Samuel leads the cognitive oversight subteam of Anthropic’s alignment science team. Their goal is to be able to oversee AI systems not based on whether they have good input/output behavior, but based on whether there’s anything suspicious about the cognitive processes underlying those behaviors. For example, one in-scope problem is “detecting when language models are lying, including in cases where it’s impossible to tell based solely on input/output” (such as when a model knows a piece of private information which it is lying about). His team is interested in both white-box techniques (e.g. interpretability-based techniques) and black-box techniques (e.g. finding good ways to interrogate models about their thought processes and motivations).