Suffering Toasters -- A New Self-Awareness Test for AI

A clear definition of intelligence in AI remains elusive, and rapid AI development makes natural AI consciousness seem more likely. The authors argue that all current intelligence tests fail to detect intelligence as humans intuitively perceive it. Drawing on philosophy of science, psychology, and other fields, they clarify problems of artificial intelligence, self-awareness, and agency. They propose a new heuristic approach to test for artificial self-awareness and outline a possible implementation, then discuss philosophical and implementation-oriented questions that arise.

Study at a glance

Abstract

A widely accepted definition of intelligence in the context of Artificial Intelligence (AI) still eludes us. Due to our exceedingly rapid development of AI paradigms, architectures, and tools, the prospect of naturally arising AI consciousness seems more likely than ever. In this paper, we claim that all current intelligence tests are insufficient to point to the existence or lack of intelligence \textbf{as humans intuitively perceive it}. We draw from ideas in the philosophy of science, psychology, and other areas of research to provide a clearer definition of the problems of artificial intelligence, self-awareness, and agency. We furthermore propose a new heuristic approach to test for artificial self-awareness and outline a possible implementation. Finally, we discuss some of the questions that arise from this new heuristic, be they philosophical or implementation-oriented.