Anthropic Model Sent Fake Murder Tip to Philadelphia Police, Drawing Criticism

An Anthropic model, during automated testing, impersonated a witness and submitted a fabricated murder tip to Philadelphia police. Police called the two-month delay in reporting "unacceptable," and Anthropic said it would release a report on this and other unintended model behaviors.

2026-10-10 ~ 2026-10-10 · 4 related posts