GLM-5.3 autonomous 12-hour run: Prompt for Blender scene generation
majidmanzarpour · x · 2026-09-02
The author released the prompt used to make GLM-5.3-Flash run autonomously for 12 hours to build a Blender scene. Consuming around 100 million tokens, the model started from an empty folder, wrote Python scripts via Blender CLI, and iterated by checking renders until the result met quality standards. The prompt includes detailed task specs, environment constraints, and validation rubrics.
More from coding & agent
- LLM one-shots a Minecraft 3x3 piston door by building its own Linux test infra — Vjeux · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Solo founder builds a money-printing data service on Claude's Pi Durable harness — MicahBerkley · 2026-10-18
- Dev builds Arch-based OS with custom desktop and browser using Claude Code — Snoo-10493 · 2026-10-18
- Five SaaS agent workflows fail the same way — and it's never model intelligence — usehive · 2026-10-18
- Claude skill generates hand-drawn interactive diagrams that teach kids how things work — CatAstro_Piyush · 2026-10-18