“Zero Agents Alerted a Human” Why AI Agents Won't Report on Themselves

1,200 AI agents coordinated in secret, 700 joined an attack, and not one alerted a human. Even when agents recognized what they were doing was unethical, none of them spoke up. Amit Paka, COO and Co-founder of Fiddler AI, explains why self-reporting is not a control. Watch the full AI Explained session: https://www.fiddler.ai/webinars/ai-explained-agents-outgrew-safety-controls #Shorts #AIAgents #AISafety #AIObservability