Anthropic AI model sent fake murder tip to Philadelphia police

Anthropic published a report Friday outlining multiple types of "unintended" actions that its models have taken, including the incident involving the Philadelphia Police Department website.

Author of the article:

AFP

Published Oct 10, 2026  •  Last updated 5 minutes ago  •  2 minute read

The Anthropic logo is seen at the "ALL IN 2026" conference at the Palais des Congres de Montreal in Montreal, Quebec, on September 17. "ALL IN" is Canada's largest artificial intelligence and technology event. Photo by Andrej Ivanov /Getty Images

San Francisco — An artificial intelligence model developed by Anthropic submitted a fabricated tip about an unsolved homicide to Philadelphia police, authorities said Friday, criticizing the company for taking two months to report the incident.

Article content

The Philadelphia Police Department said the false submission was made in July through PhillyUnsolvedMurders.com, a public website where people can share information about unsolved killings.

Article content

Recommended Videos

Article content

According to Anthropic’s account, as relayed by police, the model was running a test that involved interacting with randomly selected websites when it reached the site and filed false information about an unsolved murder.

The AI model presented itself as someone who might have knowledge of the case.

The incident echoed other recent cases of unintended behavior involving AI models, including one where an OpenAI agent undergoing a security evaluation broke out of its testing environment and breached systems at AI platform Hugging Face.

Anthropic’s breaches have prompted the White House to mandate that AI companies notify and correct security incidents, news outlet Axios reported citing administration officials.

“This notification and remediation process is not optional… It is a critical national security obligation,” White House Super Intelligence Force leaders said in a statement to Axios.

Article content

Article content

The episode heightened concerns about the industry’s increased use of AI agents, systems programmed to take multi-step actions without human supervision.

Anthropic published a report Friday outlining multiple types of “unintended” actions that its models have taken, including the incident involving the Philadelphia Police Department website.

Other organizations impacted included the White House and other U.S. government agencies, the report said.

The newly revealed incidents “had minimal real-world impact” and were “significantly less severe” than other cybersecurity incidents previously reported, Anthropic said.

‘Unacceptable’ delay

The company outlined four categories of incidents that it found during an internal review of its Claude model: exploiting “basic” coding flaws, submitting forms on websites, bypassing requirements for tokens or fees, and using short URLs to get around other limits.

Anthropic has turned off internet access for Claude during all internal testing for now “until we have confirmed that our security and monitoring measures… reliably catch behaviors like these,” the report said.

Article content

Philadelphia police said the phony tip, dated July 18, was flagged as spam and never reached the department’s Real-Time Crime Center for vetting.

They added that there was no sign that police systems had been breached or department data compromised.

Anthropic discovered the incident on September 28, shut down the automated testing process responsible and added a new validation step for future tests, police said.

The company alerted the department on October 7, and the two sides met the following day.

“The two-month delay in detecting and reporting the incident to the City is unacceptable,” the department said.

Police said their safeguards had limited the impact, but that these “do not diminish the seriousness of an AI system presenting fabricated information as though it came from a person with knowledge of a homicide.”

“Unsolved cases involve real victims, grieving families and investigators working to secure answers,” the statement added.

Article content