For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | ponyous's commentsregister

Does this use its own backend/engine? I've been working on LLM to CAD tool[0] and have realised there are so many backends and options to choose from. Since the realisation I'm trying to find the best representation for an LLM. I think OpenSCAD is currently the best and most feature complete choice, but I definitely need to dig a bit deeper. If anyone has any pointers I welcome them!

[0]: https://GrandpaCAD.com


> I think OpenSCAD is currently the best and most feature complete choice

As much as I love OpenSCAD, I would strongly disagree with your conclusion.

All the OpenSCAD language can do is boolean operations and moreover, the engine can only implement those on polygonal (triangle actually) meshes.

That's a very far cry from what a modern commercial CAD engine can do.

For example, the following things are very, very hard to do, or even specify using OpenScad:

   - Smooth surfaces, especially spline-based

   - Fillets / Chamfers between two arbitrary surfaces

   - Trimming surfaces

   - Querying partly built models and using the outcome in the subsequent construction (e.g. find the shortest segment between two smooth surfaces, building a cylinder around it and filleting it with the two surfaces, this is an effing nightmare to do within the confines of OpenSCAD)

   - Last but not least: there is no native constraint solver in OpenSCAD, neither in the language nor in the engine (unlike - say - SolveSpace)
I might have misunderstood what you're looking to do, but, yeah, digging deeper feels very much like the right thing to do.

(my) fncad doesn't have the querying, but it does have smooth csg! https://fncad.github.io/

using BOSL2 alleviates most issues I've run into with OpenScad for chamfers and the like, but it is an extra set of functions you need to remember sadly

https://github.com/BelfrySCAD/BOSL2


> BOSL2 ... but it is an extra set of functions you need to remember sadly

It's also extremely slow: it implements chamfers and fillets using morpho, and if you have a large number of fillets, the morpho algorithms (minkowski / hull) are very much non linear in time on polygonal meshes, which leads to compute time explosion if you want a visually smooth result.


you can get around this somewhat by having less visually smooth previews when editing and higher quality when you want an stl

  $fn = $preview ? 32 : 256;

I just ran into this today: https://github.com/gumyr/build123d - seems like an LLM should have no problem writing python code...


Yeah it does. In fact I believe it was written to demonstrate improved sketch constraint solving (there's a 2D version too).

Unfortunately aside from the better sketching the engine is not as capable as OpenCascade.


I have tried OpenSCAD, it seems very slow to compile to display on web. are you using the official wasm or some other ways?

you may find this useful: https://phaestus.app/blog/blog0031

Edit: Forgot I also got doom running in openscad: https://www.mikeayles.com/blog/openscad-doom/

and doom running in openscad in the browser at https://doom.mikeayles.com/


I export it as .3mf file and display it with threejs on the web. Compilation seemed fast enough - few seconds tops.

This "screenshot -> refine loop" is a great strategy and I have built it into my 3D Modeling product as well[0], but had to disable it because it would often quadruple the costs and the product is already expensive.

I am on standby to enable it though, just need a price to drop a bit more!

[0]: https://grandpacad.com


My late maternal grandfather was Slovenian, so I enjoyed your project's backstory. I've mucked around with ChatGPT and OpenSCAD so can identify with that also. Great concept and best of luck!


Thank you!


Cool button


In the coworking I am in people are hitting limits on 60$ plan all the time. They are thinking about which models to use to be efficient, context to include etc…

I’m on claude code $100 plan and never worry about any of that stuff and I think I am using it much more than they use cursor.

Also, I prefer CC since I am terminal native.


Tell them to use the Composer 1.5 model. It's really good, better than Sonnet, and has much higher usage limits. I use it for almost all of my daily work, don't have to worry about hitting the limit of my 60$ plan, and only occasionally switch to Opus 4.6 for planning a particularly complex task.


3D AI Modeling software intended for 3D printers.

https://grandpacad.com

Originally I made it for my grandpa, but I got a lot of interest so I made it into a full commercial product.

Just yesterday I published a set of 3 mini tutorials if you want to see how it works - https://youtube.com/playlist?list=PLKt1F5TvOjAHE07oBDlPXcrHc...


Ran a bunch of 3D Modeling benchmarks on Gemini 3.1 vs Gemini 3.

Unsurprisingly 3.1 performs a bit better. But surprisingly it costs 2.6x as much ($0.14 vs. $0.37 per 3D Model Generation) and is 2.5x slower (1m 24s vs. 3m 28s).

To me it feels like "lets increase our thinking budget and call it an improved model!"


I am building pretty much the same product as OP, and have a pretty good harness to test LLMs. In fact I have run a tons of tests already. It’s currently aimed for my own internal tests, but making something that is easier to digest should be a breeze. If you are curious: https://grandpacad.com/evals


https://grandpacad.com/

Dimensionally accurate AI 3D modelling. My grandpa has a 3D printer but struggles to use any complex tools. So I am working on this chat interface to allow him to do some simple models.

So far he has triggered more than 150 generations. It’s getting better every model cycle and gives me something I enjoy working on.


Really cool! I tried to make this part I've been wanting but I think forcing myself to clearly describe it made me realize there is a simpler way.


I see no mention of that, but OpenAI already has "service tier" API option[0] that improves the speed of a request by about 40% according to my tests.

[0]: https://openai.com/api-priority-processing/


I think models are smart enough for most of the stuff, these little incremental changes barely matter now. What I want is the model that is fast.


I predict a bifurcation in usage.

Serial usecases ("fix this syntax errors") will go on Cerebras and get 10x faster.

Deep usecases ("solve Riemann hypothesis") will become massively parallel and go on slower inference compute.

Teams will stitch both together because some workflows go through stages of requiring deep parallel compute ("scan my codebase for bugs and propose fixes") followed by serial compute ("dedupe and apply the 3 fixes, resolve merge conflict").


I've been using 5.1-codex-max with low reasoning (in Cursor fwiw) recently and it feels like a nice speed while still being effective. Might be worth a shot.


This is faster if their marketing is right, it uses significantly less tokens. Gemini 3 flash is very good as well.


Very interesting thanks! I wonder what would happen if you kept running Gemini in a loop for a while. Considering how much faster it ended it seems like there is a lot more potential.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You