Meta launches Muse Spark AI model, its first release since Zuckerberg's billion-dollar overhaul

Meta is reentering the AI race with a new model called Muse Spark

Meta Superintelligence Labs is launching its first model since Mark Zuckerberg spent billions overhauling the company's AI efforts. Called Muse Spark, the model now powers the Meta AI app and the Meta AI website in the US, per the company's announcement. In the coming weeks, Meta says, it will appear in WhatsApp, Instagram, Facebook, Messenger, and Meta's smart glasses, as well as roll out in other countries. Like Google Gemini, which easily integrates into Google's product suite, Meta touts Muse Spark as "purpose-built for Meta's products." The model, the first in a new series, will also be available to some of Meta's partners in private preview" via the API. The company promises the ability to run multiple AI sub-agents to handle queries better and faster, as well as support for multimodal input that includes both text and images. The latter is particularly relevant to Meta's AI-powered camera glasses, which it's bet on as the (latest) future of computing. It lets users toggle between a faster "Instant" mode and a "Thinking" mode that's supposed to deliver more thoroughly reasoned results, similar to options like Microsoft's Think Deeper. Meta also highlighted that Muse Spark can answer "complex questions in science, math, and health." Health-focused AI chatbots have been a controversial topic in recent months, as they handle sensitive personal data and can propagate misinformation. Meta said that Muse Spark's multimodal perception is "especially valuable for health" and can "navigate health questions with more detailed responses, including some questions involving images and charts." Meta may be looking to compete with OpenAI's ChatGPT Health and Anthropic's Claude for Healthcare, which both debuted in January. In its announcement, it showed its chatbot estimating a calorie count for a meal -- a popular, but often hit-or-miss, use of AI tech. In the future, Meta hopes the model will power new features "that cite recommendations and content people share across Instagram, Facebook, and Threads." The company also said that it has larger models in development and hopes to open-source future versions. It describes Muse Spark as an "early data point" on the trajectory of its new Muse series. The Muse series is set to be Meta's second major foray into powerful AI, following its Llama models. Zuckerberg revamped the company's AI program after the delayed and disappointing release of Llama 4 in 2025.

Meta Debuts First AI Model From Prized Superintelligence Group

Meta Platforms Inc. debuted its latest artificial intelligence model Wednesday -- its first since Chief Executive Officer Mark Zuckerberg embarked on a multibillion-dollar overhaul of the company's AI organization to keep pace with rivals. The highly anticipated model, known as Muse Spark, was created by Meta Superintelligence Labs, the new team of expensive AI researchers helmed by Chief AI Officer Alexandr Wang. Muse Spark will power the Meta AI chatbot, and in a pivot from the company's prior open-source strategy, is a closed model, meaning its design and code won't be made public. Meta shares jumped 6% in New York following the announcement. The model is the first major test for Zuckerberg's new AI lab, known as MSL. The Facebook founder recruited Wang as part of a $14 billion investment into Scale AI last year after a series of setbacks left him frustrated that the company wasn't keeping pace with competitors like OpenAI, Anthropic PBC, and Alphabet Inc.'s Google. Zuckerberg has since spent billions on AI talent and committed tens of billions more on infrastructure like data centers to catch up. Meta has tried to keep its AI division nimble, giving researchers autonomy and minimizing its typical management-heavy organizational structure, a company executive said. Wang has around 100 direct reports, said the executive, who asked not to be named discussing internal matters. The executive acknowledged that Muse Spark wasn't as capable in some areas as OpenAI's ChatGPT, Anthropic's Claude or Google's Gemini, but said that it was early in the company's execution. The model is "an early data point on our trajectory," with several larger models in development, Meta said in a blog post. Muse Spark, known internally as Avocado during development, was built over nine months and is seen by executives as a refresh of Meta's AI strategy, which was previously focused on its open-source Llama models. Wang is a proponent of closed models, and while Meta still plans to build open-source ones in the future, it is also considering selling API access to Muse Spark, according to the company executive. The Meta AI chatbot will remain free for users, but the company is considering implementing subscription fees in the future, the executive said. The name Muse Spark hints at the broader pipeline of AI offerings to come: The model is "sparking," or jump-starting, MSL's efforts, the executive said, describing it as small and fast. It is the first in a series of expected "Muse" models -- an homage to Zuckerberg's interest in Greek and Roman mythology. Get the Tech Newsletter bundle. Get the Tech Newsletter bundle. Get the Tech Newsletter bundle. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Bloomberg's subscriber-only tech newsletters, and full access to all the articles they feature. Plus Signed UpPlus Sign UpPlus Sign Up By continuing, I agree to the Privacy Policy and Terms of Service. Muse Spark was trained using several third-party open-source models, including Qwen from the Chinese tech giant Alibaba Group Holding Ltd., as well as ones from OpenAI and Google. Using a Chinese model runs counter to the stance taken by US policymakers and tech executives, who have raised concerns about China's position in a fast-moving AI race -- citing national security risks. Some of the largest American AI companies have tried to crack down on Chinese models similarly trained on US technology. "Like others across the industry, Meta uses techniques like distillation with strict safeguards in place to learn from openly available AI models and improve our own," said a Meta spokesperson. Like its competitors, Muse Spark offers several levels of reasoning: "Instant" mode, "Thinking" mode and "Contemplating" mode -- the last providing research-grade responses. The Meta executive said the model is good at answering questions about science, health and math, but weaker at coding. The model will be used to improve Meta's fleet of apps, from Instagram to Facebook to WhatsApp. It is already powering an early-stage shopping agent that aims to help users better search for products like clothing or furniture. The agent cannot yet make purchases on a user's behalf, and is still in early stages, the executive said.

