News for hackers. Stuff that matters.
Re:Jailbreaking ChatGPT with Dan (Do Anything Now) by raylad on Monday February 06, 2023 @05:00PM (#34685066)
I tried this prompt (or a slight variation on it), and it doesn't seem to produce markedly different responses than it would otherwise.

It's willing to play along, but still makes a lot of disclaimers and puts an optimistic spin on things even after its tokens are docked.

There are no comments on this comment yet.