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

Or we could just demand agents that offer this level of introspection?


I certainly wouldn't trust self-reporting on this


Not only trust, but how you later optimize what is in the context to cater how you use llms... There is a whole world to be explored inside that context window.




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

Search: