Comment by TGower
5 hours ago
It would be interesting to see a head to head comparison of frontier LLMs building models with OpenSCAD, Blender scripting, and Fusion MCP. My intuition would be that blender winds up the best for the immediate result due to training data prevalence and RL tuning, but the concise nature of OpenSCAD could help.
I'll have to add this to my backlog of experiments to try when I have unused tokens near a reset...
Blender gives you a mesh that isn't parameterized. Not particularly useful for making dimensional changes outside of eyeballing everything. An LLM isn't going to reliably hit your dimension targets so tweaks will be necessary.
Yeah, that's what I meant by "immediate result", if you need to edit the generated model by hand it will be hard to beat having the model and timeline available in Fusion after using Fusion MCP.
If you just need to tweak the dimensions in the script, or are satisfied with describing the changes to the LLM and having it modify the script, there isn't much difference in practice between a generated OpenSCAD script and a Blender python script.
I created an (unpublished) MCP for a CAD that didn’t have one before and LLMs are just fine at it. It looks like they can apply their higher level training across interfaces.