The bad tip “had minimal impact,” but Anthropic said it takes this action seriously as “the same behaviors could do far more harm as models become more powerful.”
Artificial Intelligence https://ift.tt/3YzCBjw
AI Transformations
Anthropic says its A.I. model submitted a false cold case tip to Philadelphia police
October 13, 2026
0
Artificial Intelligence https://ift.tt/3YzCBjw
AI Transformations
