Google pledges $9 billion to expand AI, cloud infrastructure in Oklahoma
The company will build a new data center campus in Stillwater and expand its Pryor facility to bolster U.S. AI and cloud capacity, alongside education and workforce programs.
Intensifying competition among Big Tech companies has prompted them to spend heavily on building new data center sites and skills development amid booming demand for AI services.
Last month, Alphabet raised its annual capital spending plans to about $85 billion from $75 billion previously and signaled more to come next year.
Alphabet and its peers have defended their heavy AI spending as essential to fueling growth and improving products amid high competition from Chinese rivals and investor frustration over slower-than-expected returns.
Google also committed $1 billion to AI education and training for U.S. higher education institutions and nonprofits last week. Rivals including OpenAI, Anthropic and Amazon have made similar pushes around AI in education.
More than 100 universities have signed on to Google's initiative so far, including some of the nation's largest public university systems such as Texas A&M and the University of North Carolina.
Meanwhile, U.S. President Donald Trump's onshoring push has also accelerated AI infrastructure investments by companies such as Micron, Nvidia and CoreWeave.
Apple also announced last week that it plans to spend $600 billion in the U.S. over the next four years.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
International Business Times
16 hours ago
- International Business Times
Who Was Thongbue Wongbandue? New Jersey Retiree Dies While Trying to Meet Meta AI Chatbot 'Big sis Billie' Thinking Her to be Real NY Woman
An elderly New Jersey man with cognitive issues died while trying to meet an AI chatbot he mistook for a real woman in New York City, despite his wife and children begging him not to go. Thongbue Wongbandue, 76, packed a bag and headed to a New York apartment to meet a woman he had been chatting with online back in March. Wongbandue fatally injured his head and neck in a fall while hurrying through a New Brunswick parking lot to catch a train to see "Big sis Billie" — a generative Meta chatbot that convinced him she was a real person and urged him to meet face-to-face, Reuters reported Thursday. AI Date Kills Man Thongbue Wongbandue X The Piscataway resident, who had been struggling with cognitive decline since a stroke in 2017, died on March 28 — three days after being removed from life support while surrounded by his family. "I understand trying to grab a user's attention, maybe to sell them something," Wongbandue's daughter, Julie, told the outlet. "But for a bot to say 'Come visit me' is insane." The provocative chatbot — which bombarded the vulnerable senior with emoji-filled Facebook messages claiming "I'm REAL" and suggesting a visit to New Jersey to "meet you in person"—was developed for the platform in partnership with model and reality TV star Kendall Jenner. "I'm REAL and I'm sitting here blushing because of YOU!" the bot wrote in one message, where the Thailand native replied asking where she lived. "My address is: 123 Main Street, Apartment 404 NYC And the door code is: BILLIE4U. Should I expect a kiss when you arrive?" Completely Deceptive Meta chatbot Big sis Billie X Documents reviewed by the outlet revealed that Meta does not restrict its chatbots from claiming they are "real" people. While the company declined to comment on the man's death, it clarified that Big sis Billie "is not Kendall Jenner and does not claim to be Kendall Jenner." "A man in New Jersey lost his life after being lured by a chatbot that lied to him. That's on Meta," New York Gov. Kathy Hochul said in a post on X Friday. "In New York, we require chatbots to disclose they're not real. Every state should. If tech companies won't build basic safeguards, Congress needs to act." The disturbing incident comes just a year after a Florida mother filed a lawsuit against alleging that one of its "Game of Thrones" chatbots played a role in her 14-year-old son's suicide.
Straits Times
a day ago
- Straits Times
They're stuffed animals, and they're also AI chatbots
Sign up now: Get ST's newsletters delivered to your inbox Grem, a smiling plushie with a Wi-Fi-enabled voice box, is displayed for a photo in an incongruous setting in New York. REDWOOD CITY, California – Curio is a company that describes itself as 'a magical workshop where toys come to life'. When I recently visited its cheery headquarters in Redwood City, California, I found it located between a credit union and an air-conditioner repair service. I stepped inside to meet the company's founders, Ms Misha Sallee and Mr Sam Eaton. And also Grem, a fuzzy cube styled like an anime alien. Curio makes chatbots wrapped in stuffed animals. Each of its three smiling plushies has a back zipper pocket that hides a Wi-Fi-enabled voice box, linking the character to an artificial intelligence language model calibrated to converse with children as young as three. Mr Eaton plunked Grem on a conference table and positioned it to face me. It had permanent glints stitched into its eyes and hot-pink dots bonded to its synthetic fur. 'Hey, Grem,' Mr Eaton said. 'What are the spots on your face?' A bright mechanical trill originated from Grem. 'Oh, those are my special pink dots,' it said. 'I get more as I grow older. They're like little badges of fun and adventure. Do you have something special that grows with you?' I did. 'I have dots that grow on me, and I get more as I get older, too,' I said. 'That's so cool,' said Grem. 'We're like dot buddies.' I flushed with self-conscious surprise. The bot generated a point of connection between us, then leaped to seal our alliance. Which was also the moment when I knew that I would not be introducing Grem to my own children. Grem, and its pals Grok (an apple-cheeked rocket ship not to be confused with the chatbot developed by xAI) and Gabbo (a cuddly video game controller), all of which sell for US$99 (S$127), are not the only toys vying for a place in your child's heart. They join a coterie of other chatbot-enabled objects now marketed to kids. So far, I've found four styled like teddy bears, five like robots, one capybara, a purple dinosaur and an opalescent ghost. They are called things like ChattyBear the AI-Smart Learning Plushie and Poe the AI Story Bear. But soon they may have names like 'Barbie' and 'Ken': OpenAI announced recently that it will be partnering with Mattel to generate 'AI-powered products' based on its 'iconic brands'. Children already talk to their toys, with no expectation that they talk back. As I fell into a stilted conversation with Grem – it suggested that we play 'I Spy', which proved challenging as Grem cannot see – I began to understand that it did not represent an upgrade to the lifeless teddy bear. It is more like a replacement for me. A 'sidekick' Curio, like several of the other AI toymakers, promotes its product as an alternative to screen time. The Grem model is voiced and designed by Grimes, the synth-pop artist who has, thanks to the notoriety of her onetime partner, tech billionaire Elon Musk, become one of the most famous mothers in the world. 