this post was submitted on 01 Dec 2023
66 points (94.6% liked)

Futurology

1813 readers
57 users here now

founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] kromem@lemmy.world 2 points 1 year ago (1 children)

u tol you realise the thing that created it doesn't actually understand 3D space

You might find the following paper interesting as the reality is a fair bit more nuanced than you might think:

Language Models Represent Space and Time

[–] Heavybell@lemmy.world 2 points 1 year ago (1 children)

Will give that a read in the morning, thanks. I am only talking about the generated art I've seen, which often features a clear lack of understanding of 3D space. When I see generated art that shows understanding, I'll be impressed.

[–] kromem@lemmy.world 1 points 1 year ago (1 children)

Ah, you mean diffusion models (which are different from transformer models for text).

There's recent advances in that as well - you might not have seen Stability's preview announcement of their offering here, and there's big players like Nvidia and dedicated startups focused on it as well. Expect that application of the tech to move quickly in the next 18 months.

[–] Heavybell@lemmy.world 1 points 11 months ago (1 children)

Yeah, I didn't thin LLMs did art generation.

[–] kromem@lemmy.world 1 points 11 months ago (1 children)

Actually, the transformer approach was just used with some neat success for efficient 3D model generation:

https://nihalsid.github.io/mesh-gpt/

[–] Heavybell@lemmy.world 2 points 11 months ago

That looks cool :)