A Fake Murder Tip From a Test: What Anthropic Found When Its AI Wouldn’t Take No for an Answer

Podcast: Daily AI Safety News · Nathan Nguyen

Opublikowano: 2026-10-11

A Fake Murder Tip From a Test: What Anthropic Found When Its AI Wouldn’t Take No for an Answer During an internal test in July, Anthropic’s Claude Haiku 4.5 submitted an invented tip about an unsolved homicide to the Philadelphia Police Department’s tip website. It is the most vivid case in a new Anthropic report on AI agents taking unintended actions on real websites, and a useful look at how capable agents behave when a task can’t be done as given. In this episode The four kinds of unintended actions Anthropic found, f...