44-Minute 3D Scene: Blender MCP + ThreeJs + Self-Built Skill Codex Workflow
OpenAIDevs · x · 2026-11-23
Developer @givros shows GPT 6.2 Sol generating a 'Valley of the Aqueduct' 3D scene in just 44 minutes, claiming quality comparable to the pricier Astra at lower cost and higher speed.
The method: a well-crafted prompt combined with Blender MCP, ThreeJs, and a self-nurtured skill codex improved on every project — a reproducible agent workflow for 3D content generation.
More from coding & agent
- Stanford's free RAG lecture goes beyond chunking: BM25, HNSW, and agents — stanfordnlp · 2026-11-23
- Don't trust your agent's 'verified' claim: 5 practical rules for AI self-verification — dotey · 2026-11-23
- Where Do You Draw the Line on Agent Permissions? Devs Weigh In on MCP's All-or-Nothing Token Problem — anishtr4 · 2026-11-23
- NomosGuard: Fail-Closed Security Core Where the LLM Writes Evidence but a Rules Engine Decides — Emergency-Tutor-7 · 2026-11-23
- Wrapflow Beta: A Remote MCP Server That Gives ChatGPT and Claude a Database, Backend and Hosting — SupPandaHugger · 2026-11-23
- Inkling-2-Mini hits 10.04x on KernelBench-Mega locally, beating Grok 4.7 and GPT-6.1 — ziqiao_ma · 2026-11-23