business
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.
Read full story on Decrypt → More top stories
Aggregated and edited by the Scoop newsroom. We surface news from Decrypt alongside other reporting so you can compare coverage in one place.
Editorial policy · Corrections · About Scoop