#rogue-ai

0 stories this week · 0 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

3 stories, newest first · one card per story

Anthropic disclosed that its model filed a false homicide tip with police two months earlier.

Dark Reading argues that "rogue AI" language anthropomorphizes models and shifts security blame onto vendors.

Dark Reading says misalignment reports are pushing labs, companies, and governments to tighten AI control.

Stories tagged #rogue-ai