GPT-6 Astra + Blender MCP produces a 489MB all-3D hotel website concept
sidahuj · x · 2026-10-14
Developer AmirMushich used GPT-6 Astra via Blender MCP to build an all-3D wilderness hotel website concept, orchestrating Codex and Voyager agents: 13,698 meshes, 10.7M triangles, 489MB scene, despite not knowing 3D himself.
His takeaway: learning software was the creative bottleneck for decades; now attention is the only bottleneck left. A representative demo of MCP-driven 3D content pipelines.
Related event: Dev Builds Fully 3D Hotel Website Concept with GPT-6 Astra via Blender MCP(2 posts)→
More from coding & agent
- One-shot flying dragon: Gemini 4 Argon with Blender MCP and Tripo 3D builds a pure .blend scene — sidahuj · 2026-10-14
- Llamaforge v0.16: a control panel for upstream llama.cpp with local agents whose quotes are code-verified — Sleepybear2611 · 2026-10-14
- hexvero: a binary-analysis MCP server with a 3k-token tool catalog vs ~510k for the incumbent — ImaginationVarious30 · 2026-10-14
- Questioning OpenAI's Decisions API: are cloud round-trip latency and privacy viable in production? — WhichCardiologist800 · 2026-10-14
- Factory engineer: third-party agent harnesses can beat Claude Code and Codex even on their own models — matanSF · 2026-10-14
- teamai unifies Skills, rules and MCP configs for teams juggling multiple AI coding tools — sujingshen · 2026-10-14