News for hackers. Stuff that matters.
Re:Prompt engineers have already jailbroken GPT-4 in just tw... by sho_hn on Friday March 17, 2023 @07:25AM (#35195565)
Funky to observe that this is making AI more reliable by conditioning humans to be afraid of breaking it, lest they face the music.

Somewhere inbetween "Not sure this is what we want" and "High-tech victim blaming".

There are no comments on this comment yet.