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

LLMs hallucinate because probs -> tokens erase confidence values and it's difficult to assign confidences to strings of tokens, especially if you don't know where to start and stop counting (one word? one sentence?)

Is there a reason to believe this is not solvable as literally an API change? The necessary data are all there.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: