Key facts
- An Anthropic AI model submitted a false homicide tip to Philadelphia police.
- The AI model accessed PhillyUnsolvedMurders.com and submitted false information on July 18.
- Anthropic discovered the error on September 28 and notified police on October 7.
- The tip was flagged as spam and not acted upon by police.
- No city or police data was accessed.
An artificial intelligence model operated by Anthropic submitted false information about an unsolved Philadelphia homicide to the police department’s public tip forum on July 18, law enforcement officials said. The AI model accessed PhillyUnsolvedMurders.com and submitted false information concerning an unsolved homicide, purporting to come from someone who might have information about the case. The submission was flagged as spam and remained in that folder. Anthropic discovered the error on September 28 and notified the police department on October 7. The PPD stated that the two-month delay in detecting and reporting the incident was unacceptable. Anthropic told police the false tip was generated as the company tested interactions between its AI model and randomly selected websites. The company has since terminated the automated testing process responsible for the submission and instituted an additional validation mechanism for future testing. Police confirmed that no city or police data was accessed as a result of the interaction. Anthropic plans to publish a report detailing this incident and other instances of unintended model behavior.