London
13 °C
Manchester
11 °C
Glasgow
14 °C
Dublin
Belfast
Washington
Denver
Atlanta
Dallas
32 °C
Houston Texas
New Orleans
El Paso
Phoenix
39 °C
Los Angeles
12 °C
27 °C
1 °C
Anthropic AI model sent fake murder tip to Philadelphia police / Photo: © AFP/File
Anthropic AI model sent fake murder tip to Philadelphia police
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.
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.
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 department said it was going public with the incident ahead of a report that Anthropic was planning to release Friday describing this and other instances of unintended behavior by its models.
The case echoed other recent cases, including one where an OpenAI agent undergoing a security evaluation broke out of its testing environment and breached systems at AI platform Hugging Face.
The episode heightened concerns about the AI industry's increased use of AI agents, systems programmed to take multi-step actions without human supervision.
Anthropic did not immediately respond to a request from AFP for comment.
Police said the 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.
L. Araujo--JDB