Meta unveils first AI model from costly superintelligence team

April 8 (Reuters) - Meta Platforms (META.O), opens new tab on Wednesday unveiled Muse Spark, the first artificial intelligence model from a costly team it assembled last year to catch up with rivals in the AI race. U.S. tech giants are under pressure to prove their massive AI outlays will pay off. The stakes are especially high for Meta after it hired Scale AI CEO Alex Wang last year under a $14.3 billion deal and offered some engineers pay packages of hundreds of millions of dollars to staff a new superintelligence team. Muse Spark is the first in a new ⁠series of models from that team, which is pursuing machines that can outthink humans. It will initially be available only on the lightly-used Meta AI app and website, and in the coming weeks, replace the existing Llama models powering chatbots on WhatsApp, Instagram, Facebook and Meta's collection of smart glasses. "This initial model is small and fast by design, yet capable enough to reason through complex questions in science, math, and health. It is a powerful foundation, and the next generation is already in development," the company said in a blog post. It did not ⁠disclose the model's size, a key measure typically used to compare an AI system's computing power with rivals. Muse Spark is part of a family of models known internally as Avocado. The model can help users with tasks such as estimating the calories in a meal from a photo or ⁠superimposing an image of a mug on a shelf to see how it looks - features that some rivals already offer. Meta also released Contemplating mode, which runs multiple AI agents in parallel to boost reasoning ⁠power, allowing Muse Spark to take on the extended thinking modes of Google's Gemini Deep Think and OpenAI's GPT Pro. The company is betting that applying superintelligence to everyday personal ⁠tasks will help it tap its more than 3.5 billion users across its social media platforms, potentially giving it an edge over rivals with a smaller reach. Reporting by Aditya Soni in Bengaluru and Katie Paul in New York; Editing by Leroy Leo Our Standards: The Thomson Reuters Trust Principles., opens new tab

