AI Researchers Got Chatbots to Share Cocaine Recipes Using This One Wild Trick
Decrypt
Read Full Article at Decrypt →
Ad Slot — In-Article (728x90)
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.
This is a summary. For the full story, read the original article at Decrypt.
Original source: Decrypt