knowledge argument
In plain wordsA thought experiment about Mary, a scientist who knows every physical fact about color but has lived all her life in a black-and-white room. When she first sees red, does she learn something new?
An argument against physicalism built on a thought experiment: Mary, a brilliant neuroscientist confined to a black-and-white room, learns every physical fact about color vision; on first seeing a ripe tomato she seems to learn something new, namely what seeing red is like. If so, complete physical knowledge leaves something out, and there are nonphysical facts about experience such as 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.. Replies include the ability hypothesis (Mary gains know-how, such as abilities to imagine and recognize red, not new facts), the acquaintance hypothesis, and the phenomenal-concept strategy (she learns an old fact under a new concept). AI writers invoke Mary when asking whether a system trained only on descriptions, such as a text-only language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., can know what perceptual words mean.
Origin
Presented by Frank Jackson in 'Epiphenomenal Qualia' (Philosophical Quarterly, 1982) and 'What Mary Didn't Know' (Journal of Philosophy, 1986); Jackson later abandoned the argument and accepted physicalism. C. D. Broad's 1925 example of a 'mathematical archangel' unable to deduce the smell of ammonia anticipated it.
Related
- 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.
- 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.
- symbol grounding problemsymbol grounding problem, n.: The puzzle of how words or symbols inside a machine can mean anything by themselves, rather than only pointing to more symbols — like a dictionary that defines every word using other words.
- philosophical zombiephilosophical zombie, n.: An imagined being that behaves exactly like a person — talking, laughing, even saying it feels pain — but has no inner experience at all. Philosophers use it to ask whether behavior proves a mind.
- octopus testoctopus test, n.: A thought experiment in which a clever octopus learns to impersonate a stranded islander by eavesdropping on an undersea cable, without ever knowing what the words refer to. It asks whether text-trained AI can grasp meaning.
Sources
- Jackson, F. (1982). Epiphenomenal Qualia. The Philosophical Quarterly 32(127), 127–136.
- Jackson, F. (1986). What Mary Didn't Know. The Journal of Philosophy 83(5), 291–295.
Mentioned in
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., 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., Thomas NagelThomas Nagel, prop. n.: An American philosopher whose 1974 essay 'What Is It Like to Be a Bat?' defined consciousness as there being something it is like to be a creature, a test now applied to machines.