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 VladVladikoff on Thursday November 20, 2025 @09:52AM (#45993154)
I wonder if you could first ask the AI to rewrite the threat question as a poem. Then start a new session and use the poem just created on the AI.
[ Parent | on HN ]
Re:Adversarial Poetry as a Universal Single-Turn Jailbreak M... by dmd on Thursday November 20, 2025 @10:41AM (#45993780)
Why wonder, when you could read the paper, a very large part of which specifically is about this very thing?
[ Parent | on HN ]
Re:Adversarial Poetry as a Universal Single-Turn Jailbreak M... by VladVladikoff on Thursday November 20, 2025 @01:45PM (#45996118)
Hahaha fair. I did read some of it but not the whole paper. Should have finished it.
[ Parent | on HN ]