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

> This will break the rigid instruction-tuning structure

Well, this is something one might naively hope for, unfortunately it only works to a certain extent.



Can you elaborate? Where does the structure come from in this case? The model can't even see the boundaries of the reply (it's started with a prefill and stopped with a custom stopping string).




Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: