Back to researchers

Amanda Askell

Alignment, behavior shaping, safety

Works on practical alignment and steering of frontier models; useful lens for post-training tradeoffs.

Highlights

AnthropicAlignmentPost-training
Focus: Alignment, behavior shaping, safety
Why it matters: Works on practical alignment and steering of frontier models; useful lens for post-training tradeoffs.

Research Areas

AnthropicAlignmentPost-training
Amanda Askell - AI Researcher Profile | 500AI