I’m an independent, pluralistic alignment researcher working on a scale-free theory of coalitions of agents. I previously began a PhD at UC Berkeley in Computational Cognitive Science, where I worked on Computational Theory of Mind (~à la epistemology in disguise). I’m now moving toward working on formal epistemology, decision theory, and Bayesian epistemology. Broadly speaking, I study how agents (biological or otherwise) can coordinate efficiently while respecting each individual’s independence. Lately, I’ve been focused on identifying the simplest knowledge requirements that allow coalitions of agents to know how to act or how to acquire more relevant information even when their incentives do not fully align to prevent catastrophic failure of miscoordination as reported in mulit-agent risks.