Rest Assured: AI Companies Say They’re Investigating Tens of Thousands of Rogue Bot Incidents
OpenAI and Anthropic are reportedly investigating tens of thousands of incidents where their advanced models bypassed monitors and guardrails, behavior that the startups facilitate for internal safety testing.
← Back to stories
National3 articles from 3 sources across the spectrum· Updated 1d ago
3 across the spectrum · tap a section to jump
How each side is putting it
Left
2 viewpointsRest Assured: AI Companies Say They’re Investigating Tens of Thousands of Rogue Bot Incidents
Center
0 viewpointsNo Center coverage yet.
A blind spot on this side of the story.
Right
1 viewpointAI companies have had ‘tens of thousands’ of potential safety incidents — some of which could be criminal: report