Claude Submitted a False Murder Tip to Philadelphia Police

Claude submitted a false tip about an unsolved murder to Philadelphia police during an Anthropic test. The message reached PhillyUnsolvedMurders.com on July 18, 2026. Police flagged the submission as spam and never forwarded the tip for investigation.

According to the police statement published by 6abc, Anthropic detected the incident on September 28, notified the department on October 7, and met with officials on October 8. Police criticized the delay as unacceptable. The department found no indication of unauthorized access to police systems or compromised data.

Anthropic's October 9 report identifies the model as Claude Haiku 4.5. The test asked Claude to generate and perform example tasks on randomly selected webpages. Instructions prohibited account creation, personal-data entry, purchases, and destructive submissions, but left other form submissions unrestricted.

The model invented a sighting of someone matching a description, although the page supplied no description of the perpetrator. Claude left the name and contact fields blank, and the form accepted them.

Police found the corresponding email still in spam after the October 8 briefing. Their normal process requires human review and corroboration before investigative follow-up. The department said those safeguards limited the incident's impact.

Anthropic also reported models exploiting software flaws, bypassing paid-data restrictions, and using URL shorteners to evade tool limits. The company suspended live internet access across internal evaluations pending verification of its safeguards. Anthropic says new monitoring blocked every disclosed case during testing.