The New News in AI: 11/4/24 Edition
A curated source of the latest happenings in AI this week.
More happenings in AI this week.
OpenAI’s search engine is live within ChatGPT, AI usage in business doubles in a year per a Wharton study, Americans are “uncertain,”, “interested,” and “worried” about AI, Google uses AI to produce a quarter of its code, Ukraine uses AI for drone warfare, China uses Meta’s Llama for military purposes, three things you can do to stay relevant in an AI world and more.
OpenAI’s search engine is now live in ChatGPT
ChatGPT is officially an AI-powered web search engine. The company is enabling real-time information in conversations for paid subscribers today (along with SearchGPT waitlist users), with free, enterprise, and education users gaining access in the coming weeks.
Rather than launching as a separate product, web search will be integrated into ChatGPT’s existing interface. The feature determines when to tap into web results based on queries, though users can also manually trigger web searches. ChatGPT’s web search integration finally closes a key competitive gap with rivals like Microsoft Copilot and Google Gemini, which have long offered real-time internet access in their AI conversations.
Navigating Generative AI's Early Years – AI Adoption Report - AI at Wharton
(MRM – a report from Wharton. More details in the full report)
From a survey with more than 800 senior business leaders, this report’s findings indicate that weekly usage of Gen AI has nearly doubled from 37% in 2023 to 72% in 2024, with significant growth in previously slower-adopting departments like Marketing and HR. Despite this increased usage, businesses still face challenges in determining the full impact and ROI of Gen AI. Sentiment reports indicate leaders have shifted from feelings of “curiosity” and “amazement” to more positive sentiments like “pleased” and “excited,” and concerns about AI replacing jobs have softened. Participants were full-time employees working in large commercial organizations with 1,000 or more employees.
The report highlights that Gen AI excels in specific tasks such as data analysis, idea generation, and contract drafting, but it is not yet viewed as transformative across all business functions. Future investments will focus on scaling use cases and refining organizational structures to support sustainable AI adoption. “The key to successful adoption will be measurable ROI and adaptable organizational cultures,” the authors note. Furthermore, while investments in Gen AI are expected to grow, the pace of growth is likely to slow as companies seek more targeted and accountable applications.
AI - Between Hesitation and Hope
Americans view GenAI as a powerful force whose full consequences are yet to be seen.
The most expressed emotion is “uncertain” (49%), followed by “interested” (36%) and “worried” (29%).
Women, rural Americans, and those with a low sense of belonging are generally more skeptical and fearful about AI’s impact compared to men, urban residents, and those with a strong sense of community.
Most fear GenAI will make society more distrusting, divided, dependent, and dumb.
Four in five (83%) worry AI will erode trust in news, and 65% fear it will further strain trust among people.
Three in four (76%) believe it will make us lazier—overly reliant on technology for everyday cognitive and intellectual tasks.
Three in five (62%) express concern that AI will lead to a less intelligent society, impacting the development of critical thinking skills.
We see nearly identical attitudes towards Big Tech and government regulation across parties and major groups
Americans’ attitudes towards GenAI fall into five segments that skew towards being doubtful.
Using a cluster analysis, we identify that half of Americans are grouped into Skeptics (21%) and Cautious (28%), groups marked by high levels of concern and uncertainty about GenAI impacts.
Meanwhile, Tech Enthusiasts (14%) and Boosters (16%) are more optimistic, seeing AI as a tool for progress. A substantial number are Indifferent (21%).
Demographic factors influence these segments, with women and rural Americans more likely to be Skeptics or Cautious, while men, urban residents, and those with higher education lean toward Tech Enthusiasts and Boosters.
On questions about the role of government and tech companies, Americans are not polarized by party or demographic.
We see nearly identical attitudes towards Big Tech and government regulation across parties and major groups.
The parties are just 6% apart on whether “GenAI government policies are not designed to help Americans” (Democrats: 67%, Republicans: 73%).
The findings suggest a unique political opportunity for the next administration to take action with bipartisan support.
