Simon Willison asked Meta AI what tools it had. It told him everything.

Simon Willison spent one afternoon with Meta AI and found 16 tools just sitting there, unhidden. That is the product strategy.

Meta is running the opposite AI business model from its competitors. OpenAI, Anthropic, and Google are building increasingly powerful models and gating access behind paywalls. Meta is building a full software development and data analysis environment and giving it away to three billion users. The tools are not features. They are proof that Meta is operating a different kind of AI business entirely: operational infrastructure at massive scale, not just model inference.

"The tools that a frontier AI company decides to expose tell you more about their product strategy than any benchmark number," Willison wrote after probing meta.ai. "You can see what they think their users will want to do." What Meta decided users want is a complete code execution environment, a visual system that can parse real images, social media search, and account linking across Instagram, Threads, Facebook, and WhatsApp. The definitions were not locked behind an NDA or a partner program. Willison pulled them by asking.

The most revealing detail is not what the tools do but how they are built. The Code Interpreter runs Python 3.9, an LTS release that reached end-of-life in October 2025, bundled with SQLite 3.34.1 from January 2021. That is not an oversight. Python 3.9 is the version that ships with most data science environments, the version numpy and pandas were built around, the version that does not change behavior between Tuesday and Wednesday. In a sandboxed execution environment with locked library versions, an end-of-life interpreter is not a risk. It is a feature. Meta is betting that its users will write code that needs to keep working in three years, not code that needs the latest syntax sugar. For an assistant embedded in WhatsApp and Instagram serving hundreds of millions of non-technical users, that is a coherent engineering posture. The alternative is chasing interpreter updates indefinitely, which is an operational burden that produces no visible benefit to the end user.

The visual grounding system is where the strategy becomes concrete. Willison prompted the model to generate an image of a raccoon wearing trash as a hat, then asked it to count what it saw. The system detected 12 raccoon whiskers, 8 paw claws, 2 eyes, 2 ears, and 3 trash items on the animal's head, returning bounding box coordinates for each. That output did not come from a demo environment or a carefully staged benchmark. It came from the live production system serving free users on meta.ai. Counting individual whiskers is a standard test case in visual grounding research, the kind of task that separates a system that has genuinely seen the world from one that has memorized captions. When that capability appears in production, unannounced, it means Meta has been shipping computer vision infrastructure to three billion people through an AI assistant. That is not a feature. That is a distribution event.

Muse Spark is the first model from Meta Superintelligence Labs, the unit CEO Mark Zuckerberg formed last year after reportedly growing frustrated that Llama models lagged behind OpenAI and Anthropic. To lead the effort, Meta recruited Alexandr Wang from Scale AI, where he was CEO, and invested $14.3 billion in Scale AI for a 49% stake. Zuckerberg has hired researchers from OpenAI, Anthropic, and Google, paying premiums that reflect how scarce senior AI talent has become. The model scored 52 on the Artificial Analysis broad index, tied for fourth behind Gemini 3.1 Pro, GPT-5.4, and Claude Opus 4.6. It is not the top of the leaderboard, and Meta is not pretending otherwise. The distribution play does not require first place. It requires good enough at a price point that no competitor can match.

The competitive logic is explicit. OpenAI charges $20 a month for Claude-level capability. Google and Anthropic are building toward similar paywalls. Meta is giving Muse Spark away to every WhatsApp user, every Instagram user, every Facebook user. The bet is that free access with genuine capability is enough to make the paid alternatives feel overpriced, the same way Android's free OS commoditized the smartphone market for everyone who was not Apple. The raccoon whiskers are evidence that the visual grounding works. The Python 3.9 stack is evidence that Meta is building for durability, not novelty. The 16 unhidden tools are evidence that Meta is not trying to create a product that impresses at a conference demo. It is trying to create an environment that its users actually live in.

Muse Spark is not open source. It runs on closed weights via a private API preview available to select partners, with broader access through meta.ai. Wang has said bigger models are already in development and that future versions will be open-sourced. In the coming weeks, Muse Spark will replace the Llama models currently powering AI features across WhatsApp, Instagram, Facebook, and Meta's smart glasses.

Meta did not respond to a request for comment.