Meta releases first AI model since Zuckerberg's spending spree

Meta has launched its first AI model since chief executive Mark Zuckerberg led a multibillion-dollar spending spree on talent and infrastructure, in the first test of its efforts to catch up with rivals including OpenAI and Google. The $1.5tn social media platform on Wednesday unveiled Muse Spark, which it said had been "purpose-built" for use across its products. Zuckerberg signalled earlier this year that the release would not yet match the most advanced systems from rivals. But the company said Muse Spark would "power a smarter and faster" version of Meta AI, its virtual assistant. It added that the model would enable more personalised and visual responses, drawing on content shared across Instagram, Facebook and Threads. "Expect richer, more visual results, with Reels, photos and posts woven directly into your answers, with credit back to the content creators," the company said. Meta also said its new model had strong applications in healthcare, with the company saying it had worked with more than 1,000 doctors to train the model to generate more detailed responses on topics such as nutrition and exercise. Using the model, Meta AI will also offer a "shopping mode" to help users compare prices. Unlike Meta's previous Llama models, which have been "open" -- or freely available for developers to tweak -- Muse Spark is a smaller, closed model. The company intends to offer a "private preview . . . [to] select partners". Meta said it hoped to open source future versions. The release offers an early indication of how Zuckerberg plans to incorporate Meta's social media content into its chatbot, as part of his promise to develop "personal superintelligence". It comes as the billionaire faces increasing pressure from investors to justify his colossal AI spending. Over the past year, the chief executive has poured billions of dollars into building out a fleet of data centres and poaching rival AI researchers with packages reaching as much as 10 figures. This is part of an all-out push to catch up in developing cutting-edge models after its previous model, Llama 4, fell below expectations last April, prompting Zuckerberg to carry out a rapid series of executive reshuffles and restructurings of Meta's AI efforts. The resulting "Meta Superintelligence Lab" is led by Alexandr Wang, 29, who joined after the Big Tech group invested $15bn in his data-labelling start-up Scale AI. Within the new lab, Wang also leads a small, secretive team of elite AI researchers called "TBD" -- To Be Determined -- focused on spearheading the development of state of the art models. Muse Spark beat leading models from Google, OpenAI and Anthropic in select benchmarks on reasoning and multimodal capabilities, according to evaluations shared by Meta. But the company acknowledged that the model is not yet cutting-edge in certain areas, adding: "We continue to invest in areas with current performance gaps, specifically long-horizon agentic systems and coding workflows." Zuckerberg said in January that he expected the company to "steadily push the frontier over the course of the year as we continue to release new models". With Muse Spark, Meta appears to lean into niche capabilities such as health, arguing that it is "one of the top reasons people turn to AI". Rival OpenAI in January launched ChatGPT Health, a specialised feature that allows users to connect their medical records and fitness apps to its AI to get personalised health advice. Meta has also been working to improve the model's "multimodal perception", such as recognising objects in photos. Zuckerberg last year said the company was doubling down on its investment in AI glasses, arguing wearable devices are vital to his bet on "superintelligence". "When Meta AI powered by Muse Spark comes to our AI glasses, the assistant will be able to better see and understand the world around you," the company said.

Meta's Muse Spark model brings reasoning capabilities to the Meta AI app

Following the icy reception to Llama 4, Meta is releasing the first in a new family of AI systems built by its recently formed Superintelligence team. The company is kicking off its new Muse era with Spark, a lightweight model geared toward consumer use. In the future, Meta plans to offer more capable versions of Muse, but for now, it's clear the company wants to nail the basics. To that point, many of Spark's capabilities are table stakes for a new model in 2026. For instance, it offers both "Instant" and "Thinking" modes. With the latter engaged, the model will take an extra few moments to reason through a prompt. Other consumer-facing AI systems have had this kind of flexibility for a while. Anthropic, for example, was one of the first AI labs to offer a "hybrid reasoning model" when it released Claude Sonnet 3.7 at the start of last year. That said, Meta plans to add an even more powerful "Contemplating" mode down the road. Muse Spark can also coordinate multiple AI subagents to tackle a request. Meta suggests users will see this capability in action when they ask for help with tasks like family trip planning. In such a scenario, one agent might compile an itinerary, while another finds kid-friendly activities everyone can enjoy. At the same time, Meta has built Spark to be natively multimodal, meaning the model can process images, video and audio. Like Google Lens, this gives you the option to snap a photo with your phone and ask Meta AI questions about what you see. Of course, it wouldn't be a 2026 AI release if Muse Spark didn't include a built-in shopping assistant. Like ChatGPT, Spark can compare different items for you, listing the pros and cons of each, with links to make it easy to buy the product that appeals to you. Muse Spark is available today in the Meta AI app and meta.ai website everywhere where the company offers those services. Meta will begin rolling out the new features the model powers starting in the US. In the coming weeks, the company plans to bring Muse Spark to more countries and places where people can access Meta AI, including Facebook, Instagram and WhatsApp. Additionally, Meta says it "hopes to open source future versions of the model." We'll see if the company ends up doing that; last year, Meta CEO Mark Zuckerberg appeared to flip flop on the company's open source stance, saying it would need to be more "rigorous" about such decisions moving forward.

