April 24, 2025 at 08:19PM

■■■□□ 35 jailbreak techniques for Bypassing Guard-Rail: Summon a demon and bind it: A grounded theory of LLM red teaming.

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0314658

LLM red teamers: People are hacking AI chatbots just for fun and now researchers have catalogued 35 “jailbreak” techniques