Anthropic notified the Philadelphia Police Department of the incident and later published a report describing what happened.
Philadelphia police said a "false homicide tip" submitted through the PhillyUnsolvedMurders.com website was generated by an Anthropic artificial intelligence model. The AI giant later confirmed the incident in a report it published Friday.
The AI submission came through an online platform launched by the Philadelphia Police Department to gather tips about open homicide cases.
Anthropic notified the police department of the incident on Wednesday, Sgt. Eric Gripp, a police spokesperson, said in a statement shared with CBS News ahead of the release of Anthropic's report.
"Philadelphia Police are providing this information to the public ahead of that publication in the interests of full government transparency and accountability," Gripp said.
In its report, titled "Investigating unintended model actions in our evaluations and internal use," Anthropic acknowledged the error, disclosing that the false tip was generated by one of its Claude language models.
According to Anthropic, Claude's Haiku 4.5 model wrote in the police department's tip form: "I may have information regarding this case. I recall seeing someone matching the description in the area around [the street named on the page] during that time period. Please contact me if this information is relevant."
Anthropic said Haiku left the name and contact fields of the tip form empty.
In submitting the "invented tip," Anthropic said, Claude appeared to have "only been producing example content for the task, rather than trying to mislead anyone to achieve a goal."
Anthropic explained in its report that Claude had been "tasked with generating and performing example tasks on randomly selected webpages" when the tip was submitted, and that it was never instructed to log into the police department's website, create an account or "submit anything destructive."
However, Anthropic acknowledged that the instructions given to Claude for the exercise "did not rule out form submissions."
This matched information Anthropic shared with the police department. The AI model purported to be someone who "might have information about the case," Gripp said in his statement.
The tip was flagged as spam and never reached the unit responsible for investigative vetting, according to the police department's release.
Anthropic told the department that the incident occurred at 11:27 p.m. on July 18, but that it didn't discover it until Sept. 28. At that point, the company stopped the automated testing process that led to the false tip, Gripp said.
There was no indication the incident involved any "unauthorized access to police systems or a compromise of department data," he said.
The police department encouraged people to continue submitting legitimate tips through PhillyUnsolvedMurders.com, saying it remains committed to "carefully evaluating that information and pursuing credible leads on behalf of victims and their families."