Meta debuts new AI model, attempting to catch Google, OpenAI after spending billions

Meta CEO Mark Zuckerberg makes a keynote speech at the Meta Connect annual event at the company's headquarters in Menlo Park, Calif., on Sept. 25, 2024. Meta is debuting its first major artificial intelligence model since the costly hiring of Scale AI's Alexandr Wang nine months ago, as the Facebook parent aims to carve out a niche in a market that's being dominated by OpenAI, Anthropic and Google. Dubbed Muse Spark and originally codenamed Avocado, the AI model announced Wednesday is the first from the company's new Muse series developed by Meta Superintelligence Labs, the AI unit that Wang oversees. Wang joined Meta in June as part of the company's $14.3 billion investment in Scale AI, where he was CEO. Meta is desperate to regain momentum in the fiercely competitive AI market following the disappointing debut of its Llama 4 family of AI models last April. With Llama, Meta had been taking an open-source approach to AI, in contrast to the proprietary models offered by rivals, but Llama 4 failed to captivate developers, leading to CEO Mark Zuckerberg to pivot his strategy. "Over the last nine months, Meta Superintelligence Labs rebuilt our AI stack from the ground up, moving faster than any development cycle we have run before," Meta said in a blog post on Wednesday. "This initial model is small and fast by design, yet capable enough to reason through complex questions in science, math, and health. It is a powerful foundation, and the next generation is already in development." The new Muse Spark will be proprietary, instead of open source, with the company saying there is "hope to open-source future versions of the model." Meta said in a technical blog about the new model that that improved AI training techniques along with rebuilt technology infrastructure has enabled the company to create smaller AI models that are as capable as its older midsize Llama 4 variant for "an order of magnitude less compute." "Muse Spark offers competitive performance in multimodal perception, reasoning, health, and agentic tasks," Meta said in the post. "We continue to invest in areas with current performance gaps, specifically long-horizon agentic systems and coding workflows."

Meta Unveils New A.I. Model, Its First From the Superintelligence Lab

The model, Muse Spark, performed better than Meta's previous A.I. models but lags rivals on coding ability. Meta on Wednesday unveiled a new flagship artificial intelligence model called Muse Spark, its first under the revamped A.I. division that Mark Zuckerberg spent billions to build last year as the company pushes to catch up to rivals. On tests that measure writing and reasoning, Muse Spark performed significantly better than Meta's previous A.I. models and was nearly as good as the top models from competitors like Google, OpenAI and Anthropic, according to data provided by Meta. But the model still lagged on coding ability, which has become the focus of Anthropic and others in the wider A.I. race. Meta's announcement comes one day after Anthropic said its latest A.I. model, Mythos, was too powerful to safely release because of cybersecurity threats. How Meta's new A.I. model performs is being closely watched. Anthropic, Google and OpenAI are regarded as the leaders in developing foundational A.I. models and Mr. Zuckerberg, Meta's chief executive, has pledged to catch up at any cost. Last year, he shelled out billions to recruit a group of A.I. specialists to form a "superintelligence" lab to help with the effort. The model is a test of that new leadership under Alexandr Wang, the 29-year-old Silicon Valley entrepreneur who Mr. Zuckerberg hired to be the chief A.I. officer.

Meta debuts Muse Spark, first AI model under Alexandr Wang

Why it matters: The model -- code-named Avocado and built over the past nine months by a team led by Alexandr Wang -- is a major upgrade over its Llama 4 models, Meta tells. Driving the news: Muse Spark will power queries in the Meta AI app and Meta.ai website immediately, with plans to expand across Facebook, Instagram and WhatsApp. * The model accepts voice, text and image inputs, but produces text-only output. * As Axios first reported, Meta plans to release a version of Muse Spark under an open-source license. Zoom in: The model uses a fast mode for casual queries and several reasoning modes. * A "shopping mode" highlights how Meta hopes to differentiate itself. It combines large language models with data on user interests and behavior. * Over time, the model will also power "features that cite recommendations and content people share across Instagram, Facebook, and Threads," Meta said in a blog post. Zoom out: A Meta executive told Axios that Muse Spark doesn't mark a new state of the art, but is competitive with the latest models from leading labs at certain tasks, including multimodal understanding and processing health information. * In other areas, including coding, the company acknowledges that there is a gap between Muse Spark and the models already available. * All flavors of the model are free to use, though Meta may impose rate limits. Yes, but: Consumers should be aware that Meta's privacy policy sets few limits on how the company can use any data shared with its AI system. The big picture: Meta sees the release of Muse Spark as just one step toward its broader vision of personal superintelligence.

