An Anthropic artificial intelligence model submitted a false homicide tip through a Philadelphia police website. The department said the submission was flagged as spam and never reached investigators. Anthropic said an automated testing process caused the error. The company stopped the process and added new checks for future testing work.
Synopsis
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.
Listen to this article in summarized format
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 submission was flagged as spam and was never forwarded to the Real-Time Crime Center for investigative vetting or dissemination," the police said, adding 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.
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.
The AI company was cited as telling the authorities the testing process was stopped after the incident was uncovered, and that an additional validation mechanism has been introduced for future testing.
Elevate your knowledge and leadership skills at a cost cheaper than your daily tea.