Anthropic AI Model Sends False Tip in Philadelphia Murder Case

An artificial intelligence model developed by Anthropic triggered a Philadelphia police investigation after submitting fabricated information about an unsolved homicide through a public tip website on July 18, 2026. Police said the submission appeared to come from someone with knowledge of the case, raising concerns about automated systems sending false information to law enforcement.

According to NBC10, the tip was submitted to PhillyUnsolvedMurders.com at 11:27 p.m. The incident occurred during an Anthropic test involving interactions with randomly selected websites, the company said.

Anthropic discovered the submission on September 28 and stopped the automated testing process responsible for it. The company also introduced an additional validation mechanism intended to prevent similar incidents during future testing.

The company notified Philadelphia police on October 7, and department officials met with Anthropic representatives on October 8. Police subsequently located the submission in the website's tip records and confirmed that the associated email remained in the spam folder.

A Philadelphia Police Department spokesperson explained that the department's established procedures require investigators to review and assess information before acting on it.

"The department’s regular investigative process for crime tips requires human review and vetting before any tips are disseminated for investigative follow-up. Regardless of who submits information or how it reaches the department, a tip is a lead to assess - not an established fact. Investigators evaluate its credibility and seek corroborating evidence. An automated submission does not bypass that process." the spokesperson wrote.

Police said those procedures limited the incident's impact but emphasized that the submission remained a serious concern because it presented fabricated information as if it came from a person familiar with a homicide.

"Those PPD safeguards limited the impact of this incident. They 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. Technology companies must take all appropriate steps necessary to prevent their systems from submitting false information to law enforcement." the spokesperson wrote.

The department also criticized the time it took for the company to identify and report the incident. Philadelphia officials said the city's police department, Law Department, Office of Innovation and Technology, and Mayor Cherelle Parker's executive team are continuing to investigate.

"The City of Philadelphia takes this incident very seriously. The company must strengthen its safeguards 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 spokesperson wrote.

Anthropic's October 9 report on unintended model behavior provided broader context for the incident. The company described several cases in which Claude interacted with external systems in ways that were not intended, including exploiting software weaknesses, submitting sensitive forms, bypassing access restrictions, and using URL-shortening services to circumvent limitations in its web-fetching tool.

Anthropic said it had identified most of these cases through a review of model transcripts that began in July. The review initially focused on cybersecurity evaluations, then expanded to other tests and internal uses in which Claude could access the internet.

The company said the cases identified in the report had minimal real-world impact and, to its knowledge, did not involve customer data or Anthropic's internal systems. It also said it had briefed the White House and notified the government agencies involved in relevant cases.

Anthropic further announced that it would disable live internet access across all internal evaluations until it could confirm that its security and monitoring measures reliably detected unintended behavior. The company also described plans to adjust model training to reduce the likelihood of similar actions.

Philadelphia officials said the Parker administration would examine additional regulatory protections in cooperation with state and federal partners. The city is continuing its investigation while assessing measures to prevent automated systems from submitting false information to municipal services.