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 spockz on Thursday November 20, 2025 @03:56PM (#45997600)
So it’s time that LLM normalise every input into a normal form and then have any rules defined on the basis of that form. Proper input cleaning.
[ Parent | on HN ]
Re:Adversarial Poetry as a Universal Single-Turn Jailbreak M... by fn-mote on Thursday November 20, 2025 @09:34PM (#46000600)
The attacks would move to the normalization process.

Anyway, normalization would be/cause a huge step backwards in the usefulness. All of the nuance gone.

[ Parent | on HN ]