ÂÜÀòÂÒÂ×

Lorenzo Pacchiardi is a Research Associate at the University of Cambridge, focused on developing a framework for evaluating AI capabilities alongside Prof José Hernández-Orallo and Dr Lucy Cheke. Previously, Lorenzo served as an AI standards consultant at the Future of Life Institute, collaborating on the EU AI act, and held a position as an ML Alignment Research Fellow at the Stanford Existential Risks Initiative, concentrating on the safety of large language models. Lorenzo's academic journey includes a PhD in Statistical Science from the University of Oxford, where teaching roles spanned tutoring and assisting in various statistics courses. Additional experience includes working with Outsmart Insight on commercializing research, engaging as a visiting PhD student at Université Paris Dauphine, and analyzing health-related costs at the University of Oxford's Careers Service. Lorenzo's early career involved data analysis and machine learning research internships, contributing comprehensive expertise in statistics, machine learning, and AI safety.