Voice-to-3D: AI builds a sunset Taj Mahal in Blender via MCP, shadows aside
Yamapama · x · 2026-09-21
A user demoed having an AI assistant build a 3D model directly in Blender through MCP for Blender — a single prompt, "make a 3D model of the Taj Mahal at sunset," produced a finished scene with rendering.
A reply nitpicked that the tree shadows weren't physically accurate, a reminder that agentic 3D modeling still fumbles lighting details. Still, the one-prompt-to-Blender MCP workflow is a striking glimpse of where agent tooling is headed.
More from coding & agent
- Grok VS Code extension now listed on Open VSX and the VS Code Marketplace — PawelHuryn · 2026-09-22
- LLMs Are Too Big: Aronchick on Right-Sizing Models for Log Routing — aronchick · 2026-09-22
- Dev syntax-highlights nested string literals inside a coding agent, making prompts readable again — lucasmeijer · 2026-09-22
- AI Comes for the If Statement: Tomasz Tunguz on AI replacing hardcoded rule logic — hardimanjames · 2026-09-22
- MrKan turns AI agents into kanban teammates for managing multiple projects with guardrails — agf2007 · 2026-09-22
- Thorsten Ball: Code Review Will Die, and Unit Tests Might Follow — rseroter · 2026-09-22