AIToday
Large Language ModelsAI Coding AssistantsSimon Willison's WeblogPublished: Aug 6, 2026, 06:01 JST

Claude builds full 3D browser game from 2024 tweet in one session

Claude builds full 3D browser game from 2024 tweet in one session

3 Key Points

  1. What happened

    Simon Willison prompted Claude Fable 5 (running in Claude Code for web) to build a complete 3D browser game called Raccoon Heist based on concept art and description from a 2024 tweet. Claude produced a working, playable game with procedural 3D characters, dynamically generated textures via OpenAI's image API, mobile touch controls, and a procedural WebAudio soundtrack—all without requiring further input from Willison after the initial prompt.

  2. Why it matters

    This demonstrates that current AI coding assistants can autonomously build complex, multi-system projects (3D graphics, game logic, mobile UI, audio synthesis, testing automation) in a single session. The game uses GitHub Pages for live preview during development, letting Claude iterate and self-test in real time using Playwright screenshots—a workflow that bypasses the friction of traditional back-and-forth iteration.

  3. What to watch

    The game is playable now at the GitHub Pages deployment; Willison's full transcript of Claude's decisions is publicly accessible. The mechanic of coupling Claude Code with GitHub Pages for immediate visual feedback appears to work well enough that Willison used it to defer all design decisions to the AI, asking only for autonomous quality and fun—a rare example of letting an AI fully own a creative project without human handholding.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

Willison's original 2024 tweet contained a GPT-3-generated game concept and DALL-E concept art for a raccoon heist game. Two years later, he decided to test whether a modern AI coding assistant could build the entire game from those artifacts alone, with minimal instruction. The key innovation here is not just that Claude succeeded, but the infrastructure Willison used to make the task tractable: GitHub Pages as a live-preview system during development, coupled with Claude Code's ability to commit and push changes in real time. This removed the friction of "show me what you've built so far"—Willison could watch the game materialize incrementally in the browser without leaving his phone, where he wrote the entire prompt in Notes. Claude's decision to use Playwright for self-testing is particularly striking; the AI didn't just build features, it verified them with automated playthroughs, caught canvas rendering bugs that desktop-only testing had masked, and wrote regression tests. The game itself is complete: three escalating difficulty levels, procedurally generated low-poly characters, collision detection, guards with line-of-sight logic, a scent-tracking hound that ignores line-of-sight, mobile UI, and a persistent high-score system. All textures and the title art were generated via the OpenAI API and baked into the repo, so the live game makes no external API calls.

FAQ
Can I play the game now?
Yes. The game is live on GitHub Pages at the repository branch claude/3d-raccoon-heist-game-50n293. The gameplay involves a masked raccoon sneaking out of a dumpster hideout to collect coins, gems, rings, donuts, and fish, then returning them before dawn; difficulty escalates over three nights, adding more guards and a scent-tracking hound.
How did Claude test its own work?
Claude used Playwright to take screenshots of the game at different screen sizes (desktop, portrait phone, landscape phone) and execute automated playthroughs to verify core gameplay flows—pickup, banking, chase, caught, night progression, and win/lose states. This caught two real bugs: the canvas rendering at 2× size on real phones, and a CSS inheritance issue blocking the "next night" button.
What tools and APIs did Claude use?
Claude vendored Three.js for 3D rendering (no CDN), used OpenAI's gpt-image-2 API to generate seven ground/wall textures and the title-screen art (all committed as static assets so the deployed game makes no runtime API calls), and wrote a procedural WebAudio soundtrack using JavaScript—zero audio files. Mobile gets a dynamic touch joystick; desktop uses WASD/arrows and Space.
Simon Willison's WeblogRead Original Article

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleAvnet, Weston Robot launch edge AI inspection robot for factories