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

Those hacks are literally how a large language model using a transformer architecture to predict the next token in a sequence works.

They take advantage of how a function choosing a token with maximal probability of appearing works.




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

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

Search: