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

There are plenty of examples in the RL training showing it how and when to prompt the human for help or additional information. This is even a common tool in the "plan" mode of many harnesses.

Conversely, it's much harder to represent a lack of doing something

 help



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

Search: