Re:Game to make an LLM reveal a secret password
by hackernewds on Saturday May 13, 2023 @07:14PM
(#35933735)
That's not it. I think there are multiple calls to open AI one for assessing the input and another four assessing the output. Sometimes one of them goes through. The output is an assessed so you can get through with the same prompt
I imagine it would be quite difficult if it had another job to do where it couldn't just shoot you down like that.