Can a Machine be Conscious? Towards Universal Criteria for Machine Consciousness

TL;DR

The paper addresses the lack of universal criteria for machine consciousness and proposes five sequential, assumption-free criteria that can be applied across competing definitions of consciousness. It details a framework in which consciousness must exist, others must exist, physical matter must be sufficient, the machine must have a conducive substrate, and consciousness must be observable, with each criterion building on the previous ones. By integrating perspectives from philosophy of mind, neuroscience, and AI, the authors connect the criteria to established concepts such as neural correlates of consciousness and integrated information theory, while acknowledging debates around subjectivity and observability. The work aims to provide a practical, interdisciplinary tool for researchers and policymakers to assess machine consciousness and to guide future theory development and empirical validation.

Abstract

As artificially intelligent systems become more anthropomorphic and pervasive, and their potential impact on humanity more urgent, discussions about the possibility of machine consciousness have significantly intensified, and it is sometimes seen as 'the holy grail'. Many concerns have been voiced about the ramifications of creating an artificial conscious entity. This is compounded by a marked lack of consensus around what constitutes consciousness and by an absence of a universal set of criteria for determining consciousness. By going into depth on the foundations and characteristics of consciousness, we propose five criteria for determining whether a machine is conscious, which can also be applied more generally to any entity. This paper aims to serve as a primer and stepping stone for researchers of consciousness, be they in philosophy, computer science, medicine, or any other field, to further pursue this holy grail of philosophy, neuroscience and artificial intelligence.