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 agrees to pay Texas $1.4 billion data privacy settlement

Published

on

By

Google agrees to pay Texas .4 billion data privacy settlement

A Google corporate logo hangs above the entrance to the company’s office at St. John’s Terminal in New York City on March 11, 2025.

Gary Hershorn | Corbis News | Getty Images

Google agreed to pay nearly $1.4 billion to the state of Texas to settle allegations of violating the data privacy rights of state residents, Texas Attorney General Ken Paxton said Friday.

Paxton sued Google in 2022 for allegedly unlawfully tracking and collecting the private data of users.

The attorney general said the settlement, which covers allegations in two separate lawsuits against the search engine and app giant, dwarfed all past settlements by other states with Google for similar data privacy violations.

Google’s settlement comes nearly 10 months after Paxton obtained a $1.4 billion settlement for Texas from Meta, the parent company of Facebook and Instagram, to resolve claims of unauthorized use of biometric data by users of those popular social media platforms.

“In Texas, Big Tech is not above the law,” Paxton said in a statement on Friday.

“For years, Google secretly tracked people’s movements, private searches, and even their voiceprints and facial geometry through their products and services. I fought back and won,” said Paxton.

“This $1.375 billion settlement is a major win for Texans’ privacy and tells companies that they will pay for abusing our trust.”

Google spokesman Jose Castaneda said the company did not admit any wrongdoing or liability in the settlement, which involves allegations related to the Chrome browser’s incognito setting, disclosures related to location history on the Google Maps app, and biometric claims related to Google Photo.

Castaneda said Google does not have to make any changes to products in connection with the settlement and that all of the policy changes that the company made in connection with the allegations were previously announced or implemented.

“This settles a raft of old claims, many of which have already been resolved elsewhere, concerning product policies we have long since changed,” Castaneda said.

“We are pleased to put them behind us, and we will continue to build robust privacy controls into our services.”

Continue Reading

Technology

Virtual chronic care company Omada Health files for IPO

Published

on

By

Virtual chronic care company Omada Health files for IPO

Omada Health smart devices in use.

Courtesy: Omada Health

Virtual care company Omada Health filed for an IPO on Friday, the latest digital health company that’s signaled its intent to hit the public markets despite a turbulent economy.

Founded in 2012, Omada offers virtual care programs to support patients with chronic conditions like prediabetes, diabetes and hypertension. The company describes its approach as a “between-visit care model” that is complementary to the broader health-care ecosystem, according to its prospectus.

Revenue increased 57% in the first quarter to $55 million, up from $35.1 million during the same period last year, the filing said. The San Francisco-based company generated $169.8 million in revenue during 2024, up 38% from $122.8 million the previous year.

Omada’s net loss narrowed to $9.4 million during its first quarter from $19 million during the same period last year. It reported a net loss of $47.1 million in 2024, compared to a $67.5 million net loss during 2023.

The IPO market has been largely dormant across the tech sector for the past three years, and within digital health, it’s been almost completely dead. After President Donald Trump announced a sweeping tariff policy that plunged U.S. markets into turmoil last month, taking a company public is an even riskier endeavor. Online lender Klarna delayed its long-anticipated IPO, as did ticket marketplace StubHub.

But Omada Health isn’t the first digital health company to file for its public market debut this year. Virtual physical therapy startup Hinge Health filed its prospectus in March, and provided an update with its first-quarter earnings on Monday, a signal to investors that it’s looking to forge ahead.

Omada contracts with employers, and the company said it works with more than 2,000 customers and supports 679,000 members as of March 31. More than 156 million Americans suffer from at least one chronic condition, so there is a significant market opportunity, according to the company’s filing.

In 2022, Omada announced a $192 million funding round that pushed its valuation above $1 billion. U.S. Venture Partners, Andreessen Horowitz and Fidelity’s FMR LLC are the largest outside shareholders in the company, each owning between 9% and 10% of the stock.

“To our prospective shareholders, thank you for learning more about Omada. I invite you join our journey,” Omada co-founder and CEO Sean Duffy said in the filing. “In front of us is a unique chance to build a promising and successful business while truly changing lives.”

WATCH: The IPO market is likely to pick up near Labor Day, says FirstMark’s Rick Heitzmann

The IPO market is likely to pick up near Labor Day, says FirstMark's Rick Heitzmann

Continue Reading

Technology

Google would need to shift up to 2,000 employees for antitrust remedies, search head says

Published

on

By

Google would need to shift up to 2,000 employees for antitrust remedies, search head says

Liz Reid, vice president, search, Google speaks during an event in New Delhi on December 19, 2022.

Sajjad Hussain | AFP | Getty Images

Testimony in Google‘s antitrust search remedies trial that wrapped hearings Friday shows how the company is calculating possible changes proposed by the Department of Justice.

Google head of search Liz Reid testified in court Tuesday that the company would need to divert between 1,000 and 2,000 employees, roughly 20% of Google’s search organization, to carry out some of the proposed remedies, a source with knowledge of the proceedings confirmed.

The testimony comes during the final days of the remedies trial, which will determine what penalties should be taken against Google after a judge last year ruled the company has held an illegal monopoly in its core market of internet search.

The DOJ, which filed the original antitrust suit and proposed remedies, asked the judge to force Google to share its data used for generating search results, such as click data. It also asked for the company to remove the use of “compelled syndication,” which refers to the practice of making certain deals with companies to ensure its search engine remains the default choice in browsers and smartphones. 

Read more CNBC tech news

Google pays Apple billions of dollars per year to be the default search engine on iPhones. It’s lucrative for Apple and a valuable way for Google to get more search volume and users.

Apple’s SVP of Services Eddy Cue testified Wednesday that Apple chooses to feature Google because it’s “the best search engine.”

The DOJ also proposed the company divest its Chrome browser but that was not included in Reid’s initial calculation, the source confirmed.

Reid on Tuesday said Google’s proprietary “Knowledge Graph” database, which it uses to surface search results, contains more than 500 billion facts, according to the source, and that Google has invested more than $20 billion in engineering costs and content acquisition over more than a decade.

“People ask Google questions they wouldn’t ask anyone else,” she said, according to the source.

Reid echoed Google’s argument that sharing its data would create privacy risks, the source confirmed.

Closing arguments for the search remedies trial will take place May 29th and 30th, followed by the judge’s decision expected in August.

The company faces a separate remedies trial for its advertising tech business, which is scheduled to begin Sept. 22.

Continue Reading

Trending