News for hackers. Stuff that matters.

A comment on Prompt injection: what’s the worst that can happen?. Parent comment

Re:Prompt injection: what’s the worst that can happen? by simonw on Friday April 14, 2023 @06:12PM (#35575485)
GPT-4 with a system prompt is definitely better, but better isn't good enough: for a security issue like this we need a 100% reliable solution, or people WILL figure out how to exploit it.
[ Parent | on HN ]
Re:Prompt injection: what’s the worst that can happen? by M4v3R on Saturday April 15, 2023 @02:25AM (#35578131)
I agree and I think OpenAI is aware of this issue. I’ve read the other day that they are employing a “red team” - group of people that basically are tasked with breaking their models so they can find weak spots and fix them.
[ Parent | on HN ]