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

TL;DR

This paper critiques existing AI intelligence tests, proposes a new heuristic for assessing AI self-awareness, and discusses philosophical and practical implications of this approach.

Contribution

It introduces a novel heuristic test for AI self-awareness, addressing limitations of current intelligence assessments and integrating interdisciplinary insights.

Findings

Current tests are insufficient for detecting AI consciousness

Proposes a new heuristic approach to measure AI self-awareness

Discusses philosophical and implementation challenges

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.