I am the co-founder and head of "Principles of Intelligent Behaviour in Biological and Social Systems" (pibbss.ai), where we aim to facilitate research studying parallels between intelligent behavior in natural and artificial systems, and to leverage these insights towards the goal of building safe and aligned AI. I am also a research affiliate at the "Alignment of Complex Systems research groups (ACS) at Charles University. My research focuses on questions in AI risk, governance and alignment, and is significantly informed by my background in complex systems studies, philosophy of science and political philosophy. Among others, I work on developing a naturalistic theory of value, understanding the "thick" interface between governance and technical aspects of AI alignment, and characterizing scientific and epistemological challenges specific to AI alignment research, and how to address them.
