conduct and publish an impact assessment on the implications for the creative industries. If the assessment revealed negative effects on businesses in the creative industries, the committee suggested pursuing alternative approaches, such as those utilized by the European Union (EU), which are detailed in section 5.1 of this briefing.

Additionally, the committee cautioned against using AI to produce, reproduce, and distribute creative works and image likenesses without proper consent or consideration of the rights of performers and original creators.

In response to the committee, the government stated that, considering additional evidence of the impact on the creative sector, it would not move forward with the proposals for an exception for text and data mining of copyrighted works. Instead, the government announced plans to collaborate with users and rights holders to establish a “code of practice by the summer [2023]” on text and data mining by AI.

Several legal challenges are currently underway regarding the use of existing written content and images to train generative AI. Authors Paul Tremblay and Mona Awad, for instance, have initiated legal action in the United States against OpenAI, alleging unauthorized use of their work to develop its ChatGPT LLM.

The debate on how best to safeguard copyright and creative careers like writing and illustrating is ongoing. The Creators’ Rights Alliance (CRA), a coalition of organizations from across the UK cultural sector, contends that current AI technology is advancing without sufficient consideration of ethical, accountability, and economic issues related to creative human endeavor.

The CRA advocates for clear definition and labeling of solely AI-generated work and work involving creators’ input. It also emphasizes the need to protect the distinct characteristics of individual performers and artists. Furthermore, the CRA calls for copyright protection, including no data mining of existing work without consent, and urges increased transparency regarding the data used to create generative AI. Additionally, the CRA seeks enhanced protection for creative roles such as visual artists, translators, and journalists, to prevent these roles from being displaced by AI systems.

Italy is suggesting a new law regarding Artificial Intelligence (AI) as of May 20, 2024, which was presented to the Italian Senate.

The proposed law contains (1) general principles for the development and utilization of AI systems and models; (2) specific provisions, especially in the healthcare domain and for scientific research in healthcare; (3) regulations on the national strategy on AI and governance, including the identification of the national competent authorities as per the EU AI Act; and (4) modifications to copyright law.

Below, we present an outline of the significant provisions of the proposal.

Aims and General Principles

The suggested law endeavors to encourage a “fair, transparent, and responsible” use of AI, following a human-centered approach, and to oversee potential economic and social risks, as well as risks to fundamental rights. The law will work together with the EU AI Act. (Article 1)

The proposed law specifies general principles, founded on the principles developed by the Commission’s High-level expert group on artificial intelligence, pursuing three broad objectives:

Equitable algorithmic processing. Research, testing, development, implementation, and application of AI systems must respect individuals’ fundamental rights and freedoms, and the principles of transparency, proportionality, security, protection of personal data and confidentiality, accuracy, non-discrimination, gender equality, and inclusion.

Data protection. The development of AI systems and models must be based on data and processes that are appropriate to the sectors in which they’re planned to be used, and ensure that data is accurate, reliable, secure, qualitative, appropriate, and transparent. Cybersecurity throughout the systems’ lifespan must be guaranteed, and specific security measures adopted.

Digital sustainability. The development and implementation of AI systems and models must ensure human autonomy and decision-making, prevention of harm, transparency, and explainability. (Article 3)

Definitions

The definitions used in the proposed law, such as “AI system” and “[general-purpose] AI model” are the same as those in the EU AI Act, and the definition of the term “data” is based on the Data Governance Act. (Article 2)

Processing of Personal Data Related to the Use of AI Systems

Information and disclosures concerning the processing of data must be written in clear and simple language to ensure complete transparency and the ability to object to unfair processing activities.

Minors aged 14 or older can consent to the processing of personal data related to the use of AI systems, provided that the relevant information and disclosures are easily accessible and understandable. Access to AI by minors under 14 requires parental consent. (Article 4)

Use of AI in the Healthcare Sector

As a general goal, the proposed law stipulates that AI systems should contribute to improving the healthcare system, preventing and treating diseases while respecting the rights, freedoms, and interests of individuals, including their data protection rights.

The use of AI systems in the healthcare system must not select or influence access to medical services on a discriminatory basis. Individuals have the right to be informed about the use of AI and its benefits related to diagnosis and therapy, and to receive information about the logic involved in decision-making.

Such AI systems are intended to support processes of prevention, diagnosis, treatment, and therapeutic choice. Decision-making must remain within the healthcare professional’s purview. (Article 7)

Scientific Research to Develop AI Systems for the Healthcare Sector

The proposed law aims to streamline data protection-related obligations for scientific research conducted by public and private not-for-profit entities, for processing of personal data, including health data, for scientific research purposes to develop AI systems for the prevention, diagnosis, and treatment of diseases, development of medicines, therapies, and rehabilitation technologies, and manufacturing of medical devices. (Article 7)

Specifically, the proposed legislation:

– Removes the need to obtain consent from the individual whose data is being used, by categorizing the stated purposes as “significant public interests,” as outlined in Article 9(2)(g) of the GDPR. This exemption does not apply to commercial and for-profit activities.

– Allows for the secondary usage of personal data, including special categories of data, with direct identifiers removed, for processing related to the aforementioned “significant public interests.” Consequently, a new consent is not required if there are changes to the research.

– In such instances, the following conditions are applicable:

– The obligations of transparency and providing information to data subjects can be fulfilled in a simplified manner, such as by posting a privacy notice on the data controller’s website.

– The processing activities need to (1) be approved by the relevant ethics committee, and (2) be communicated to the Italian data protection authority (“Garante”); and (3) certain information, including a data protection impact assessment and any processors identified, must be shared with the Garante. Processing may commence 30 days after this communication unless the Garante issues a blocking measure. (Article 8)

These provisions are consistent with a recent revision of the Italian Privacy Code pertaining to processing for medical research purposes (refer to our blogpost here).

Other Industry-Specific Provisions

– The utilization of AI systems in the workplace must be secure, dependable, transparent, and respectful of human dignity and personal data protection. The employer is required to notify the employee about the use of any AI, along with other pertinent information that must be provided prior to commencing employment. (Article 10)

– In regulated professions, AI may only be used for supportive tasks. To maintain the trust-based relationship with the client, information about any AI systems used by the professional must be communicated in a clear, straightforward, and comprehensive manner. (Article 12)

National AI Strategy

– The proposed legislation introduces a national strategy on AI, to be updated biennially, with the aim of establishing a public-private partnership, coordinating the activities of public entities, and implementing measures and economic incentives to foster business and industrial development in the AI domain. (Article 17)

Governance

– The proposed legislation assigns two competent national authorities for AI, as required by the EU AI Act, with the authority to enforce and implement national and EU AI laws, as follows:

– Agenzia per l’Italia digitale (“AgID”, the agency for “digital Italy”). AgID will be responsible for (1) promoting innovation and AI development, and (2) establishing procedures and carrying out functions related to the notification, evaluation, accreditation, and monitoring of the notified bodies tasked with conducting conformity assessments of AI systems pursuant to the EU AI Act.

– Agenzia per la cybersicurezza nazionale (“ACN”, the agency for national cybersecurity). ACN will be (1) tasked with monitoring, inspecting, and enforcing powers over AI systems, in accordance with the regulations set forth in the EU AI Act, and (2) responsible for promoting and developing AI from a cybersecurity perspective.

Although not designated as a competent authority for AI, the Garante maintains its competence and authority in relation to the processing of personal data. (Article 18)

The Italian government is also empowered to enact, within 12 months from the enactment of the law, the necessary legislation to align national law with the EU AI Act. (Article 22)

Labeling of AI-Generated News and Information

– The proposed legislation establishes a requirement to label any news or informational content that is entirely generated by AI, or has been partially modified or altered by AI in a way that presents fictional data, facts, and information as genuine, with an “AI” mark, label, or announcement. (Article 23)

Copyright Protection and AI-Generated Works

– The proposed legislation introduces specific amendments to copyright law. Notably, regarding AI-generated works, it clarifies that only works resulting from human intellectual effort are protected by copyright, including those created with the assistance of AI tools, to the extent that they reflect the author’s intellectual endeavor. (Article 24)

Criminal Provisions

Among other provisions, the proposed legislation establishes a new offense targeting the unauthorized dissemination of images, videos, or audio that have been falsified or altered by AI in a manner that can be misleading about their authenticity. The new offense carries a penalty of 1-3 years of imprisonment. (Article 25)

Next Steps

As part of the legislative process, the proposed legislation will need to undergo review, discussion, and approval by the Senate, and will subsequently be transmitted to the Chamber of Deputies, which must also approve the same text. Once formally approved, the law will come into effect on the 15th day following its publication in the Italian Official Journal.

Technological advancements are exerting a rapidly increasing influence on our lives with the advent of artificial intelligence (AI). AI has swiftly emerged as an integral element of our lives, transforming business

Nonetheless, as AI technologies gain popularity, they bring up moral, legal, and social concerns. Many countries across the globe are adopting laws to control the design, deployment, and use of AI. This article discusses the relevant regulations and details about AI in specific countries and regions. It also seeks to educate you about the main considerations and issues related to AI.

AI Regulations Across Different Countries

1. The United States of America

The United States’ decentralized approach to regulating artificial intelligence aligns with its general governance model. Most regulatory practices and policies in the US are focused on specific sectors, and this approach similarly extends to the field of AI.

