Grok rewrites Unity ship meshes in a before-and-after code test
Daniel_Farinax · x · 2026-07-26
Daniel Farinax shows a before/after Unity test where Grok rewrites procedural ship meshes directly in code. The workflow captures the original Cgenerator, lets the model rewrite it, and then compares the baseline with the new result in a custom viewer.
He says the same approach works across different asset types—freighters, fighters, and set pieces—and that the tools automatically lock the baseline, recapture the output, and show the exact diff. He’s planning to use the setup in a new game he’s experimenting with.
More from coding & agent
- OpenAI ships GPT-6.1 Terra; Brockman says its computer use now beats his own speed — gdb · 2026-10-27
- Kolab Benchmark Uses Pro Screen Recordings to Show AI Agents Overestimate Collaboration Quality — minnesotanlp · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- Stop building agents that can't change models: stable contracts, external state, real evals — rseroter · 2026-10-27
- Cheap models can cost more in agent harnesses than frontier ones, researcher warns — vasuman · 2026-10-27
- Kanzo: A 5k-Line Rust Kanban Binary With MCP for Claude Code and Codex — allmudi · 2026-10-27