global workspace theory
In plain wordsA 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.
A theory on which a mental content becomes conscious when it enters a limited-capacity workspace whose contents are broadcast to many specialized, otherwise independent processors — for perception, memory, language, evaluation and motor control — making the information available for report, reasoning and flexible action. Bernard Baars's original version used the metaphor of a theater with a spotlight of attention. The global neuronal workspace version of Stanislas Dehaene, Jean-Pierre Changeux and colleagues locates the workspace in long-range networks linking prefrontal and parietal cortex, and predicts a sudden, self-sustaining 'ignition' of activity when a stimulus becomes conscious. Because the theory is functional, it lends itself to AI: several 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. derive from it, and architectures in which specialized modules share a workspace have been built, although whether transformertransformer, n.: The design behind today's chatbots and much of modern AI. It handles text by letting every word look at every other word and decide which of them matter for understanding it. language models contain anything like a limited-capacity workspace is disputed.
On global workspace theory, the question is whether any bottleneck in the model forces its modules to compete for a shared broadcast.
Origin
Proposed by Bernard Baars in A Cognitive Theory of Consciousness (1988), drawing on the 'blackboard' architectures of 1970s AI. The neuronal version was introduced by Stanislas Dehaene, Michel Kerszberg and Jean-Pierre Changeux (PNAS, 1998) and developed by Dehaene and Lionel Naccache (2001).
Usage note
Critics such as Ned Block argue that the theory explains access consciousnessaccess consciousness, n.: Information in the mind that is available for use — for thinking, speaking and guiding behavior — whether or not any feeling comes with it. rather than phenomenal experience. An adversarial collaboration published in Nature in April 2025 tested the neuronal version against integrated information theoryintegrated information theory, n.: A 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.; its results challenged key predictions of both theories.
Related
- access consciousnessaccess consciousness, n.: Information in the mind that is available for use — for thinking, speaking and guiding behavior — whether or not any feeling comes with 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.
- integrated information theoryintegrated information theory, n.: A 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.
- 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.
- 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.
- cognitive architecturecognitive architecture, n.: A blueprint for a complete thinking system — how memory, attention, learning and decision-making fit together — used both to build general AI agents and to model how the human mind works.
- integrated information theoryintegrated information theory, n.: A 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.
Sources
- Baars, B. J. (1988). A Cognitive Theory of Consciousness. Cambridge University Press.
- Dehaene, S., Kerszberg, M. & Changeux, J.-P. (1998). A Neuronal Model of a Global Workspace in Effortful Cognitive Tasks. PNAS 95(24), 14529–14534.
- Cogitate Consortium et al. (2025). Adversarial Testing of Global Neuronal Workspace and Integrated Information Theories of Consciousness. Nature.
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., integrated information theoryintegrated information theory, n.: A 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., The Society of MindThe Society of Mind, prop. n.: AI pioneer Marvin Minsky's 1986 book arguing that intelligence comes from huge numbers of tiny, simple processes working together, no one of which is smart by itself., access consciousnessaccess consciousness, n.: Information in the mind that is available for use — for thinking, speaking and guiding behavior — whether or not any feeling comes with it., 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., higher-order theories of consciousnesshigher-order theories of consciousness, n.: Theories holding that a mental state is conscious when the mind, in effect, notices it — when some further thought or perception represents you as being in that state., 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., recurrent processing theoryrecurrent processing theory, n.: A theory that we consciously see something only when signals in the brain's visual areas loop back on themselves, not when they merely sweep forward once.