ABSTRACT
ABSTRACT Many authors have proposed constraining the behavior of intelligent systems with “machine ethics” to ensure positive social outcomes from the development of such systems. This c hapter critically analyzes the prospects for machine ethics, identifying several inherent limitations. Although machine ethics may increase the probability of ethical behavior in some situations, it cannot guarantee it due to the nature of ethics, the computational limitations of computational agents, and the complexity of the world. Additionally, machine ethics, even if it were to be “solved” at a technical level, would be insufficient to ensure positive social outcomes from intelligent systems.
