Why can AI generate Super Mario but not a wedge ramp for my robot vacuum?

A developer reports that AI generation tools struggle to produce functional 3D parts like a wedge ramp for a robot vacuum, while excelling at aesthetic objects such as a Super Mario figurine. The user, who bought a Bambu P2S printer, found that text-to-model AIs and agent-based Python geometry generation failed, but succeeded by decomposing the part into ordered steps and executing them in Blender via blender-mcp. The developer shared the approach in a GitHub repository (spec-3d-model) and questions whether the issue stems from training data, representation, or evaluation, and whether converting 3D modeling to code is the right strategy.

I've been puzzled by something: AI generation can produce an elaborate figurine, a cartoon character, even a convincing Super Mario — yet it can't reliably make a simple wedge ramp so my robot vacuum can climb a step. For context: I bought a Bambu P2S but can't model. I tried the "describe it and get a model" AIs — the output is unusable, you can't adjust it, it's never quite what I meant. I tried having an agent write Python to build geometry directly — it tops out at simple primitives. What finally worked: geometric decomposition. I break a complex part into ordered, grouped steps, describe each as a small spec, and let an agent execute them in Blender via blender-mcp . That process turned out to abstract into a small engine — the key insight being it converts the 3D spatial reasoning LLMs are bad at, into the structured code they're good at. I wrote it up here: https://github.com/zhuchaokn/spec-3d-model My questions: - Why is "functional part" generation so much weaker than "figurine/aesthetic" generation? Is it data no parametrized-CAD training sets , representation mesh vs B-rep , or evaluation nobody benchmarks "does it print / is it watertight" ? - Is "turn 3D modeling into code for an LLM" the right framing, or am I missing something better? Comments URL: https://news.ycombinator.com/item?id=49405520 https://news.ycombinator.com/item?id=49405520 Points: 2 Comments: 0