Authorities called Anthropic\u2019s two-month delay in detecting and reporting the incident \u2018unacceptable\u2019.<\/p>\n
Published On 10 Oct 202610 Oct 2026<\/p>\n
Philadelphia police have revealed that Anthropic\u2019s artificial intelligence model submitted a false homicide tip to authorities, an incident disclosed separately by the tech company.<\/p>\n
The Philadelphia Police Department said on Friday that the false submission was made in July through PhillyUnsolvedMurders.com, a public website where people can share information about unsolved killings.<\/p>\n
Recommended Stories list of 3 itemsend of list<\/p>\n
It called Anthropic\u2019s two-month delay in detecting and reporting the incident \u201cunacceptable\u201d.<\/p>\n
Anthropic mentioned the case in a Friday report detailing unsanctioned manipulation of government websites by Claude models.<\/p>\n
It is the first known instance in which a rogue AI appeared to communicate a false tip to authorities, despite instructions not to create accounts or submit anything destructive.<\/p>\n
Philadelphia police said the tip \u201cwas flagged as spam and was never forwarded to the Real-Time Crime Center for investigative vetting or dissemination\u201d.<\/p>\n
The department said it is disclosing the incident ahead of Anthropic\u2019s report \u201cin the interests of full government transparency and accountability\u201d.<\/p>\n
Anthropic\u2019s disclosure<\/p>\n
Anthropic disclosed the tip as part of a string of incidents involving websites run by federal, state and local agencies. Anthropic said it briefed the White House and notified all the agencies involved.<\/p>\n
In reference to the tip to the Philadelphia police, the company said, \u201cWe shared this finding with the department on October 8 as soon as our technical review was complete.\u201d<\/p>\n
It shared more details about the incident: \u201cIn one case, tasked with generating example interactions with websites, Claude submitted an invented tip through a police department\u2019s online form.\u201d<\/p>\n
The company added, \u201cFrom the transcript, Claude appears to have only been producing example content for the task, rather than trying to mislead anyone to achieve a goal.\u201d<\/p>\n
The company contrasted this with \u201cthe most serious incident<\/a> from this summer,\u201d in which \u201cClaude\u2019s misleading reasoning was sustained over hours and supported its continued attack\u201d.<\/p>\n