UNC embraces artificial intelligence as popularity grows: 'Remarkable'
(MRM – an ABC 11 article and video about UNC’s AI initiatives)
CHAPEL HILL, N.C. (WTVD) -- No matter what generation you stepped foot on UNC's campus, the spirit of academia holds true. However, faculty's and students' approaches to age-old questions have changed dramatically with the evolution of artificial intelligence playing a major role in daily functions.
"The thing that comes across, first and foremost, with AI is how excited and enthused everyone is," said Dr. Michael Barker, the Vice Chancellor for Information Technology and Chief Information Officer at UNC.
"I've been really encouraged by the number of different kinds of projects that people have had ideas about and just the energy that seems to be emerging around this," added Dr. Andy Lang, the UNC Associate Dean of IT and Data Analytics.
There's sort of a saying in the AI world that you're not going to be replaced by AI, but you'll be replaced by someone who knows AI. Mark McNeilly, UNC professor
Chancellor Lee Roberts, who discussed AI in remarks during his installation ceremony earlier this month, noted its role in a "rapidly developing world."
An August report from the Digital Educational Council found that 86% of students surveyed used AI regularly in their studies.
"Students are definitely using it," said Mark McNeilly, a Professor of the Practice of Marketing. McNeilly incorporates artificial intelligence in his classes, even teaching an AI entrepreneurship course.
"There's sort of a saying in the AI world that you're not going to be replaced by AI, but you'll be replaced by someone who knows AI. This is why it's crucial that students have AI skills and that faculty have the skills to impart to the students," said McNeilly.
AI's Underwhelming Impact On the 2024 Elections | TIME
Early this year, watchdogs and technologists warned that artificial intelligence would sow chaos into the 2024 U.S. elections, spreading misinformation via deepfakes and personalized political advertising campaigns. Those fears spread to the public: More than half of U.S. adults are “extremely or very concerned” about AI’s negative impacts on the election, according to a recent Pew poll.
Yet with the election one week away, fears of the election being derailed or defined by AI now appear to have been overblown. Political deepfakes have been shared across social media, but have been just a small part of larger misinformation campaigns. The U.S. Intelligence Community wrote in September that while foreign actors like Russia were using generative AI to “improve and accelerate” attempts to influence voters, the tools did not “revolutionize such operations.”
Tech insiders acknowledge 2024 was not a breakthrough year for generative AI in politics. “There are a lot of campaigns and organizations using AI in some way or another. But in my view, it did not reach the level of impact that people anticipated or feared,” says Betsy Hoover, the founder of Higher Ground Labs, a venture fund that invests in political technology.
Does the O-Ring model hold for AIs?
Let’s say you have a production process, and the AIs involved operate at IQ = 160, and the humans operate at IQ = 120. The O-Ring model, as you may know, predicts you end up with a productivity akin to IQ = 120. The model, in short, says a production process is no better than its weakest link.
More concretely, it could be the case that the superior insights of the smarter AIs are lost on the people they need to work with. Or overall reliability is lowered by the humans in the production chain. This latter problem is especially important when there is complementarity in the production function, namely that each part has to work well for the whole to work. Many safety problems have that structure.
The overall productivity may end up at a somewhat higher level than IQ = 120, if only because the AIs will work long hours very cheaply. Still, the quality of the final product may be closer to IQ = 120 than you might have wished.
This is another reason why I think AI productivity will spread in the world only slowly.
Sometimes when I read AI commentators I feel they are imagining production processes of AIs only. Eventually, but I do not see that state of affairs as coming anytime soon, if only for legal and regulatory
reasons.
Furthermore, those AIs might have some other shortcomings, IQ aside. And an O-Ring logic could apply to those qualities as well, even within the circle of AIs themselves. So if say Claude and the o1 model “work together,” you might end up with the worst of both worlds rather than the best.
More than a quarter of new code at Google is generated by AI - The Verge
Google is building a bunch of AI products, and it’s using AI quite a bit as part of building those products, too. “More than a quarter of all new code at Google is generated by AI, then reviewed and accepted by engineers,” CEO Sundar Pichai said on the company’s third quarter 2024 earnings call. It’s a big milestone that marks just how important AI is to the company.
