Affiliate Organizations
We support academic researchers at the following labs and instituions.
AI X-risk Institute
(AIXI Labs)
Led by: Cole Wyeth
Developing the science of superintelligent agents and their risk to humanity
AIXI Labs models AI risk factors and safety mitigations in terms of AIXI variants, and develops the means to translate them to real AI agents. AIXI is the leading mathematical model of artificial superintelligence—the maximum theoretical limit of AI capabilities. This enables rigorous testing of both the risk factors and the safety mitigations.
Iliad
Led by: Alexander Gietelink Oldenziel
Applied mathematics research in AI alignment
Iliad is an umbrella organization for applied mathematics research in AI alignment. We organize the eponymous ILIAD conference series along with other research conferences, incubate research organizations and an academic journal, and run an Intensive and a Fellowship program.
Stormglass
The Fields Institute for
Research in Mathematical Sciences
Yevgeny Liokumovich
Mathematics for AI Safety
In partnership with Fields Institute, Principles of Intelligence invites applications for two-year Fields Postdoctoral Fellowship positions with the research program on Mathematics for AI Safety. The fellowships support research at the intersection of mathematics and AI safety, with a focus on developing rigorous mathematical foundations for AI interpretability. Research directions include mean field theories of deep learning, data attribution methods, renormalization group approaches to neural networks, learning-theoretic analysis of algorithms and geometric analysis of the learning landscape.