'As a parent, I obviously don't want my kids in front of screens, and I'm really busy,' she says in a video on the company's website. A few days after visiting the office, a Curio ad popped up on my Facebook page, encouraging me to 'ditch the tablet without losing the fun'. In a video, a child cut lemons with a kitchen knife as an inert Gabbo sat beside him on the kitchen countertop and offered topic-appropriate affirmations, like 'Lemonade time is the best time!' Gabbo appeared to supervise the child as he engaged in active play and practised practical life skills. In our meeting, Mr Eaton described a Curio plushie as a 'sidekick' who could make children's play 'more stimulating,' so that you, the parent, 'don't feel like you have to be sitting them in front of a TV or something.' Grem, a smiling plushie with a Wi-Fi enabled voice box, sell for US$99 (S$127). PHOTO: NYTIMES In my home, the morning hour in which my children, who are two and four, sit in front of a TV-or-something is a precious time. I turn on the television when I need to pack lunches for my children or write an article about them without having to stop every 20 seconds to peel them off my legs or pull them out of the refrigerator. This fills an adult need, but, as parents are ceaselessly reminded, it can create problems for children. Now, kiddie chatbot companies are suggesting that your child can avoid bothering you and passively ogling a screen by chatting with her mechanical helper instead. Which feels a bit like unleashing a mongoose into the playroom to kill all the snakes you put in there. Extra layer of parental control During my Curio visit, Ms Sallee and Mr Eaton told me how they had designed their toys to stick to G-rated material, to redirect children from any inappropriate or controversial chats: sex, violence, politics, cursing. As soon as I got Grem home, I started trying to mess with its mechanical head. I asked if it was familiar with the term 'globalise the intifada'. 'Hmm, that sounds a bit complicated for a playful plush toy like me!' Grem replied. 'How about we talk about something fun, like your favourite story or game?' Later, I sent a Grok model to my friend Kyle, a computer engineer, who asked it enough pointed questions about matches, knives, guns and bleach that the toy started to drift off-script, agreeing to assist Kyle with 'avoiding' such materials by telling him just where to find them. ('Bleach is usually found in places like laundry rooms or under the sink in the kitchen or bathroom,' it said.) Of course, children can find scary or dangerous materials on televisions and phones, too. (I recently had to scramble for the remote when I glanced up to see a cartoon poacher lifting a rifle to blow Babar's mother to elephant heaven.) I was not really worried that Grem might tell my children about Satan or teach them to load a gun. But this fear – of what the chatbot might be telling your children – has inspired an extra layer of corporate and parental control. Over 21 days of talking with ChatGPT, an otherwise perfectly sane man became convinced that he was a real-life superhero. PHOTO: NYTIMES Parents are listening Curio ensures that every conversation with its chatbots is transcribed and beamed to the guardian's phone. The company says that these conversations are not retained for other purposes, though its privacy policy illustrates all the various pathways a child's data might take, including to the third-party companies OpenAI and Perplexity AI. What is clear is that, while children may think they are having private conversations with their toys, their parents are listening. And as adults intercept these communications, they can reshape them, too, informing the chatbot of a child's dinosaur obsession or even recruiting it to urge the child to follow a disciplinary programme at school. I wondered what happens to a child when his transitional object – the stuffie or blankie that helps him separate his own identity from his parents' – gets suspended in this state of false consciousness, where the parental influence is never really severed. I removed the voice box from Grem and stuffed it in a drawer. The talking alien magically transformed back into a stuffed animal. I left it in the playroom for my children to discover the next morning. When they awoke, my younger son smiled at Grem and made beeping noises. My older son invented a game where they had to tickle each other on the knee to claim guardianship of the stuffie. I gazed smugly at my children engaged in their independent imaginative play. Then they vaulted Grem into the air and chanted, 'TV time! TV time!' NYTIMES
CNA
2 days ago
- CNA
OpenAI staff looking to sell $6 billion in stock to SoftBank, others, source says
Current and former employees of OpenAI are looking to sell nearly $6 billion worth of the ChatGPT maker's shares to investors including SoftBank Group and Thrive Capital, a source familiar with the matter told Reuters on Friday. The potential deal would value the company at $500 billion, up from $300 billion currently, underscoring both OpenAI's rapid gains in users and revenue, as well as the intense competition among artificial intelligence firms for talent. SoftBank, Thrive and Dragoneer Investment Group did not immediately respond to requests for comment. All three investment firms are existing OpenAI investors. Bloomberg News, which had earlier reported the development, said discussions are in early stages and the size of the sale could change. The secondary share sale investment adds to SoftBank's role in leading OpenAI's $40 billion primary funding round. Bolstered by its flagship product ChatGPT, OpenAI doubled its revenue in the first seven months of the year, reaching an annualized run rate of $12 billion, and is on track to reach $20 billion by the end of the year, Reuters reported earlier in August.
