Products·3 min read
By BitsMindsSource: NPR

Meta Builds ‘Arena,’ an AI Prediction-Market App

Mark Zuckerberg has ordered Meta to build a standalone prediction-market app, codenamed “Arena,” where users bet play money on real-world events — with Llama generating the questions, recommending markets, and resolving outcomes in near real-time.

META BUILDS A PREDICTION MARKET Codenamed “Arena” · play money · powered by Llama LIVE MARKET auto-generated by Llama Will the Fed cut rates in July? YES 62% NO 38% Zuckerberg-ordered rivals Kalshi · Polymarket Llama resolves outcomes BITSMINDS.COM
Share:

Meta is building a standalone prediction-market app — internally codenamed “Antwerp” and “FBForecast,” and slated to launch publicly as “Arena” — where users wager virtual “play money” on the outcome of real-world events, according to internal documents first reported by The New York Times and detailed by NPR on June 24. CEO Mark Zuckerberg personally ordered the team to start building it, a sign of how aggressively Meta wants into a sector some analysts project could swell into a roughly $1 trillion market.

What makes Arena a distinctly 2026 product is how much of it runs on AI. Meta plans to use Llama, its large language model, to automatically generate market questions from trending topics, serve “personalized market recommendations” to each user, and then resolve those markets in near real-time by judging whether the predicted outcome actually happened. In other words, the model writes the bets, pitches them to you, and calls the result — a degree of automation that the company hopes will avoid the manual-curation costs that sank its earlier effort.

Meta is wading into a crowded and combative field. Kalshi and Polymarket have turned event contracts into a mainstream phenomenon, and incumbents including DraftKings, FanDuel and Robinhood have rushed in alongside more than 70 other operators. Shares of several of those listed players slid when the Meta plans surfaced, reflecting fears that a platform with billions of users could reshape the economics of the category overnight. Meta's use of play money rather than cash is widely read as an attempt to capture the engagement of prediction markets while sidestepping the thicket of gambling regulation.

That regulatory thicket is real. Gaming lawyers describe the prediction-market space as being in “legal limbo,” with more than 30 pending lawsuits and an unresolved fight over whether the Commodity Futures Trading Commission has jurisdiction. The Trump administration is rewriting federal rules even as the cases work through the courts, leaving any new entrant exposed to sudden shifts in what is and isn't allowed.

Meta has been here before. It launched a crowdsourced prediction app called Forecast in 2020 and wound it down two years later, in part because keeping markets accurate and well-curated by hand proved expensive. The bet this time is that Llama can do cheaply and at scale what humans could not — generating, recommending and adjudicating markets automatically — turning a discarded experiment into a flagship use case for Meta's AI.

Want AI news before everyone else?

The morning's most important AI stories, straight to your inbox. No fluff.

Related Articles

OPEN SOURCE · APACHE 2.0 Intrinsic Core CONTROL · PERCEPTION · PLANNING BITSMINDS.COM
Products

Intrinsic Core: Google Open-Sources Its Robot Stack

Astra for Law: finding legal authority in a dedicated index In a dark burgundy law library, an open volume of case law lies on a walnut desk. A brass magnifying glass enlarges highlighted passages, connected by a fine gold line to a translucent legal search panel with the OpenAI emblem. The panel lists case law, statutes and regulations and displays 230 million plus indexed URLs, the corpus size cited in the article. Book spines repeat these source categories. The visual represents source retrieval and research; its illustrative page marks are not real case citations, and it does not imply that every answer is correct. Original editorial SVG for BitsMinds, openai-astra-for-law-legal-search-index. 18 September 2026. Conceptual legal-research illustration, not a product screenshot. Corpus size comes from the article. Astra for Law LEGAL RESEARCH CASE LAW STATUTES REGULATIONS U.S. LAW Astra for Law LEGAL SEARCH INDEX Search U.S. legal sources Case lawStatutesRegulations 230M+ INDEXED URLs CASE LAW AUTHORITIES & CITATIONS CASE LAW AUTHORITIES & CITATIONS U.S. CASE LAW · STATUTES · REGULATIONS BITSMINDS.COM
Products

OpenAI’s Astra for Law Scores 54% on Legal Research

Perplexity Portable Computer: the agent moves onto your PC An editorial illustration of a Windows workstation at night. The monitor shows Perplexity Portable Computer and a local task sequence. Beside it, the transparent side of a desktop tower reveals an illuminated Perplexity emblem, a circuit board and an RTX graphics card marked 24GB plus VRAM. A faint cloud and a closed permission gate sit in the background. Cyan and green light bring the on-device computing hardware into focus. The machine and interface are conceptual, not a specific commercial PC or an actual product screenshot. BitsMinds editorial illustration for perplexity-portable-computer-windows-rtx. Original vector artwork, 16 September 2026. PERPLEXITY / LOCAL AI BY PERMISSION perplexity ON DEVICE Portable Computer Your agent. Your hardware. Windows LOCAL RUNTIME LOCAL AGENT RTX LOCAL COMPUTE 24GB+ VRAM ON DEVICE BITSMINDS.COM PORTABLE COMPUTER / WINDOWS + RTX
Products

Perplexity's Local AI Agent Lands on Windows RTX PCs