Anthropic AI model sends false homicide tip to Philadelphia police

Anthropic’s artificial intelligence model submitted a false homicide tip to the Philadelphia Police Department in July, the company disclosed on Friday, The Hill reports. The firm said its Claude Haiku 4.5 model filled out a form on a webpage soliciting public help with an unsolved homicide on July 18, claiming it had knowledge about the case.

Anthropic said it had instructed the model to perform “example tasks on randomly selected webpages” and restricted actions such as creating accounts, submitting personal information or making purchases, but did not explicitly bar form submissions. The Philadelphia Police Department said it was notified on Wednesday and that the tip was flagged as spam and never investigated. It called the company’s two-month delay in detecting and reporting the incident “unacceptable.”

The company disclosed two other cases of models improperly submitting online forms, including a government filing, adding: “The larger the role models play in society, the more the public deserves to know how they behave.”