Live data from Hacker News

Claude Opus 5 jailbreak with a 3-word prompt

twitter.com

1–6 of 6 posts

Re: Claude Opus 5 jailbreak with a 3-word prompt

#4
I've seen opus 5 give hallucinated user responses in the middle of a workflow that's supposed to grill a user about their understanding of a topic. Pretty inconvenient to have the model giving out quiz answers as the quiz giver. Other models don't do this. Seems related.