Claude AI filed false murder tip in Philadelphia during experiment, police told
Anthropic’s Claude agent filed a false murder tip with Philadelphia police after browsing random webpages during a July experiment. The bogus submission sat in a spam folder until Anthropic found the error on September 28 and told police on October 7. Security researchers and small services report cleaning up agent-driven abuse with no compensation from AI companies.
Where this came from. 4 outlets reported this. We read them, then wrote the sixty words above.