On the possibility of deep alignment

Abstract

I consider motivation and value-alignment in AI systems from the perspective of (constrained) entropy maximization. Though the structures encoding knowledge in any physical system can be understood as energetic constraints, only living agents harness entropy in the endogenous generation of actions. I argue that this exploitation of "mortal" or thermodynamic computation, in which cognitive and physical dynamics are inseparable, is of the essence of desire, motivation, and value, while the lack of true endogenous motivation in simulated "agents" predicts pathologies like reward hacking.