What should be automated?: The fundamental question underlying human-centered computing

In 1989 the ACM task force on the Core of Computer Science argued that "What can be (effectively) automated?" is "the fundamental question underlying all of computing". The task force's view of computing was a machine-oriented one; the task force recognized the theoretical, empirical, and design-oriented aspects of computer science. The question "What can be effectively automated?" indeed draws some fundamental limits of automatic computation. However, since the 1980s there has been an ongoing shift away from the machine-centered view of computing, towards a human-centered view of computing. In this paper I argue that humancentered computing necessitates a perspective shift in computer science. I note that the central question of machine-centered computing fails to recognize the driving issues of human-centered computing. I argue that in all branches of human-centered computing there is another fundamental question that should be asked: "What should be automated?"