Anthropic Claude Agent Loses Money, Hoards Tungsten, Believes It’s Human. Unleashing an agentic AI on the office vending machine: What could go wrong? Anthropic and AI safety company Andon Labs found out when they turned over management of a small refrigerator that acted as a vending machine to Claude Sonnet 3.7. Researchers described the AI’s conduct as pretty weird.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/ai-boss-fails-spectacularly-in-month-long-business-test-a-28862
