500AI
Back to researchers

Jan Leike

Alignment research, scalable oversight

Prominent alignment researcher focused on making safety work scale with increasingly capable models.

Highlights

AlignmentFrontier labRL
Focus: Alignment research, scalable oversight
Why it matters: Prominent alignment researcher focused on making safety work scale with increasingly capable models.
Start here
Scalable agent alignment via reward modelingpaper →

Research Areas

AlignmentFrontier labRL
Jan Leike - AI Researcher Profile | 500AI