John (Yueh-Han) Chen AI safety researcher at the ML Alignment & Theory Scholars program. His work includes evaluating chain-of-thought controllability and monitorability in language models. Previously conducted research at New York University and Berkeley AI Research.
John (Yueh-Han) Chen AI safety researcher at the ML Alignment & Theory Scholars program. His work includes evaluating chain-of-thought controllability and monitorability in language models. Previously conducted research at New York University and Berkeley AI Research.