You On AI Field Guide · Multiple Realizability The You On AI Field Guide Home
TxtLowMedHigh
CONCEPT

Multiple Realizability

The thesis that one and the same mental state can be instantiated by indefinitely many physical systems—the argument that opens the door to a machine mind, and that says nothing about whether anyone has walked through it.
Multiple realizability is the insight that pain is not the firing of any particular fiber, because pain is felt by creatures—mammals, reptiles, an octopus, perhaps one day a machine—with radically different neural hardware. What pain has in common across them is not a substance but a structure, a functional role, and so the mental is multiply realizable: the same kind can be realized by many physical kinds. Hilary Putnam made this the argument that buried the identity theory, and it is the argument that, more than any other, licenses the dream of a mind running on silicon. But it cuts in two directions at once. It establishes a possibility, not an actuality: that a mind could be made of silicon does not mean that this language model, with this architecture, is one. The argument opens a door; it does not tell you whether anyone has walked through. In the cycle that began with [YOU] on
← Home0%
CONCEPTBook →

Keep reading with YOU ON AI

Unlock the full book, 10,000+ field-guide entries, and a 1000+ thinker library. If you have a book code, register now — it takes a minute.

Register with book code Sign in