OpenAI in talks with Saudi Arabia, India to raise capital: Reports - The Economic Times Video
ChatGPT maker OpenAI has held talks with Saudi Arabia's Public Investment Fund (PIF), India's Reliance Industries, and the United Arab Emirates' MGX about participating in a $40 billion financing round, according to a report by The Information. The investors could contribute at least hundreds of millions of dollars each, the report said, citing sources familiar with the discussions.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Indian Express
17 minutes ago
- Indian Express
Will AI replace us? Yuval Noah Harari's stark warning about a future without borders
In yet another illuminating conversation, renowned author Yuval Noah Harari, known for his acclaimed works 'Sapiens' and 'Nexus', shared his unique perspective on the rapid rise of AI and how it will impact humanity. 'AI will not be one big AI. We are talking about potentially millions or billions of new AI agents with different characteristics, again, produced by different companies, different countries,' the author said in his latest conversation at the WSJ Leadership Institute. During the conversation, one of the guests asked Harari that through history, organising principles like religion and church shaped society in a unified way, but with AI there is no single central force. There are many different AIs being built with different goals and values. What happens when there isn't one dominant AI but many competing AIs evolving quickly? What kind of world does that create? In his response the author said that we are dealing with potentially millions or billions of new AI agents. 'You'll have a lot of religious AIs competing with each other over which AI will be the authoritative AI rabbi for which section of Judaism. And the same in Islam, and the same in Hinduism, in Buddhism, and so forth. So you'll have competition there. And in the financial system. And we just have no idea what the outcome will be.' He said that we have thousands of years of experience with human societies, and at least we have some experience as to how these things develop. But, when it comes to AI, we have zero experience. 'What happens in AI societies when millions of AIs compete with each other? We just don't know. Now this is not something you can simulate in the AI labs.' Harari went on to say that in case OpenAI wanted to check the safety or the potential outcome of its latest AI model, it cannot simulate history in the laboratory. While it may be able to check for all kinds of failures in the system, it cannot predict what happens when there are millions of copies of these AIs in the world developing in unknown ways. He went on to call it the biggest social experiment in human history, of which all of us are a part, and nobody has any idea how it will develop. In an extension of his argument, Harari used the analogy of the ongoing immigration crisis in the US, Europe and elsewhere. According to him, people are worried about immigrants for three reasons – they will take our jobs, they come with different cultural ideas, and they will change our culture. 'They may have political agendas; they might try to take over the country politically. These are the three main things that people keep coming back to.' According to the author, one can think about the AI revolution as simply a wave of immigration of millions or billions of AI immigrants that will take people's jobs and have very different cultural ideas, and that may even try to gain some kind of political power. 'And these AI immigrants or digital immigrants, they don't need visas; they don't cross a sea in some rickety boat in the middle of the night. They come at the speed of light,' he said, adding that far-right parties in Europe talk mostly about human immigrants but overlook the wave of digital immigrants that is coming to Europe. Harari feels that any country that cares about its sovereignty should care about the future of the economy and culture. 'They should be far more worried about the digital immigrants than about the human immigrants.' When the host asked the acclaimed author what it meant to be human at the moment, Harari responded by saying, 'To be aware for the first time that we have real competition on the planet.' The author said that while we have been the most intelligent species by far for tens of thousands of years, now we are creating something that could compete with us in the near future. 'The most important thing to know about AI is that it is not a tool like all previous human inventions; it is an agent. An agent in the sense that it can make decisions independently of us, it can invent new ideas, and it can learn and change by itself. All previous human inventions, you know, whether they're printing presses or the atom bomb, they are tools that empower us,' said Harari. The host said that there is a lot of responsibility on leaders because how they act is how the AI will be. 'You cannot expect to lie and cheat and have a benevolent AI.' In his response, Harari acknowledged that there is a big discussion around the world about AI alignment. He said that there are a lot of efforts focused on the idea that if we can design these AIs in a certain way, if we can teach them certain principles, they will be safe. However, there are two problems with this approach – firstly, the definition of AI is that it can learn and change by itself; secondly, if you think of AI as a child that can be educated, it surprises or horrifies you. 'The other thing is, everybody who has any knowledge of education knows that in the education of children, it matters far less what you tell them than what you do. If you tell your kids not to lie, and your kids watch you lying to other people, they will copy your behaviour, not your instructions.' Similarly, Harari explained that if AIs that are being educated are given access to a world where they see humans behave, even some of the most powerful humans, including their makers, lying, then the AIs will copy that behaviour. 'People who think that I can run this huge AI corporation, and while I'm lying, I will teach my AIs not to lie; it will not work. It will copy your behaviour,' he said.