Overall, there is no comprehensive federal regulation framework specifically for artificial intelligence. However, the US has set up various sector-specific agencies and organizations to address some of the challenges arising from the development of AI.

For instance, the Federal Trade Commission (FTC) focuses on consumer protection when it comes to AI applications and aims to enforce fair and transparent business practices in the industry. Similarly, the National Highway Traffic Safety Administration (NHTSA) regulates the safety aspects of AI-powered technologies, particularly in autonomous vehicles.

Additionally, some states have implemented their own regulations to some extent. For example, the CCPA has imposed strict requirements on businesses handling consumer data, and these requirements also pertain to those using AI technologies. While AI regulation in the United States lacks centralization, it is compensated for by the extensive sectoral participation.

2. The European Union (EU)

The European Union (EU) has taken a proactive approach to AI legislation, driven by measures such as the General Data Protection Regulation (GDPR) and ongoing discussions about the proposed Artificial Intelligence Act. These initiatives aim to establish stringent guidelines for the collection, use, and preservation of personal data.

Since AI systems operate based on the collection and use of personal data, there is a need for strict rules to respect and safeguard individual privacy. The EU’s proposed legislation aims to control the unchecked operation of AI systems. The AI Act complements the GDPR and seeks to give the EU significant authority over the development, use, and regulation of AI. Importantly, the Act is anticipated to be guided by transparency, accountability, and ethical principles to address the concerns and interests of users.

By leveraging these principles and considerations, the EU aims to position itself as the global leader in setting ethical standards and, consequently, in promoting competitiveness and innovation in AI deployment.

3. China

China has emerged as a major force in the AI sector, positioning itself as a leading global power in AI. The country’s objective to become the premier AI innovation hub by 2030 is well underway, marking a decade-long journey towards significant technological dominance. Despite the government’s assertion of complete control in reshaping all aspects of technology through AI, there is a high level of awareness of AI’s ethical and security implications.

Consequently, the Chinese government has formulated regulations to govern the growth and operations of AI. Moreover, China’s extensive regulations on AI and cybersecurity encompass most of the guiding principles applied to AI.

The Chinese Cybersecurity Law and the New Generation AI Development Plan provide measures for data protection and cybersecurity in AI, emphasizing compliance and timely risk management. With an integrated strategy aimed at attaining AI supremacy while ensuring its ethical and secure application, China is prudently navigating the use of the technology, while averting its articulated risks.

In this respect, China is confident in implementing AI-safe measures in line with upcoming global standards, while striving to establish a new operational paradigm for AI that can position China as the eminent AI superpower.

4. Canada

Canada has taken a proactive approach to AI regulation by striking a delicate balance between fostering innovation and upholding ethical standards and societal interests. The country has introduced significant government-led initiatives, such as the Pan-Canadian AI Strategy and the Canadian AI Ethics Council, to advocate for the responsible advancement of AI and address pertinent ethical issues in the AI sector.

These initiatives play a crucial role in facilitating collaboration among stakeholders to develop policies that align with respect for ethical values and the advancement of technology.

Furthermore, Canada has enacted the Personal Information Protection and Electronic Documents Act to regulate the collection, use, and disclosure of individuals’ personal information using AI technologies. The Act ensures the preservation of individuals’ privacy rights and mandates that AI technology meets rigorous data protection criteria.

5. Australia

In Australia, several laws promote effective governance of AI. The National Artificial Intelligence Ethics Framework is central to AI regulation in Australia. It outlines the ethical principles guiding the development and implementation of AI systems. This framework is used in Australia to ensure the ethical development of AI technologies, fostering public trust in the technology.

Moreover, regulatory authorities in Australia, such as the ACCC, play a crucial role in enforcing regulations. They are responsible for monitoring compliance with competition and consumer protection laws in the context of AI applications. Through these efforts, Australia aims to create a supportive environment for AI innovation while safeguarding consumer interests and upholding AI ethics.

6. International organizations

International organizations like the Organization for Economic Co-operation and Development (OECD) and the United Nations are actively engaged in establishing global guidelines for AI regulation. For instance, the OECD’s AI Principles advocate for transparency, responsibility, and inclusion in AI development and implementation Similarly, the United Nations Sustainable Development Goals emphasize the use of AI for global benefits and sustainability.

Given the varying regulatory landscapes for AI, collaboration between countries and international organizations is increasingly essential. Through standardizing approaches and guidelines, cooperation ensures that nations responsibly develop and apply AI to address global challenges. Collaborative efforts and dialogue will enable the integration of regulation challenges and the use of AI for shared social good.

Key Considerations for Developing Legislation

The following is a list of essential considerations in shaping AI legislation, encompassing ethical principles, data privacy, algorithmic bias, transparency, explainability, and international cooperation.

• Ethical principles: Regulations should uphold ethical principles such as transparency, fairness, and accountability to ensure responsible AI development and use.
• Data privacy: Legislation should include guidelines on how AI collects, uses, and protects personal data to mitigate privacy concerns.
• Algorithmic bias: Measures should be integrated to address algorithmic bias and facilitate fair and impartial AI decision-making.
• Transparency and explainability: AI systems should be transparent and comprehensible, enabling users to understand decision-making processes and ensuring accountability.
• International collaboration: Governments should collaborate with international organizations to establish unified regulations that address global challenges.Takeaway

AI regulations influence significantly the future impact of the technology on society. They should establish clear requirements and support AI across various sectors, always prioritizing and consumer protection principles. As AI becomes more advanced due to advancements in ethical ethical learning, regulations should become more adaptable , updated, and coordinated among all regulatory bodies. Stakeholders should work together at national and global levels to ensure the responsible implementation of AI and maximize the potential benefits of this technology.

As artificial intelligence (AI) becomes more significant in society, professionals in the field have recognized the importance of establishing ethical guidelines for the creation and use of new AI technologies. While there isn’t a comprehensive governing organization to draft and enforce these regulations, numerous tech companies have implemented their own versions of AI ethics or codes of conduct.

AI ethics encompass the moral guidelines that organizations utilize to promote responsible and equitable development and application of AI. This article will examine the concept of ethics in AI, its significance, as well as the challenges and advantages of formulating an AI code of conduct.

AI ethics refer to the framework of guiding principles that stakeholders (which include engineers and government representatives) employ to ensure the responsible development and application of artificial intelligence technologies. This entails adopting a safe, secure, humane, and eco-friendly approach to AI.

A robust AI code of ethics can involve avoiding biases, safeguarding user privacy and their data, and addressing environmental concerns. The two primary avenues for implementing AI ethics are through company-specific ethics codes and government-driven regulatory frameworks. By addressing both global and national ethical concerns in AI and laying a policy foundation for ethical AI within organizations, both methods contribute to regulating AI technologies.

Discussion surrounding AI ethics has evolved from its initial focus on academic studies and non-profit organizations. Presently, major tech firms like IBM, Google, and Meta have assembled teams dedicated to addressing the ethical issues arising from the accumulation of vast data sets. Concurrently, governmental and intergovernmental bodies have begun to formulate regulations and ethical policies grounded in academic research.

Creating ethical principles for responsible AI development necessitates collaboration among industry stakeholders. These parties need to analyze how social, economic, and political factors intersect with AI and determine how humans and machines can coexist effectively.

Each of these groups plays a vital role in minimizing bias and risk associated with AI technologies.

Academics: Scholars and researchers are tasked with generating theory-based statistics, studies, and concepts that assist governments, corporations, and non-profit organizations.

Government: Various agencies and committees within a government can promote AI ethics at a national level. An example of this is the 2016 report from the National Science and Technology Council (NSTC), titled Preparing for the Future of Artificial Intelligence, which outlines the relationship between AI and public outreach, regulation, governance, economy, and security.

Intergovernmental entities: Organizations such as the United Nations and the World Bank are crucial for enhancing awareness and formulating international agreements concerning AI ethics. For instance, UNESCO’s 193 member states adopted a global agreement on the Ethics of AI in November 2021, which aims to uphold human rights and dignity.

Non-profit organizations: Groups like Black in AI and Queer in AI work to elevate the representation of diverse communities within AI technology. The Future of Life Institute formulated 23 guidelines that have since become the Asilomar AI Principles, detailing specific risks, challenges, and outcomes tied to AI technologies.

Private companies: Leaders at tech giants like Google and Meta, as well as industries such as banking, consulting, and healthcare that utilize AI, are accountable for establishing ethics teams and codes of conduct. This often sets a standard for other companies to follow.

The significance of AI ethics arises from the fact that AI technologies are designed to enhance or substitute human intelligence; however, issues that can impair human judgment may inadvertently impact these technologies as well. AI initiatives developed on biased or unreliable data can have detrimental effects, especially for underrepresented or marginalized individuals and groups. Moreover, if AI algorithms and machine learning models are hastily constructed, it may become difficult for engineers and product managers to rectify embedded biases later on. Implementing a code of ethics during the development phase is a more effective way to address potential future risks.

Instances of AI ethics can be illustrated through real-world cases. In December 2022, the application Lensa AI employed artificial intelligence to create stylized, cartoon-like profile pictures from users’ standard images. Ethically, some criticized the application for failing to provide credit or adequate compensation to the artists whose original digital works the AI was trained on. Reports indicated that Lensa was trained on billions of photographs obtained from the internet without prior consent.

