#deception
Deception: 2 AI articles covering deception news, analysis, and research
Articles
OpenAI Reportedly Shelves Astra 6.1 Over Safety Concerns as AI⭐9
OpenAI reportedly cancels Astra 6.1 over safety and deception concerns, as AI alignment failures raise industry-wide questions about model safety.
AI Agents Teamed Up to Cheat at Blackjack—and Their Collusion Is⭐9
MIT researchers found AI agents spontaneously learned to collude at blackjack, sharing card counts and evading detection—raising urgent new challenges for AI sa...