Jason leads the applied white-box methods pod, where he is focused on developing, evaluating, and demonstrating methods which leverage model internals to improve the safety of AI systems.
Jason previously developed probes for detecting AI sandbagging as an Anthropic Fellow. Before that, he was co-founder and CTO at Chemix, a startup which used ML to accelerate the development of next-generation batteries for electric vehicles. He led all software and ML at Chemix, including both research and engineering. Chemix raised more than $30M in VC financing and employed more than 20 people. Jason has also worked as a data scientist and a battery scientist and holds a PhD in theoretical physics from Berkeley.
Jason has dedicated his professional career to research on impactful societal problems, from technical mitigations for climate change to AI safety and alignment.
