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

101–110 of 171 posts

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

#101

Post by alnwlsn »

ReptileMan wrote: post #4

The only thing faster moving that AI these days are the goalposts. Three years ago we would have been amazed if models were able to produce anything, now we have the luxury of nitpicking. Even the worst entries in the benchmark are quite impressive.

Using reference images is a huge step for this sort of thing. The text-only approaches I've seen before were never going to be that good even with "perfect" AI, simply because describing 3D objects in text is not something that anyone is really any good at.

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

#102

Post by thedougd »

I've been trying out MCP servers for FreeCAD to mixed results.

One area I had near magic was providing a land survey which includes details in writing of the plat. It took those directions and beautifully reconstructed the boundaries to exact precision in CAD.

Where I ran into trouble was creating good constraints on sketches without being overly explicit. I kept running into it creating distance constraints from an arbitrary point instead of using other elements in the diagram that a human drafter would think to do by default.

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

#103

Post by lukeschlather »

lifty wrote: post #51
xnx wrote: post #21

Earlier quoted context omitted.

> In future are we going to have same model for everything? A model that knows more in general, will often be better at specific tasks. e.g. If you ask a model to "make a program that estimates the annual production of a solar installation", it needs to have been trained on a lot more than just Python code.

You might combine a general world model with a python coding model in that case. Not sure if it's better, just saying.

What's the difference between a "general world model combined with a python coding model" and a multimodal LLM?

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

#104

Post by rlt »

dempedempe wrote: post #86
simplyluke wrote: post #39

Earlier quoted context omitted.

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…

It's like this with a lot of things now. For example, Nix's learning curve used to be a huge barrier to entry. Now with LLMs, I'm using nix-darwin and home-manager for dotfiles, package management, and have individual flakes in all of my projects for cryptographically reproducible builds!

Nit: there’s nothing “cryptographic” about reproducible builds.

“Reproducible build” already usually implies bit-by-bit reproducibility.

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

#105

Post by jlhawn »

> Antigravity was the only autonomous agent that implemented the Pantheon’s signature interior ceiling pattern: repeated square coffers visible through the oculus.

That is seriously really impressive. I looked at the 3D model and didn't even thing to LOOK INSIDE the building before reading this.

Here's [1] the 3D model with `show_cutaway` enabled.

[1] https://modelrift.com/models/pantheon-benchmark-antigravity-...

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

#106

Post by seniorsassycat »

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 to remove everything except a sliver, to view a slice and internal details. But without hash marks, texture, or outlines it can be hard to tell the forms.

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

#107

Post by mchusma »

mellosouls wrote: post #2

Antigravity may well Top the whatever benchmark but: My Antigravity (forced) replacement for Gemini CLI requires me to log on via browser every time I use it, and my Antigravity IDE won't update at all, so: If it's ok I'd prefer they just work on reaching a baseline acceptable rollout before worrying about being Top in anything. Ps actual title: OpenSCAD LLM Benchmark: Building the Pantheon

I just left the google I/O feeling less confident about google's execution here. - Gemini 3.5 flash is strange. Old cutoff, basically better than 3.1 pro at soem things worse at others, sometimes cheaper, sometimes more expensive than 3.1 pro. - Antigravity had seemed abandoned, and people speculated them cutting it off, and they kind of did migrating everyone to a new antigravity - Google "shipped the org chart" and they have so many AI products and none seem best of breed (e.g. the Gemini integration in google docs is worse than claude)

I was actually hoping for "Opus level intelligence at Haiku costs" model or "Sonnet level performance in Gemini 3.0 pricing", either of these would have been a workhorse, plus a competitor to Claude/Codex (1 app to do things). I got neither.

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

#108

Post by hereme888 »

jlhawn wrote: post #105

> Antigravity was the only autonomous agent that implemented the Pantheon’s signature interior ceiling pattern: repeated square coffers visible through the oculus. That is seriously really impressive. I looked at the 3D model and didn't even thing to LOOK INSIDE the building before reading this. Here's [1] the 3D model with `show_cutaway` enabled. [1] https://modelrift.com/models/pantheon-benchmark-antigravity-...

Was just going to say.... I looked inside by accident, and it gives a better impression of intelligence and effort than the outside.

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

#109

Post by lern_too_spel »

surajrmal wrote: post #53
jeromegv wrote: post #46

Earlier quoted context omitted.

Gemini cli was open source. Antigravity cli is not. Not at feature parity, missing many features and now we are forced to migrate away from Gemini cli before anti gravity cli is ready.

The difference in its ability is immense. Even with less features it makes a lot of sense to switch. It really shows how much the harness matters almost equally to the model.

At least one of the missing features is a basic piece of functionality (showing token quota used). Without it, you're pretty much guaranteed to get locked out for a week with no warning.

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

#110

Post by lern_too_spel »

spiderfarmer wrote: post #9

Next month they'll be beaten again. And next year Google will probably sunset Antigravity. If it doesn't make Google billions, don't trust them.

Why should I care if they sunset it? I switch between multiple agentic coding tools on the same projects, sometimes several times per day. The cost of switching is basically zero.
Post reply on HN