I’m a philosopher with research interests in ethics, decision theory, and the philosophy of artificial intelligence. My research covers both theoretical and applied questions, with an emphasis on teasing out the implications of abstract principles for important real-world problems. I'm interested in questions like how much weight we should give to tiny probabilities of extreme outcomes, how to make choices that affect the size of the future population, and how to conceptualize and formalize important properties of artificial agents like deceptiveness, power-seeking, and “corrigibility”.
I'm currently an assistant professor at the University …
I’m a philosopher with research interests in ethics, decision theory, and the philosophy of artificial intelligence. My research covers both theoretical and applied questions, with an emphasis on teasing out the implications of abstract principles for important real-world problems. I'm interested in questions like how much weight we should give to tiny probabilities of extreme outcomes, how to make choices that affect the size of the future population, and how to conceptualize and formalize important properties of artificial agents like deceptiveness, power-seeking, and “corrigibility”.
I'm currently an assistant professor at the University of Toronto. I previously held research positions with the Population Wellbeing Initiative at UT Austin, the Global Priorities Institute at Oxford, and the Centre for Philosophy, Politics and Economics at Groningen, after doing my PhD at the University of Maryland.
You can reach me at christian.tarsney (at) utoronto.ca.
