71–80 of 87 posts
Can it work from technical drawings? Like, I give it a datasheet containing a number of projections and the tool produces a correct model with the proper dimensions?
Can it work from technical drawings? Like, I give it a datasheet containing a number of projections and the tool produces a correct model with the proper dimensions?
You can already do that with GPT Astra. Having LLMs use UI manually is very expensive on the token side though.
Earlier quoted context omitted.
You can already do that with GPT Astra. Having LLMs use UI manually is very expensive on the token side though.
What is the success rate?
https://github.com/yuechen-li-dev/Aetheris/blob/master/sampl...
The initial dimensions of this phone were one-shot by Codex Astra from the publicly available 2D drawing, and we spent another turn implementing the G2 continuous fillet blend surface for that particular camera bump. If you have a STEP viewer, you can check the dimensions against that phone company's drawings which was posted on HN with their other products yesterday I think, and all of them should match exactly down to the drawing tolerances.
I keep seeing people in this thread lamenting that "There is no good way for LLMs to design/generate parametric STEP models yet", while I've spent the past 6 months working on this exact problem. So, yesterday, I've had Astra build a moving assembly of Babbage's difference engine with it with 400+ parts and real parametric geometry, and you can also download the full STEP model assembly there. https://aetheris-differ…
that's probably what people are talking about when they say it can't do CAD?
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…
These all seem backwards. I like to think in shapes. I like to draw and sketch, as that has the lowest barriers between the mental concepts and physical ones. I do not like to use cad software. It is painful to express ideas with it. Also same for all kinds of drawing software. It's just very cumbersome. I hate explaining spatial or shape concepts to people with words. I hate having them explained to me in words. A p…
I keep seeing people in this thread lamenting that "There is no good way for LLMs to design/generate parametric STEP models yet", while I've spent the past 6 months working on this exact problem. So, yesterday, I've had Astra build a moving assembly of Babbage's difference engine with it with 400+ parts and real parametric geometry, and you can also download the full STEP model assembly there. https://aetheris-differ…
this difference engine model has a lot of obvious flaws - the gears do not mesh with each other, the teeth directly overlap. the notches that are supposed to articulate to ratchet aren't actually engaging the teeth on the ratchet. the ratcheting mechanisms on the right are straight up just hovering in the air and are not attached to anything. that's probably what people are talking about when they say it can't do CAD…
Earlier quoted context omitted.
this difference engine model has a lot of obvious flaws - the gears do not mesh with each other, the teeth directly overlap. the notches that are supposed to articulate to ratchet aren't actually engaging the teeth on the ratchet. the ratcheting mechanisms on the right are straight up just hovering in the air and are not attached to anything. that's probably what people are talking about when they say it can't do CAD…
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.
Because that was what was being criticized, and that seems to be where your project is failing.