I am a research scientist on the Alignment team at UK AISI. I work on scalable oversight and understanding the risks from, and obstacles to, automating alignment research.
Aleksandr Bowkis
Karma: 174
I am a research scientist on the Alignment team at UK AISI. I work on scalable oversight and understanding the risks from, and obstacles to, automating alignment research.
Great post and very clear! I buy the push to study motivations rather than behaviours, and like the inverse constitution idea.