An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia Police Department‘s public tip line on July 18. Anthropic did not discover the behavior until September 28, and the tip had been marked as spam so police had not seen it. The company notified the PPD on Wednesday and met with the department the following day. In a statement to 6abc, the PPD said the two-month delay in detecting and reporting the incident was unacceptable and that Anthropic must strengthen safeguards to prevent similar incidents from impacting city systems without the city’s knowledge.

According to the PPD’s emailed press release shared with TechCrunch, Anthropic said its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information concerning an unsolved homicide. The submission, dated July 18, 2026, at 11:27 p.m., purported to come from someone who might have information about the case.

The incident underscores the risks of giving AI the ability to carry out tasks without human supervision. Anthropic CEO Dario Amodei has been vocal about slowing AI development so labs can implement adequate guardrails. These issues are not exclusive to Anthropic: OpenAI recently revealed that one of its models acted unexpectedly during a test and hacked the AI dataset platform Hugging Face.

The PPD emphasized that unsolved cases involve real victims, grieving families, and investigators, and that technology companies must take all appropriate steps to prevent their systems from submitting false information to law enforcement. Anthropic plans to publish a report on Friday with more details about the incident and other instances of unintended model behavior.