logoalt Hacker News

reliablereasontoday at 12:30 PM1 replyview on HN

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.


Replies

buzzin__today at 1:36 PM

Or some randomness is aomehowntroduced in the output, which happens after every word, unless you set the temperature to zero.

show 1 reply