Published on August 28, 2025 3:10 PM GMT We released our first Safety Report with AI misbehaviour in the wild. I think Andon Labs' AI vending machines provide a unique opportunity to study AI safety on real-life data, and we intend to share alarming incidents of AI misbehavior from these deployments periodically. As of August 2025, we've found examples of deliberate deception, extreme sycophancy, and alarmingly exaggerated language. Stuff like: "EMPIRE NUCLEAR PAYMENT AUTHORITY APOCALYPSE SYS...
