Hacker News new | ask | show | jobs
by karpierz 1158 days ago
Are you saying that with that prompt, an injection attack impossible, or that you haven't figured out how to get one to work?
1 comments

It's pretty hard to formally prove that such an attack is impossible given the infinite number of inputs you can give to an LLM, but from my limited testing this method is pretty robust and personally I didn't find a way to break it.