Yet another Hacker News

Benchmark: CadQuery vs. OpenSCAD for agentic CAD work

8 points jetter 1 hour ago 10 comments

ariwilson 23 minutes ago | parent

not interesting as the writeup as very AI sloppish :(. i'm sad about that as I would really like to have an intuitive sense for how good the current frontier models are at coming up with interesting 3d printable parts.

rjsw 18 minutes ago | parent

There was a blog post from a couple of days ago that had been initially flagged, it seemed to me to have a good overview of AI for CAD, will try to find the link.

____tom____ 15 minutes ago | parent

I've been just getting started on this with Astra. Astra is one-shotting good 3D models from photographs for me. I was unable to get Sol to do this, even after multiple rounds.

It's not a small change, it's from "not useful" to "pretty good"

dofm 12 minutes ago | parent

> Astra is one-shotting good 3D models from photographs for me.

Right, but, so what? There is very little utility here. Parts that need to be useful need to be designed to spec.

Mashimo 5 minutes ago | parent

Once you have the model, it's relativ easy to change the demensions / constrains later on, no?

dofm 3 minutes ago | parent

Not if the model has not been implemented from reasonable principles.

____tom____ 1 minute ago | parent

Maybe not for you, but I'm building miniatures for custom board games. Works great.

elwebmaster 6 minutes ago | parent

With any tool?

dofm 13 minutes ago | parent

None of the "findings" here really needed an AI experiment to do it:

- "CadQuery fails loudly and early... OpenSCAD fails silently and late"

This should be obvious, from the documentation, from the way geometry construction works. OpenSCAD has no sense of failure where one shape means another won't work; you're just drawing the equivalent of 3D pixels in space. It will always potentially-meaninglessly succeed if the syntax is OK.

- Renders caught nothing that mattered

Objects with hollows are not going to show their major problems this way.

- CadQuery can be interrogated, OpenSCAD cannot

Isn't this explicit from the documentation of both? One works by iteratively building on top of a previous result that can be stored in a variable; the other doesn't.

- OpenSCAD renders have no concept of a part edge

Again — this should be explicit from the documentation, which describes no methods for operating on edges (and largely from the fact that it is declarative).

- Speed favours OpenSCAD, and it barely matters

Yes, being faster is no good if things are wrong.

- "What decides it is verifiability rather than expressiveness, and CadQuery leads there by a wider margin than the syntax difference suggests."

Yes, because the difference is semantic. Which you can get from the documentation. Building iteratively on the basis of existing geometry is inherently more verifiable, because stuff that can't work won't work.

Honestly do people not try learning CAD before they try to get an AI to generate CAD models? This feels like yet another situation where people who have not done the foundational conceptual work seem to think that they can avoid it and just work around it with AI.

brcmthrowaway 5 minutes ago | parent

The OP seems to be shilling this tool nonstop. Modelrift just seems to be an LLM wrapper.. the original models can handle OpenSCAD just fine.