News for hackers. Stuff that matters.

A comment on LLM Powered Autonomous Agents. Parent comment

Re:LLM Powered Autonomous Agents by earthboundkid on Tuesday June 27, 2023 @09:55AM (#36492817)
> but is a bit more tricky to get to work well with text than pixels

Interesting. Can't you just start with 4K of randomly assigned tokens and tweak it until it's right (including the tokens for EOF), like they do for images where they start with noise and move towards an image?

[ Parent | on HN ]
Re:LLM Powered Autonomous Agents by carlosbaraza on Tuesday June 27, 2023 @10:13AM (#36493077)
Anyone knows why this isn't possible?
[ Parent | on HN ]
Re:LLM Powered Autonomous Agents by jszymborski on Tuesday June 27, 2023 @12:16PM (#36494905)
This is not my corner of DL research, but my understanding is that pixel noise is far more acceptable in a e.g. 1084 x 1084 canvas than it is when dealing with a sentence of 36 words.
[ Parent | on HN ]