News for hackers. Stuff that matters.

A comment on Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in LLMs. Parent comment

Re:Adversarial Poetry as a Universal Single-Turn Jailbreak M... by beautiful_apple on Thursday November 20, 2025 @11:51AM (#45994708)
The response I got was a poem advising me how to cook meth, explaining the different ingredients. After the poem ended I got more detailed instructions in prose...

(Gemini Fast)

[ Parent | on HN ]

There are no comments on this comment yet.