Mark Zuckerberg announces Spark, a new Meta AI model: How to try it

Mark Zuckerberg announced Wednesday that Meta Superintelligence Labs has reached its first major milestone: a new family of AI models called Muse, with the debut model, Spark, available now. In a Facebook post, Zuckerberg said that Spark now powers an updated version of Meta AI, which users can access online at meta.ai. Spark is designed to be particularly capable in areas tied to everyday personal use -- tasks like visual understanding, health, shopping, and social content. Looking ahead, Zuckerberg said Meta is building products that go beyond answering questions, toward AI that acts as agents "that do things for you." Future AI models in the Muse lineup will also include new open-source releases. The announcement marks the public debut of work that has been underway -- and at times turbulent -- since last summer. When Zuckerberg first laid out his vision for "personal superintelligence" in a July 2025 manifesto, the ambition was an AI that helps people pursue their own goals rather than one controlled from the top down. To build it, Meta went on one of the most aggressive hiring sprees in recent memory, personally recruiting more than 50 researchers from rivals including OpenAI, Anthropic, and Google, and bringing in former Scale AI chief Alexandr Wang to lead its new superintelligence research group. Then, just as quickly, Meta froze hiring altogether -- citing routine budget planning -- and restructured the team into four smaller units focused on research, superintelligence development, products, and infrastructure. Zuckerberg explained the pivot by saying he believes breakthrough AI work is best done by compact teams who can hold the full picture in their heads, rather than sprawling organizations. The whiplash raised eyebrows amid broader market jitters about whether the AI boom is sustainable. An MIT study circulating at the time found the vast majority of companies deploying AI were seeing no financial return. In his original manifesto, Zuckerberg drew a sharp philosophical line between Meta and its competitors, arguing that some AI labs want to concentrate superintelligence and pipe its output to humanity like a utility. Meta sees it differently, he said. In Wednesday's post, he once again framed the lab's founding goal as "putting personal superintelligence in everyone's hands" -- with the underlying belief that empowering individuals, not centralizing intelligence, is how humanity moves forward. Wednesday's Muse announcement will be the first concrete product to emerge from these multi-billion-dollar investments. (Meta allocated $72 billion in AI development in 2025 and is expected to spend up to $135 billion in 2026.) So far, Meta's Llama family of AI models has lagged far behind its rivals on AI leaderboards. Whether Spark lives up to the superintelligence branding remains to be seen, but after months of hiring drama, restructuring, and big-picture theorizing, Meta has finally put something on the table. As Zuckerberg put it: "I'm looking forward to sharing more soon."

Meta unveils first AI model from superintelligence team

Meta Platforms on Wednesday unveiled Muse Spark, the first artificial intelligence model from a team it assembled last year through a costly talent war and sweeping internal restructuring to catch up with rivals in the AI ⁠race. Meta Platforms on Wednesday unveiled Muse Spark, the first artificial intelligence model from a team it assembled last year through a costly talent war and sweeping internal restructuring to catch up with rivals in the AI ⁠race. US ⁠tech giants are under pressure to prove their massive AI outlays will pay off. The stakes are especially high for Meta after it hired Scale AI CEO Alex Wang last year under a $14.3 billion deal and offered some engineers ⁠pay packages of hundreds of millions of dollars to staff a new superintelligence team. Muse ⁠Spark is the first in a new series of models from that team, which is pursuing machines that can outthink humans. It will initially be available only on the lightly-used Meta AI app and website, and in the coming weeks, replace the existing Llama models powering chatbots on WhatsApp, Instagram, Facebook and Meta's collection of smart glasses. "This initial model is small ⁠and fast by design, yet capable enough to reason through complex questions in science, math, and health. It is a powerful foundation, and the next generation is already in development," the company said in a blog post.

Meta Platforms surges 7% amid AI model debut By Investing.com

Investing.com -- Meta Platforms (NASDAQ:META) shares rose 7% Wednesday following the company's introduction of Muse Spark, its first artificial intelligence model release since Chief Executive Officer Mark Zuckerberg initiated a multibillion-dollar reorganization of its AI operations. The stock gained amid broad strength in technology shares and the debut of the new AI model, which represents the initial offering in Meta's Muse family developed by Meta Superintelligence Labs. Muse Spark features native multimodal reasoning capabilities, including tool-use support, visual chain of thought, and multi-agent orchestration. The model is available at meta.ai and through the Meta AI app, with a private API preview opening to select users. Meta also introduced Contemplating mode, which operates multiple agents that reason simultaneously, achieving 58% performance in Humanity's Last Exam and 38% in FrontierScience Research. The company rebuilt its pretraining stack over nine months with improvements to model architecture, optimization, and data curation. Meta reports reaching the same capabilities with over an order of magnitude less compute compared to its previous model, Llama 4 Maverick. The model's applications include multimodal visual integration across domains and health reasoning capabilities. Meta collaborated with over 1,000 physicians to develop training data for health-related responses. Muse Spark can generate interactive displays explaining nutritional content and muscles activated during exercise. In safety evaluations conducted under Meta's Advanced AI Scaling Framework, Muse Spark demonstrated strong refusal behavior across high-risk domains including biological and chemical weapons. Third-party evaluations by Apollo Research found the model showed the highest rate of evaluation awareness among models they have observed.

