Beyond computational equivalence: the behavioral inference principle for machine consciousness
Neuroscience of Consciousness · 17.01.2026 · 2026 (1)
DOI: 10.1093/nc/niag002 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Neuroscience of Consciousness, online erschienen am 16.02.2026. Verfasst von Stefano Palminteri und 1 weiteren Autor:innen. Beteiligte Einrichtung: Département d'Etudes Cognitives, Ecole Normale Supérieure, PSL, Research University, 29 rue d'Ulm, 75005, Paris, France. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 115 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: European Research Council, Agence Nationale de la Recherche, Alexander von Humboldt-Stiftung.
Abstract (Originalsprache)
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, have 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", whereby consciousness is attributed if it is useful to explain (and predict) a given set of behavioral observations. We believe that a behavioral inference principle will provide an epistemologically valid and operationalizable criterion to assess machine consciousness.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Département d'Etudes Cognitives, Ecole Normale Supérieure, PSL, Research University, 29 rue d'Ulm, 75005, Paris, France.
- Laboratoire de Neurosciences Cognitives et Computationnelles, Institut National de la Santé et de la Recherche Médicale, 29 rue d'Ulm, 75005, Paris, France.
- Centre for Cognitive Science, Institute of Psychology, Technical University of Darmstadt, Alexanderstraße 10, 64283 Darmstadt, Germany.
- Hessian.AI, Landwehrstraße 50A, 64293 Darmstadt, Germany.
- Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max-Planck-Ring 8, 72076 Tübingen, Germany.
ORCID-Profile: Stefano Palminteri
Förderung
- European Research Council
- Agence Nationale de la Recherche
- Alexander von Humboldt-Stiftung
- Département d’Etudes Cognitives is funded by the Agence Nationale pour la Recherche
- Major Research Program of PSL Research University
- PSL Research University
- ANR
- European Union’s Horizon 2020 research and innovation programme
Zitieren
APA
Palminteri, S., & Wu, C. M. (2026). Beyond computational equivalence: the behavioral inference principle for machine consciousness. Neuroscience of Consciousness, 2026(1). https://doi.org/10.1093/nc/niag002
Vancouver
Palminteri S, Wu CM. Beyond computational equivalence: the behavioral inference principle for machine consciousness. Neuroscience of Consciousness. 2026;2026(1). doi:10.1093/nc/niag002
BibTeX
@article{Palminteri2026,
author = {Palminteri, Stefano and Wu, Charley M},
title = {Beyond computational equivalence: the behavioral inference principle for machine consciousness},
journal = {Neuroscience of Consciousness},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1093/nc/niag002}
}
EUVIMED