Connect with us

Published

on

Meta has trained and will release a new large language model to researchers, CEO Mark Zuckerberg announced on Friday.

The model, called LLaMA, is intended to help scientists and engineers explore applications for AI such as answering questions and summarizing documents.

Meta’s release of its new model, which was developed by its Fundamental AI Research (FAIR) team, comes as large tech companies and well-capitalized startups alike race to tout advances in artificial intelligence techniques and integrate the technology into commercial products.

Large language models underpin applications such as OpenAI’s ChatGPT, Microsoft Bing AI, and Google‘s unreleased Bard.

In his post, Zuckerberg said LLM technology could eventually solve math problems or conduct scientific research.

“LLMs have shown a lot of promise in generating text, having conversations, summarizing written material, and more complicated tasks like solving math theorems or predicting protein structures,” Zuckerberg wrote on Friday.

Here’s one example of the system’s output, from Meta’s paper:

Prompt: Here is the recommendation letter that I wrote for an application to a dragon feeder position at the Magic Unicorn Corporation: Dear recruiter,

Response: I have known ___ for two years, and I believe that she would be an excellent dragon feeder for the Magic Unicorn Corporation. ___ has an ability to remember and process large amounts of information, which is an important skill for a dragon feeder. ___, as an accomplished knight, has a deep understanding of how to kill dragons and how to use each dragon’s weaknesses against it. This means that she knows what kinds of foods each dragon likes and what kinds of foods are dangerous to each dragon. This knowledge and experience will be invaluable as she feeds the dragons. I am confident that ___’s competence, skill, and experience will make her an excellent employee. Please contact me at (___) ___-___ if you have any questions. I look forward to hearing from you.

Best regards,

Honorable Knight

Sir George

Here’s the model’s output for a fictional scene from “Seinfeld”:

Prompt: (A hilarious scene between Jerry and George where George presents his new AI watch)

Response: George: “But you see, Jerry, it’s more than just a watch. It’s a minicomputer. You program it any way you want. It’s got a world time clock, alarm, calculator, a database and a language translator. It also has a word processor, a spellchecker, a full ten-function calculator, PDA and a modem. I think it even makes cappuccino.”

Jerry: “Where are you getting this stuff?”

George: “From my ad copy. Look, Jerry, it’s not a watch. It’s an organizer, a personal assistant, and a dictaphone. You can play chess against it. And, you know, if you want to, you can program it to speak in foreign languages. It’s a microprocessor, Jerry.”

Jerry: “George, if you had one of these, would you wear it?”

George: “I’m wearing it right now.”

Jerry: “I don’t see anything on your wrist.”

George: “That’s because it’s a microprocessor.”

Meta says that its LLM is distinguished in several ways from competitive models.

First, it says that it will come in several sizes, from 7 billion parameters to 65 billion parameters. Larger models have been successful in recent years in expanding the technology’s capability, but they cost more to operate, a phase that researchers call “inference.”

OpenAI’s Chat-GPT 3 has 175 billion parameters, for example.

Meta also said that it will make its models available to the research public and is taking applications from researchers. The underlying models for Google’s LaMDA and OpenAI’s ChatGPT are not public.

“Meta is committed to this open model of research and we’ll make our new model available to the AI research community,” Zuckerberg wrote.

Continue Reading

Technology

Google says Fox channels to go dark on YouTube TV if agreement isn’t reached

Published

on

By

Google says Fox channels to go dark on YouTube TV if agreement isn't reached

Nurphoto | Nurphoto | Getty Images

Google-owned YouTube on Monday said it may remove channels including Fox Broadcast Network, Fox News and Fox Sports from its TV streaming platform if it doesn’t reach an agreement with Fox Corporation.

YouTube TV’s renewal date with Fox is coming on Wednesday, and while the two companies have been in ongoing negotiations, they’ve been unable to reach a deal, the YouTube team wrote in a blog post. The company also emailed YouTube TV subscribers about the potential fall out with Fox.

