News for hackers. Stuff that matters.
Re:Stealing Part of a Production Language Model by lnyan on Tuesday March 12, 2024 @07:37AM (#39678336)
no, I think it might be

- LLM(prompt_0) = arch/spec of LLM

- LLM(prompt_1) = full weights of LLM

Note that it does not conform the definition of quine as a quine takes no input.

Anyways, constructing a transformer that can autoregressively output its weights would be quite interesting.

Re:Stealing Part of a Production Language Model by sdenton4 on Tuesday March 12, 2024 @11:16AM (#39680521)
Easy if all the weights are zero...