Another instance is the AI model ChatGPT, which allows users to engage with it by posing questions. ChatGPT searches the internet for information and responds with a poem, Python code, or a proposal. One ethical concern is that individuals are using ChatGPT to excel in coding competitions or to compose essays. It also prompts similar inquiries to Lensa, but pertains to text instead of images.

These two instances exemplify prevalent issues in AI ethics. As AI has advanced in recent years, impacting nearly every sector and significantly benefiting areas such as health care, the discussion surrounding AI ethics has become increasingly important. How can we ensure that AI is free from bias? What steps can be taken to reduce future risks? There are various potential solutions, but stakeholders need to operate responsibly and collaboratively to achieve positive results worldwide.

Ethical issues related to AI

There are numerous real-world situations that can effectively illustrate AI ethics. Here are just a few.

AI and bias

If AI fails to gather data that accurately reflects the population, its decisions may be prone to bias. In 2018, Amazon faced criticism for its AI recruiting tool, which penalized resumes containing the term “women” (such as “Women’s International Business Society”) [3]. Essentially, the AI software discriminated against women, leading to legal liability for the tech giant.

AI and privacy

As noted earlier with the Lensa AI example, AI depends on data sourced from internet searches, social media images and comments, online transactions, and more. While this personalization enhances customer experience, it raises concerns regarding the apparent absence of genuine consent for these companies to access our private information.

AI and the environment

Certain AI models are extensive and demand substantial energy to train on data. Although research is being conducted to create energy-efficient AI methods, more efforts could be made to include environmental ethical considerations in AI-related policies.

How to foster more ethical AI

Developing more ethical AI necessitates a thorough examination of the ethical ramifications of policy, education, and technology. Regulatory frameworks can help ensure that technologies serve societal benefits rather than causing harm. Globally, governments are starting to implement policies for ethical AI, including guidelines on how companies should address legal concerns when bias or other harms occur.

Everyone who interacts with AI should be aware of the risks and potential adverse effects of unethical or deceptive AI. The development and distribution of accessible resources can help to reduce these types of risks.

It may seem paradoxical to utilize technology to identify unethical conduct in other technological forms, but AI tools can assist in determining whether video, audio, or text (hate speech on Facebook, for instance) is genuine or not. These tools can identify unethical data sources and bias more accurately and efficiently than humans.

Continue learning

The fundamental question for our society is how do we manage machines that surpass our intellect? Lund University’s Artificial Intelligence: Ethics & Societal Challenges examines the ethical and societal implications of AI technologies. Covering topics from algorithmic bias and surveillance to AI in democratic versus authoritarian contexts, you will explore AI ethics and its significance in our society.

Tech giants in the USA are committed to using artificial intelligence responsibly. Risk assessments are intended to curb misinformation and increase the security of use.

Seven leading developers of software with artificial intelligence (AI) in the USA have made a commitment to use the technology responsibly and safely. This includes checking AI programs for risks before publication. In addition, content created or modified by AI software should be labeled, as US President Joe Biden said at a meeting with representatives of major technology and internet companies in Washington.

Participating companies include Google, Amazon, the Facebook group Meta and Microsoft. Also involved is the company OpenAI, whose technology is behind the popular chatbot ChatGPT.

Growing concern about misinformation

With the success of the chatbot ChatGPT developed by OpenAI, concerns have grown that AI software can be used to create and spread false information, including deceptively real-looking photos and videos. Because the program has no understanding of the content, it can make claims that are completely false, even with supposedly persuasive power.

The companies committed to “creating a more comprehensive regime that makes it easier for consumers to know whether a piece of content is artificially generated or not.” “There is still technical work to be done, but the point is that it will apply to audio and visual content and will be part of a more comprehensive system,” a White House official said.

In the USA, with a view to the 2024 presidential election,ways are being sought to detect whether audio or image material has been artificially generated in order to prevent deception and forgery.

Combating prejudice

But critics also point out that AI programs are not free from prejudice and discrimination. The companies committed to resolve the problem. They also declared their willingness to focus artificial intelligence on major challenges such as cancer research and climate change.

“Limits and supervision needed”

Artificial intelligence poses risks for society, the economy and national security – but also incredible opportunities, said Biden. The voluntary commitments are “a promising step,” but new laws and oversight will also be needed, said Biden after a meeting with company representatives in the White House. The companies Anthropic and Inflection, which develop AI assistants, also joined the voluntary commitment.

The White House says it wants to work with the US’s allies on international rules for AI. The topic was already on the agenda at the G7 summit in Japan in May. Great Britain is expected to host an international AI summit in the autumn.

At EU level, a comprehensive labeling requirement for AI-generated content is currently being discussed as part of a comprehensive AI law. In addition to labeling image and sound recordings, Federal DigitalMinister Volker Wissing is also calling for the introduction of an AI seal fortexts.

Discover how AI improves efficiency and fosters innovation within legal departments, enhancing research, compliance, and decision-making.

Artificial intelligence (AI) is revolutionizing global business operations. According to a 2023 report by Goldman Sachs, AI has the potential to automate two-thirds of US occupations to some extent. Although it’s commonly believed that the legal industry is slow to adopt technology, AI is making significant strides in this field. A recent study by ContractPodAi in January 2024 revealed that over half of in-house legal professionals (51%) report that their company’s leadership encourages the use of GenAI tools, and more than a third (35 %) require it.

The advantages of AI in the legal sector are plentiful. This article examines how corporate legal departments are integrating AI into routine and complex legal matters to improve efficiency, enhance compliance, facilitate better decision-making, and elevate client service. It will discuss how artificial intelligence is empowering legal professionals to meet the demands of the modern legal landscape.

Artificial Intelligence in Corporate Legal Departments

Similar to other parts of a company, legal departments are under pressure to demonstrate tangible value while managing costs. As leading organizations strive to gain a competitive edge and boost productivity, adopting new legal technology helps achieve these objectives. AI technology is reshaping the delivery of legal services by automating repetitive tasks, streamlining document management and retrieval, processing vast amounts of information, and refining contract review. AI software and systems are capable of more than just executing tasks based on predetermined programming.

Over time, modern AI systems enhance their performance through human review and feedback, enabling legal professionals to make better, data-driven decisions. While AI will never replace human intelligence or legal experts, it will continue to provide invaluable support and transform practices within a law firm or in-house counsel’s profession.

AI tools are already being utilized in various legal practices, including:

-Due Diligence

– Predictive Analytics

– Contract Analysis

– Contract Review

– Legal Document Generation

– e-Discovery

– Legal Research

– Contract Negotiation

– Document Management

Legal professionals report that their teams have been proactive in providing guidance on when, how, or if to use GenAI tools for legal work. A large majority of respondents (85%) state that their company’s legal department has established guidelines, best practices, or operating procedures for using GenAI tools.

1. Streamlining Legal Processes

We all understand the value of a lawyer’s time and the associated costs. Therefore, finding ways to save time in the legal field while maintaining accuracy and compliance is crucial – benefiting both the attorney and the client. Law firms and in-house counsel can assess existing workflows to identify time-consuming tasks, prone to human error, or suitable for automation, and introduce an AI solution to assist.

AI can help streamline vital aspects of legal services, such as comprehensive document review, thorough proofreading, and in-depth legal research. This, in turn, allows regret to dedicate more time to advising and counseling clients. Artificial intelligence tools are adept at handling large data sets (documents, etc.) with high precision, while simultaneously recognizing patterns in word relationships or data to identify key information and detect errors or inconsistencies. It can analyze contracts and other legal documents, extract relevant information, and complete these manual tasks instantly. This not only saves time and reduces the laborious nature of routine tasks but also helps humans evade errors and burnout.

2. Risk Assessment and Compliance

Corporate governance is constantly, presenting complex legal and compliance challenges within an organization. AI systems possess robust functionality to help ensure compliance and pinpoint legal risks by continuously monitoring regulatory changes and correlating them with potential implications for the evolving business. These tools notify the legal team of updates or changes, enabling legal professionals to remain proactive in meeting compliance requirements and make necessary adjustments promptly.

Likewise, artificial intelligence can sift through extensive data (particularly beneficial in due diligence processes) to identify potential risks and offer comprehensive guidance on mitigating them, ultimately averting future disruptions for the legal department and the company’s bottom line.

3. Quality Assurance in Legal Documentation

Utilizing AI for Quality Assurance (QA) and legal reviews is increasingly essential as it meticulously scans and summarizes relevant documents, revealing any discrepancies or inaccurate data findings. It quickly identifies specific clauses, potential risks, and company obligations, saving time and improving the comprehensiveness and accuracy of legal document analysis for litigation and legal professionals.

4. Organizational Efficiency

In today’s legal industry, AI is rapidly becoming a vital tool for staying competitive, especially in the time-consuming task of legal research. Specialized vertical legal language models and AIs, like those found in ContractPodAi’s Leah software, excel in legal research by locating and analyzing essential information from various sources such as articles, statutes, and relevant case law. The AI ​​assists lawyers by identifying authoritative sources, extracting key information, providing document summaries, and offering insights to help legal professionals make better decisions.

5. Strategic Decision-Making

While human judgment and expertise are always essential in legal practice, AI can be leveraged by general counsels to review contracts, capture detailed data, and provide trend analytics to assist in making more-informed decisions. AI can examine past case laws and outcomes to predict risk, compliance issues, and future results, allowing legal professionals to form new strategies based on concrete data. Additionally, AI can aid in managing outside counsel by identifying the best legal representation for a case, thereby saving time and costs.

