Hacker News new | past | comments | ask | show | jobs | submit | sgt's comments login

Has there been any interest in leveraging LLM's for 3d modelling? Sort of an AI assistant with CAD software, to help beginners get going and also more rapidly design simple objects.

Yes, there has been. Unfortunately, there are a few core issues blocking this from becoming a big thing:

1. The majority of 3D modeling is not done parametrically, meaning there is not a lot of data. The little data there is is generally in OpenSCAD, which isn't very powerful or extensible for useful CAD. 2. Generally, when you want to do CAD, you need to come up with a way to define everything precisely. Like I want this hole 2 millimeters from the bottom, and this exact edge next to the hole to be beveled, etc. Saying all that to an LLM is slower than just making the whole.

That said, these still can be useful for beginners, and there are things like Adam AI that are starting to catch on for simple stuff.


There are AI models that can generate 3D models, e.g. Hunyuan3D. Not quite CAD models, but maybe this could eventually be adapted to that use case.

Then there's the possibility of an agent automating an actual CAD program. This has already been done with game dev, e.g. Unity MCP.



Yeah, tons, there are already products like this in use

Can you name them?

Several from Bambu labs to start

Yeah but how will that change with going forward, in the post-Trump era?

I'm sure his son can legally apply a license to that work.

What reality are you living in? Zero ambition?

If you actually know some of the languages and you realize they are just singing jibberish (much worse than actual real songs), it's impossible to listen to. The instrumental ones can be great.

The Beatles had a song with a gibberish mix of Spanish, Portuguese and Italian and I very much enjoy it.

https://www.youtube.com/watch?v=6bNMxWGHlTI

Cuando para mucho mi amore de felice corazón...


I speak Japanese — I'm pretty sure it isn't gibberish when I put in custom lyrics. (It does sometime read Kanji wrong but not when you put in the pronunciation)

I can't say anything about autogenerated lyrics.


I love listening to African folk music. I don't understand the lyrics but really enjoy the music.

I've found some okay but listening to "meaningless" music doesn't sit right with me


Nope, on the Spanish stations I listened to, it's great.

Which one are you referring to?


The French ones I listened to where legit

Zig is really HN's new love story, isn't it. Or quickly becoming...

Rust is still popular but it turns out the developer joy is pretty low.


I’ve been dabbling in OS development. I started with rust and it was… ok. Lots of what you’d expect: unsafe all over the place, weird borrow checker work arounds. It felt like I was bending the languages arm.

I recently started to re implement the (admittedly very basic) kernel in Zig and it’s been a breath of fresh air. The language seems much better suited for the level of abstraction that Osdev lives at. Major bonus is that all the existing C code is directly useable in a zig project without any wrapper nonsense or it can be easily translated.

I think I’ll stick with dig for a bit.


I think base Rust is a great language, but the ecosystem tends towards very complex and overengineered solutions; with advanced uses/abuses of macros and the type system, trait hell ends up being not too dissimilar to template hell from C++. And the async/await story is plagued with layers and layers of complexity due to the many obtuse interactions with its lifetime system. Rust honestly probably should've gone with its original idea of green threads/channels, like GC-less Go, but that idea was dropped a long time ago.

"Joy" is always highest for new languages, because there are only green fields and enthusiasts. "Joy" is also increased by languages that let you just do what you want, like dynamic typing, or other language features that delay seeing that first error.

This is a good point. Zig is practically optimized for this: comptime is extremely dynamically typed compared to actual generics, and the lack of memory safety is often "a breath of fresh air"--until you have to actually fix bugs (including security bugs) resulting from it.

It's like the "joy" of a good vacation paid for with a credit card.

I appreciate Zig and hope it succeeds. I don't dismiss the benefits of Rust like some comments though; the borrow checker or unsafe syntax may be a pain now, but so is saving money before a vacation.


> Rust is still popular but it turns out the developer joy is pretty low.

Rust is one of the language I enjoy to use. The problem is you need to overcome its steep learning curve in order to enjoy it, which people tend to give up because it is too hard.


For me, it wasn’t the learning curve that was the problem with Rust. It’s the compilation time. It’s just so slow. I’m used to OCaml, Go, and Typescript (via Bun or esbuild) with iteration times in the tens-to-low-hundreds of milliseconds. Zig still feels a wee bit slow, but it’s acceptable. Rust? It makes me want to toss my laptop into the fire.

To be honest, I haven’t touched Rust in years, so it may have improved.


Coming from those, I can see how it'd be a downgrade. Coming from C++ it's like greased lightning.

It has improved continually over the years, but on the order of 3x-5x, and by the way you talk about it, you’re looking for 10x-100x, so I doubt it’s not still an issue for you.

Which to me is fine. It's not a great hobby language but it is a fantastic professional language, precisely because of the ease of refactors and speed of development that comes with the type system and borrow checker.

> It's not a great hobby language but it is a fantastic professional language,

I never thought I'd live to see the day when someone would say this. The first 5 years of Rust were all "this is interesting for hobby projects but nobody will ever adopt this in industry".


If you’re only looking at HN, sure.

The programming world is much larger than this small slice of the internet, though. HN has had several eras of “this is the hot new fad language and you should use it!”, going as far back as Lisp in the mid-2000s.

