Tomek Korbak

Tomek Korbak is a Member of Technical Staff at OpenAI, where he works on monitoring LLM agents for misalignment. Previously, he worked on AI control and safety cases at the UK AI Security Institute and on honesty post-training at Anthropic. He earned a PhD at the University of Sussex focused on reinforcement learning from human feedback and studied cognitive science, philosophy, and physics at the University of Warsaw.

Career