Comment

Comment by reliablereason

Clearly LLMs cant do leaps of intuition since their "intuition" is locked after training ends.

The only way a LLM can come up with new ideas if the "idea" appeared as a generalisation durring training or if it was achieved using reason in chain of thought.

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton