ILIAD 2024
ILIAD 2024 was a 5-day, multi-track conference bringing together researchers in theoretical AI alignment.
About ILIAD 2024
ILIAD 2024 was the first iteration of ILIAD Conference, a series of conferences on theoretical AI alignment. It took place August 28 - September 3, 2024 in Berkeley, California.
ILIAD 2024 Program
ILIAD 2024 featured an unconference format where participants proposed and led their own sessions, as well as a range of topic-specific workshop tracks:
Computational Mechanics is a framework for understanding complex systems by focusing on their intrinsic computation and information processing capabilities. Pioneered by J. Crutchfield to turbulence, it later found popularity in AI alignment. The track lead was Paul Riechers.
Singular Learning Theory, developed by S. Watanabe, is the modern theory of Bayesian learning. SLT studies the loss landscape of neural networks, using ideas from statistical mechanics, Bayesian statistics and algebraic geometry. The track lead was Jesse Hoogland.
Agent Foundations uses tools from theoretical economics, decision theory, Bayesian epistemology, logic, game theory and more to deeply understand agents: how they reason, cooperate, believe and desire. The track lead was Daniel Herrmann.
Causal Incentives is a collection of researchers interested in using causal models to understand agents and their incentives. The track lead was James Fox.
“How It All Fits Together” turned its attention to the bigger picture — where are we coming from, and where are we going? — under the direction of John Wentworth.