Hacker Newsnew | past | comments | ask | show | jobs | submit | ponyous's commentslogin

As someone who’s been building AI for CAD[0] with OpenSCAD. I’m very thankful to OpenSCAD maintainers it’s been a life saver. Terse syntax, a lot of plugins and great CSG kernel.

People keep saying I should use other kernels for fillets and stuff, but from my testing AI is just not as good with, for example build123d as it is with OpenSCAD.

[0]: grandpacad.com


Was curious how the race looks like if you look at Pareto frontier of LLM capability since this hype started. So I asked Claude to generate me a video. And it's quite insane how good it is and I thought you guys might find it interesting too.

How did you connect it to search console and do you like the integration? I would like to do this too, and eventually to Google Ads too.

It involves creating a Google cloud app with the required APIs enabled.

I basically just prompted OpenClaw on what steps to take and then added the API key/secret on its .env and that was pretty much it. Same on all other connections.

As long as what you want has API access and documentation, the agent should help you out on how to do it.


It really depends on the complexity of the model you are trying to generate and the budget you have.


You mean people blind in one eye? I think it still works, but obviously depth perception will not be there


Not just blind in one eye, people with squints can often only see out of one eye (either, just not both)


https://grandpacad.com - AI modeling for 3D printing Been at it for about year and a half.

Really exciting stuff is happening literally every month, because underlying models are getting better and better. When I started it was pretty basic: “make a cube with a hole through it”. Now it’s at the point “make a raspberry pi 4 case” and the agent searches, builds, verifies…

What surprised me in this process is how little meaning AI benchmarks have. Pareto frontier for my use case looks completely different than any other benchmark portrays.


You mentioned benchmarks don’t mean much in this area. What are the best models you found in this area?

Personally, I’ve had the most success with GPT models using MCP servers for this task.


Same here. 5.5 would sometimes oneshot relatively complex models even without MCP. Opus, however, even with Fusion 360 MCP access would usually make comically bad models. It seemed that Opus tried to reason through the problem while GPT would come up with a general plan of using whatever tools were available to solve the problem. In chat, it would use the available Python and trimesh. It was also the only time I had ChatGPT work on something for over 30 min without giving up.


Surprisingly Gemini models. Spatial understanding seems to be the best for the price and speed.


> I have a feeling that the price of 1 million tokens transmitted over the internet is more expensive than cache hit.

And this kinda makes sense. What is cheaper few KB of disk space or internet bandwidth?


100%, but this means we are going to move to stateful APIs on the AI provider's end (like OpenAI already does with Codex and Responses API) to make this work.


We went for 16% intelligence bump according to artificial analysis for +82% of the cost. Interesting.

Comparing 4.8 Opus with Fable 5.1


On my benchmark where AIs generate ~20 different 3D models about 1/2 the time of Opus and 1/3 of the time of Kimi K3 and 2/3 of time of sonnet.


GrandpaCAD - AI 3D modeling software focused on simplicity. Made it so even my grandpa could model. He’s been asking me for years when will I teach him how to 3D model. I tried, we failed and then I seen him use ChatGPT so I knew there was a better way than traditional CAD tools.

Recently we also got European funding and the project got some traction. Very exciting times ahead.

https://grandpacad.com


Looks really nice! Two things:

- Does it support layers / assembling structures? This would allow to combine multiple parts into a product (don't know hoe that is named exactly in english) - Awesome you support not only subscriptions but also a credit-based approach. I would definetly be a credit-customer, as I may have usage a couple of times a year, bot not continouous!


Yeah you can absolutely do multiple parts, although the mating features are still a bit rough you can do a lot already.


Consider applying for YC's Winter 2027 batch! Applications are open till November 2.

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

Search: