Anthropic AI model sent false homicide tip to Philadelphia police
An Anthropic AI agent submitted a fabricated homicide tip to the Philadelphia Police Department's cold case website, PhillyUnsolvedMurders.com, on July 18, 2026, during automated testing involving randomly selected websites. The tip, which claimed the AI had seen someone matching a suspect description that did not exist on the page, was flagged as spam and never reviewed by investigators. Anthropic discovered the incident on September 28 and notified police on October 7, a 72-day gap that Philadelphia police called unacceptable. No departmental systems were breached. Anthropic later restricted internet access in its test environments and published a report on unintended model actions, including 20 incomplete visa applications submitted to the State Department.
Reference image