logoalt Hacker News

skeptic_ai • yesterday at 11:49 AM • 1 reply • view on HN

That’s why you just ask: do you think this is a good idea? Correct me if I’m wrong


Replies

mrandish • yesterday at 8:48 PM

> do you think this is a good idea?

LLMs can be quite good at that... sometimes, and maybe most times. Where they can fall short is when "good idea" is comprised of inter-locking conditional definitions and variable evaluation thresholds denominated in differently weighted currencies.