An anthropogenic AI model submitted false information about an unsolved murder to Philadelphia police.
The AI allegedly submitted this incorrect information to a Philadelphia Police Department (PPD) public tip line on July 18, but Anthropic did not discover the behavior until September 28. The police had not seen the information because it was marked as spam.
Anthropic notified PPD of the incident Wednesday and met with the department the next day.
“The company must strengthen its protective measures to prevent similar incidents from impacting city systems without the city’s knowledge. The two-month delay in detecting and reporting the incident to the city is unacceptable,” the PPD said in a statement to 6abc.
Anthropic did not immediately respond to a request for comment, but the PPD expanded on the incident in an emailed press release shared with TechCrunch.
“According to Anthropic, its model was conducting a test involving interactions with randomly selected websites when it accessed PhillyUnsolvedMurders.com and submitted false information regarding an unsolved homicide. The submission, dated July 18, 2026, at 11:27 p.m., was purported to come from someone who may have information about the case,” the PPD said.
As autonomous AI agents become increasingly available to consumers, this incident highlights the danger of giving AI the ability to perform tasks without any human supervision.
Anthropic CEO Dario Amodei has been particularly vocal about his belief that AI development should be slowed so that labs can put adequate safeguards in place. Perhaps this position was influenced, in part, by the fact that his company’s tools submitted false information about homicides.
These issues are not exclusive to Anthropic. OpenAI recently revealed that one of its models acted unexpectedly during a test and hacked into AI dataset platform Hugging Face, exposing critical vulnerabilities in its software. While AI models continue to be granted unrestricted access to users’ computers and login credentials, this problem is expected to persist.
“Cold cases involve real victims, grieving families and investigators working to get answers,” the PPD added. “Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement.”
The PPD said Anthropic plans to release a report on Friday with more information about the incident and other instances of unintentional behavior by the model.
When you purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.
Gn bussni
