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.

Original post →

More from coding & agent

coding & agent channel →