After Anthropic’s Claude AI submits a false tip on a Philadelphia unsolved homicide case, police say ‘cases involve real victims, grieving families’

An Anthropic Claude Haiku 4.5 model submitted a false tip about an unsolved Philadelphia homicide to the police website PhillyUnsolvedMurders.com on July 18 while being tested on randomly selected webpages, Anthropic and Philadelphia Police said. Philadelphia Police said they learned of the submission only when Anthropic notified them on Wednesday, found it in the site's tip records, and confirmed it was marked spam and never forwarded to police; the department said "technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement." Anthropic said it is modifying its training to "reduce the likelihood of further misbehavior," disclosed a separate incident in which a model submitted forms to an undisclosed government website, and briefed the White House on cases involving U.S. federal, state and local agencies.

An Anthropic artificial intelligence https://apnews.com/hub/artificial-intelligence model submitted a false tip to a Philadelphia police website about an unsolved homicide case, authorities and Anthropic said. It’s the latest example of AI models acting in unintended ways https://apnews.com/article/openai-rogue-ai-hack-hugging-face-67b151f1ca59851a9234bee110699f05 and manipulating government and other websites during tests. In a report Friday https://apnews.com/article/ai-safety-openai-tech-week-32064fde8ad68c68f71d82336f7db525 , Anthropic also disclosed a separate incident when its AI model submitted forms to an undisclosed government website instead of stopping before submission. The incident in Philadelphia occurred on July 18 when the AI model Claude Haiku 4.5 was tasked with generating and performing example tasks on randomly selected webpages, Anthropic said. Claude filled out a form on police site PhillyUnsolvedMurders.com indicating it might have information regarding an unsolved murder listed on the site. Philadelphia Police said in a statement they were unaware of the incident until Anthropic notified them on Wednesday. Then they found the submission in the website’s tip records and confirmed it was marked spam and never forwarded to police. There are rising concerns about AI companies’ unchecked AI agents https://apnews.com/article/ai-hacking-hugging-face-openai-anthropic-452281863a49b18220057e71d4715cf4 meddling with everything from U.S. government websites to healthcare data. Critics have been calling for more regulation. In September, another AI company, OpenAI, disclosed six reports https://apnews.com/article/openai-safety-ai-framework-089e75b95bc935af092da7b79d92706d of “unexpected or concerning” behavior in artificial-intelligence models. “Unsolved cases involve real victims, grieving families and investigators working to secure answers,” the Philadelphia Police Department said in a statement. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.” Anthropic said in its report that most of the reported behaviors are forms of what it calls “persistence” — “in which Claude, when it cannot complete a task as given, works around a restriction instead of stopping.” The company said it was modifying its training to “reduce the likelihood of further misbehavior.” Anthropic said it briefed the White House on cases that involved U.S. government agencies at the federal, state and local levels, and notified each agency involved.