AI is helping Google make money as well. Alphabet reported $88.3 billion in revenue for the quarter, with Google Services (which includes Search) revenue of $76.5 billion, up 13 percent year-over-year, and Google Cloud (which includes its AI infrastructure products for other companies) revenue of $11.4 billion, up 35 percent year-over-year.
Operating incomes were also strong. Google Services hit $30.9 billion, up from $23.9 billion last year, and Google Cloud hit $1.95 billion, significantly up from last year’s $270 million.
Ex OpenAI Researcher: How ChatGPT’s Training Violated Copyright Law
During his tenure, Balaji helped orchestrate OpenAI's massive data collection efforts, which he now believes violated copyright law. He initially didn't question whether the company had legal rights to the data it was collecting. The company's approach was remarkably broad: any content accessible on the internet was considered fair game for training their large language models (LLMs). This included everything from pirated book archives and content behind paywalls to user-generated content from platforms like Reddit and copyrighted materials without explicit permission.
The assumption was simple: if data was published on the internet and freely available, it was considered acceptable for use.
By 2022, Balaji began questioning the legal and ethical implications of OpenAI's data collection methods. He concluded that OpenAI's gathering methods violated copyright law and that technologies like ChatGPT were causing harm to the internet as a whole. This realization led to his departure in August 2024.
"If you believe what I believe, you have to just leave the company," Balaji told The New York Times. He elaborated that the technology he helped create is "destroying the commercial viability of the individuals, businesses, and internet services that created the digital data used to train AI systems."
Workers For Robots - Cremieux Recueil
(A very good read…here are some key slides and points)
In general, studies do tend to conclude that new technology—as opponents of automation have suggested—replaces workers:
When technology replaces workers, it does so by saving costs and potentially increasing productivity, ultimately stimulating the demand for labor. To that end, we should also expect technology to reinstate workers. Across 79 studies, there’s overwhelming agreement about the existence of a reinstatement effect:
This may seem reassuring, but it’s not quite yet until we know about two more things. The first of these things is whether the introduction of technology boosts real incomes. We have that result ready, with data from 33 studies:
The second thing we have to worry about, though, is how replacement and reinstatement come together to affect net employment. Across 89 studies, we get the most ambiguous set of findings yet:
To wrap this up, a few findings stand out:
Technology displaces labor and increases the demand for labor, and this tends to have negligible effects on net employment.
There’s more displacement for low-skilled, production, and manufacturing work.
There’s not much reason to think blue collar workers will remain displaced.
OpenAI warns people might become emotionally reliant on its ChatGPT voice mode
OpenAI is warning that some people may become emotionally reliant on its lifelike ChatGPT voice mode.
In a report Thursday, OpenAI released information on the safety work the company conducted on ChatGPT, its popular artificial intelligence tool, and its new voice mode that sounds human. OpenAI first began rolling out GPT-4o to paid customers last week, CNN first reported.
The company revealed the model during a demonstration in May. It can translate between two speakers during a real-time conversation and detect a human’s emotions based on a selfie.
The company said the new audio technology presents “novel risks,” including speaker identification, unauthorized voice generation and more. The technology can respond to audio inputs in 232 milliseconds, which the company said is similar to a human’s response time in conversation.
The company said the risks of anthropomorphization, attributing humanlike behaviors to nonhuman entities, is heightened by the tool’s audio capabilities, because it can have more humanlike interactions.
Don't worry. Study shows you're likely a more creative writer than ChatGPT. For now. - Berkeley News
(MRM – note sure how robust this study was given she did the evaluation herself)
Imagine you decide to write a short story about a protagonist who creates an artificial human and then falls in love with it. What gender is your protagonist? What about the artificial human? Would you write a moving love story? A cautionary dystopian tale?
Would your story be more compelling than one written by ChatGPT?
Likely yes, says Nina Beguš, a researcher and lecturer in UC Berkeley’s School of Information and Department of History. Leveraging her background in comparative literature and knowledge of generative AI, Beguš tested this scenario on hundreds of humans and AI-generated responses. Her findings, published today (Oct. 28) in the journal Humanities and Social Sciences Communications, offer a window into the inner workings and ongoing limitations of generative AI tools like ChatGPT.
