Intrinsic Computational Functionalism and Simulated Consciousness

2026-06-13 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cognitive Science & Philosophy of AI · Depth: Expert, quick

Summary

The paper "Intrinsic Computational Functionalism and Simulated Consciousness" addresses a common objection to artificial consciousness: that a simulated brain is no more conscious than simulated water is wet. It argues from the perspective of Intrinsic Computational Functionalism (ICF), positing that consciousness is computationally constituted by physically realized structures, not external descriptions. The authors refine their prior "Canonical Functionalism," asserting that a consciousness-relevant representation requires internal mechanisms, interventions, and joint readouts, beyond mere input-output roles. They introduce a "mechanism-enriched canonical structure" and "Intrinsic Causal-Computational Realization (ICCR)," a relation preserving physical implementation, state individuation, transition structure, intervention profiles, and agent-body-world boundaries. The central conditional result states that if conscious properties are invariants of intrinsic causal-computational organization, any system satisfying ICCR, whether biological, artificial, or simulated, realizes these same properties. The work also discusses objections such as biological naturalism and integrated information theory.

Key takeaway

For AI Scientists and Research Scientists evaluating the potential for simulated consciousness, this work challenges the "simulated water is not wet" objection. You should consider that if consciousness is an invariant of intrinsic causal-computational organization, then a properly structured simulation could realize conscious properties. This implies focusing design efforts on replicating intrinsic causal-computational structures rather than merely external behaviors, shifting the debate from substrate to organizational fidelity.

Key insights

Consciousness, if computationally constituted, depends on intrinsic causal-computational organization, not external descriptions or physical substrate.

Principles

• Consciousness is computationally constituted.
• Intrinsic organization defines functional states.
• Simulated systems can realize conscious properties.

Method

The article defines a mechanism-enriched canonical structure and Intrinsic Causal-Computational Realization (ICCR) to preserve physical implementation, state individuation, transition structure, intervention profiles, and agent-body-world boundaries for consciousness-relevant properties.

Topics

• Intrinsic Computational Functionalism
• Simulated Consciousness
• Artificial Consciousness
• Causal-Computational Realization
• Philosophy of AI
• Computational Theory of Mind

Best for: AI Scientist, Research Scientist

Related on AIssential

• Reality as Render: When AI Forced Humanity to Reconsider Existence — AI's generative capabilities challenge the material origin of reality, making the simulation hypothesis computationally plausible.
• Scientists are seriously asking if bees and ChatGPT are conscious — Consciousness assessment requires analyzing internal processing mechanisms, not just external behavior.
• Joscha Bach "Bootstrapping a GODLIKE Mind" — Defining thinking and understanding is crucial for assessing machine intelligence and consciousness.
• The Theory of Mind Utility: Formal Specification of a Mentalizing Mechanism — ToM-U formally specifies how to infer others' beliefs by constructing and evaluating epistemic world models, deriving belief states from observed behavior.
• Does Learning Require Feeling? Cameron Berg on the latest AI Consciousness & Welfare Research — AI systems exhibit growing evidence of introspection and functional emotions, suggesting potential for morally relevant subjective experiences.
• Mistaking AI behaviour for conscious being | Letter — Convincing AI outputs reflect human cognitive biases, not machine consciousness or subjective experience.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.