Iliad develops AI safety as a theoretical and experimental science through research, training and fieldbuilding.
Apply to our Intensive or FellowshipSupport and grow promising technical AI safety research organizations.
Develop researchers through the Iliad Intensive and Fellowship.
Strengthen technical AI safety through conferences, publishing and shared infrastructure.
Iliad develops researchers through intensive study and mentored research.
The Intensive builds a foundation in technical AI alignment. The Fellowship gives researchers the time, mentorship, and support to pursue research of their own. Together, they offer two distinct routes into deeper technical work.
A four-week taught program in foundational AI alignment for researchers and technical practitioners with strong mathematical backgrounds.
A three-month mentored research program for researchers developing work in mathematical and theoretical AI safety.
Iliad brings researchers together through programs, workshops, conferences, and other research gatherings.
Find current dates, locations, and application or registration details for upcoming Iliad events.
Iliad incubates technical research organizations and projects working on foundational AI safety.
We focus on mathematically grounded theory that yields experimentally testable predictions, alongside empirical work that informs better theory. Across the federation, teams pursue distinct directions while sharing this approach.
Mathematical models of artificial superintelligence and formal approaches to AI risk.
Visit AIXI Labs
Theoretical model organisms for understanding neural networks and generating testable predictions.
Visit Principia
Research into the causal mechanisms of training and how design choices shape model behaviour.
Visit Stormglass
Research into how agentic behaviour emerges in AI systems and interacting agents.
Visit XOR Labs
Iliad strengthens technical AI safety through conferences, publishing and shared research infrastructure.
This work connects researchers and supports the exchange, development and publication of foundational AI alignment research.
Iliad in practice
The Intensive was a game changer for me. It gave me a coherent view of the AI safety/alignment landscape, showed me how to connect math and physics skills with alignment, connected me with a network of researchers, and afforded me the time to start work in this area. It also came at the perfect moment, as AI is rapidly transforming much of society, including my corner of academia.
— April, 2026 Intensive Participant