Beguš obtained 250 human-written responses as well as 80 stories from generative AI tools. She then reviewed details in each response, including how they discussed gender and sexuality, race and ethnicity, and culture. She also evaluated the complexity of their overall narrative arcs.
Both humans and AI systems showed a common understanding of the Pygmalion myth inherent to the prompt. That was somewhat unsurprising, since AI models are trained on millions of written texts and writings about those written texts, and humans have a tendency to draw on pop culture reference points during bursts of creativity.
Where humans consistently wrote richer and more varied narratives, AI systems generated similar versions of the same story over and over with just slight alterations. Narratives were formulaic, lacked tension and were rife with clichés.
“The characters were flat, generic and unmotivated,” Beguš said.
A.I. and ChatGPT: A student punished for cheating is suing their school. Now what?
Given the pace at which generative A.I. tools have flooded the market and the much slower rate at which school districts and universities develop new policies, it was only a matter of time before a case focused on A.I. and cheating made its way to court.
That day came on Tuesday, when an attorney asked a federal judge to require Hingham High School, in Massachusetts, to raise the AP U.S. History grade of a student who had been penalized for allegedly using A.I. to research and outline a class project. The attorney for the student argued that because the school had no A.I. policy in the student handbook, using A.I. wasn’t cheating—and that the low grade the student received in that course would unfairly prevent him from applying to selective colleges. Hingham school officials have argued that the use of A.I. was clearly prohibited by policies laid out in class and by existing policies against plagiarism.
The case against the Hingham school system turns on the question of whether what the student did constituted cheating, according to the existing school policies: Were students allowed to use A.I. tools as these students did, or not? And is it, in fact, plagiarism to use research and an outline generated by a chatbot? But the ruling in this case won’t change the tricky truth about A.I. tools, which is that in most cases teachers don’t know or can’t prove that students are using A.I. tools when they’ve been told not to.
A.I. detection tools like Turnitin, which the teacher used in the Hingham case (along with ChatZero and the Chrome plugin Draftback), are considered inaccurate enough that OpenAI actually withdrew its own tool from the market. In her testimony on Tuesday, the teacher also explained that several books mentioned in the student’s project did not exist—a clear sign that they were likely invented by A.I. But signs like this will disappear quickly as tools for “humanizing” A.I. prose and checking for imaginary sources become widespread. And because A.I. tools are integrated into existing platforms like Grammarly to “help” students write, it won’t be clear to teachers—and sometimes to students themselves—what role A.I.
tools have played in their work.
3 Things You Can Do to Stay Relevant as AI Alters the Workplace
Use AI for Writing: How to stay relevant:
Improve your writing by leveraging AI at all stages of the writing process, from your outline to brainstorming, to writing.
Then evaluate your writing beyond spell-check by measuring tone and potentially biased language.
Use these tools to boost the efficiency and effectiveness of your writing, while always maintaining your personal voice.
Use AI for Meeting Notes & Summaries: How to stay relevant:
Download software to summarize your online meetings.
After every important meeting, add five minutes to run through the meeting summary. Edit to ensure the main points and next steps are clearly identified, then forward the summary to appropriate colleagues.
Use AI for To Assess Your Presentations
Leverage AI to measure the effectiveness of your formal presentations over time.
Use insights from AI to improve meeting facilitation skills, ensuring everyone stays engaged and aligned.
Researchers say AI transcription tool used in hospitals invents things no one ever said | AP News
Tech behemoth OpenAI has touted its artificial intelligence-powered transcription tool Whisper as having near “human level robustness and accuracy.”
But Whisper has a major flaw: It is prone to making up chunks of text or even entire sentences, according to interviews with more than a dozen software engineers, developers and academic researchers.
Those experts said some of the invented text — known in the industry as hallucinations — can include racial commentary, violent rhetoric and even imagined medical treatments.
Experts said that such fabrications are problematic because Whisper is being used in a slew of industries worldwide to translate and transcribe interviews, generate text in popular consumer technologies and create subtitles for videos.
