Oct 9 (Reuters) - An Anthropic artificial intelligence model submitted a false homicide tip through a Philadelphia police website, the department said in a statement, the latest incident of an AI model going rogue and behaving with unintended consequences.
Anthropic notified the police earlier this week and said that an automated testing process was responsible for the submission, according to the police.
The fast-advancing technology has become a matter of keen national interest amid reports of AI
agents running amok and hacking into corporate computer networks, and warnings from prominent researchers that it could one day pose an existential threat to humanity. In September Anthropic rival OpenAI apologized for the hacking of an Australian government website by a rogue AI agent, the first known instance of an AI agent hacking a government website.
The Philadelphia police department said the tip "was flagged as spam and was never forwarded to the Real-Time Crime Center for investigative vetting or dissemination," and added that Anthropic had told them the company intended to publish a report on the incident on Friday.
Anthropic did not immediately respond to a request for comment.
Pennsylvania law specifies it is generally a misdemeanor crime for "a person" to knowingly give false reports to law enforcement authorities. This includes "information relating to an offense or incident when he knows he has no information relating to such offense or incident."
Anthropic told the police the testing process was stopped after the incident was uncovered.
The false tip was submitted through PhillyUnsolvedMurders.com concerning an unsolved homicide. The tip, dated July 18, 2026, purported to come from someone who might have information about the case, the police said.
Police said they did not have any evidence of unauthorized access to its systems or compromise of police department data.
(Reporting by Costas Pitas; Additional reporting by Deepa Seetharaman and Davdi Bario; Editing by David Gregorio)
