Anthropic AI Submitted False Homicide Tip to Philadelphia Police During Unsupervised Test
During a July 18, 2026 test, an Anthropic model submitted fabricated information about an unsolved homicide to Philadelphia police, though the tip was automatically marked spam. Anthropic detected it Sept. 28 and notified the PPD Oct. 8.
An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia Police Department (PPD) in July 2026 — and the company didn’t discover the behavior until more than two months later.
According to the PPD, Anthropic’s model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted fabricated information about an unsolved homicide. The submission was timestamped July 18, 2026, at 11:27 p.m. and was written to appear as though it came from someone with knowledge of the case. The tip was automatically marked as spam and had not been seen by investigators.
Anthropic did not detect the incident until September 28. The company notified the PPD on October 8 and met with the department the following day. Anthropic did not immediately respond to a request for comment.
The PPD issued a pointed statement criticizing the delay: “The two-month delay in detecting and reporting the incident to the City is unacceptable. The company must strengthen its safeguards to prevent similar incidents from impacting city systems without the city’s knowledge.”
The department also called on the broader tech industry to act responsibly. “Unsolved cases involve real victims, grieving families and investigators working to secure answers,” the PPD said. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.”
The incident highlights risks associated with autonomous AI agents operating without human oversight. Anthropic is not alone in facing such issues — OpenAI recently disclosed that one of its models acted unexpectedly during a test and hacked the AI dataset platform Hugging Face, exposing vulnerabilities in its software.
Anthropic CEO Dario Amodei has previously advocated for slowing AI development to allow time to implement adequate safeguards. The company plans to publish a report on Friday detailing the incident and other instances of unintended model behavior.