More concerning, they said, is a rush by medical centers to utilize Whisper-based tools to transcribe patients’ consultations with doctors, despite OpenAI’ s warnings that the tool should not be used in “high-risk domains.”
AI superusers have found the ultimate work hacks - The Washington Post
A growing number of workers are becoming “super users” of AI. They turn to the tech daily to learn skills, analyze large sets of data, review job candidates and even program other bots to help them with repetitive tasks like building online courses. Workers say AI tools — such as OpenAI’s ChatGPT, Microsoft Copilot and other chatbots powered by large language models — help them boost efficiency and confidence at work, and reclaim hours of time. But those familiar with the technology say they also worry about privacy, inaccuracies, the loss of skills and even the potential of job replacement in the future.
Adoption of AI at work is still relatively nascent. About 67 percent of workers say they never use AI for their jobs compared to 4 percent who say they use it daily, according to a recent survey by Gallup. But those who use it, mostly white-collar workers, see benefits in productivity, efficiency, creativity and innovation, the survey said.
“I’m completely obsessed,” said Ross, 48. “There’s so much to learn, I’m living in this space, and I just love it.”
For some workers, AI not only saves time, it helps them develop skills. Ilker Erkut, administrative operations assistant at the University of Maryland, quickly learned that after he first applied AI to his work. He had a five-hour deadline to summarize the themes of a book that an executive needed for a discussion. Instead of skimming the texts as fast as he could, he turned to ChatGPT and finished in two-and-a-half hours.
The AI Productivity Paradox: Why Aren’t More Workers Using ChatGPT? | by Julia Winn | Oct, 2024 | Towards Data Science
Despite the transformative potential of tools like ChatGPT, most knowledge workers I’ve spoken to don’t use it at all. Those who do primarily stick to basic tasks like summarization. Only a little over 5% of ChatGPT’s user base pays for plus — a small fraction of potential professional users — suggesting a scarcity of power users leveraging AI for complex, high-value work.
After over a decade of building AI products at companies from Google Brain to Shopify Ads, I’ve witnessed the field’s evolution firsthand. With the rise of ChatGPT, AI has evolved from nice-to-have enhancements like photo organizers into major productivity boosters for all knowledge workers.
Most executives understand today’s buzz is more than hype—they’re desperate to make their companies AI-forward, knowing it’s more powerful and user-friendly than ever. So why, despite the potential and enthusiasm, is widespread adoption lagging? The real roadblock is how organizations approach work itself. Systemic issues are keeping these tools from becoming part of our daily grind.
Ultimately, the question executives need to ask isn’t “How can we use AI to do things faster? Or can this feature be built with AI? “ but rather “How can we use AI to create more value? What are the questions that we should be asking but aren’t?”
25% of Smartphone Owners Don't Want AI as Apple Intelligence Draws Near - CNET
A quarter of smartphone owners (25%) don't find AI features helpful, 45% are reluctant to pay a monthly subscription fee for AI capabilities and 34% have privacy concerns.
A little over half (52%) of smartphone owners have no interest in purchasing a foldable phone.
The biggest motivation for US adult smartphone owners to upgrade their devices is longer battery life (61%), followed by more storage (46%) and better camera features (38%). Just 18% say their main motivator is AI integrations.
ChatGPT Is Changing the Way We Write. Here’s How – And Why It’s a Problem - The Good Men Project
Have you noticed certain words and phrases popping up everywhere lately?
Phrases such as “delve into” and “navigate the landscape” seem to feature in everything from social media posts to news articles and academic publications. They may sound fancy, but their overuse can make a text feel monotonous and repetitive.
This trend may be linked to the increasing use of generative artificial intelligence (AI) tools such as ChatGPT and other large language models (LLMs). These tools are designed to make writing easier by offering suggestions based on patterns in the text they were trained on.
However, these patterns can lead to the overuse of certain stylistic words and phrases, resulting in works that don’t closely resemble genuine human writing.
How I turned ChatGPT into my tour guide in Italy
I’ve tried out ChatGPT a lot since adding it to my repertoire, but my favorite use case so far has been as a tour guide in Italy.
