AI Ethics: On the Computational Complexity of Ethics: Moral Tractability for Minds and Machines

Debates on whether AI can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities; e.g., whether artificial systems could be autonomous, conscious, or equipped with human-like rationality. In this talk, I tackle the problem from the other end by exploring – using computational complexity – what kind of moral machines are possible based on what computational systems can or cannot do. In particular, I:

• (i) describe how the computational complexity of ethical problems can be framed within Marr’s 3-level analysis;
• (ii) use complexity results to analyze a range of problems based on consequentialism, deontology, and virtue ethics;
• (iii) discuss the consequences the results have for the prospect of moral machines.

Finally, I demonstrate how computational tractability can be used to also inform philosophical and psychological research on human morality by advancing the Moral Tractability Thesis.

Bio

Jakob Stenseke is a PhD candidate in Practical Philosophy at Lund University. His interdisciplinary research project – titled How to build nice robots: ethics from theory to machine implementation – broadly explores the possibilities and challenges for creating artificial moral agents, that is, AI systems capable of acting in reference to what is morally good or bad. This includes the theoretical possibility (how and to what extent can artificial agents be moral?), normative desirability (why and in what way do we want or need ”ethical” machines?), and technical engineering (how do you actually build ethical AI?) of artificial moral agents.