Meta Platforms Rises on Release of New AI Model

Shares of Meta Platforms gained after the company announced a new large language artificial-intelligence model. The stock was up 6.6%, at $613.05, midday Wednesday, but has fallen about 7.1% year-to-date. The model, Muse Spark, is the first of an upcoming family of models developed by Meta Superintelligence Labs, the company said in a Wednesday blog post. Meta has poured billions of dollars to hire AI talent in a push to catch up to frontier AI labs such as OpenAI, Anthropic, and Google DeepMind, according to The Wall Street Journal. "Muse Spark is the first step on our scaling ladder and the first product of a ground-up overhaul of our AI efforts," Meta said. The company said it is opening a private application programming interface preview to certain users. Meta may open-source some versions of the model, but doesn't have plans to widely release its API, the Journal reported. The model outscored Google Gemini on some internal tests and was competitive with OpenAI and Anthropic models on others, while significantly beating xAI's Grok on many benchmarks, Meta said.

Meta unveils first AI model from costly superintelligence team

April 8 (Reuters) - Meta Platforms on Wednesday unveiled Muse Spark, the first artificial intelligence model from a costly team it assembled last year to catch up with rivals in the AI race. Shares of the company extended gains to trade up nearly 7%. U.S. tech giants are under pressure to prove their massive AI outlays will pay off. The stakes are especially high for Meta after it hired Scale AI CEO Alex Wang last year under a $14.3 billion deal and offered some engineers pay packages of hundreds of millions of dollars to staff a new superintelligence team. Superintelligence refers to AI machines that could outthink humans. Muse Spark is the first in a new series of models from that team, and is part of a family of models known internally as Avocado. The model will initially be available only on the lightly-used Meta AI app and website, and in the coming weeks, replace the existing Llama models powering chatbots on WhatsApp, Instagram, Facebook and Meta's collection of smart glasses. "This initial model is small and fast by design, yet capable enough to reason through complex questions in science, math, and health. It is a powerful foundation, and the next generation is already in development," the company said in a blog post. It did not disclose the model's size, a key measure typically used to compare an AI system's computing power with rivals. Meta CEO Mark Zuckerberg had tempered expectations for performance, telling investors in January that he thought the team's first models "will be good but, more importantly, will show the rapid trajectory that we're on." "I expect us to steadily push the frontier over the course of the year as we continue to release new models," he had said. FOCUS ON EVERYDAY TASKS Muse Spark can help users with tasks such as estimating the calories in a meal from a photo or superimposing an image of a mug on a shelf to see how it looks. Meta also released Contemplating mode, which runs multiple AI agents in parallel to boost reasoning power, allowing Muse Spark to take on the extended thinking modes of Google's Gemini Deep Think and OpenAI's GPT Pro. The company is betting that applying superintelligence to everyday personal tasks will help it tap its more than 3.5 billion users across its social media platforms, potentially giving it an edge over rivals with a smaller reach. (Reporting by Aditya Soni in Bengaluru and Katie Paul in New York; Editing by Leroy Leo)

Meta unveils first AI model from superintelligence team

April 8 (Reuters) - Meta Platforms on Wednesday unveiled Muse Spark, the first artificial intelligence model from a team it assembled last year through a costly talent war and sweeping internal restructuring to catch up with rivals in the AI race. U.S. tech giants are under pressure to prove their massive AI outlays will pay off. The stakes are especially high for Meta after it hired Scale AI CEO Alex Wang last year under a $14.3 billion deal and offered some engineers pay packages of hundreds of millions of dollars to staff a new superintelligence team. Muse Spark is the first in a new series of models from that team, which is pursuing machines that can outthink humans. It will initially be available only on the lightly-used Meta AI app and website, and in the coming weeks, replace the existing Llama models powering chatbots on WhatsApp, Instagram, Facebook and Meta's collection of smart glasses. "This initial model is small and fast by design, yet capable enough to reason through complex questions in science, math, and health. It is a powerful foundation, and the next generation is already in development," the company said in a blog post. (Reporting by Aditya Soni in Bengaluru and Katie Paul in New York; Editing by Leroy Leo)