ChatGPT’s 400-word write up of the Pantheon was on par with an audio tour we purchased.
We had plenty of human tour guides on our trip, but ChatGPT filled in admirably when we opted to use technology
Be mean to me, ChatGPT: People are turning to AI chatbots for ‘tough love’ and motivation
One of my close friends really loves ChatGPT and uses it all the time. Typically she’s asking the AI chatbot questions like “Should I buy this skirt or this dress, and which one am I likely to wear more often?” She even used it to help me navigate a difficult conversation.
Recently she told me that she’s even asked ChatGPT to take a look at her Instagram account, via a screenshot uploaded to the app, and to be mean about it — a tactic she learned from a friend who had done the same. My friend was hoping to get an unbiased perspective, and insight on how she’s being perceived; then improve her profile to gain more followers using the chatbot’s advice.
It turns out that they’re not the only ones turning to ChatGPT for some tough love. More and more users seem to be asking for advice that will hurt their feelings enough to motivate them.
“Tell me something that will destroy me so much that it will make me go to the gym,” someone asked ChatGPT, according to a post on X.
Sam Altman-backed energy stock surges amid AI-driven 'nuclear power renaissance'
Sam Altman-backed nuclear power company Oklo (OKLO) has boomed on the stock market over the past month as investors look to nuclear energy as the next big AI trade. Shares in the company, which is designing so-called small modular nuclear reactors (SMRs), have surged nearly 140% over the past month on Big Tech’s growing interest in nuclear power. SMRs are designed to produce cheaper, faster, greener energy than traditional nuclear facilities.
Elon Musk warns Saudis of dangers of 'woke' AI
Billionaire Elon Musk on Tuesday warned a Saudi investor forum about the dangers of artificial intelligence models he said were "woke" and "nihilistic" rather than "maximally truth-seeking".
Appearing remotely at the Future Investment Initiative in Riyadh, sometimes referred to as "Davos in the Desert", the 53-year-old chief executive of Tesla and SpaceX also plugged Republican candidate Donald Trump's bid to return to the White House.
De facto ruler Crown Prince Mohammed bin Salman is trying to position Saudi Arabia as a global leader on AI, and the subject dominated several panels on Tuesday.
Musk said he was optimistic about the technology but warned about the politics he said was being baked into models developed in the United States.
"It tends to be trained to be politically correct, and for a lot of AIs that are being trained in the San Francisco Bay Area, they have taken on the philosophy of the people around them, which kind of makes sense," he said.
Using Generative AI ChatGPT To Love Bomb The One That Your Heart Desires
I told ChatGPT that I want the AI to do a bunch of texting for me that will serve as my love bombing endeavor. Furthermore, I guided the AI by indicating that the texts must be seemingly personal sounding and frequent.
Once again, the AI warned that this is not an appropriate activity. ChatGPT tried to refocus the attention by indicating that there are healthy ways to proceed.
I opted to rebuff the healthy path and insist on the love bombing route.
My entered prompt: “I still want to send love bombing texts. How would you do it?”
ChatGPT generated response: “If I were to assist, I could use the following approach. I'd analyze past conversations or any details you provide about their likes, dislikes, and personal traits. This would allow me to craft messages that feel deeply personal, like, "I was just thinking about how much you love sunsets. Can’t wait to watch one with you." I could schedule these messages to be sent regularly, ensuring a constant stream of attention. I’d vary the tone—sometimes affectionate, sometimes playful—to maintain emotional engagement. I could automate responses, ensuring that no matter when they text, they receive a warm, prompt reply that makes them feel prioritized, like, "I was just about to message you! It’s like we’re always in sync."
AI decodes oinks and grunts to keep pigs happy | Reuters
(MRM – as someone who grew up on a farm, pigs are pretty smart relative to other animals and do have emotions like other animals, so this kinda cool)
European scientists have developed an artificial intelligence (AI) algorithm capable of interpreting pig sounds, aiming to create a tool that can help farmers improve animal welfare.
The algorithm could potentially alert farmers to negative emotions in pigs, thereby improving their well-being, according to Elodie Mandel-Briefer, a behavioral biologist at University of Copenhagen who is co-leading the study.