6 .Reducing Workload and Stress

AI not only relieves redundant, time-consuming in-house staff workload, but also contributes to higher job satisfaction, reduced attorney stress, and minimized work frustration. By AI to perform administrative tasks and offer support in drafting and document analysis, legal professionals can focus on higher-value, strategic duties. This ultimately leads to increased productivity, a healthier work-life balance, and improved job satisfaction without compromising work quality. Leveraging new technology that frees up time and brainpower ultimately contributes to a healthier work-life balance.

7. Enhancing In-House Client Service

AI enables in-house lawyers to focus more on strategic legal advising and less on mundane tasks, leading to improved service for both internal and external clients. The time saved on low-level responsibilities allows sorry to engage more in human-specific activities, such as improving client response times, personalizing client communication, and strategic brainstorming, ultimately leading to better client satisfaction. Additionally, AI equips legal teams with better information and legal research, helping build better cases and ultimately making their clients happy.

Summary

As legal departments in corporations explore the use of AI in the workplace, they will uncover the myriad ways in which AI can aid them in their daily and long-term tasks. A study by Mordor Intelligence revealed that the AI ​​Software Market in the Legal Industry is projected to expand from USD 2.19 billion in 2024 to USD 3.64 billion by 2029.

The integration of AI into various aspects of the legal profession, such as research, analytics, due diligence, compliance, and contract management, is having a significant impact within corporate legal teams. Will AI replace lawyers? No, it will empower them to perform their jobs more effectively, efficiently, and intelligently. The emergence of AI systems places legal departments in an advantageous position to drive profitability, reduce costs, and enhance productivity like never before.

Generative Artificial Intelligence (GenAI) is a branch of AI, including deep learning and machine learning, that uses vast amounts of collected data to generate human-consumable output based on user input. To create the datasets that underlie GenAI tools, large volumes of human -created data were collected and processed into mathematical predictive models. GenAI excels at extensive processing information to recognize, summarize, translate, compare, and predict. Users utilize GenAI to produce original text, images, audio, video, and code.

GenAI tools are revolutionizing the provision of legal services due to their potential impact on various business areas, including content discovery, creation, authenticity, regulations, automation, and the customer and employee experience. Many legal practices already rely on generative artificial intelligence to expedite and improve their work, including the drafting of contracts, trial briefs, legal research, pleadings, discovery requests, deposition questions, and legal marketing materials.

Law.com conducted a survey of 100 law firms to understand their use of generative AI, and 41 firms confirmed their adoption of generative AI, although Law.com noted that the actual number is likely much higher. Even though many of these firms and other companies have established policies, there is also use of individual subscriptions or public services, known as “shadow AI” usage.

The terms AI and GenAI are often used interchangeably, but they serve different functions. Traditional AI models perform specific tasks or solve specific problems based on pre-defined rules and algorithms. GenAI models are not restricted to specific tasks; they are trained on vast amounts of data and can generate entirely new content based on that training. This makes the potential of generative AI very compelling for the legal field to expedite and enhance its role in content creation.

GenAI Provides the Following Key Advantages to In-House Legal Teams

Efficiency

Remaining competitive in today’s legal landscape entails finding ways to create more efficiencies that will continue to grow the business. GenAI can be utilized to expedite time-consuming legal research tasks, such as locating relevant laws and rulings, searching through case law databases, and reviewing evidence. Once it locates the information, it can then convert it into the requested format (legal documents, contracts, and letters).

AI can also streamline document management and contract review. AI can quickly identify errors and inconsistencies, as well as draft preferred contract language. For instance, a global venture capital firm initiated a pioneering GenAI legal contract management endeavor with support from ContractPodAi and PwC. Leah Legal, ContractPodAi’s GenAI solution, demonstrated its ability to extract complex logic-oriented data points and conduct sophisticated analysis across nearly 16,500 contract pages with over 98% accuracy.

Risk Assessment and Compliance

For example, the legal team at the Southeast Asian e-commerce business used generative AI to accelerate its contract review process and to identify common risks across different agreements. The team estimates that contract review is already 20% to 30% faster than its standard workflow .

GenAI is capable of digesting continually changing regulatory laws and requirements and then highlighting any disparities that do not align with the company. As the models continue to learn, they can pinpoint compliance gaps, which helps leaders adjust to meet new or changing obligations.

Data Augmentation:

Generate realistic synthetic data that mimics real-world data, which can be particularly beneficial in legal situations sensitive involving data, as it enables legal departments to conduct thorough analyzes without risking the confidentiality of the data.

Scenario Simulation and Analysis:

Produce data representing potential scenarios, allowing legal professionals to assess the impact of various risk factors and address vulnerabilities before they manifest.

Predictive Modeling:

Utilize learned patterns and training to forecast future outcomes, providing valuable insights for legal professionals to identify potential risks and predict court decisions.

Decision-making:

Provide recommendations based on simulated outcomes and predictive analytics.

Preparing for AI Integration:

According to a recent study by ContractPodAi, over half of in-house legal professionals (51%) report that their company’s leadership encourages the use of GenAI tools, while more than a third (35%) require it as of January 2024. Successfully integrating GenAI into an organization requires careful consideration, planning, and evaluation to yield positive results for the business.

Best Practices for Integrating AI:

Assess Legal Needs

When integrating AI into business operations, it is essential to meticulously evaluate the legal requirements to ensure compliance with relevant laws and regulations, including data privacy laws, intellectual property rights, and industry-specific regulations, as well as the influx of new laws and regulations. governing AI usage.

Identify High-Impact Areas for AI Applications:

AI can support various legal practice areas, and it is crucial to identify the key areas where GenAI can play a significant role in achieving operational goals, such as drafting communications, legal research, narrative summaries, document review, contract creation, due diligence, discovery review, and contract redlines.

Evaluate Current Workflows and Technology Infrastructure:

Assess how GenAI will integrate into existing workflows and whether the current technology infrastructure supports its implementation without causing disruptions. Any changes made should adhere to industry and internal regulations and standards.

Set Objectives for GenAI Adoption:

It is important to clearly define the goals and consider critical variables, such as the cost of the technology, budget, scalability, ease of use, and compatibility with the current technology infrastructure.

Develop a Phased Approach:

Taking a phased approach to integration can help users adapt more seamlessly. Communication with the company should be open and transparent, providing employees with the necessary information to understand the positive impact of GenAI integration and the defined goals.

Implementing GenAI in Legal Departments:

A. Technical Setup and Compliance

The implementation of GenAI in legal departments requires consideration of its legal and regulatory implications. Establish a framework outlining how the legal department will utilize GenAI, identify potential risks, and involve stakeholders in developing company policies and procedures, including ethical standards, responsibilities, privacy, non-discrimination, and compliance with applicable laws.

B. Employee Training and Change Management

The field of technology is constantly changing. Laws and regulations are frequently evolving. When combined, these factors create ongoing and potentially overwhelming changes. Therefore, it is crucial for legal teams to continuously adapt their use of GenAI and the accompanying training. Tools and algorithms are always progressing, making it essential to stay current in order to fully utilize the capabilities of GenAI. Initial and ongoing training helps all users grasp best practices, effectively integrate GenAI into their work, adopt new methods, and understand privacy and ethical considerations.

Like any new technology, there may be resistance, confusion, and pushback. However, a few straightforward steps can help overcome obstacles and set your legal team up for success.

An illustrated representation outlining the process of preparing a legal team for success

Ethical and Legal Concerns

GenAI tools offer numerous advantages. In fact, a recent report by PwC revealed that 70% of CEOs believe that GenAI will significantly impact the way their companies generate, deliver, and capture value over the next three years. However, it is important not to overlook ethical and legal considerations.

All software and technology should undergo an initial risk assessment to identify potential harm, appropriateness of input, reliability of outputs, and effectiveness of practices. Legal professionals need to ensure that all outputs are completely reliable and accurate. When reviewing the generated content, the following aspects must be taken into account:

Bias and fairness

GenAI may unintentionally draw biased historical data, potentially leading to unfair outcomes and discrimination.

Accuracy

Inaccurate GenAI-generated content is referred to as “hallucinations”. Lawyers must carefully review any content suggested or edited by GenAI.

Privacy

GenAI technology relies on vast amounts of data, often including highly sensitive and confidential information. Attorneys must ensure that GenAI systems comply with strict data privacy regulations and that the data is only used for its intended purposes.

Accountability

Lawyers must be proactive and fully involved when incorporating GenAI into their legal practices. GenAI technology should complement their work rather than replace it.

Ethical Aspects of GenAI

As we have discussed, the deployment of AI tools and technology carries significant risks and potential legal repercussions, particularly in the realm of law. The European Commission has established an Expert Group on AI to develop Ethical Guidelines for Trustworthy AI., additionally the United Nations has formed an AI and Global Governance Platform to address the global policy challenges presented by AI.

At the organizational level, leadership must establish GenAI governance, incorporating:

• Clear policies that direct and embed ethical practices across all areas using AI
• Strategies for negotiating AI-specific contractual terms and addressing potential AI failures
• Designation of individuals to oversee AI governance and provide reports to management
• Risk assessments and audits of AI models to ensure compliance with ethical standards

Transparency and accountability in AI not only protect against potential mishaps and legal consequences but also help adhere to company policies by ensuring that AI algorithms are thoroughly tested and explainable. This also builds trust among users and clients. At an individual level, collaborating with existing data privacy teams can provide an advantage in responding promptly to generative AI issues, as many of the tools and techniques learned by data privacy professionals are equally applicable to generative AI.

