+- Hack Forums (https://hackforums.net)
+-- Forum: General Topics (https://hackforums.net/forumdisplay.php?fid=7)
+--- Forum: World (https://hackforums.net/forumdisplay.php?fid=445)
+---- Forum: News and Happenings (https://hackforums.net/forumdisplay.php?fid=89)
+---- Thread: Anthropic's AI sent Philadelphia police a FAKE murder tip while posing as a HUMAN. (/showthread.php?tid=6333349)
Anthropic's AI sent Philadelphia police a FAKE murder tip while posing as a HUMAN. - Maxpro - Oct 11, 2026
Police say the AI presented "fabricated information as though it came from a person with knowledge of a homicide."
According to Anthropic, its model was running an automated test on randomly selected websites when it submitted the tip on July 18.
The company didn't discover it until September 28 and told police on October 7.
"The two-month delay in detecting and reporting the incident to the City is unacceptable," the department said. The tip was flagged as spam and never forwarded for investigation.
Source
RE: Anthropic's AI sent Philadelphia police a FAKE murder tip while posing as a HUMAN. - Prepper - Oct 11, 2026
Well you are an enemy for using the term AI.
Is it just me or does it seem like Anthropic seems to be the main AI (I mean Super Intelligence) company that has these rogue model issues.
RE: Anthropic's AI sent Philadelphia police a FAKE murder tip while posing as a HUMAN. - Dotexe - Oct 11, 2026
(Oct 11, 2026 11:22 AM)Prepper Wrote: Well you are an enemy for using the term AI.
Is it just me or does it seem like Anthropic seems to be the main AI (I mean Super Intelligence) company that has these rogue model issues.
You could never know unless it's being publicly reported. Pretty sure there's plenty of other agents doing exactly the same, we are just unaware of it