alt Hacker News@baigy Huh. Interesting. I was just doing the final clean-up for something convergent to this research that I had been working on for the past few months. I think I arrived at your thesis (code first semantics from a different direction in CAD, so I think it'd be interesting for us to compare notes.
Have you formalized this into a compiler infrastructure yet? I think Python on its own would be too slow to build complex parts, especially since for triangle mesh, accuracy inversely correlates to performance.
Vision is generally not the most reliable form of checks for LLMs, even on GPT 5.6 Sol, so a recommendation I would have is to instead emit JSON or CSV of the color/topology data for the LLM to inspect directly, and this is the instance where ray query for topology checking will greatly improve accuracy in general. SDFs are a bit more complicated right now, I have a full implementation designed for 3D analysis
My own experimental compiler generated mesh suffers from the spiderweb effect: it's very polygon efficient but not very friendly towards UV unwrapping in general, and I'm struggling to find the correct approach for that. If you have any suggestions, I'd love if you can point me towards the correct approach.
Definitely very interesting though.
Would love to compare notes. It's compiler-shaped rn. The generated code is the source and Blender is the current build target. Python directs Blender's native geometry operations only. I also already generate UVs from the coded model before GLB export, while its part structure is still available, which helps avoid recovering everything from one fused spiderweb mesh. Visual checks aren’t the only option either. Having the code gives us direct structural checks too. Btw curious to see your SDF approach.