Atoosa Kasirzadeh 2023 Early Career Fellow
Affiliation Assistant Professor, University of Edinburgh; Incoming Assistant Professor, Carnegie Mellon University Hard Problem Solved challenges of safety and control, human alignment and compatibility with increasingly powerful and capable AI and eventually AGI.

Atoosa Kasirzadeh is a philosopher, mathematician, and systems engineer. She is an Assistant professor in the philosophy department and the research lead at the Centre for Technomoral Futures at the University of Edinburgh, and a Research Lead at the Alan Turing Institute. Prior to this, she held research positions at DeepMind and Australian National University. In September 2024, she will start as an assistant professor at Carnegie Mellon University to conduct research on AI ethics, safety, and governance

She holds a Ph.D. in philosophy of science and technology from the University of Toronto and a Ph.D. in mathematics from the Ecole Polytechnique of Montreal. Her current research is focused on ethics, safety, and philosophy of AI, with a particular focus on sociotechnical value alignment for generative models.

AI2050 Project

Atoosa Kasirzadeh’s AI2050 project examines the value alignment problem for AI: how can we make sure that the goals and values of AI systems align with our own? Her approach—unlike other approaches which aim for a primary technical analysis— tackles the problem by integrating insights from philosophy, systems theory, game-theory, and hands-on AI expertise. It will apply multidisciplinary analysis to large language systems and their multi-modal variants to align them with human values in a responsible way. More generally, the project seeks to ensure that AI systems will be aligned with human values to secure a brighter future for everyone.