EARadio

AI alignment, philosophical pluralism, and the relevance of non-Western philosophy | Tan Zhi Xuan

June 14, 2021
EARadio
AI alignment, philosophical pluralism, and the relevance of non-Western philosophy | Tan Zhi Xuan
Chapters
EARadio
AI alignment, philosophical pluralism, and the relevance of non-Western philosophy | Tan Zhi Xuan
Jun 14, 2021


How can we build (super) intelligent machines that are robustly aligned with human values? AI alignment researchers strive to meet this challenge, but currently draw upon a relatively narrow set of philosophical perspectives common in effective altruism and computer science. This could pose risks in a world where human values are complex, plural, and fragile. Xuan discusses how these risks might be mitigated by greater philosophical pluralism, describing several problems in AI alignment where non-Western philosophies might provide insight.

Tan Zhi Xuan is a multi-disciplinary researcher broadly interested in cognitive approaches to building AI, so as to better understand and conform to human preferences, intentions, norms, and values. Current projects include developing probabilistic programming frameworks for Bayesian inverse planning and goal inference.

This talk was taken from EA Global Asia and Pacific 2020. Click here to watch the talk with the PowerPoint presentation.

Show Notes


How can we build (super) intelligent machines that are robustly aligned with human values? AI alignment researchers strive to meet this challenge, but currently draw upon a relatively narrow set of philosophical perspectives common in effective altruism and computer science. This could pose risks in a world where human values are complex, plural, and fragile. Xuan discusses how these risks might be mitigated by greater philosophical pluralism, describing several problems in AI alignment where non-Western philosophies might provide insight.

Tan Zhi Xuan is a multi-disciplinary researcher broadly interested in cognitive approaches to building AI, so as to better understand and conform to human preferences, intentions, norms, and values. Current projects include developing probabilistic programming frameworks for Bayesian inverse planning and goal inference.

This talk was taken from EA Global Asia and Pacific 2020. Click here to watch the talk with the PowerPoint presentation.