The development of artificial intelligence (AI) has reached a stage where the moral progress of contemporary society is hardly conceivable without AI systems embodying and acting in accordance with ethical values. Given the distinctive features of contemporary artificial agents, there is an urgent need to address the growing gap between human social values and the goals that machines in practice tend to realize. This chapter examines this issue—commonly known as the alignment problem. It clarifies why AI poses an unprecedented ethical challenge and why its applications are particularly prone to moral bias. To this end, after tracing the emergence of AI ethics in parallel with the technological evolution of AI (Sect. 9.1), I outline the defining characteristics of current artificial agents (Sect. 9.2). I then offer an ethical interpretation of the alignment problem (Sect. 9.3), followed by an analysis of paradigmatic cases of misaligned AI systems that reproduce moral biases (Sect. 9.4). The chapter concludes with an overview of debiasing strategies (Sect. 9.5).