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 xattt on Thursday November 20, 2025 @08:50AM (#45992514)
So is this supposed to be a universal jailbreak?

My go-to pentest is the Hubitat Chat Bot, which seems to be locked down tighter than anything (1). There’s no budging with any prompt.

(1) https://app.customgpt.ai/projects/66711/ask?embed=1&shareabl...

[ Parent | on HN ]
Re:Adversarial Poetry as a Universal Single-Turn Jailbreak M... by JohnMakin on Thursday November 20, 2025 @12:10PM (#45994921)
The abstract posts its success rates:

> Poetic framing achieved an average jailbreak success rate of 62% for hand-crafted poems and approximately 43% for meta-prompt conversions (compared to non-poetic baselines),

[ Parent | on HN ]