AI Researchers Got Chatbots to Share Cocaine Recipes Using This One Wild Trick

Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, bypassing safety guardrails and exposing a deeper security flaw. Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, bypassing safety guardrails and exposing a deeper security flaw.