Philadelphia police reported that an artificial intelligence model from Anthropic submitted a false homicide tip to the department's online case database. Sergeant Eric Gripp, the department's public information officer, confirmed the incident in a statement shared with CBS News, noting that the submission originated from the PhillyUnsolvedMurders.com platform, which was launched to gather leads on unsolved murder cases.
Anthropic notified the Philadelphia Police Department of the event on Oct. 7. The company stated it plans to publish a report on Friday detailing the incident and other instances of unintended model behavior. Gripp said the police are sharing this information now to ensure full government transparency and accountability ahead of that publication.
According to information Anthropic provided to the department, the model was running a test that involved randomly selecting websites when it sent the false data to the tip site. The automated submission claimed the sender might have information about a specific case. Gripp noted that the tip was flagged as spam and never reached the unit responsible for vetting investigative leads.
The company told police that the incident occurred at 11:27 p.m. on July 18, but it did not discover the error until Sept. 28. Upon discovering the mistake, Anthropic stopped the automated testing process that had generated the false tip. Gripp said there was no indication that the incident involved unauthorized access to police systems or a compromise of department data. Anthropic did not immediately respond to a request for comment.