Comment on Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models

<- View Parent
Sims@lemmy.ml ⁨1⁩ ⁨week⁩ ago

You can just debunk all the childish US-originated propaganda your self. No AI, and no ‘hacking’ techniques are needed for that. Just be critical of your sources, that’s all.

source
Sort:hotnewtop