A Cognitive Scientist's guide to Machine Consciousness
Stefano Palminteri, Charley M Wu
PsyArXiv January 5, 2025 preprint DOI: 10.31234/osf.io/s7ptu (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper |
|---|---|
| Key points | Argues that the current computational functionalist consensus, which ascribes consciousness based on computational equivalence, should be rejected in favor of a "behavioral inference principle" that the authors propose as an epistemologically unbiased and operationalizable criterion for assessing machine consciousness. |
Abstract
Large Language Models (LLMs) have rapidly become a central topic in AI and cognitive science, due to their unprecedented performance in a vast array of tasks. Indeed, some even see 'sparks of artificial general intelligence' in their apparently boundless faculty for conversation and reasoning, Their sophisticated emergent faculties, which were not initially anticipated by their designers, has ignited an urgent debate about whether and under which circumstances we should attribute consciousness to artificial entities in general and LLMs in particular. The current consensus, rooted in computational functionalism, proposes that consciousness should be ascribed based on a principle of computational equivalence. The objective of this opinion piece is to criticize this current approach and argue in favor of an alternative “behavioral inference principle”. We believe that a behavioral inference principle will provide an epistemologically unbiased and operationalizable criterion to assess machine consciousness.