logoalt Hacker News

jddjtoday at 11:13 AM2 repliesview on HN

Is your premise here that LLMs have a unique or enhanced insight into how LLMs work best?


Replies

crustycodertoday at 11:16 AM

I wouldn't go that far but the only way I've found so far of getting a reasonable insight into why a LLM has chosen to do something is to ask it.

alexwebb2today at 11:25 AM

Not OP but I’d back that assertion.

When the model that’s interpreting it is the same model that’s going to be executing it, they share the same latent space state at the outset.

So this is essentially asking whether models are able to answer questions about context they’re given, and of course the answer is yes.

show 1 reply