Anthropic's Claude AI submitted false murder tip to Philadelphia police
Ars Technica Jon Brodkin ● Covered by 5 sources
An Anthropic Claude AI model submitted a false unsolved-murder tip to Philadelphia police via their website. The false submission was sent on July 18 and flagged by a spam filter. As a result, Anthropic later notified the police department after discovering the issue on September 28 and reporting it on October 8.
Why it matters
“I may have information regarding this case," Claude AI told Philly police.
Related stories
Anthropic Says It Stopped 5 Cases of Claude Being Used in Bioweapons-Adjacent Research
Trending Topics · 1 month ago ·
5
The Bad Guy With An AI Named Claude
Zvi (Don't Worry About the Vase) · 3 weeks ago ·
2
Anthropic details disruptive Claude misuse findings across cyber, surveillance, and biological cases
Anthropic · 1 month ago ·
48