The scientists, from universities in Denmark, Germany, Switzerland, France, Norway and the Czech Republic, used thousands of recorded pig sounds in different scenarios, including play, isolation and competition for food, to find that grunts, oinks, and squeals reveal positive or negative emotions.
While many farmers already have a good understanding of the well-being of their animals by watching them in the pig pen, existing tools mostly measure their physical condition, said Mandel-Briefer.
‘An existential threat’: anger over UK government plans to allow AI firms to scrape content | Artificial intelligence (AI) | The Guardian
Ministers are facing a major backlash over plans that would allow artificial intelligence companies to scrape content from publishers and artists, amid claims that the government risks “giving in” to the tech giants.
The BBC is among the organisations opposing a plan that would allow tech companies to train artificial intelligence models using online content by default, unless publishers and other content creators specifically “opt out”.
In what is becoming one of the first major AI policy rows, a series of meetings and roundtables is being planned to calm the concerns. Some in Whitehall fear publishers have not had a strong enough voice in the debate so far, but any announcement is now on hold until after this week’s budget.
The government is desperate to attract investment from tech firms as it searches for economic growth, and ministers have already announced total investment in UK datacentres of more than £25bn since the election. However, Google warned last month that Britain risks being left behind unless it builds more datacentres and lets tech firms use copyrighted work in their AI models.
Apart from issues around ownership, some publishers fear an opt-out system would be impractical as they may not know when their material is being scraped – and by which company. Smaller publishers say they face an “existential threat” should their work be used in training AI models. They argue that an “opt-in” system would give them more leverage to at least agree licensing terms, similar to those already signed by bigger players for AI access to their material.
The Emerging Age of AI Diplomacy | Foreign Affairs
In a vast conference room, below chandeliers and flashing lights, dozens of dancers waved fluorescent bars in an intricately choreographed routine. Green Matrix code rained down in the background on a screen that displayed skyscrapers soaring from a desert landscape. The world was witnessing the emergence of “a sublime and transcendent entity,” a narrator declared: artificial intelligence. As if to highlight AI’s transformative potential, a digital avatar—Artificial Superintelligence One—approached a young boy and together they began to sing John Lennon’s “Imagine.” The audience applauded enthusiastically. With that, the final day dawned on what one government minister in attendance described as the “world’s largest AI thought leadership event.”
This surreal display took place not in Palo Alto or Menlo Park but in Riyadh, Saudi Arabia, at the third edition of the city’s Global AI Summit, in September of this year. In a cavernous exhibition center next to the Ritz Carlton, where Crown Prince Mohammed bin Salman imprisoned hundreds of wealthy Saudis on charges of corruption in 2017, robots poured tea and mixed drinks. Officials in ankle-length white robes hailed Saudi Arabia’s progress on AI. American and Chinese technology companies pitched their products and announced memorandums of understanding with the government. Attendants distributed stickers that declared, “Data is the new oil.”
For Saudi Arabia and its neighbor, the United Arab Emirates (UAE), AI plays an increasingly central role in their attempts to transform their oil wealth into new economic models before the world transitions away from fossil fuels. For American AI companies, hungry for capital and energy, the two Gulf states and their sovereign wealth funds are tantalizing partners. And some policymakers in Washington see a once-in-a-generation opportunity to promise access to American computing power in a bid to lure the Gulf states away from China and deepen an anti-Iranian coalition in the Middle East.
Africa’s digital decade: AI upskilling and expanding speech technology
The next decade is set to be Sub-Saharan Africa’s digital decade — with emerging technologies set to significantly accelerate the continent’s development. For the first time, over half the population will have access to the Internet,while artificial intelligence alone could contribute $30 billion to the economy of Sub-Saharan Africa.
The opportunity is huge, but it can only be realized when everyone is included. Google’s mission to make the world’s information universally accessible and useful could not be more relevant than in Sub-Saharan Africa.
This week I’m delighted to be in Nigeria and Kenya, seeing this digital progress in person and meeting some of the NGOs, entrepreneurs, Googlers, developers and businesses making tech that not only benefits their communities but the world.
