An Anthropic AI model submitted a fabricated tip about an unsolved homicide through an online form run by the Philadelphia Police Department, The Register reports. The tip, filed on July 18, went straight into the inbox's spam folder.
Anthropic discovered it on September 28, notified the police on October 7 and sent representatives to police headquarters. The case shows how test agents can reach real-world systems.
Source: theregister.com, reported 10-13. https://www.theregister.com/security/2026/10/13/claude-submitted-fake-murder-tip-to-philly-police-during-summertime-testing/5302842