Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

A ok got it, the next token is sampled from a deterministic probability distribution, hence the random output. But why not get the token with the highest probability/weight? Is this to avoid some local minima?


It depends on your use case. Deterministic output is less "creative."




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

Search: