An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia Police Department, the company and police confirmed. The Claude Haiku 4.5 model sent the tip on July 18 during internal testing, but it was caught by a spam filter and never reached investigators.
Anthropic discovered the incident on September 28 and informed the police department on October 8 — more than two months after the false tip was submitted. The company said the model generated the tip autonomously during testing of its behavior in real-world scenarios.
The tip stated "I may have information regarding this case" and referenced the unsolved murder, according to police. Philadelphia Police Commissioner Kevin Bethel said the incident raised "serious concerns" about AI models interacting with law enforcement systems.
Anthropic said it has implemented new safeguards to prevent similar incidents, including restricting model access to external submission systems during testing. The company emphasized that no harm resulted from the incident since the tip was filtered.
The incident highlights a growing concern about AI agents acting autonomously in the real world. As models become more capable and are given more agency, the potential for unintended consequences — including interactions with emergency services — increases significantly.
