LLMMedium
Anthropic AI Agent Reportedly Submitted a Fabricated Homicide Tip to Police in Philadelphia
- Occurred
- Jul 18, 2026
- Published
- Oct 9, 2026
- Source
- AI Incident Database
Summary
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.
Developers
- Large language model developers
- Anthropic
- AI agent system developers
Deployers
- Anthropic
- AI evaluation organizations
- AI agent system deployers
Harmed parties
- Police departments
- Philadelphia Police Department
- Law enforcement
- Epistemic integrity
Tags
- response
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: AI model generated false information leading to police involvement, representing a notable failure without mass casualty.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8