intentional stance
In plain wordsPredicting what something will do by treating it as if it had beliefs and goals — as we do with people, and often with chess programs and chatbots — whatever is really going on inside.
A strategy for predicting and explaining what a system will do by crediting it with rationality: one works out which beliefs and desires would make sense for something in its position, with its apparent purposes, and expects it to act on them. Daniel Dennett contrasted it with the physical stance (predicting from physics and chemistry) and the design stance (predicting from what the system was built to do). On his view, any system whose behavior can be predicted reliably and in rich detail from the intentional stance is an intentional system and really has beliefs and desires in the only sense that matters, a position between realism and instrumentalism about minds. The stance is routinely taken toward chess programs and AI agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done., and researchers debate whether such talk is useful shorthand, a real attribution of goal-directednessgoal-directedness, n.: How much a system behaves as if it is pursuing a goal — steering toward particular outcomes and finding new ways around obstacles put in its path., or a source of misleading anthropomorphismanthropomorphism, n.: Treating something that isn't human — a pet, a car, a chatbot — as if it had human thoughts, feelings or intentions. AI that talks fluently makes this temptation unusually strong..
Taking the intentional stance — the agent wants the tests to pass — predicted its shortcut better than any inspection of its weights.
Origin
Introduced by Daniel Dennett in 'Intentional Systems' (Journal of Philosophy, 1971) and developed in his book The Intentional Stance (1987).
Related
- 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.
- anthropomorphismanthropomorphism, n.: Treating something that isn't human — a pet, a car, a chatbot — as if it had human thoughts, feelings or intentions. AI that talks fluently makes this temptation unusually strong.
- theory of mindtheory of mind, n.: Being able to work out what someone else believes, wants or knows — even when it is not what you believe — and to use that to guess what they will do next. Researchers test whether AI has it.
- goal-directednessgoal-directedness, n.: How much a system behaves as if it is pursuing a goal — steering toward particular outcomes and finding new ways around obstacles put in its path.
- 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.
- simulator theorysimulator theory, n.: A way of thinking about AI language models as simulators that can play any character found in their training text, rather than as a single agent with its own beliefs and goals.
- anthropomorphismanthropomorphism, n.: Treating something that isn't human — a pet, a car, a chatbot — as if it had human thoughts, feelings or intentions. AI that talks fluently makes this temptation unusually strong.
Sources
- Dennett, D. C. (1971). Intentional Systems. The Journal of Philosophy 68(4), 87–106.
- Dennett, D. C. (1987). The Intentional Stance. MIT Press.
Mentioned in
anthropomorphismanthropomorphism, n.: Treating something that isn't human — a pet, a car, a chatbot — as if it had human thoughts, feelings or intentions. AI that talks fluently makes this temptation unusually strong., 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., 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., theory of mindtheory of mind, n.: Being able to work out what someone else believes, wants or knows — even when it is not what you believe — and to use that to guess what they will do next. Researchers test whether AI has it., belief–desire–intention modelbelief–desire–intention model, n.: A way of designing software agents around three human-like ideas: what the agent believes about the world, what it wants, and which plans it has committed to carrying out., folk psychologyfolk psychology, n.: The everyday way people explain and predict each other's actions in terms of beliefs, desires and intentions, as in 'she took an umbrella because she thought it would rain'., 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., simulator theorysimulator theory, n.: A way of thinking about AI language models as simulators that can play any character found in their training text, rather than as a single agent with its own beliefs and goals.