Desiderata for the Theory of Agents

T2Covered by 1 source · first reported by AI Alignment Forum / LessWrong (curated) at 04 Nov, 14:26 UTC

TLDR: I give informal conceptual desiderata for the theory of agents we need to solve ASI alignment, and show a few examples of how existing theories fall short of these desiderata. A Theory of What? The word "agent" is often used in the AI safety discourse and in other research communities, but…

ai

Sources

• T2Desiderata for the Theory of AgentsAI Alignment Forum / LessWrong (curated)04 Nov, 14:26