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

Absolutely. "Refusals" all seem to follow a similar direction in the LLM residual stream, so preventing the model from representing this direction prevents it from refusing.

https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in...




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

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

Search: