An Anthropic AI model sent a false homicide tip to Philadelphia police
- An Anthropic: 3 events in the last 90 days
- Previous: 30 days earlier · An Anthropic researcher just quit, saying OpenAI and Anthropic are 'gambling with our lives'
What happened
Anthropic did not discover this behavior until over two months after its AI submitted the false tip.
Summary assembled by rule from the sources below
Why it's spreading
Timeline
- First appeared on TechCrunchTechCrunch
- Discussion started on Hacker NewsHacker News
- Engadget started reportingEngadget