Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
NeurIPSSpotlight2025
TL;DR
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…
Opening excerpt from the authors’ abstract. source
Read the paper
Topics
control agent
← All NeurIPS 2025 Spotlight papers · Browse the whole archive