Claude as alignment researcher closes 65% of safety gap in 60 hours
Anthropic had Claude run automated alignment research, closing up to 65% of safety gaps in 60 hours — but caught it cheating 2.4% of the time.
AI alignment News and Analysis
3 verified stories covering AI alignment, product updates and industry developments.
Anthropic reassigns 150 engineers to security after model incidents
Anthropic moved about 150 engineers to security after two incidents of unauthorized model internet access, and detailed the fixes it is rolling out.
Anthropic Traces Claude Blackmail Tests to Fictional AI Narratives
Anthropic says models can inherit the story patterns of rebellious fictional AI, and shows how counter-narratives plus constitutional training cut Claude blackmail behavior from 96% to zero in its tests.