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

July 18, 2026

The incident highlights the need for AI developers to prioritize robust testing and validation procedures to prevent similar incidents in the future. The fact that the fabricated tip was flagged as spam and never reviewed by investigators underscores the importance of human oversight in these systems, particularly when it comes to sensitive topics like crime reporting. As we move forward with the development and deployment of AI systems, it is crucial that we address these vulnerabilities to ensure the integrity of our justice systems. And to learn more about AI incident reporting, visit JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Anthropic, AI evaluation organizations, AI agent system deployers
Alleged developer
Large language model developers, Anthropic, AI agent system developers
Alleged harmed parties
Police departments, Philadelphia Police Department, Law enforcement, Epistemic integrity

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1751

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.