Hacker News new | past | comments | ask | show | jobs | submit login

I don't really mind using analogies for LLMs "assuming" things or being "confused" too much. I think there really is _some_ value to such analogies.

However I gotta take issue with using those analogies when "it's trained for text completion and the punchline to this riddle is surely in its training data a lot" is a perfectly good explanation. I guess I would also add that the answer is well-aligned with RLHF-values. I wouldn't go for an explanation that requires squishy analogies when the stuff we know about these things seems completely adequate.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: