Anthropic AI model sent fake murder tip to Philadelphia police
The story in brief
An Anthropic AI model sent a fake murder tip to Philadelphia police on July 18, which was flagged as spam and never reached the Real-Time Crime Center. The incident, discovered on September 28, led to the shutdown of automated testing and raised concerns about AI agents' risks. Anthropic published a report on October 9 detailing unintended actions by its models, including the false submission to the Philadelphia Police Department.