From cacophony to hierarchy: a principled framework for assessing AI consciousness

2026-09-28

AI Summary

This study addresses the challenges of theoretical confounding, limited quantifiability, and the absence of a unified framework in assessing AI consciousness. It proposes a five-level functional descriptive hierarchy grounded in supervenience. Methodologically, by extending Marr’s levels of analysis and integrating coarse-graining with multiple realizability, the work maps mainstream consciousness theories onto this framework, develops operationalizable metrics, and implements structured probabilistic assessment via Bayesian inference. The research advocates shifting metaphysical debates toward "structured agnosticism" and reveals that current consciousness evaluations for large language models are highly sensitive to prior assumptions. Furthermore, it identifies significant overlap between consciousness metrics and architectural features of general intelligence, offering a novel perspective for understanding the evolution of AI capabilities.

Abstract

The question of AI consciousness is one of the most urgent pre-emptive problems in philosophy and computer science, yet progress is hampered by a cacophony of competing theories that often talk past each other. Separating the hard problem from the mapping problem allows the deepest metaphysical disagreements to be set aside: granting that experience supervenes on a system's organisation, the tractable question becomes at which grain of description that supervenience base sits. We extend Marr's three levels of analysis into a five-level hierarchy of functional descriptions (behavioural, computational, intrinsic causal-structural, organismic, and organism-environment) grounded in supervenience, coarse-graining, and multiple realisability. The major theories of consciousness are positioned within this hierarchy according to which level they take to be critical, and for each level we develop operationalisable indicators and assess current AI systems against them. A Bayesian model then combines theoretical credences with indicator evidence into an overall credence in a system's capacity for consciousness. In illustrative assessments, the verdict for current LLMs is driven as much by where theoretical credence is placed as by how the evidence is read: under different stipulated readings and credence distributions, assessments range from below 0.01 to roughly 0.8, showing sensitivity to assumptions. Finally, the consciousness indicators at each level closely overlap with the architectural features needed for general intelligence, suggesting that increasingly capable AI may become a stronger candidate for consciousness. The framework supports a structured agnosticism, in which theoretical commitments are made explicit, credences are updated as evidence accumulates, and assessments take the form of aggregated probabilities rather than verdicts.

Problem

• AI consciousness
• theories of consciousness
• consciousness assessment
• hard problem
• mapping problem

Innovation

• AI consciousness
• five-level hierarchy
• Bayesian model
• operationalisable indicators
• supervenience