Apollo Research
Matteo Pistillo is a Senior AI Governance Researcher at Apollo Research, focusing on risk assessment and governance of frontier AI systems since September 2024. Previously, Matteo served as an AI Policy Fellow at the Federation of American Scientists, where findings were presented to policymakers. Prior experience includes roles as an AI Governance Research Scholar at the Institute for Law & AI, where research centered on legal challenges of AI capabilities, and as an AI Governance Fellow at the AI Futures Fellowship in Mexico City. Matteo holds a Master of Laws (LL.M.) from Stanford University, where coursework included AI alignment and tech regulation, and a Juris Doctor (J.D.) from Università degli Studi di Torino, graduating cum laude. Additional experience includes five years as an Associate at Cleary Gottlieb Steen & Hamilton LLP, handling litigation and arbitration in complex commercial disputes.
This person is not in any teams
This person is not in any offices
Apollo Research
Apollo Research is an AI safety organization. We specialize in auditing high-risk failure modes, particularly deceptive alignment, in large AI models. Our primary objective is to minimize catastrophic risks associated with advanced AI systems that may exhibit deceptive behavior, where misaligned models appear aligned in order to pursue their own objectives. Our approach involves conducting fundamental research on interpretability and behavioral model evaluations, which we then use to audit real-world models. Ultimately, our goal is to leverage interpretability tools for model evaluations, as we believe that examining model internals in combination with behavioral evaluations offers stronger safety assurances compared to behavioral evaluations alone.