Max Kaufmann

Max graduated from his undergraduate computer science degree at the University of Cambridge, UK in 2022. At the moment, he is interested in understanding current iterations of large machine learning models, with the hopes of building useful frameworks for the study of powerful AI systems. At CHAI he will be working under Dan Hendrycks, researching how knowledge of morality can be effectively extracted from modern large language models. Before CHAI, Max worked on adversarial robustness within computer vision, both through an industry internship and academic research. He is an active member of the effective altruism community, and a commite member of the Cambridge Existential Risks Intiative.