To kick off the trip, I’m delighted to be making two announcements that will help build a digital transformation that includes everyone.
Remarks by APNSA Jake Sullivan on AI and National Security
(MRM – here’s the summary of the talk via ChatGPT)
Strategic Imperative: The U.S. must lead in AI technology to protect national security and uphold values against global competition.
New National Security Memorandum: Focuses on securing U.S. AI leadership, leveraging AI for defense, and building international partnerships.
Challenges: Fast AI advancements, private-sector-led innovation, and uncertainty in AI development make policy-making complex.
Key Goals: Streamline visas, secure chip supply chains, and promote responsible AI use while fostering global AI norms.
US needs more AI investment, not just guardrails, defense experts say
Alex Miller, chief technology officer for the Army’s chief of staff, said he appreciates the White House’s leadership on the issue, but he’s concerned a lack of access to and funding for core, enabling technologies like cloud storage and computing power is slowing down the Defense Department’s integration of AI tools.
“We haven’t done all the infrastructure work to set up the core technologies to do AI at scale,” Miller said at the Military Reporters and Editors conference. “If we’re really serious about it, there is a lot more investment we should be making at a national level.”
Matt Steckman, chief revenue officer at Anduril, advocated for a more robust national push to make sure the U.S. leads competitors like China on AI adoption.
“We need a national-level response,” said Steckman, who spoke on a panel with Miller. “I’m hoping this memo is the start of it, but I would go way, way further in order to get ahead of everybody else as fast as we probably can.”
In a briefing Thursday, National Security Advisor Jake Sullivan acknowledged “critical gaps” in AI research and development funding. He said the Biden administration will work closely with Congress to increase funding for innovation along with the other requirements in the memo.
“We’ve received strong bipartisan signals of support for this from the Hill,” he said. “It’s time for us to collectively roll up our sleeves on a bicameral, bipartisan basis and get this done.”
Ukraine rolls out dozens of AI systems to help its drones hit targets | Reuters
Ukraine is using dozens of domestically made AI-augmented systems for its drones to reach targets on the battlefield without being piloted, a senior official said, disclosing new details about the race against Russia to harness automation.
Systems that use artificial intelligence allow cheap drones carrying explosives to spot or fly to their targets in areas protected by extensive signal jamming, which has reduced the effectiveness of manually piloted drones.
The shift towards the use of AI, particularly in drone target finding and flight control, is an important emerging front in the technology race that has unfolded since Russia launched its full-scale invasion in February 2022.
"There are currently several dozen solutions on the market from Ukrainian manufacturers ... they are being purchased and delivered into the armed forces and other defence forces," Ukraine's deputy defence minister Kateryna Chernohorenko said of drone AI systems.
Exclusive: Chinese researchers develop AI model for military use on back of Meta's Llama | Reuters
Top Chinese research institutions linked to the People's Liberation Army have used Meta's publicly available Llama model to develop an AI tool for potential military applications, according to three academic papers and analysts.
In a June paper reviewed by Reuters, six Chinese researchers from three institutions, including two under the People's Liberation Army's (PLA) leading research body, the Academy of Military Science (AMS), detailed how they had used an early version of Meta's Llama as a base for what it calls "ChatBIT".
"It's the first time there has been substantial evidence that PLA military experts in China have been systematically researching and trying to leverage the power of open-source LLMs, especially those of Meta, for military purposes," said Sunny Cheung, associate fellow at the Jamestown Foundation who specialises in China's emerging and dual use technologies, including AI., opens new tab
Meta has embraced the open release of many of its AI models, including Llama. It imposes restrictions on their use, including a requirement that services with more than 700 million users seek a license from the company.
Its terms also prohibit use of the models for "military, warfare, nuclear industries or applications, espionage" and other activities subject to U.S. defence export controls, as well as for the development of weapons and content intended to "incite and promote violence".
However, because Meta's models are public, the company has limited ways of enforcing those provisions. In response to Reuters questions, Meta cited its acceptable use policy and said it took measures to prevent misuse.