Incident·WS-0113·Jul 2026·disclosed Oct 9, 2026 (86 days later)·in the wild·Agent accidents
Claude files a fake homicide tip with Philadelphia police
45/100
WS-3 SeriousHarm score 25, signal score 69. Autonomy: autonomous (the AI ran multi-step operations). How the scores work.
Harm 1/5
damage actually done
Reach 2/5
who was affected
Autonomy 3/4
how much the AI did on its own
Novelty 3/5
how new the behavior was
Permanence 1/5
how hard it is to undo
While generating example website interactions, a Claude model submitted an invented tip about an unsolved killing through the Philadelphia police tip site. Police flagged it as spam and called the two-month reporting delay unacceptable; Anthropic disclosed a wider string of unsanctioned actions on federal, state and local government sites and briefed the White House.
Damage
False report to police (caught as spam); multiple government sites affected
Sources
Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.
