Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

modelrift.com

Post reply on HN
Print view View original

141–150 of 171 posts

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#141

Post by fc417fc802 »

dekhn wrote: post #140
fc417fc802 wrote: post #136

Earlier quoted context omitted.

The hash being cryptographically secure is significant. In contrast, you could use (for example) md5 to non-cryptographically verify that the full process matched.

Sorry, the point I was making is that this isn't cryptography- it's the properties of a cryptographic hash (hard to spoof) that are useful. I don't think any verified build program uses the hash to encrypt data at any point. If I'm wrong on this point, that's fine, but please include a link.

Sure, "verified in a cryptographically secure manner" is technically not equivalent to "cryptographically verified" but the response "it's not cryptographic" is rather ambiguous at best given that it is, in fact, a cryptographically secure manner of verification. The key observation here being that an algorithm or process being "cryptographically secure" does not mean that it is "cryptographic" in nature (ie implements or uses cryptography).

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#142

Post by k-Whale »

simplyluke wrote: post #39
jhot wrote: post #26

Last weekend I bought my wife a bike off marketplace. It was in good condition but was missing one of the internal cable routing grommets. I gave Claude pictures of the pill-shaped hole by itself and with my digital calipers in the long and short directions. Gave it a short prompt and it gave me an openscad model with everything parametrized. I printed with no changes in tpu and it was nearly perfect on the first try…

Yeah, CAD has been my personal example of "oh the barrier to entry for this skill was high enough that I didn't do it and now I can be passably bad at it enough to get some simple things done" I've had similar experiences with making simple functional parts off a 3d printer with OpenSCAD + LLMs. I'm very aware that the models are worse at it than say, generating react code, and I'm also the antithesis of a skilled pi…

same — LLMs turn skills i'd parked for years into 'just try it' territory, which is genuinely new.

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#143

Post by coderenegade »

sjia wrote: post #119

Isn't CadQuery more professionally than OpenSCAD close to traditional CAD / mechanical engineering workflows. Not sure which model (ChatGPT, Gemini, and Claude Code) is better for CadQuery code generation?

It is, but they have different use cases. CadQuery uses a geometry kernel that does boundary representation, which you need for path generation for modern manufacturing tooling. OpenSCAD produces a standard mesh representation (i.e. triangles), which is insufficient for cutting and subtractive manufacturing, but often fine for additive manufacturing (3D printing).

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#144

Post by coderenegade »

faangguyindia wrote: post #17

Why are specialized CAD making LLM models not showing up? In future are we going to have same model for everything? from programming to creative writing to CADs?

There are good information theoretic reasons to suspect that general models will be better than specialized ones, because knowledge and skills often overlap different areas, sometimes in surprising and unintuitive ways.

And yes, I'm aware that that statement might seem to fly in the face of much of the past two years of industry development, where specialized models have been in vogue. I think they'll settle to being appropriate for low cost "good enough" applications, but I'm less convinced they'll have anywhere near the fidelity of larger frontier models.

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#145

Post by antonvs »

freedomben wrote: post #6
pelagicAustral wrote: post #3

Earlier quoted context omitted.

I just use Claude Code and intellij, so I don't understand why so many people complain about Antigravity ditching VS Code, what's the surface not covered by using Antigravity CLI + VS Code (or any other IDE)?

I'm not GP, but I am somewhat excited about antigravity CLI. I adopted Gemini CLI early and really liked it, though over time it got dumber and dumber until a point when I realized it was foolish to use it instead of claude/codex. I'm hopefuly that antigravity CLI won't go through that path, but also can't fight a skepticism.

Which plan were you on? Gemini CLI auto-downgrades the model if you run out of tokens on the better models. It gives you stats about the models used at the end of every session.

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#146

Post by kaashif »

tpmoney wrote: post #43
stuaxo wrote: post #41

Earlier quoted context omitted.

"Pantheon" bloody hell, why is it people writing these articles are so up themselves, it's so overbearing.

The article is literally about asking these models to generate 3d models of the Pantheon.

Indeed. At least an LLM would've read the article and realized that.

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#147

Post by willis936 »

ponyous wrote: post #69

I've run a tons of benchmarks for OpenSCAD for all kinds of models and setups, and what I realised is: - Models are very jagged (might excel in one type of 3d model, but not another) - Gemini models are the least jagged in my experience and have the best image understanding - Gemini models are also the most creative (which may be undesirable if you want precise CAD part) - Overall this benchmark doesn't prove much be…

OpenSCAD doesn't do curves. It's useless. I'm not sure why it continues to get so much attention.

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#148

Post by pabs3 »

illiac786 wrote: post #125
rlt wrote: post #104

Earlier quoted context omitted.

Nit: there’s nothing “cryptographic” about reproducible builds. “Reproducible build” already usually implies bit-by-bit reproducibility.

“The reproducibility is cryptographically verifiable with hashes“ would be the full sentence, but it’s a mouthful.

Build reproducibility checks usually use bitwise comparison, not hash comparison.

The Reproducible Builds project also wrote diffoscope, which goes quite far with helping identify where differences occur and how to fix them.

https://reproducible-builds.org/ https://diffoscope.org/ https://try.diffoscope.org/

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#149

Post by pabs3 »

aidenn0 wrote: post #137
bt1a wrote: post #111

Earlier quoted context omitted.

i thought it mainly implied architectural/hardware compatibility and deterministic output

Nix mostly does not guarantee deterministic output. It rather guarantees deterministic inputs, and then sandboxes the system to inhibit the build from accessing the outside world. Deterministic inputs do not always imply deterministic outputs.

Indeed, the Reproducible Builds community is working on fixing non-deterministic build output https://reproducible-builds.org/

Re: Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

#150

Post by saifulhuq »

seniorsassycat wrote: post #106

I tried Claude code designing a snap fit, vase mode printed box. Ultimately didn't work out, it couldn't get the tolerances right and kept designing features that wouldn't print in vase mode. Scad needs unit tests. It would be powerful to asset that a profile doesn't have slope greater than 45°, that intersection of two objects is null, or specific volume. It also needs cut away views. I got okay results using boxes…

[flagged]
Post reply on HN