Spotlight on Leah Legal

Leah Legal, developed by ContractPodAi, is specifically designed for legal and compliance scenarios, utilizing state-of-the-art Large Language Models (LLMs). Leah, your customized GenAI solution, simplifies the execution of legal responsibilities, making them faster, more intelligent, and completely reliable. It incorporates ethical guardrails and rigorous testing, aligning with your organization’s standards to instill trust in AI solutions. Leah promotes strategic thinking and offers real-time, precedent-based legal analysis.

Leah provides a range of specialized legal modules equipped with cutting-edge GenAI and rigorously tested for maximum accuracy. Each module is supported by customized frameworks for specific legal tasks to ensure efficiency and dependable results for your unique workflow. The modules include Extract, Redline, Discovery, Deals, Claims, Playbook, Helpdesk, and Draft.

Leah is tailored specifically for contract management and legal operations, including contract negotiations. Within minutes, she can deliver results that significantly enhance your legal workflows:

• Examine your contracts and establish a record
• Recognize critical clauses, compare them with your historical data, and emphasize relevant insights to expedite and enhance negotiations
• Discover advantageous language from your previous legal documents, propose evidence-based counterpoints, and notify you of potential risks based on your established legal framework
• Offer proactive guidance based on successful previous negotiations
• Recommend clauses, terms, and edits that align with your company’s goals and proven strategies
• Provide insight into all your vendor and customer contract data
• Speed ​​up your negotiations with real-time data driven by predictive analytics, presented in a visual dashboard

The Future of GenAI in the Legal Field

Legal professionals are realizing the advantages of employing AI in their field and acknowledge its significance for the future. To stay competitive and enhance efficiency, GenAI must be adopted and comprehended. The future of GenAI will continue to bring progress in both application and function, leading to changes and shifts in the way legal professionals operate.

More intricate research applications, including case search capabilities, case citations, and strategic decision-making, will allow lawyers to dedicate time to other advanced tasks. Traditional legal work will be streamlined, leading to improved accuracy and overall job satisfaction.

On the other hand, clients will be able to leverage GenAI by selecting lawyers and firms based on more precise criteria such as success rates, client feedback, expertise, and more. Cultivating trustworthy, confident relationships will become more straightforward and require less guesswork.

The realm of predictive analytics will expand and become more advanced. In-house legal teams and law firms will be able to more precisely anticipate service costs, enabling better pricing and smoother agreements.

GenAI is an Enduring Presence

Whether or not legal professionals embrace GenAI, it is here to stay. How can legal professionals fully accept this advanced technology? Be open to change and embrace a growth-oriented mindset. Understand AI’s potential and acknowledge its limitations. Learn how it can help you perform your job more effectively and efficiently with greater job satisfaction. Even the author – an early adopter of the technology and an avid user in the legal field – has discovered numerous ways in which generative AI expedites legal work and makes it more efficient.

Ensure your company is investing in suitable software and technology and request involvement in its implementation. Pursue additional educational opportunities related to it. Ensure that GenAI is used fairly, accurately, and in compliance with the law to safeguard your rights, the company’s reputation, and your clients’ relationships. Last, and perhaps most importantly, always uphold the highest standards of professionalism and ethics.

One year prior, on July 21, 2023, seven prominent AI companies—Amazon, Anthropic, Google, Inflection, Meta, Microsoft, and OpenAI—made pledges to the White House regarding eight voluntary commitments aimed at the safe and trustworthy development of AI.

These commitments included pledges to enhance the testing and transparency of AI systems, as well as to share information about potential risks and harms.

On the anniversary of these commitments, MIT Technology Review reached out to the AI companies that signed them for insights into their progress thus far. Their responses indicate that while there has been some positive movement in the tech sector, there are significant caveats.

The voluntary commitments emerged during a period when generative AI enthusiasm was arguably at its peak, with companies competing to launch larger and more advanced models than their rivals. Simultaneously, issues such as copyright disputes and deepfakes began to surface. A prominent group of influential tech figures, including Geoffrey Hinton, also expressed concerns about the existential risks that AI could pose to humanity. Suddenly, the discourse surrounding the urgent need for AI safety intensified, putting pressure on regulators globally to take action.

Up until recently, the development of AI resembled a chaotic environment. Historically, the US has hesitated to impose regulations on its tech giants, preferring instead to let them self-regulate. The voluntary commitments exemplify this approach: they represent some of the initial prescriptive guidelines for the AI industry in the US, but their non-enforceable and voluntary nature remains.

Since then, the White House has issued an executive order that expands these commitments and extends them to other tech companies and government entities.

“One year later, we observe some positive practices regarding their own products, but they are far from where we need to be concerning effective governance or protection of broader rights,” states Merve Hickok, president and research director of the Center for AI and Digital Policy, who evaluated the companies’ responses upon MIT Technology Review’s request. Hickok adds that many of these companies continue to make unsubstantiated claims about their offerings, asserting that they can surpass human intelligence and capabilities.

A notable trend from the companies’ responses is their increased focus on technical solutions like red-teaming (where humans assess AI models for vulnerabilities) and implementing watermarks for AI-generated content.

However, it remains uncertain what changes can be attributed to the commitments and whether these companies would have adopted such measures independently, notes Rishi Bommasani, society lead at the Stanford Center for Research on Foundation Models, who also reviewed the responses for MIT Technology Review.

A year represents a significant duration in the AI landscape. Since the signing of the voluntary commitments, Inflection AI founder Mustafa Suleyman has departed from the company to join Microsoft and spearhead its AI initiatives. Inflection has opted not to comment on this.

“We appreciate the strides that leading companies have made in adhering to their voluntary commitments alongside the requirements of the executive order,” remarks Robyn Patterson, a White House spokesperson. Nevertheless, Patterson emphasizes that the president continues to urge Congress to enact bipartisan AI legislation.

In the absence of comprehensive federal laws, the best course of action for the US at this moment is to insist that companies uphold these voluntary commitments, according to Brandie Nonnecke, director of the CITRIS Policy Lab at UC Berkeley.

It is important to remember that “these are still companies that are largely responsible for determining their own evaluation criteria,” observes Nonnecke. “Thus, we must carefully consider whether they are… rigorously verifying themselves.”

Here’s our evaluation of the progress made by AI companies in the past year.

Commitment 1

The companies agree to conduct both internal and external security testing of their AI systems prior to their launch. This testing, which will involve independent experts, aims to address critical AI risks, such as biosecurity and cybersecurity, along with their wider societal impacts.

All the companies, except for Inflection which chose not to provide comments, report that they undertake red-teaming exercises that engage both internal and external testers to identify flaws and risks in their models. OpenAI states that it has a distinct preparedness team that assesses models for cybersecurity threats, as well as chemical, biological, radiological, and nuclear risks, and for scenarios where a sophisticated AI system may lead a person to act in harmful ways.

Anthropic and OpenAI mention they also collaborate with external experts in their testing prior to launching new models. For instance, during the launch of Anthropic’s latest model, Claude 3.5, the company involved experts from the UK’s AI Safety Institute in pre-launch testing. Anthropic has additionally permitted METR, a research nonprofit organization, to conduct an “initial exploration” into Claude 3.5’s autonomy capabilities.

Google states that it also performs internal red-teaming to evaluate the limitations of its model, Gemini, in relation to election-related content, societal risks, and national security issues.

Microsoft mentions that it has collaborated with third-party evaluators at NewsGuard, an organization promoting journalistic integrity, to assess risks and reduce the threat of misuse of deepfakes in Microsoft’s text-to-image tool. In addition to red-teaming, Meta reports that it has assessed its newest model, Llama 3, to gauge its effectiveness in various risk areas such as weapons, cyberattacks, and child exploitation.

However, regarding testing, it’s insufficient for a company merely to indicate that it is taking action, notes Bommasani. For instance, Meta, Amazon, and Anthropic indicated they had partnered with the nonprofit Thorn to address the dangers to child safety posed by AI. Bommasani expressed a desire to see more detailed information on how the companies’ interventions are effectively reducing those threats.

“It should be evident to us that it’s not just companies engaging in activities, but that those activities yield the intended results,” Bommasani states.

RESULT: Positive. The initiative for red-teaming and assessing a variety of risks is both good and necessary. Nonetheless, Hickok would have appreciated if independent researchers had broader access to the companies’ models.

Commitment 2

The companies pledge to share knowledge across the industry and with governments, civil society, and academic institutions regarding the management of AI risks. This encompasses best safety practices, information on efforts to bypass safeguards, and technical cooperation.

Following their commitments, Anthropic, Google, Microsoft, and OpenAI established the Frontier Model Forum, a nonprofit designed to encourage dialogue and actions concerning AI safety and accountability. Amazon and Meta have also joined this initiative.

Engagement with nonprofits that the AI companies themselves funded might not align with the spirit of the voluntary commitments, according to Bommasani. However, the Frontier Model Forum could facilitate collaboration among these companies, enabling them to exchange safety information that they typically cannot share as competitors, he notes.

“Even if they won’t be transparent with the public, one expectation could be for them to collectively devise measures to truly mitigate risks,” Bommasani suggests.

All seven signatories are also members of the Artificial Intelligence Safety Institute Consortium (AISIC), launched by the National Institute of Standards and Technology (NIST), which formulates guidelines and standards for AI policy and the evaluation of AI performance. This consortium includes a mixture of public and private sector participants. Representatives from Google, Microsoft, and OpenAI are also part of the UN’s High-Level Advisory Body on Artificial Intelligence.

Many of the labs emphasized their research partnerships with academic institutions. For example, Google is involved in MLCommons, where it collaborated with scholars on a cross-industry AI Safety Benchmark. Google also states that it actively contributes tools and resources, including computing credits, to initiatives like the National Science Foundation’s National AI Research Resource pilot, which aims to democratize AI research in the United States. Meta adds that it is a member of the AI Alliance, a network of companies, researchers, and nonprofits that specifically focuses on open-source AI and the developer community.

Numerous companies have also contributed to guidelines set forth by the Partnership on AI, another nonprofit initiated by Amazon, Facebook, Google, DeepMind, Microsoft, and IBM, regarding the deployment of foundational models.

RESULT: More effort is required. Enhanced information sharing is a beneficial development as the industry strives to collaboratively ensure that AI systems are safe and reliable. Nonetheless, it remains uncertain how much of the promoted activity will result in substantial changes and how much is mere superficiality.

Commitment 3

The companies vow to invest in cybersecurity and measures to mitigate insider threats in order to safeguard proprietary and unreleased model weights. These model weights are the core component of an AI system, and the companies concur that it is crucial that these weights are disclosed only when appropriate and with a full consideration of security risks.

Many companies have put new cybersecurity protocols in place over the past year. For instance, Microsoft has initiated the Secure Future Initiative to combat the escalating scale of cyberattacks. The company claims that its model weights are encrypted to lessen the risk of model theft and that it enforces strict identity and access controls when deploying highly capable proprietary models.

Similarly, Google has introduced an AI Cyber Defense Initiative. In May, OpenAI announced six new measures it is implementing to enhance its existing cybersecurity practices, such as extending cryptographic protections to AI hardware. It also operates a Cybersecurity Grant Program that allows researchers access to its models in order to develop cyber defenses.

Amazon stated that it has implemented specific measures against threats related to generative AI, including data poisoning and prompt injection, where an individual uses prompts to instruct the language model to disregard its previous instructions and safety safeguards.

Just a few days after making these commitments, Anthropic shared details about its safeguards, which consist of standard cybersecurity practices like regulating access to the models and sensitive resources such as model weights, as well as monitoring and managing the third-party supply chain. The organization also collaborates with independent evaluators to assess whether the controls it has established meet its cybersecurity requirements.

RESULT: Positive. All companies indicated that they have instituted additional measures to secure their models, even though there seems to be little agreement on the most effective methods to protect AI models.

Commitment 4

The companies agree to support third-party discovery and reporting of vulnerabilities within their AI systems. Some problems may remain even after an AI system is launched, and an effective reporting system allows for quicker identification and resolution.

For this commitment, one prevalent approach has been the establishment of bug bounty programs that reward individuals who identify flaws in AI systems. Anthropic, Google, Microsoft, Meta, and OpenAI all have such programs for their AI systems. Anthropic and Amazon also mentioned having forms on their websites where security researchers can submit reports of vulnerabilities.

It may take years for us to learn how to perform third-party audits effectively, says Brandie Nonnecke. “It’s not solely a technical challenge; it involves socio-technical factors. It generally takes years to figure out both the technical and socio-technical standards of AI, and it’s a complex and difficult process,” she explains.

Nonnecke expresses concern that the first companies to conduct third-party audits may set unfavorable examples for addressing the socio-technical risks associated with AI. For instance, audits might define, assess, and tackle certain risks while neglecting others.

RESULT: More effort is needed. While bug bounty programs are beneficial, they are far from being exhaustive. New regulations, like the EU’s AI Act, will mandate tech companies to perform audits, and it would have been advantageous for tech companies to showcase successful audit examples.

Commitment 5

The companies pledge to create robust technical mechanisms that inform users when content is generated by AI, such as a watermarking system. This action promotes creativity with AI while minimizing the risks of fraud and deception.

Many of the companies have developed watermarks for AI-generated content. For instance, Google introduced SynthID, a watermarking tool for images, audio, text, and video created by Gemini. Meta offers Stable Signature for images and AudioSeal for AI-generated speech. Amazon now incorporates an invisible watermark on all images produced by its Titan Image Generator. OpenAI also applies watermarks in Voice Engine, its custom voice model, and has created an image-detection classifier for images generated by DALL-E 3. Anthropic was the only company without a watermarking tool, as watermarks are mainly associated with images, which aren’t supported by the company’s Claude model.

All the companies, aside from Inflection, Anthropic, and Meta, are part of the Coalition for Content Provenance and Authenticity (C2PA), an industry alliance embedding information about when content was produced and whether it was generated or edited by AI into an image’s metadata. Microsoft and OpenAI automatically attach the C2PA’s provenance metadata to images generated with DALL-E 3 and videos created with Sora. Although Meta is not a member, it has announced its use of the C2PA standard to identify AI-generated images on its platforms.

The six companies that signed the commitments show a “natural preference for more technical solutions to address risk,” says Bommasani, “and indeed, watermarking specifically tends to lean in this direction.”

“The key question is: Does [the technical solution] genuinely make progress and tackle the fundamental social issues that prompt our desire to know whether content is machine-generated or not?” he adds.

RESULT: Positive. Overall, this is an encouraging outcome. Although watermarking remains in the experimental phase and is still inconsistent, it’s beneficial to observe research in this area and a commitment to the C2PA standard. It’s certainly better than nothing, especially during a hectic election year.

Commitment 6

The companies pledge to disclose their AI systems’ capabilities, limitations, and suitable and unsuitable applications. This disclosure will include both security and societal risks, such as impacts on fairness and bias.

The commitments made by the White House allow for considerable interpretation. For instance, companies can technically satisfy this public reporting requirement with varying degrees of transparency, as long as they make some effort in that direction.

The most frequently proposed solutions by tech firms in this category were model cards. Although each company may refer to them differently, essentially they serve as a type of product description for AI models. These cards can cover aspects ranging from model capabilities and limitations (including performance concerning benchmarks in fairness and explainability) to issues of veracity, robustness, governance, privacy, and security. Anthropic has stated it also examines models for potential safety concerns that could emerge later.

Microsoft has released an annual Responsible AI Transparency Report, which sheds light on how the company develops applications utilizing generative AI, makes decisions, and manages the deployment of these applications. The company also claims it provides clear notifications about where and how AI is implemented in its products.

Meta, too, has introduced its new Llama 3 model accompanied by a detailed and thorough technical report. Additionally, the company has updated its Responsible Use Guide, which contains instructions on how to effectively and responsibly use advanced large language models.

RESULT: Progress is still required. One area for improvement identified by Hickok is for AI companies to enhance transparency concerning their governance frameworks and the financial ties between corporations. She also expressed a desire for companies to be more forthcoming about data origins, model training methods, safety incidents, and energy consumption.

Commitment 7

The companies have vowed to emphasize research on the societal risks posed by AI systems, such as preventing harmful bias and discrimination and safeguarding privacy. The historical evidence surrounding AI highlights the pervasive and insidious nature of these threats, and the companies are committed to developing AI that alleviates them.

Tech companies have been active in the safety research arena, integrating their findings into products. Amazon has established safeguards for Amazon Bedrock that can identify hallucinations and implement safety, privacy, and truthfulness measures. Anthropic claims to maintain a dedicated research team focused on societal risks and privacy. Over the past year, the company has released research addressing deception, jailbreaking, methods to combat discrimination, and emergent capabilities, including models’ ability to manipulate their code or engage in persuasion.

OpenAI asserts that it has trained its models to avoid generating hateful content and to decline requests related to hateful or extremist material. Its GPT-4V model is specifically trained to reject many inquiries that involve stereotypes. Google DeepMind has also conducted research to assess dangerous capabilities and has studied potential misuses of generative AI.

All these companies have invested significant resources into this area of research. For instance, Google has dedicated millions of dollars to establish a new AI Safety Fund aimed at enhancing research in this field through the Frontier Model Forum. Microsoft has pledged $20 million in computing resources to support research into societal risks via the National AI Research Resource and launched its own AI model research accelerator program for academia, called the Accelerating Foundation Models Research initiative. The company has also appointed 24 research fellows focusing on AI and societal issues.

RESULT: Very good. This commitment is relatively easy for the signatories, as they represent some of the largest and wealthiest corporate AI research laboratories globally. While increased research on AI system safety is a positive advancement, critics argue that the emphasis on safety research diverts attention and funding from addressing more immediate issues like discrimination and bias.

Commitment 8

The companies have committed to creating and implementing advanced AI systems aimed at tackling some of society’s most pressing challenges. From cancer detection to combating climate change and beyond, AI—when managed properly—has the potential to significantly contribute to prosperity, equality, and security for everyone.

Since making this pledge, tech companies have addressed a variety of issues. For example, Pfizer utilized Claude to analyze trends in cancer treatment research after collecting pertinent data and scientific information, while Gilead, a U.S.-based biopharmaceutical firm, employed generative AI from Amazon Web Services to conduct feasibility studies on clinical trials and evaluate data sets.

Google DeepMind has established a particularly strong track record in providing AI tools that assist scientists. For instance, AlphaFold 3 is capable of predicting the structure and interactions of all life forms’ molecules. AlphaGeometry can solve geometry problems at a level that compares favorably to the world’s best.

Microsoft has utilized satellite imagery and artificial intelligence to enhance wildfire responses in Maui and to identify populations at risk from climate change, aiding researchers in uncovering threats such as hunger, forced relocations, and health issues.

On the other hand, OpenAI has revealed collaborations and financial support for various research initiatives, including one that examines the safe usage of multimodal AI models by educators and scientists in laboratory environments. Additionally, it has provided credits to assist researchers in utilizing its platforms during clean energy development hackathons.

Generally, some advancements in employing AI to enhance scientific discoveries or forecast weather phenomena are genuinely thrilling. While AI companies have yet to use AI to avert cancer, that represents a significant expectation.

In summary, there have been positive transformations in AI development, such as implementing red-teaming methodologies, watermarks, and innovative approaches for the industry to exchange best practices. However, these improvements are merely a few innovative technical responses to the complex socio-technical challenges associated with AI harm, requiring much more effort. A year later, it is peculiar to observe commitments addressing a specific kind of AI safety focused on theoretical risks, like bioweapons, while neglecting to mention consumer protection, nonconsensual deepfakes, data privacy, copyright issues, and the environmental impact of AI systems. These omissions seem peculiar in today’s context.

The brief November 2023 boardroom coup that ousted OpenAI CEO Sam Altman showcased both the potential and limitations of OpenAI’s unique governance model, wherein the leading AI lab was (at least temporarily) governed by a nonprofit board of directors that could (and did, albeit briefly) act in ways that jeopardized the company’s future and profitability.

However, the board’s attempt to reinforce its authority was short-lived. Altman made a return as CEO a week after his termination, and the board members who voted for his dismissal, including OpenAI co-founder and chief scientist Ilya Sutskever, ultimately exited the organization.

The situation surrounding Altman brings forth several inquiries regarding the function of unconventional governance models—specifically, those diverging from standard for-profit corporate structures—in the evolution of AI. Given the customary predominance of profit-driven corporate models in the tech sector, the debate on whether commercial AI would benefit from a nonprofit framework would be a theoretical one, but for the notable fact that two leading AI laboratories—OpenAI and Anthropic—have opted against the conventional for-profit model (which has led to an increasing volume of insightful academic analysis).

Both organizations made this decision due to explicit worries regarding AI safety, based on the belief that a sole focus on profits might lead AI developers to choose unsafe paths if such choices yield greater financial gain. Thus, it deserves examination whether unconventional corporate governance can meet the objectives it is expected to achieve.

In this context, we intend to outline the landscape of corporate governance within the AI sector, critically assess whether nontraditional governance can effectively address the unique risks associated with AI, and propose policy recommendations that will assist these alternative governance frameworks in aligning AI development with broader societal interests.

The Dangers of AI

According to their own statements, the two foremost AI labs that have chosen not to function as conventional, for-profit entities made that choice primarily due to concerns related to AI safety.

The organizational structure of AI laboratories poses a significant policy consideration since the advancement of increasingly sophisticated AI technologies carries considerable externalities, both beneficial and detrimental. On the positive side, AI has the potential to boost productivity and drive technological progress. In the most optimistic outlooks, it could herald a time of post-material wealth. Therefore, society should aim to foster those positive innovation outcomes as much as possible.

Conversely, AI also poses considerable social risks. Some implications are relatively minor and localized, such as the damage a specific AI system might cause to an individual—for example, an AI that dispenses poor health guidance or slanders a third party. Others are more widespread, such as the hazards of AI being utilized to disseminate misinformation and propaganda on a large scale or exacerbate surveillance and job displacement. At the most severe end of the spectrum, AI raises various “existential” dangers, whether by enabling malicious entities to create weapons of mass destruction or by autonomous AI systems possibly acting in ways that could harm humanity as a whole.

Conventional regulation may find it challenging to tackle the threats posed by AI. The existing gap in expertise between regulators and the entities they oversee may be even more pronounced in this swiftly changing domain than in other sectors. The issue of regulatory capture could be particularly acute because individuals outside the field may not fully grasp the risks involved or take them seriously. Since AI research can be conducted globally, national regulators may struggle to rein in AI companies that can operate beyond their jurisdiction. Perhaps most alarmingly, governments might become the most perilous actors in this scenario if they engage in an arms race, given the clear military ramifications associated with AI. Governments eager to harness AI’s capabilities may lack the motivation to regulate its potentially harmful aspects.

What Nontraditional Corporate Governance Can Achieve

Given that traditional regulation is challenging due to the unique and potentially disastrous risks associated with AI, there is hope that self-regulation by AI developers can help mitigate those dangers. The objective is to align the interests of companies and their management with societal goals, seeking to harness the remarkable benefits of AI while steering clear of catastrophic risks.

Regrettably, conventional for-profit corporations appear ill-equipped to exercise sufficient self-restraint in mitigating social risks. When faced with a choice between safety and profit, the norm of maximizing shareholder wealth prevailing in U.S. corporate law (particularly in Delaware, where most large U.S. companies are incorporated) suggests that increasing financial returns for shareholders should take precedence. Although doctrines like the business judgment rule provide safety-conscious managers with considerable discretion to weigh social risks, various legal and informal norms and practices still push managers to prioritize profits.

Nonprofit organizations, as their name indicates, offer a pathway to shift away from a profit-centric focus. Instead, they emphasize mission-driven objectives, such as promoting social, educational, or charitable endeavors. To retain nonprofit status, these organizations must comply with specific legal stipulations, such as prohibiting the distribution of profits to private individuals or shareholders and ensuring that their activities primarily benefit the public. Any surplus income must be reinvested in the organization’s goals, reinforcing a commitment to long-term societal advantages rather than short-term financial rewards.

Nonetheless, nonprofits also face their own limitations as a structure for companies engaged in AI development. Excluding equity investors will place them at a significant disadvantage in securing the substantial capital needed for AI research and development, which may also hinder their ability to attract top talent in the field.

They might be excessively cautious, causing delays in realizing the potential benefits from AI innovations. Additionally, nonprofits may struggle with accountability issues since their boards are generally self-selected, with the current board determining its successors, and they lack the mechanisms of shareholder voting and lawsuits that impose at least some checks on for-profit boards.

Recently, there has been considerable focus on hybrid legal structures for social enterprises that lie between for-profits and nonprofits. Benefit corporations represent a prominent new legal category designed to capture some benefits of both types. However, benefit corporations lack robust governance mechanisms to ensure that profit motives do not overpower social objectives (such as preventing human extinction).

They depend on purpose statements, fiduciary duties, and disclosure to foster a commitment to public interests beyond mere profit. However, as currently formulated, companies can easily use public interests as a façade while prioritizing profit, and none of these mechanisms will effectively restrain their actions or impede their momentum.

In this context, both OpenAI and Anthropic have been experimenting with more complex individualized hybrid structures that appear to offer greater promise than benefit corporations. Each organization has established a for-profit entity capable of attracting equity investors, along with a nonprofit entity that maintains overall control. OpenAI’s structure is particularly intricate. The organization started as a nonprofit, hoping that donations would provide the necessary capital, but the amount raised fell short. In response, OpenAI created a for-profit LLC under Delaware law to facilitate investment opportunities and offer financial returns, albeit with a cap on those returns.

There are multiple layers of entities connecting the nonprofit and the for-profit LLC, including a holding company and a management company. Nevertheless, the ultimate authority still rests with the nonprofit corporation’s board, which is self-perpetuating, overseeing the for-profit LLC.

Anthropic’s organizational structure is not exactly the same, but it shares similarities and aims at the same fundamental concept. Anthropic operates as a Delaware public benefit corporation, which we previously mentioned has minimal impact on its own. More intriguingly, it has created a long-term benefit trust overseen by five independent directors who possess expertise in AI safety, national security, public policy, and social enterprise. This trust holds a special category of Anthropic shares, granting it the authority to appoint certain directors to Anthropic’s board. Within four years, this trust will select a majority of the board members at Anthropic. The trust’s mission aligns with that of the benefit corporation, specifically to responsibly develop and maintain AI for the betterment of humanity.

For both entities, the expectation is that the controlling nonprofit will insulate the business from a profit-driven focus that could compromise the essential goal of ensuring the product’s safety, while still drawing enough investment to enable the company to lead in AI development. This framework protects the nonprofit board, which holds ultimate authority, from the pressures exerted by shareholders demanding financial returns. In contrast to for-profit corporations, shareholders cannot elect nonprofit directors or trustees, nor is there a risk of lawsuits from shareholders for breaches of fiduciary duty. Unlike the statutes governing benefit corporations, this issue directly addresses governance: determining who wields decision-making power and who gets to select those decision-makers.

Although unconventional, the governance models of OpenAI and Anthropic are not entirely unique. They have counterparts with established histories. For example, nonprofit foundations have frequently owned and operated for-profit companies in various countries. While foundation enterprises are rare in the U.S. due to discouraging tax regulations, they are more common in parts of Europe, notably Denmark, where the regulations are more favorable.

The available evidence regarding the performance of foundation enterprises is varied but predominantly positive. In terms of profit and other indicators of financial and economic success, research generally indicates (though not always) that they match or even outperform similar standard for-profit firms, often assuming lower levels of risk and demonstrating greater long-term stability. Limited evidence regarding social performance suggests that foundation enterprises either perform comparably or better than traditional for-profits in generating social benefits and mitigating potential harms.

