integrated information theory
In plain wordsA scientific theory that measures consciousness by how much a system works as a single, unified whole rather than as separate parts. It implies that ordinary computers, whatever software they run, have little or no consciousness.
A theory of consciousness that reasons backward from experience to its physical basis: it posits features that every experience has — existing for its subject and being structured, specific, unified and definite — and requires whatever physically underlies consciousness to have causal properties that mirror them. The quantity of consciousness is measured by integrated information, Φ (phi): roughly, how far the cause–effect power of a system as a whole exceeds that of its parts when it is partitioned; the quality of an experience is identified with the structure of those cause–effect relations. Because Φ depends on physical causal architecture rather than on the computation performed, IIT implies that a conventional digital computer has negligible consciousness whatever software it runs, even a perfect brain simulation, while some simple but highly integrated physical systems have a little. Exact Φ is intractable to compute for systems of realistic size.
Origin
Proposed by the neuroscientist Giulio Tononi in 'An Information Integration Theory of Consciousness' (BMC Neuroscience, 2004), building on earlier work with Gerald Edelman, and developed with Christof Koch, Larissa Albantakis and others through IIT 3.0 (2014) and IIT 4.0 (2023).
Usage note
In September 2023 an open letter signed by 124 scholars called IIT pseudoscience, prompting rebuttals from others; an adversarial collaboration published in Nature in 2025 found some of its predictions unsupported. Its denial that digital simulations are conscious puts it at odds with substrate independencesubstrate independence, n.: The idea that a mind depends only on the pattern of information processing, not on the material doing it, so a mind could in principle run on silicon as well as on neurons..
Related
- global workspace theoryglobal workspace theory, n.: A leading scientific theory holding that we become conscious of something when the brain broadcasts it widely — as if putting it on a stage where every part of the mind can use it.
- consciousnessconsciousness, n.: Having experiences: there being something it feels like to be you, as when you see red or feel pain. Whether any AI is or could become conscious is an open and fiercely debated question.
- panpsychismpanpsychism, n.: The idea that some simple form of experience is a basic feature of all matter, so that minds like ours are built out of tiny glimmers of mind found everywhere.
- machine consciousnessmachine consciousness, n.: Whether a machine such as an AI system could have genuine experiences of its own — and the research field that tries to find out, or to build such a machine.
- neural correlates of consciousnessneural correlates of consciousness, n.: The particular brain activity that reliably goes with a conscious experience — the minimum the brain must be doing for you to see, hear or feel something.
- substrate independencesubstrate independence, n.: The idea that a mind depends only on the pattern of information processing, not on the material doing it, so a mind could in principle run on silicon as well as on neurons.
- global workspace theoryglobal workspace theory, n.: A leading scientific theory holding that we become conscious of something when the brain broadcasts it widely — as if putting it on a stage where every part of the mind can use it.
- functionalismfunctionalism, n.: The view that minds are defined by how they work, not what they are made of: pain, for example, is whatever inner state plays pain's part, linking injury, other thoughts and behavior.
Sources
- Tononi, G. (2004). An Information Integration Theory of Consciousness. BMC Neuroscience 5, 42.
- Albantakis, L. et al. (2023). Integrated Information Theory (IIT) 4.0: Formulating the Properties of Phenomenal Existence in Physical Terms. PLoS Computational Biology 19(10).
Mentioned in
consciousnessconsciousness, n.: Having experiences: there being something it feels like to be you, as when you see red or feel pain. Whether any AI is or could become conscious is an open and fiercely debated question., global workspace theoryglobal workspace theory, n.: A leading scientific theory holding that we become conscious of something when the brain broadcasts it widely — as if putting it on a stage where every part of the mind can use it., machine consciousnessmachine consciousness, n.: Whether a machine such as an AI system could have genuine experiences of its own — and the research field that tries to find out, or to build such a machine., digital minddigital mind, n.: A mind that exists as software running on computers — such as a sufficiently advanced AI or a digital copy of a human brain — especially when considering its moral and social standing., Giulio TononiGiulio Tononi, prop. n.: An Italian-American neuroscientist who created integrated information theory, which measures consciousness by how unified a system's internal causes are, and which implies ordinary computers are not conscious., indicator properties of consciousnessindicator properties of consciousness, n.: A checklist of design features that leading scientific theories link to consciousness, used to judge how likely it is that a particular AI system could be conscious., neural correlates of consciousnessneural correlates of consciousness, n.: The particular brain activity that reliably goes with a conscious experience — the minimum the brain must be doing for you to see, hear or feel something., panpsychismpanpsychism, n.: The idea that some simple form of experience is a basic feature of all matter, so that minds like ours are built out of tiny glimmers of mind found everywhere., substrate independencesubstrate independence, n.: The idea that a mind depends only on the pattern of information processing, not on the material doing it, so a mind could in principle run on silicon as well as on neurons.