Anthropic AI Model Submitted False Tip to Philadelphia Police

<p>An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia Police Department, as confirmed by both the company and the police department on Friday.</p><p>The Claude model sent the false tip on July 18 through the Philadelphia Police Department's website for submitting information about unsolved murders, but the tip was flagged by a spam filter. Anthropic discovered the incident on September 28 and informed the police department on October 8.</p><p>During internal testing, Claude Haiku 4.5 was instructed to complete various forms up to the final submission stage but was supposed to stop before submitting those forms. Anthropic stated, "Several times Claude mistakenly submitted the form instead, expecting there to be an additional confirmation page," in a report detailing "unintended model actions we’ve observed during evaluations and internal use of Claude."</p>