otherAdded by a member
Research agenda for training aligned AIs using concave utility functions following the principles of homeostasis and diminishing returns — LessWrong
Roland Pihlakas
Abstract
This conceptual overview post is intended to explain what I mean by the principles of "homeostasis", "diminishing returns", and "balancing" - how the…
Research area
agent foundationsagentic aiai values alignmentdeceptiondiminishing returnsevalsgovernancehomeostasisloss aversionmulti-objective balancingmulti-objective reinforcement learningsocio-technical accountabilityutility functionsverification
Published
—
Source
other
Sign in to read and join the discussion.