Time of India
34 minutes ago
- Time of India
Anthropic says looking to power European tech with hiring push
By Tom Barfield American AI giant Anthropic aims to boost the European tech ecosystem as it expands on the continent, product chief Mike Krieger told AFP Thursday at the Vivatech trade fair in Paris. The OpenAI competitor wants to be "the engine behind some of the largest startups of tomorrow... (and) many of them can and should come from Europe", Krieger said. Tech industry and political leaders have often lamented Europe's failure to capitalise on its research and education strength to build heavyweight local companies - with many young founders instead leaving to set up shop across the Atlantic. Krieger's praise for the region's "really strong talent pipeline" chimed with an air of continental tech optimism at Vivatech. French AI startup Mistral on Wednesday announced a multibillion-dollar tie-up to bring high-powered computing resources from chip behemoth Nvidia to the region. The semiconductor firm will "increase the amount of AI computing capacity in Europe by a factor of 10" within two years, Nvidia boss Jensen Huang told an audience at the southern Paris convention centre. Among 100 planned continental hires, Anthropic is building up its technical and research strength in Europe, where it has offices in Dublin and non-EU capital London, Krieger said. Beyond the startups he hopes to boost, many long-standing European companies "have a really strong appetite for transforming themselves with AI", he added, citing luxury giant LVMH, which had a large footprint at Vivatech. 'Safe by design' Mistral - founded only in 2023 and far smaller than American industry leaders like OpenAI and Anthropic - is nevertheless "definitely in the conversation" in the industry, Krieger said. The French firm recently followed in the footsteps of the US companies by releasing a so-called "reasoning" model able to take on more complex tasks. "I talk to customers all the time that are maybe using (Anthropic's AI) Claude for some of the long-horizon agentic tasks, but then they've also fine-tuned Mistral for one of their data processing tasks, and I think they can co-exist in that way," Krieger said. So-called "agentic" AI models - including the most recent versions of Claude - work as autonomous or semi-autonomous agents that are able to do work over longer horizons with less human supervision, including by interacting with tools like web browsers and email. Capabilities displayed by the latest releases have raised fears among some researchers, such as University of Montreal professor and "AI godfather" Yoshua Bengio, that independently acting AI could soon pose a risk to humanity. Bengio last week launched a non-profit, LawZero, to develop "safe-by-design" AI - originally a key founding promise of OpenAI and Anthropic. 'Very specific genius' "A huge part of why I joined Anthropic was because of how seriously they were taking that question" of AI safety, said Krieger, a Brazilian software engineer who co-founded Instagram, which he left in 2018. Anthropic is still working on measures designed to restrict their AI models' potential to do harm, he added. But it has yet to release details of its "level 4" AI safety protections foreseen for still more powerful models, after activating ASL (AI Safety Level) 3 to corral the capabilities of May's Claude Opus 4 release. Developing ASL 4 is "an active part of the work of the company", Krieger said, without giving a potential release date. With Claude 4 Opus, "we've deployed the mitigations kind of proactively... safe doesn't have to mean slow, but it does mean having to be thoughtful and proactive ahead of time" to make sure safety protections don't impair performance, he added. Looking to upcoming releases from Anthropic, Krieger said the company's models were on track to match chief executive Dario Amodei's prediction that Anthropic would offer customers access to a "country of geniuses in a data centre" by 2026 or 2027 - within limits. Anthropic's latest AI models are "genius-level at some very specific things", he said. "In the coming year... it will continue to spike in particular aspects of things, and still need a lot of human-in-the-loop coordination," he forecast.
Mint
34 minutes ago
- Mint
I used an AI stylist for five days and hated it
For five days, generative AI became my personal stylist. It told me what to wear and how to wear it. It chose my hairstyle and lip colour. It even suggested to the manicurist that yellow was my colour. Generative AI—which can do everything from write code, conduct makeshift therapy sessions and create designs for fashion designers—could add close to $300 billion in the next five years to the operating profits of apparel, fashion and luxury sectors, says a 2023 report by consulting firm McKinsey. It can do so, the report adds, by helping streamline design and supply chain issues, but more importantly, it can allow shoppers to try on clothes via their devices, and add chatbots as shopping assistants to help people sift through their wardrobe and make better style decisions. So, I decided to dive into the world of AI with three apps to see if algorithms could change the way I dress. Also read: Gen Z can't stop buying fast fashion and won't repeat outfits—here's why One was ChatGPT, the popular US-born general-purpose tool, and the other two were newly launched homegrown platforms, Glance AI and Slayrobe. These three AI advisers, or stylists, saved me time and lessened the burden of making a decision each time I opened my wardrobe. But they seemed to have one agenda: turn me into a blind follower of trends. Sample this conversation with ChatGPT. Me: Hey ChatGPT, What should I wear to office today? I work in a newsroom and I want to wear something corporate-ish but a little casual and it should look all very effortless. ChatGPT: That's a great idea. I'd suggest going for something like this: A simple, well-fitted blazer in a neutral colour (like navy, black or grey), but leave it unbuttoned to keep it relaxed. Pair it with a plain shirt. Chinos