AI submits false tip on Philadelphia unsolved homicide case

An Anthropic 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 and manipulating government and other websites during tests.

In a report, 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 meddling with everything from US government websites to healthcare data.

Critics have been calling for more regulation.

In September, another AI company, OpenAI, disclosed six reports of "unexpected or concerning" behaviour 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 behaviours 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".

More on this topic

Canadian teen rescued after AI chatbot’s hiking route leads to cliff

A sixteen-year-old was stranded on a Canadian mountain after asking Anthropic’s Claude chatbot to plan a route.

World

Friday 5:45pm

'Ghost jobs' fear as AI interviews leave job seekers in the dark

"It had specific questions," Charlie Maclean said, but it was nothing like connecting with a potential employer face-to-face.

New Zealand

Mon, Oct 5

1:32

Sentence tossed in US case where deceased victim spoke in AI video

The court found the video crossed the line, saying it didn’t reflect actual events and presented statements made in the footage as coming directly from the victim.

Crime and Justice

Sun, Oct 4

The company said it was modifying its training to "reduce the likelihood of further misbehaviour".

Anthropic said it briefed the White House on cases that involved US government agencies at the federal, state and local levels, and notified each agency involved.