Evolutionary Computation and AI Safety: Research Problems Impeding Routine and Safe Real-world Application of Evolution

As the capabilities and pervasiveness of machine learning (ML) and artificial intelligence (AI) increasingly affect society, there is increasing concern about the safety of such systems, i.e. the potential of accidental harm from implementation errors and unintended consequences in ML algorithms. As a result, there has been increasing interest in the nascent field of AI safety [1, 2, 3, 4, 5, 6], which seeks to understand and solve the technical challenges in developing and deploying AI that does what it is intended to do. The purpose of this chapter is to explore how the study of AI safety intersects with that of evolutionary computation (EC), to both highlight an exciting and important set of safety problems within EC, and to suggest that evolution and EC have important insights that could benefit the general study of AI safety. To frame the problem of AI safety, we adopt the framework of Amodei et al. [1], which defines AI safety as concerned with accidents in ML systems, and defines five problems within three broad categories of issues: (1) specifying the wrong objective function, (2) making safe and efficient use of a true but expensive objective (e.g.