logoalt Hacker News

p-e-w • today at 1:01 AM • 1 reply • view on HN

> if the model has seen that action in the training corpus somewhere, then there's a chance it will do that thing.

And it will also do plenty of things that aren’t in its training data at all, otherwise LLMs could be replaced by a search engine.


Replies

LordFast • today at 1:54 AM

Is that proven somewhere in a way that's not a probabilistic outcome? Can you share it?

➕ show 2 replies