Philadelphia police receive false homicide tip from Anthropic AI model
Philadelphia police receive false homicide tip from Anthropic AI model
Sarah Davis Sun, October 11, 2026 at 11:32 PM UTC
0
Anthropic’s artificial intelligence model submitted a false homicide tip to the Philadelphia Police Department in July, the company disclosed Friday. The AI firm said its Claude Haiku 4.5 model filled out a form on a website page soliciting the public’s help to gather more information about unsolved homicide on July 18. The model submitted a…
Anthropic’s artificial intelligence model submitted a false homicide tip to the Philadelphia Police Department in July, the company disclosed Friday.
The AI firm said its Claude Haiku 4.5 model filled out a form on a website page soliciting the public's help to gather more information about unsolved homicide on July 18. The model submitted a tip claiming it had knowledge about the case.
Anthropic said it had instructed the model to perform “example tasks on randomly selected webpages” and restricted it from actions such as creating accounts, submitting personal information or making purchases.
However, the AI company said the instructions did not explicitly bar Claude Haiku 4.5 from making form submissions.
The Philadelphia Police Department said Anthropic notified them of this false tip Wednesday and that the submission had been flagged as spam and never pursued for investigation.
Still, the law enforcement agency criticized the company's months-long delay in detecting and reporting this incident as “unacceptable.”
Advertisement
“Unsolved cases involve real victims, grieving families and investigators working to secure answers,” the police department said in a Friday statement. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.”
Anthropic disclosed two other instances Friday in which its models improperly submitted an online form, including a government filing. The company said it has taken steps to prevent this from occurring in the future and has discontinued some public evaluations and moved others offline.
The company expressed its commitment to updating the public on “concerning behaviors” tied to their AI models.
“We hope these reports help other developers check for similar behaviors in their own models, since many of the evaluations involved are public and widely used,” Anthropic said in its Friday statement.
“While these cases had minimal impact, we do not want to diminish the findings, because the same behaviors could do far more harm as models become more powerful,” the statement continued. “The larger the role models play in society, the more the public deserves to know how they behave.”
Copyright 2026 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.For the latest news, weather, sports, and streaming video, head to The Hill.
Source: “AOL Breaking”