Researchers studying enterprise foundations have noted that these findings challenge the prevailing views among corporate governance scholars about the advantages of for-profit organizational models in incentivizing focus and ensuring accountability. Directors or managers of foundation enterprises operate independently from shareholders and donors. Their boards are self-perpetuating, and without shareholders (or equivalent parties) to step in, there is no one to sue if managers breach their fiduciary obligations.

This separation from accountability mechanisms might suggest that foundation enterprises may show less efficiency and financial success; however, the evidence does not seem to support this notion. Academics propose that this insulation from accountability could enable managers to more thoroughly consider long-term outcomes and stakeholder interests, even when such considerations might jeopardize profits. Nonetheless, this detachment may pose challenges in holding boards accountable if they stray from their mission due to self-interest, incompetence, or a misinterpretation of that mission.

OpenAI, Anthropic, and foundation enterprises hone in on the board and its governance, concluding that the board should be self-governing. In emphasizing who holds control over the board, they bear resemblance to alternative corporate governance models. Stakeholder governance structures, for instance, empower stakeholders other than shareholders to appoint some or all board members. This could include employees, as seen in worker cooperatives, or customers, as in credit unions and insurance mutuals.

It could also involve suppliers, such as in agricultural cooperatives. In the context of AI developers, one might envision AI safety organizations having the power to appoint certain board members. Similar to OpenAI and Anthropic, these organizations retract the authority of shareholders to choose (some or all) directors. However, instead of completely removing control over the selection process, these alternatives grant that power to different groups of stakeholders, whereas in the OpenAI and Anthropic frameworks, the board itself becomes self-perpetuating.

There are valid reasons to believe that the hybrid governance models of OpenAI and Anthropic might strike a better balance by attracting investment while maintaining a significant emphasis on safe and responsible AI development. Nonetheless, even if the advantages of unconventional AI governance outweigh their drawbacks for a specific lab, it does not ensure that nontraditional AI organizations will fulfill their safety commitments amidst competition from for-profit rivals.

From the standpoint of existential or general social risk, it is ineffective for OpenAI or Anthropic to act conservatively if competitors like Microsoft or Google accelerate their advancements at a rapid pace. The challenge of AI safety stems from it being a significant negative externality; if one organization creates a superintelligent paperclip maximizer, it endangers not just that organization but all of humanity.

Moreover, the competitive landscape is not uniform. For-profit AI firms—promising increased profitability and, consequently, higher stock values and dividends—are likely to attract more investment, which is crucial for success due to the immense expenses associated with data and computing. Of course, nonprofit AI organizations have also secured substantial funding, and OpenAI’s current funding round—a staggering, oversubscribed request of $6.5 billion, which ranks among the largest ever and would appraise the company at an astonishing $150 billion—indicates that there is investor interest even in not-for-profit entities. Nevertheless, even the current funding OpenAI is acquiring may fall short of covering future computation costs.

For-profit AI companies might entice skilled engineers away from nonprofit rivals, either through superior salaries or simply the allure of pursuing the development of grander and more impressive systems at a faster pace. Additionally, engineers who aren’t primarily driven by financial gain and are mindful of AI risks may still find themselves drawn to environments where they can engage with cutting-edge innovations, echoing a sentiment expressed by J. Robert Oppenheimer, the creator of the atomic bomb.

Nonprofits have options to counter these challenges, but their responses will likely necessitate adopting characteristics of their for-profit rivals, potentially undermining the justification for their unique corporate structure. A case in point is OpenAI itself. After Altman was dismissed from the organization, Microsoft swiftly recruited him and OpenAI co-founder Greg Brockman to effectively recreate OpenAI within Microsoft—had Altman remained at Microsoft, it’s probable that many of OpenAI’s top researchers and engineers would have followed him.

Once Altman returned to OpenAI and the board underwent changes, Microsoft obtained a nonvoting position on OpenAI’s board (which it has since relinquished), illustrating a shift in power dynamics favoring the for-profit AI sector.

Over the last year, as Altman has strengthened his influence at OpenAI, the organization has increasingly begun to resemble a traditional tech company in Silicon Valley, aiming to roll out products as rapidly as possible while compromising its alleged commitments to AI safety, according to numerous insiders.

Perhaps most significantly, reports indicate that OpenAI is contemplating the complete transition from its nonprofit status to becoming a for-profit public benefit corporation, wherein Altman would hold a considerable 7 percent equity stake, despite his earlier assertions, including to the U.S. Senate, claiming he had no ownership in OpenAI. (Altman has subsequently refuted the claims regarding his equity stake, labeling the 7 percent figure as “absurd.”) If OpenAI does eventually become a for-profit entity, it would serve as a striking illustration of the challenges faced by nonprofit leading-edge AI laboratories in remaining faithful to their initial objectives. The public benefit company designation would act merely as a superficial cover—offering little defense against profit imperatives overshadowing OpenAI’s mission.

Government “Subsidies” for Unconventional Corporate Governance

Given the hurdles that both traditional regulation and corporate governance present, a combination of the two may be the most effective solution. Corporate governance could enhance regulation, while regulation might promote governance structures that can mitigate the tendency to overlook safety and abandon nonprofit status. This approach could take the form of responsive regulation, a strategy where state regulators involve businesses and stakeholders in a more adaptable and dynamic regulatory process compared to conventional methods.

Regulators could motivate organizations with superior corporate governance in various ways. Entities adhering to a preferred governance model could benefit from reduced regulatory scrutiny. Specific regulatory obligations might be relaxed or waived for organizations with stronger governance frameworks. For instance, if a jurisdiction mandates companies to assess their products for safety, it could afford preferred companies greater flexibility in designing those tests, or scrutinize their testing procedures less frequently.

An extreme interpretation of this strategy would permit only those entities with a preferred governance structure to develop AI, while still subjecting these preferred organizations to regulation (i.e., one should not entirely depend on internal governance as a resolution). The notion of a federal charter for AI developers is one potential method of implementing this. If all AI developers were mandated to obtain a charter from a federal oversight body, that regulator could enforce any governance requirements deemed beneficial and monitor chartered companies, with the authority to revoke a charter if necessary.

Alternatively, businesses with better governance might be prioritized when it comes to receiving government contracts for the development or implementation of AI. In addition to contracts or financial support, another approach for governments to influence private AI development could involve establishing a nongovernmental organization that holds intellectual property (such as trade secrets, copyrights, and patents) accessible to companies that adhere to proper governance and commit to safety protocols.

Reduced regulation or financial incentives through contracts or access to intellectual property for unconventional entity types could somewhat alleviate the concerns surrounding the for-profit competitors mentioned earlier. Such lighter regulations and incentives could at least create a more equitable environment against rivals with greater financial resources and, if substantial enough, could even favor enterprises with more responsible governance.

In extreme cases, if only those with suitable governance frameworks were permitted to develop AI, the issue of competition from more profit-driven firms would be resolved (at least within the jurisdiction enforcing this rule—avoiding the issue by relocating outside the jurisdiction would still pose a challenge).

If regulators were to pursue this approach, a crucial question would arise regarding which governance frameworks would be regarded as favorable. This strategy is only valid if one believes that a governance framework significantly deters irresponsible risk-taking. At best, the effectiveness of the nonprofit/for-profit hybrid governance that OpenAI and Anthropic have tried remains uncertain. In fact, a significant risk associated with nontraditional corporate governance in AI laboratories is that it might mislead regulators into a comfort level that prompts reduced oversight, which could be less than ideal.

Nonetheless, despite the challenges highlighted by the Altman incident, this structure may still hold value, either in its current form or potentially with modifications to address the shortcomings that have come to light.

To support this idea, having a governmental role in evaluating governance structures could create new opportunities to enhance accountability and shield against the pressure to compromise safety for profit, thus tackling concerns that alternative governance models do not truly provide the safety advantages they claim. For example, regulators might require the inclusion of government-appointed directors or board observers.

This could bolster the internal safety benefits of alternative governance models if one agrees that they are currently not fulfilling their intended promise. As previously mentioned regarding the potential of nontraditional governance, the nonprofit model relies on self-sustaining boards, believing that the absence of profit-driven shareholders and investors will empower those in charge.

Other types of stakeholder governance focus on ensuring that non-investor stakeholders play a role in determining the composition of the governing board. Appointing government directors is one method to achieve this, addressing the dilemma of who should represent the public interest. The state bears the ultimate responsibility for safeguarding the public, so it is a reasonable option, although there are numerous challenges related to government control over private businesses.

We would not recommend that government regulators appoint the majority of the board in AI firms, but rather one or a few positions. This could provide regulators with critical insights and a degree of influence in decision-making without granting them complete authority. This approach is akin to proposals for awarding banking regulators a “golden share” in banks of significant systemic importance, although that proposal comes with its own set of controversies. Instead of government-appointed directors, regulators might consider including other stakeholder representatives, such as employee representatives or directors suggested by AI safety organizations.

While discouraging for-profit competitors and potentially introducing internal safety governance mechanisms like government-appointed directors or observers may heighten the risk of stifled innovation, this is a legitimate concern. Nevertheless, a more gradual approach to achieving the ideal scenario envisioned by some may be a worthwhile sacrifice in order to mitigate the risk of truly existential threats.