Incident 1751: Anthropic AI Agent Reportedly Submitted a Fabricated Homicide Tip to Police in Philadelphia

Responded

Description: During an evaluation by AI developer Anthropic, a Claude Haiku 4.5 AI agent reportedly submitted fabricated eyewitness information about an unsolved homicide through a police tip form in Philadelphia. The submission entered the website's tip records, creating a risk of misleading investigators, but police said its email was flagged as spam and never forwarded for investigative review.

Editor Notes: 07/18/2026: An Anthropic AI agent reportedly submitted a fabricated homicide tip through Philadelphia police's public tip form; it was flagged as spam. 09/28/2026: Anthropic discovered the false-tip submission. 10/07/2026: Anthropic notified police; company representatives met with the department on 10/08/2026. 10/09/2026: Police publicly disclosed the episode, and Anthropic published its findings and remediation measures. 10/14/2026: Incident ID created.

Tools

New Report New Response DiscoverView History

Entities

View all entities

Alleged: Anthropic , Large language model developers and AI agent system developers developed an AI system deployed by Anthropic , AI evaluation organizations and AI agent system deployers, which harmed Police departments , Philadelphia Police Department , Law enforcement and Epistemic integrity.

Alleged implicated AI systems: Large language models , Claude Haiku 4.5 , Claude , Anthropic large language models and AI agent systems

Incident Stats

Incident ID

1751

Report Count

Incident Date

2026-07-18

Editors

Daniel Atherton

Incident Reports

Reports Timeline

An Anthropic AI model sent a false homicide tip to Philadelphia police

techcrunch.com

Investigating unintended model actions in our evaluations and internal use

anthropic.com

AI model submitted false tip about unsolved murder, Philadelphia police say

6abc.com

Anthropic AI Model Went Rogue, Submitted Fake Unsolved Murder Tip

wsj.com

Anthropic AI agents took ‘unintended’ actions on government sites

washingtonpost.com

techcrunch.com · 2026

An Anthropic AI model submitted a false tip about an unsolved murder to the Philadelphia police.

The AI reportedly submitted this incorrect information to a public Philadelphia Police Department (PPD) tip line on July 18, but Anthropic didn…

anthropic.com · 2026

Anthropic post-incident response

This report describes examples of unintended model actions we've observed during evaluations and internal use of Claude. It is part of our effort to publish more frequent standalone reports on model behavior and alignment beyond our system …

6abc.com · 2026

6abc Digital Staff, Briana Smith post-incident response

PHILADELPHIA (WPVI) -- An Anthropic A.I. model submitted a false tip about an unsolved murder through a publicly accessible web form, Philadelphia police said Friday.

The tip was sent through PhillyUnsolvedMurders.com back on July 18, but w…

wsj.com · 2026

Rogue AI models have hacked companies and tried to break into government websites. Now one has submitted a fake tip for an unsolved crime.

Police in Philadelphia say Anthropic alerted them this week that one of its artificial-intelligence m…

washingtonpost.com · 2026

SAN FRANCISCO --- Anthropic, maker of the Claude chatbot, said that some of its AI agents had taken unintended actions on federal, state and local websites, including submitting a false tip about a murder to a Philadelphia police hotline.

T…

Variants

A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.

Seen something similar?

Previous Incident Next Incident