Jacob Hilton is VP of Research at the Alignment Research Center, where he works on mechanistic understanding of neural network behavior and AI alignment. Previously, he researched reinforcement learning, truthfulness, scaling laws, and interpretability at OpenAI. He has a background in combinatorial set theory and pure mathematics.
Jacob Hilton is VP of Research at the Alignment Research Center, where he works on mechanistic understanding of neural network behavior and AI alignment. Previously, he researched reinforcement learning, truthfulness, scaling laws, and interpretability at OpenAI. He has a background in combinatorial set theory and pure mathematics.
Career
Jacob Hilton holds a PhD in Mathematics, specializing in combinatorial set theory from University of Leeds.