Towards an Extended Requirements Problem Formulation for Superintelligence Safety

Abstract

Under the headline "AI safety", a wide-reaching issue is being discussed, whether in the future some "superhuman artificial intelligence" / "superintelligence" could pose a threat to humanity. In addition, the late Steven Hawking warned that the rise of robots may be disastrous for mankind. A major concern is that even benevolent superhuman artificial intelligence (AI) may become seriously harmful if its given goals are not exactly aligned with ours, or if we cannot specify precisely its objective function. Metaphorically, this is compared to king Midas in Greek mythology, who expressed the wish that everything he touched should turn to gold, but obviously this wish was not specified precisely enough. In our view, this sounds like requirements problems and the challenge of their precise formulation. Hence, we take a new perspective on the problem by exploring it using insights from requirements engineering (RE). In addition, the overall issue calls for a major RE endeavor, figuring out the wishes and the needs with regard to a superintelligence, which will in our opinion most likely be a very complex softwareintensive system based on AI. In this paper, we introduce the idea of developing a new theoretical formulation of an extended requirements problem applicable to it, since it involves goals of both stakeholders and of the AI-based system-to-be-built.