Claude Generates Complex 3D World and Game Engine from Vague Prompt
repligate · x · 2026-07-31
A developer used Claude to generate a large-scale 3D world in one shot from a very vague prompt about building a realistic castle town.
Using only Three.js, the model constructed buildings, procedural textures, and even a time-of-day system and viewer. It autonomously took screenshots to self-correct and maintained focus to completion, demonstrating impressive self-direction and engineering capability.
Related event: Claude Generates 3D Games and Scenes via Single Prompts(7 posts)→
More from coding & agent
- Harness open-sources desktop and mobile apps for orchestrating agent fleets across frameworks and machines — dee_hw · 2026-10-16
- Open-Source Google Analytics MCP Server Lets LLMs Query GA Data via Natural Language — modelcontextprotocol · 2026-10-16
- LLM ideation experiment: just ask for non-obvious ideas — and Opus beats smaller models by a wide margin — arjunrajlab · 2026-10-16
- a16z podcast: AI cut a 6-month feature to 10 days and widened engineer gaps 10x — a16z · 2026-10-16
- "Hold On, My Agents Are Freezing My Screen": The Daily Grind of the Agent Era — every · 2026-10-16
- Dev builds MCP feeding Claude 3,000 real launch videos to fix samey AI output — Designer_Landscape25 · 2026-10-16