in a neutral shade, or dark jeans if you want to keep it even more casual. Casual loafers or stylish sneakers. Keep accessories minimal. Me: This is too boring. And it's 40 degrees Celsius here, so blazer is out. I'm a fashion writer and I want something different and stylish. Suggest more options? ChatGPT: Wow! A fashion writer, I'm jealous of you, girl! Of course, here's something for that 'unbothered but unmistakably stylish" look. Lightweight cotton shirt with 3/4th sleeves or rolled long sleeves. Tuck it in slightly at the front (French tuck) for that casual-editor vibe. Straight or wide-leg trousers in breathable fabrics like linen. Chunky flats or sleek platform slides. Bold earrings or a structured minimalist necklace. Go for a low sleek bun. Add gold hoops—bam, you're Anna Wintour's cooler cousin. It's not bad advice, but recommending rolling up the sleeves or adding an ankle-length skirt for a Parisian touch isn't exactly going to up my style game. Then, I turned to Slayrobe. After logging into the app, you have to enter your height, identify your body shape (round, triangle, rectangle, inverted triangle, hourglass), features you want to flaunt/downplay, and your 'style agenda" (Effortless Chic, Dreamy Diva, Bold Boss, Timeless Queen). Then comes a barrage of looks, from clothes to jewellery, all based on algorithms trained on over 70,000 styling decision points. You can also buy the suggested options—the app leads the user to the respective product's brand website. There's colour analysis in case you wish to know which shades are meant for your skin tone. And a wardrobe organiser allows you to upload a photo of your garments and create looks, like Cher Horowitz's outfit-picking computer in Clueless (1995). 'Women are being overfed with trends, and despite this, the universal feeling remains: We have nothing to wear," says Slayrobe's founder-CEO Pooja Lalwani, who's earlier worked on fashion tech initiatives at Google and Tommy Hilfiger. 'I wanted to create one platform where you can get help organising your wardrobe, style yourself better, know your colours and then post about it." The women-only app is designed to let you post your photos on the feed and as Stories, and follow other people—much like Instagram. After choosing the option of Dreamy Diva as my 'vibe", I asked the stylist bot to help me find some timeless office wear style ideas. The responses were: 'Embrace soft, flowing fabrics", 'accessorise with delicate details", don't 'overdo with embellishments" .... again, all useful tips but nothing new. But for a school student like Aashna Gulati such information is useful. 'I am still figuring out what my style is," says Mumbai-based Gulati, 16, who constantly experiments with AI apps to find fashion inspiration. 'I shop after seeing (on AI stylist apps) what will look good on me. I want to dress like Kendall (Jenner), Kareena (Kapoor Khan) but I don't have their stylists, so this is the best option for me." Also read: The salwar returns to the runway with a new look That's the promise of an AI stylist. It might not give you exactly what you're looking for but it can direct you towards what you might like. 'AI gets the basics right. It can tell you how a sage green blouse, a pair of canary blue trousers and a burgundy bag will look together but it can't tell whether that combo will suit you," says celebrity stylist Isha Bhansali, who's styled the likes of actor Ayushmann Khurrana. 'It's also about how much you care about personal style. Many people are just happy with following trends and shopping accordingly, and AI helps with exactly that." Glance AI works on this theme: it creates fully styled, shoppable looks based on your body type, personal taste, lifestyle and mood, all on the phone. After entering my details, Glance AI offered a variety of looks in a somewhat Pinterest moodboard way. Under Ready For Safari, for instance, I could see a myself—the app asks you to upload a selfie—wearing a moss green casual shirt from two brands, one ₹664 and other, ₹1,799, depending on your budget. The options were followed by text explaining how the collection 'merged utility and sophistication, featuring earthy tones, linen and structured silhouettes for an elevated, adventure-ready and stylish look". Choice of a green shirt for safari? Definitely not out of the box. 'We're built for Gen Z and millennial consumers," says Mansi Jain, senior vice-president and general manager, Glance AI. 'These are users who want AI to curate for them—not just show options. It marks a shift from marketplace models to inspiration-first commerce, where the AI stylist becomes the first touchpoint of fashion discovery." Can an AI stylist replace a human stylist? It depends on who you ask. Bhansali compares AI to a calculator, saying 'it works on calculations, trends and not emotions, and fashion is so much about emotions." Jain's take: 'Unlike human stylists, AI stylists scale to millions, adapt in real-time, and learn from every interaction. Our models don't just react to trends—they understand your style graph, predict what will resonate, and visualise you in it with near-photorealistic accuracy." The thing is AI can offer answers when you're searching for your sense of style but it cannot serve you that personal touch that makes you you. Whether it was the taupe blouse ChatGPT suggested I wear for an interview, or the smokey party make-up I did after going through different looks on Glance AI, or the red salwar-kameez I zeroed in on for a family puja, they were all 'uniform"-like answers. And so very boring and predictable. As Bhansali says, 'If I told ChatGPT I am on my period, it won't suggest anything white because that information has been fed into it. But what if my mood is to wear white? Style can be dictated by algos, not personal style." When I asked ChatGPT if it believes AI stylists can supersede human counterparts, it said: 'AI is the calculator. The human stylist is the architect. Both can do math. Only one can build the Taj Mahal." Also read: Why labubu dolls, Disney cartoons have entered the adult wardrobe
