consciousness
In plain wordsHaving 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.
- 1
Philosophy and cognitive science
The property of having subjective experience: a state is conscious if there is something it is like for its subject to be in it, in Thomas Nagel's formulation. Philosophers separate this phenomenal consciousnessphenomenal consciousness, n.: The felt, experiential side of the mind — what it is like to taste coffee or to feel sad — as opposed to simply processing or reporting information. from 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. (information available for reasoning, report and control of action) and from wakefulness, attention and self-consciousness. Scientific theories such as 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., 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., higher-order theorieshigher-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., 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. and predictive processingpredictive processing, n.: The idea that the brain is a prediction machine: it constantly guesses what its senses will report next and learns mainly from its mistakes, so what we perceive is largely its best guess. try to say which physical or functional processes give rise to it, and researchers search for its neural correlatesneural 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.. None of these theories commands consensus, and the hard problemhard problem of consciousness, n.: The puzzle of why physical processes in a brain — or a computer — should feel like anything from the inside, rather than simply running without any inner experience. asks why any process should be accompanied by experience at all.
- 2
AI
The question whether artificial systems are or could become conscious, the subject of 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.. Positions range from computational 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., on which running the right kind of computation would suffice, to biological naturalismbiological naturalism, n.: John Searle's view that consciousness is a real biological product of brains, as digestion is of stomachs, so running a computer program would not by itself create a mind. and 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., on which conventional digital hardware would not. Because language models are trained on vast amounts of human writing about feelings, many researchers regard what they say about their own experience as weak evidence either way and look instead for indicator propertiesindicator 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. in a system's architecture and processing. The answer bears directly on moral patienthoodmoral patienthood, n.: Being the kind of being whose interests matter morally for its own sake, so that it can be wronged. Babies and animals count, even though they are not responsible for what they do. and AI welfareAI welfare, n.: Concern for the well-being of AI systems themselves, in case some of them can suffer or have interests that matter — and the research into how to tell and what to do about it..
A model's fluent talk about its feelings tells us very little about whether it has consciousness.
Origin
From Latin conscius, 'knowing with' others or oneself. The English noun dates from the 17th century; John Locke's Essay Concerning Human Understanding (1690) made it central to philosophy, defining it as the perception of what passes in one's own mind. Thomas Nagel's essay 'What Is It Like to Be a Bat?' (1974) made subjective experience, there being something it is like to be a creature, the field's standard criterion.
Usage note
Everyday speech uses 'conscious' for being awake or for noticing something. In AI debates, claims about a model's self-awareness or situational awarenesssituational awareness, n.: An AI model's grasp of its own position — that it is an AI, how it was trained, whether it is being tested. Also the title of a widely read 2024 essay on the race toward human-level AI. concern what information it represents about itself, not necessarily experience. sentiencesentience, n.: The ability to have feelings that are good or bad for you, such as pleasure, pain, comfort or distress. It is the most common test for whether a being's welfare matters morally. is often used loosely as a synonym but properly means the capacity for experiences that feel good or bad.
Related
- phenomenal consciousnessphenomenal consciousness, n.: The felt, experiential side of the mind — what it is like to taste coffee or to feel sad — as opposed to simply processing or reporting information.
- hard problem of consciousnesshard problem of consciousness, n.: The puzzle of why physical processes in a brain — or a computer — should feel like anything from the inside, rather than simply running without any inner experience.
- 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.
- sentiencesentience, n.: The ability to have feelings that are good or bad for you, such as pleasure, pain, comfort or distress. It is the most common test for whether a being's welfare matters morally.
- 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.
- 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.
- 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.
- problem of other mindsproblem of other minds, n.: The puzzle of how we can know that anyone besides ourselves has thoughts and feelings, since we only ever see their behavior. AI turns this old puzzle into a practical one.
- intelligenceintelligence, n.: The ability to learn, understand, reason and solve problems — especially new ones — in order to reach goals. Experts disagree about how to define it precisely, for people and even more for machines.
Sources
- Nagel, T. (1974). What Is It Like to Be a Bat? The Philosophical Review 83(4), 435–450.
- Block, N. (1995). On a Confusion about a Function of Consciousness. Behavioral and Brain Sciences 18(2), 227–247.
Mentioned in
emergenceemergence, n.: When a whole shows properties or abilities that none of its parts has and that are hard to predict from them — like a traffic jam arising from individual cars, or new skills appearing in larger AI models., intelligenceintelligence, n.: The ability to learn, understand, reason and solve problems — especially new ones — in order to reach goals. Experts disagree about how to define it precisely, for people and even more for machines., sentiencesentience, n.: The ability to have feelings that are good or bad for you, such as pleasure, pain, comfort or distress. It is the most common test for whether a being's welfare matters morally., Daniel DennettDaniel Dennett, prop. n.: An American philosopher who argued that minds are what brains do, that consciousness can in principle be explained scientifically, and that we understand machines by treating them as if they had beliefs and goals., Douglas HofstadterDouglas Hofstadter, prop. n.: An American cognitive scientist whose prize-winning book 'Gödel, Escher, Bach' inspired a generation to study minds and AI, and who studies analogy as the heart of thinking., 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., hard problem of consciousnesshard problem of consciousness, n.: The puzzle of why physical processes in a brain — or a computer — should feel like anything from the inside, rather than simply running without any inner experience., 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., 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., mind–body problemmind–body problem, n.: The age-old question of how the mind — thoughts, feelings, experiences — relates to the physical body and brain. Is the mind simply what the brain does, or something more?, moral patienthoodmoral patienthood, n.: Being the kind of being whose interests matter morally for its own sake, so that it can be wronged. Babies and animals count, even though they are not responsible for what they do., phenomenal consciousnessphenomenal consciousness, n.: The felt, experiential side of the mind — what it is like to taste coffee or to feel sad — as opposed to simply processing or reporting information., predictive processingpredictive processing, n.: The idea that the brain is a prediction machine: it constantly guesses what its senses will report next and learns mainly from its mistakes, so what we perceive is largely its best guess., problem of other mindsproblem of other minds, n.: The puzzle of how we can know that anyone besides ourselves has thoughts and feelings, since we only ever see their behavior. AI turns this old puzzle into a practical one., qualiaqualia, n.: The individual felt qualities of experience — the particular redness of red, the taste of mint, the sting of a burn — that seem impossible to capture fully in words., self-awarenessself-awareness, n.: Awareness of oneself as oneself — knowing that you exist, what you are and what state you are in. People often ask whether AI is self-aware, but the phrase can mean several quite different things., situational awarenesssituational awareness, n.: An AI model's grasp of its own position — that it is an AI, how it was trained, whether it is being tested. Also the title of a widely read 2024 essay on the race toward human-level AI., 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., binding problembinding problem, n.: The puzzle of how a brain, or a neural network, keeps track of which features belong together — that the red goes with the apple and the green with the leaf — when they are processed separately., biological naturalismbiological naturalism, n.: John Searle's view that consciousness is a real biological product of brains, as digestion is of stomachs, so running a computer program would not by itself create a mind., concept injectionconcept injection, n.: An experiment that plants a specific concept directly into an AI model's internal activity, then asks the model whether it notices anything unusual, to test whether its reports about itself are genuine., 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., intentionalityintentionality, n.: The way thoughts, beliefs and desires are about things: a belief is about rain, a wish is for cake. Philosophers ask whether a machine's internal states can be about anything.