Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
(emergent-values.ai)
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values.
As AIs rapidly advance and become more agentic, the risk they pose is governed not only by their capabilities but increasingly by their propensities, including goals and values.