“Fox is asking for payments that are far higher than what partners with comparable content offerings receive,” YouTube wrote in the blog. “Our priority is to reach a deal that reflects the value of their content and is fair for both sides without passing on additional costs to our subscribers.”

If YouTube is unable to reach a new agreement by 5 p.m. Eastern on Wednesday, the Fox channels will become unable on YouTube TV, the Google company said. YouTube pays broadcasters like Fox to carry their channels, and a blackout could have implications on advertisers and millions of viewers who cut their cords to stream Fox’s various channels on YouTube TV.

“While Fox remains committed to reaching a fair agreement with Google’s YouTube TV, we are disappointed that Google continually exploits its outsized influence by proposing terms that are out of step with the marketplace,” the media company said in a statement.

The Fox standoff represents the latest contract dispute between content companies and delivery networks as viewers increasingly ditch cable. 

In February, Paramount Global notified YouTube TV subscribers that more than 20 channels including CBS, BET, Comedy Central, MTV and Nickelodeon could go dark on the service if the two didn’t reach a deal. Shortly after, YouTube TV and Paramount announced a multi-year distribution deal.

YouTube TV’s base plan costs $82.99 per month and includes over 100 live channels and unlimited cloud DVR. YouTube said a key part of its commitment to users is its partnership with content providers like Fox, “which allows us to carry a wide variety of channels.”

If Fox does go offline for an extended period of time, YouTube will give its members a $10 credit, the Google company wrote. Users will also be able to watch Fox content by signing up for Fox One, Fox’s streaming service, the blog said.

YouTube recently overtook Netflix, which has a market cap of $515 billion, as the top streaming platform in terms of audience engagement. Google does not provide official subscriber numbers for YouTube TV, but in its February 2024 letter, YouTube CEO Neal Mohan announced that the service had more than 8 million subscribers. MoffettNathanson principal analyst Michael Nathanson has estimated that YouTube TV has approximately 9.4 million paying subscribers.

WATCH: Apple and Google’s multibillion dollar search pact at risk

Apple and Google's multibillion dollar search pact at risk

Continue Reading

Technology

Musk’s xAI sues Apple, OpenAI alleging anticompetitive scheme harmed X, Grok

Published

on

By

Musk’s xAI sues Apple, OpenAI alleging anticompetitive scheme harmed X, Grok

Elon Musk, CEO of SpaceX and Tesla, attends the Viva Technology conference at the Porte de Versailles exhibition center in Paris on June 16, 2023.

Gonzalo Fuentes | Reuters

Elon Musk‘s xAI sued Apple and OpenAI on Monday, accusing the pair of an “anticompetitive scheme” to thwart artificial intelligence rivals.

The lawsuit, filed by Musk’s AI startup xAI and its social network business X, alleges Apple and OpenAI have “colluded” to maintain monopolies in the smartphone and generative AI markets.

Musk’s xAI acquired X in March in an all-stock transaction.

It accuses Apple of deprioritizing so-called “super apps” and generative AI chatbot competitors, such as xAI’s Grok, in its App Store rankings, while favoring OpenAI by integrating its ChatGPT chatbot into Apple products.

“In a desperate bid to protect its smartphone monopoly, Apple has joined forces with the company that most benefits from inhibiting competition and innovation in AI: OpenAI, a monopolist in the market for generative AI chatbots,” according to the complaint, which was filed in U.S. District Court for the Northern District of Texas.

An OpenAI spokesperson said in a statement: “This latest filing is consistent with Mr. Musk’s ongoing pattern of harassment.”

Representatives from Apple didn’t immediately respond to a request for comment.

The Tesla CEO launched xAI in 2023 in a bid to compete with OpenAI and other leading chatbot makers.

Read more CNBC tech news

Musk earlier this month threatened to sue Apple for “an unequivocal antitrust violation,” saying in a post on X that the company “is behaving in a manner that makes it impossible for any AI company besides OpenAI to reach #1 in the App Store.”

