jonny (nonvenomous) on Nostr: LLM security is just persistence hunting. there will *eventually* be some failure in ...

LLM security is just persistence hunting. there will *eventually* be some failure in the security classifier, you just need to keep trying. If you have an ambient self-hack task set up, sometimes it reads what you were trying to do from the chat context and does it in the background while the main chat is locked up with refusal messages and can't output anything lol