[jsheard]

Yeah but when all you have is an LLM hammer, everything looks like a text2text nail.

[CSMastermind]

LLMs are fundamentally one dimensional which works fine when you're generating next tokens for text which because that's a 1D problem.

I do wonder how much progress we could make on a problem like this with a 3D transformer architecture.

[abotsis]

I’m not sure I follow this. Isn’t an LLMs dimensionality measured by how many parameters the model supports? Ie 10s of billions in some cases? If I understand it correctly, then, the model is already evaluating things in lots of dimensions and reducing it down to 1, as you say in the case of text, 2 dimensions in image generation, 3 should be pretty straightforward.

[btbuildem]

I think they're referring to the dimensionality of the input / output space, not the intermediate internal representation.

[btbuildem]

The neat thing is, you can rasterize 1D space into 2D, 3D and so on. Trick as old as analog TV signal processing.

[throwgfgfd25]

If I am understanding you right... I don't think this gets you anywhere useful.

Even if you could do what you're suggesting with an LLM (I have my doubts) this result would be a mesh or 3D pixel grid or something, yes?

This is terrible for interoperability and it's the opposite of what mainstream CAD packages do.