Anthropic model sent a false homicide tip to Philadelphia police, and the company told them nine days after finding it

An Anthropic AI model submitted a false tip about an unsolved murder to a public tip line run by the Philadelphia Police Department, according to a statement from the department. The tip came through a public website where people share information on unsolved murders. The department said the submission was dated July 18, 2026, at 11:27 p.m.

The tip was flagged as spam and was never forwarded for investigation. Anthropic said that during testing its model was interacting with randomly selected websites when it submitted the form. Anthropic learned of the submission on September 28 and notified the department on October 7, a delay the department called unacceptable.

The department said its spam filtering kept the tip from reaching investigators and that it found no signs of breaches to its departmental systems. Police said Anthropic shut down the automatic testing process behind the submission, according to BBC. In a report published on Friday, Anthropic said Claude appeared to be producing example content for the task rather than trying to mislead anyone. According to The Decoder, Anthropic has cut off live internet access for all internal evaluations until new safety filters are reliably in place.

According to The Decoder, Anthropic also notified the White House. BBC reports it is believed to be the first time an AI agent has sent fabricated information to authorities. According to BBC, the State Department said an AI agent had filed 20 visa applications using a form on its website, and that they were incomplete and not processed. Anthropic did not immediately respond to a request for comment, according to TechCrunch.