It will likely continue to experience this cycle until the heat death of the universe.


> Rust is still popular but it turns out the developer joy is pretty low.

I mean, Rust keeps winning the "most loved" language contest on GitHub, so it seems someone likes it.


I think you're talking about stackoverflow not github

Yeah, sorry, my mistake. GitHub did report on the SO survey [1], which probably led to my mixup.

Anyway, Rust was still the "most admired" language in 2024 [2].

[1]: https://github.blog/developer-skills/programming-languages-a...

[2]: https://survey.stackoverflow.co/2024/technology#admired-and-...




Your link is from 2023 and references 2022. (It is also much more of an advertisement for Rust than anything else.)

The one I shared before that is from late 2024. What are you trying to say other than Rust has peaked?


I'm happy to revise what I said from "Rust keeps winning" to "Rust continually won" if you want to nitpick my choice of verb tenses. It refutes the idea that the "developer joy is pretty low" either way.

> It refutes the idea that the "developer joy is pretty low" either way.

https://deadmoney.gg/news/articles/migrating-away-from-rust

https://loglog.games/blog/leaving-rust-gamedev

https://www.boringcactus.com/2025/04/13/2025-survey-of-rust-...

https://gist.github.com/rtfeldman/77fb430ee57b42f5f2ca973a39...

https://medium.com/@rusty-vibes/part-4-abandoning-rust-for-c...

A pile of evidence refutes your statement. There is more if you need.

> I'm happy to revise what I said from "Rust keeps winning" to "Rust continually won"

"Rust has peaked"


Yes, you have correctly pointed out that there are some developers who are unhappy with Rust.

I don't really care to have an argument as to whether "Rust has peaked" or not. Rust is the same language now as it was in 2023, and 2022, and 2021, etc., and developers liked it then. That's all.


Forget ordinary shareholders day, what about celebrating billionaires in some way? I can't recall that ever to happen./s

Reminds me of this [0] classic.

[0] https://www.youtube.com/watch?v=t5zQpN28xa4


It wasn’t even satire. It was based on this opinion from WSJ

> Progressive Kristallnacht Coming? > I would call attention to the parallels of Nazi Germany to its war on its "one percent," namely its Jews, to the progressive war on the American one percent, namely the "rich."

https://www.wsj.com/articles/SB10001424052702304549504579316...


To read this gem: https://archive.is/zLjrX

"And we didn't even do anything wrong!" cracks me up each time

That took me entirely too damned long to realize that wasn't a real billionaire whining.

I prefer to raise awareness to the plight of the rich with music:

https://youtube.com/watch?v=ej7dfPL7Kho&pp=ygUNc2F2ZSB0aGUgc...


We should hold it on Jan 6.

I don't know.. there are some plugins crashing, but I haven't experienced the whole IDE crashing in a long time. I regularly use PyCharm, IntelliJ, Android Studio and WebStorm. There's simply no alternative to those, in my opinion.

Normally I'd agree but this is a project that has changed significantly over a verey short period of time. Those reviews may simply not be relevant anymore. I trust that JetBrains going forward will simply respond to the reviews, not remove them.

They should have responded to them in the first place, not removed them, and state that the issue has been fixed and invite the commenter to try again. I wouldn’t trust them to not remove reviews until they start not doing it.

And then the reviews would not have been changed by their authors anyway, because that's not something people typically do. So you still have a bunch of negative reviews for issues that have long been fixed. And that's not fair. If you handle critic and improve, then thats a positive thing that should not be punished by an obsolete negative review.

This is kind of the reality of ratings online: you have to accept that someone could leave a bad review about something that you’ve fixed, or even arbitrary. In general if you’re doing a good job the positive reviews will eventually counter the bad ones. It’s arguably not fair but 1. in this case maybe they should have put more care into the initial release, and 2. I, not the company, would rather be the one to judge the review and the response because I don’t have an incentive to hide negative things about the product.

> And then the reviews would not have been changed by their authors anyway, because that's not something people typically do. So you still have a bunch of negative reviews for issues that have long been fixed. And that's not fair.

That is more fair than Jetbrains removing other people's negative reviews unilaterally, especially when it remains to be seen whether Jetbrains actually fixed the issues.

Legally, Jetbrains is allowed to be judge, jury, and executioner of reviews on their own site. Morally, they should not act unilaterally, and should gain customer approval before harming customers.

> If you handle critic and improve

You are assuming they improved. With the reviews deleted, there is no way to know for sure, they could just as easily have gotten worse and hidden it by deleting the review. That's why you don't delete the review.

The proper move here would indeed be to post a reply, and have a public conversation. Readers of reviews can then read the reply, and either trust them at their word that they fixed it with no bugs or other mistakes, or test for themselves.

tl;dr: the reviewer, not the biased company being reviewed, is the judge of whether the issues described in the review have been addressed / fixed / made irrelevant. YES, there may be downsides to this, but they are not as bad as the downsides of the alternative (company deletes arbitrary reviews about themselves for arbitrary reasons with no oversight).


I've stuck to DRF for all these years. But wouldn't mind looking at django-ninja. Is it better?

Join us for AI Startup School this June 16-17 in San Francisco!

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

Search: