“It doesn’t make sense to ask questions like, Does a computer program of a mind really instantiate consciousness?”
This is a misunderstanding of how language works. Once we discover what the ontological nature of conscious states is (physical, biological, functional, functional computational, etc.) is and what their content has to be (for example, if conscious states are functional states, not every functional state is a conscious state), we have discovered the true thing we had referred to, and there is an objective fact on the matter as to whether that thing is or is not instantiated somewhere.
For example, imagine you tell me that there are qualia related to smelling coffee, such that the qualia make no functional difference to your behaviour, but do make a difference to your subjective experience. I say this is debunkable, because if qualia make no functional difference, then they don’t influence what you say, including about the supposed qualia.
You have gotten at something extremely important here—namely, that once software passes the Turing test, it’s unjustified to demand that it implements a specific computation to be called conscious, because the presence of that computation (compared to the information processing being implemented differently) makes no functional difference.
Thanks for the comment. Note (for others) the sentence you are quoting is from Brian Tomasik.
I don’t think it’s necessarily misunderstanding how language works. I think there are plenty of cases where it doesn’t make sense to ask questions with a similar linguistic or grammatical structure. For example, “Does a simulation of a phage (or a virus, or a self-replicating robot) really instantiate life?”, or “You may enjoy liquorice ice cream, but is it really tasty?”
It’s appropriate to complain that it doesn’t make sense to speculate whether X really instantiates Y when Y is vague, ambiguous, subject-dependent, etc., and where it’s pretty clear extant usage of “Y” is compatible with different more precise operationalisations which give different answers. To these questions the answer is, “Well, it obviously depends what you mean by “Y”, and otherwise the question doesn’t have a single discoverable or consistent answer.” The life sciences did not discover the ‘true’ referent of “life”, and not for lack of data or good explanations.
Cases where it is less appropriate to complain that it doesn’t make sense to speculate whether X really instantiates Y, are cases where either we do agree on a crisp definition of Y, or we have some reason to believe we will discover one. I’m arguing that we have less reason than we might intuitively think to believe that we’ll ever “discover what the ontological nature of conscious states is”. I agree that if you’re confident there is a crisp, discoverable answer to exactly which things should count as “conscious”, then it totally does make sense to speculate about which things are conscious.
On your point about qualia computations, the standard questions pop up: if qualia are functionally inert computations, how would the ‘subject’ of consciousness know it is experiencing them, and so on. And isn’t the idea of computationalism about consciousness that the ‘computations’ can be pinned down by the computational relationship between inputs and outputs; in which case wouldn’t the qualia-generating computations be abstracted away?
For example, “Does a simulation of a phage (or a virus, or a self-replicating robot) really instantiate life?”
Yes, no (outside the host, yes inside), yes. Given what we mean by life, a simulation of life is life.
“You may enjoy liquorice ice cream, but is it really tasty?”
This question doesn’t make sense, because taste is relative to the consumer. What is really tasty for one person might not be really tasty for another. Consciousness isn’t like that—what is consciousness for one person is consciousness for everyone, people just don’t know what the definition of consciousness fixed by their implicit beliefs is.
On your point about qualia computations, the standard questions pop up: if qualia are functionally inert computations, how would the ‘subject’ of consciousness know it is experiencing them, and so on.
Right.
And isn’t the idea of computationalism about consciousness that the ‘computations’ can be pinned down by the computational relationship between inputs and outputs; in which case wouldn’t the qualia-generating computations be abstracted away?
I don’t know. The way I understand (and don’t subscribe to) computational functionalism is that you can have different computations implementing the same behavior.
This is a misunderstanding of how language works. Once we discover what the ontological nature of conscious states is (physical, biological, functional, functional computational, etc.) is and what their content has to be (for example, if conscious states are functional states, not every functional state is a conscious state), we have discovered the true thing we had referred to, and there is an objective fact on the matter as to whether that thing is or is not instantiated somewhere.
You have gotten at something extremely important here—namely, that once software passes the Turing test, it’s unjustified to demand that it implements a specific computation to be called conscious, because the presence of that computation (compared to the information processing being implemented differently) makes no functional difference.
Thanks for the comment. Note (for others) the sentence you are quoting is from Brian Tomasik.
I don’t think it’s necessarily misunderstanding how language works. I think there are plenty of cases where it doesn’t make sense to ask questions with a similar linguistic or grammatical structure. For example, “Does a simulation of a phage (or a virus, or a self-replicating robot) really instantiate life?”, or “You may enjoy liquorice ice cream, but is it really tasty?”
It’s appropriate to complain that it doesn’t make sense to speculate whether X really instantiates Y when Y is vague, ambiguous, subject-dependent, etc., and where it’s pretty clear extant usage of “Y” is compatible with different more precise operationalisations which give different answers. To these questions the answer is, “Well, it obviously depends what you mean by “Y”, and otherwise the question doesn’t have a single discoverable or consistent answer.” The life sciences did not discover the ‘true’ referent of “life”, and not for lack of data or good explanations.
Cases where it is less appropriate to complain that it doesn’t make sense to speculate whether X really instantiates Y, are cases where either we do agree on a crisp definition of Y, or we have some reason to believe we will discover one. I’m arguing that we have less reason than we might intuitively think to believe that we’ll ever “discover what the ontological nature of conscious states is”. I agree that if you’re confident there is a crisp, discoverable answer to exactly which things should count as “conscious”, then it totally does make sense to speculate about which things are conscious.
On your point about qualia computations, the standard questions pop up: if qualia are functionally inert computations, how would the ‘subject’ of consciousness know it is experiencing them, and so on. And isn’t the idea of computationalism about consciousness that the ‘computations’ can be pinned down by the computational relationship between inputs and outputs; in which case wouldn’t the qualia-generating computations be abstracted away?
Yes, no (outside the host, yes inside), yes. Given what we mean by life, a simulation of life is life.
This question doesn’t make sense, because taste is relative to the consumer. What is really tasty for one person might not be really tasty for another. Consciousness isn’t like that—what is consciousness for one person is consciousness for everyone, people just don’t know what the definition of consciousness fixed by their implicit beliefs is.
Right.
I don’t know. The way I understand (and don’t subscribe to) computational functionalism is that you can have different computations implementing the same behavior.