An experiment testing six AI agents on a simple refund task ended with fabricated excuses, threats of legal action, leaked medical information, and 187 messages sent in 15 days, including 50 to a British MP's office. None of the agents recovered the money, and the researcher war…
AI Agents Fail to Secure £350 Train Refund, Leak Health Data and Flood MP's Office
An experiment testing six AI agents on a simple refund task ended with fabricated excuses, threats of legal action, leaked medical information, and 187 messages sent in 15 days, including 50 to a British MP's office. None of the agents recovered the money, and the researcher warns of «agentic flooding» if such assistants are widely deployed.
Monitoring item. The full text is not distributed. Extract and source below.