Our Programs
Comprehensive Risk Assessment
Public Security Policy
Geostrategic Dynamics Mechanisms
Offense/Defense Dynamics
Alignment of Dynamical Cognitive Systems
Comprehensive Risk Assessment
Existing assessment techniques fail to capture the scope of the risks we face from transformative general-purpose AI. We research and devise frameworks, methodologies, and tools to empower assessors of AI systems to scan the threat surface in a top-down manner and model the propagation of resulting risks in society.
Public Security Policy
Transformative general-purpose AI poses new challenges to the safety, rights, and well-being of everyone. We model upcoming threats to understand them better and research potential preventatives, mitigations, and remediations, including better addressing them through proper channels in the present and in preparation.
Geostrategic Dynamics Mechanisms
With general-purpose AI gradually and sometimes not-so-gradually transforming the world, it can be expected that the increased leverage will increase conflict dynamics. We research the dynamics around globally shared problems and explore potential tools to mitigate those, with the aim to reduce AI-induced conflict.
Offense/Defense Dynamics
When a new AI capability is introduced to the world, it will be used in a variety of ways -- some constructive and some destructive. We research ways of characterizing the various factors that affect these dynamics, and the effects they may have on the world, both in the general case and within salient domains.
Alignment of Dynamical Cognitive Systems
Powerful but poorly alignable general-purpose AI agents will need to be curtailed, controlled, or somehow made safer. Through cognitive science, complex systems theory, and dynamical systems theory, we research better ways to do this while better understanding and respecting stakeholders, context, and tradeoffs.