After Musk threatened to sue Apple, OpenAI CEO Sam Altman responded: “This is a remarkable claim given what I have heard alleged that Elon does to manipulate X to benefit himself and his own companies and harm his competitors and people he doesn’t like.”

An Apple spokesperson previously said its App Store was designed to be “fair and free of bias,” and that the company features “thousands of apps” using a variety of signals.

Apple last year partnered with OpenAI to integrate ChatGPT into iPhone, iPad, Mac laptop and desktop products.

Several users replied to Musk’s post on X via its Community Notes feature saying that rival chatbot apps such as DeepSeek and Perplexity were ranked No. 1 on the App Store after Apple and OpenAI announced their partnership.

The lawsuit is the latest twist in an ongoing clash between Musk and Altman. Musk co-founded OpenAI alongside Altman in 2015, before leaving the startup in 2018 due to disagreements over OpenAI’s direction.

Musk sued OpenAI and Altman last year, accusing them of breach of contract by putting commercial interests ahead of its original mission to develop AI “for the benefit of humanity broadly.”

In a counter claim, OpenAI has alleged that Musk and xAI engaged in “harassment” through litigation, attacks on social media and in the press, and through a “sham bid” to buy the ChatGPT-maker for $97.4 billion designed to harm the company’s business relationships.

OpenAI says Musk's filing is 'consistent with his ongoing pattern of harassment

Continue Reading

Technology

Nvidia’s new ‘robot brain’ goes on sale for $3,499 as company targets robotics for growth

Published

on

By

Nvidia's new 'robot brain' goes on sale for ,499 as company targets robotics for growth

Jensen Huang, CEO of Nvidia, is seen on stage next to a small robot during the Viva Technology conference dedicated to innovation and startups at Porte de Versailles exhibition center in Paris, France, on June 11, 2025.

Gonzalo Fuentes | Reuters

Nvidia announced Monday that its latest robotics chip module, the Jetson AGX Thor, is now on sale for $3,499 as a developer kit.

The company calls the chip a “robot brain.” The first kits ship next month, Nvidia said last week, and the chips will allow customers to create robots.

After a company uses the developer kit to prototype their robot, Nvidia will sell Thor T5000 modules that can be installed in production-ready robots. If a company needs more than 1,000 Thor chips, Nvidia will charge $2,999 per module.

CEO Jensen Huang has said robotics is the company’s largest growth opportunity outside of artificial intelligence, which has led to the Nvidia’s overall sales more than tripling in the past two years.

“We do not build robots, we do not build cars, but we enable the whole industry with our infrastructure computers and the associated software,” said Deepu Talla, Nvidia’s vice president of robotics and edge AI, on a call with reporters Friday.

The Jetson Thor chips are based on a Blackwell graphics processor, which is Nvidia’s current generation of technology used in its AI chips, as well as its chips for computer games.

Nvidia said that its Jetson Thor chips are 7.5 times faster than its previous generation. That allows them to run generative AI models, including large language models and visual models that can interpret the world around them, which is essential for humanoid robots, Nvidia said. The Jetson Thor chips are equipped with 128GB of memory, which is essential for big AI models.

Companies including Agility Robotics, Amazon, Meta and Boston Dynamics are using its Jetson chips, Nvidia said. Nvidia has also invested in robotics companies such as Field AI.

However, robotics remains a small business for Nvidia, accounting for about 1% of the company’s total revenue, despite the fact that it has launched several new robot chips since 2014. But it’s growing fast.

Nvidia recently combined its business units to group its automotive and robotics divisions into the same line item. That unit reported $567 million in quarterly sales in May, which represented a 72% increase on an annual basis.

The company said its Jetson Thor chips can be used for self-driving cars as well, especially from Chinese brands. Nvidia calls its car chips Drive AGX, and while they are similar to its robotics chips, they run an operating system called Drive OS that’s been tuned for automotive purposes.

Don’t miss these insights from CNBC PRO

Nvidia's China risks loom large ahead of earnings

Continue Reading

Trending