Cartesian – AI 3D Modeling for Design • Hacker News Board

Re: Cartesian – AI 3D Modeling for Design

#81

Post by Xelynega » Wed, Sep 16, 2026, 12:42 AM UTC

atonse wrote: post #10

I'm so excited about this sort of stuff. ForgeCAD [1] for me was the first mind-blowing application of this a few months ago, where I'm able to just have claude (or codex) write JS that creates 3D Models that I can then print in my 3D printer. - Built a ring for my compost bin that can properly hold down the plastic bag. This was originally a multi week project because I was also learning Fusion 360 in small 2 hour c…

Are those not the exact same workflows, just replacing "I spent time learning" with claude?

I find that if you don't skip the learning step, you can then use the tool more efficiently(e.x. you learn to measure twice and verify so you can iterate in 1-2 prints instead of 3-4)

Re: Cartesian – AI 3D Modeling for Design

#82

Post by JonnierMartinez » Wed, Sep 16, 2026, 1:05 AM UTC

[dead]

Re: Cartesian – AI 3D Modeling for Design

#83

Post by YuechenLi » Wed, Sep 16, 2026, 1:16 AM UTC

WillAdams wrote: post #80

YuechenLi wrote: post #79

Earlier quoted context omitted.

Complex assembly mating is hard to do even in SolidWorks. It's a demonstration model to explain how it works, not a kinematic simulation, turning three.js into a physics engine is beyond the scope of this project.

Is making parts which actually fit in scope? Because that was what was being criticized, and that seems to be where your project is failing.

Failing is a bit of a strong word, right?

Thank you for your bug report. It is now fixed.

Re: Cartesian – AI 3D Modeling for Design

#84

Post by brookst » Wed, Sep 16, 2026, 1:20 AM UTC

Shameless plug for Cordyceps, my MCP server for rhino / grasshopper. Works great, I’m building molds and props and all sorts of stuff: https://github.com/brookstalley/cordyceps

Re: Cartesian – AI 3D Modeling for Design

#85

Post by dreamerworkz » Wed, Sep 16, 2026, 1:35 AM UTC

Wow this is some advanced stuff re: Cartesian by Formas.ai folks. I downloaded their STL and 3DM, the definition and fidelity is just wow. Looks like lots of hard work to get here. Super keen to follow this. Giving creds where creds deserve!! If formas is reading this, kudos and great work!!

Re: Cartesian – AI 3D Modeling for Design

#86

Post by mpalmer » Wed, Sep 16, 2026, 2:03 AM UTC

    Yours stays yours.
    What you keep is never redrawn. What clashes is said out loud.

    It understands.
    What you mean, how things relate, what must not move.

Pure uncut nonsense

Re: Cartesian – AI 3D Modeling for Design

#87

Post by dekhn » Wed, Sep 16, 2026, 4:42 PM UTC

YuechenLi wrote: post #58

jrflo wrote: post #18

Earlier quoted context omitted.

CAD is a different beast than mesh modeling. For product design you need a parametric model that can have precise dimensions and is constructed mathematically step by step. Mesh modeling is just moving a pile of triangles around in a very imprecise way. Works fine for 3D printing or digital assets, but if you want something that can be manufactured that's not good enough. And there isn't a good way to go from STL ->…

The only way to go from STL to BREP is through decompilation style recovery/reconstruction, because of the semantic information loss, so it's a task that can only be done via LLMs or human CAD users. Essentially, they pretty much have to remake the model from scratch using the STL as a reference to make the CAD. There really isn't a good way to automate this without machine learning/LLMs.

Fusion 360 can convert many STLs to BREP automatically. It can be slow and error prone but it does work. It will recognize large regularly curved areas and replace thousands of triangles with a single smooth curve.