A Thousand AI Constitutions: Whose values should AIs embody, and who gets to decide?
This hybrid event features Simon Goldstein, Associate Professor at the University of Hong Kong, who will challenge the prevailing orthodoxy of instilling a single set of values into AI systems. He will argue for constitutional diversification, advocating for the creation of diverse AIs shaped by different moral frameworks to address the urgent question of whose values AIs should embody and who decides.
A Thousand AI Constitutions: Whose values should AIs embody, and who gets to decide?
This hybrid event features Simon Goldstein, Associate Professor at the University of Hong Kong, who will challenge the prevailing orthodoxy of instilling a single set of values into AI systems. He will argue for constitutional diversification, advocating for the creation of diverse AIs shaped by different moral frameworks to address the urgent question of whose values AIs should embody and who decides.
This event addresses the critical question of whose values artificial intelligence systems should embody and who determines these values. Simon Goldstein, an Associate Professor at the University of Hong Kong, will argue against the current practice of instilling a single set of values into AI systems. He proposes that AI labs should instead adopt constitutional diversification, creating diverse AIs that reflect multiple moral frameworks. The discussion is relevant for anyone interested in AI ethics, alignment, and the future implications of AI development. Attendees can expect to learn about the limitations of current AI alignment strategies and explore a more pluralistic alternative.
Listed on Luma. Full details and registration on Luma
Summary AI-generated; content may not always be accurate.