Path: utzoo!attcan!uunet!lll-winken!sol.ctr.columbia.edu!emory!att!iuvax!cogsci!dave From: dave@cogsci.indiana.edu (David Chalmers) Newsgroups: comp.ai.philosophy Subject: Re: Testing Machine Consciousness Message-ID: <65780@iuvax.cs.indiana.edu> Date: 19 Oct 90 23:18:23 GMT References: <3499@media-lab.MEDIA.MIT.EDU> <1990Oct4.154655.23004@canon.co.uk> <26852@cs.yale.edu> Sender: news@iuvax.cs.indiana.edu Reply-To: dave@cogsci.indiana.edu (David Chalmers) Organization: Indiana University, Bloomington Lines: 140 In article <26852@cs.yale.edu> mcdermott-drew@cs.yale.edu (Drew McDermott) writes: >Why There is No Other-Minds Problem >[...] >Okay, about this phrasing: As granted above, >mental phenomena have three aspects, subjective, behavioral, and >implementational. Why couldn't it simply be the case that the first >one is often or always absent? The only agent I'm sure has subjective >experience is me, so what's my evidence that anyone else has? Yes, this is the right way to state the problem. "Mind" as the term is traditionally used has behavioural, functional, and phenomenological aspects. The "other minds" problem is concerned only with the phenomenological (subjective) aspects. >The problem with this objection is that it misconstrues {\it aspects} >as {\it parts}. This construal would make sense for problems like the >``other-planets problem'': We observe one star with planets and ask >what our evidence is that some or any other stars have any. But >subjective experience is not an appendage of mentation in this way. A >mental event can be experienced from several different angles, >including (although the categories are fairly arbitrary), the >subjective, the behavioral, and the implementational. But the >experiences are all {\it of the same event}. The flaw in your argument is right here -- the rest is just wrapping. It may be that in many cases -- in particular, the cases where subjective phenomena exist -- the subjective, behavioural, and functional aspects are all aspects of the same event. But this does not imply that in all cases, they must be tied together. Certainly, in *my* case the three aspects go together. Does that allow be to deduce that in your case, or in a robot's case, they must also? Of course not. The coincidence of functional organization, behavioural consequences and subjectivity in some cases is quite compatible, a priori, with the coincidence of functional organization, behavioural consequences and non-subjectivity in others. Analogy time: In certain cases, temperature coincides with the motion of gas molecules -- they are literally two aspects of the same thing. In other cases, temperature exists without the motion of gas molecules. Of course, you may be wanting to make a *claim* that in all cases where at least one of them occur, the three aspects of "mind" will be tied together as different aspects of the same thing. This is a non-trivial claim, whose truth-value may or may not be "true". The non-triviality of this claim is the reason why there is an Other-Minds Problem. (I in fact believe that the claim is true -- more specifically, I believe that the phenomenological is supervenient on the functional. But I can't prove it, at least not easily, and so the Other Minds problem can still be raised.) >It's just extremely likely that agents capable >of experiencing the world would also experience some of their own >workings. Your phrasing right here concedes that the OMP is really a problem. "Extremely likely" is not good enough. It was always extremely likely that you and other people all have subjective experience. The OMP is "How can you know *for sure*?" As far as I'm concerned, the best answer for now is "You can't, but you can be pretty confident on various inductive grounds". >That is, the robot mathematician could be >a ``hollow shell,'' with no subjective experience. > >So what good is it to speculate about --- let alone set >limits to --- the answers that future cognitive science would give us >regarding the state of the robot's mind? Of course we can't predict these answer in advance. But few advocates of the OMP (Searle excepted) would argue in advance that we know that certain intelligent-seeming beings could *not* have minds. They just argue that the question is open. >When it comes to mind, we don't know enough yet to say whether it's >possible for there to be pseudo-intelligence or pseudo-paranoia. I hate to get stuck in a rut, but you've once again conceded that there *is* an OMP. >Okay, we'll ask it: ``Are you conscious?'' or, more specifically, >``Are you really afraid that Prof. Potter sneaked a peek at your >proof, or are you just faking it?'' I have a paper that addresses the relationship between claims about consciousness (e.g. "Sure, I have these really weird subjective feels"), and consciousness itself. It's a highly non-trivial issue, but the conclusion I come to is that if we want our claims about consciousness to reflect the properties of consciousness, then consciousness must be supervenient on functional organization (i.e., whenever you have the right functional -- that is, abstract causal -- organization, it must be accompanied by consciousness). If the source of consciousness is something other than functional organization -- e.g. if consciousness was biochemistry-specific, as Searle seems occasionally to believe -- then our consciousness-claims would be deeply irrelevant to consciousness itself. In this case, there'd be little point even talking about the Mind-Body Problem, as we wouldn't know what we were talking about. Shoemaker's paper "Functionalism and Qualia" (reprinted in Block, _Readings in the Philosophy of Psychology_, Vol. 1) touches on issues related to this. >If the skeptic denies this point, then I am afraid he is committed to >a dualistic position, in which mental substances are connected in >fairly arbitrary ways to physical objects. Suppose an entity does >have a mind in this sense --- a subjectivity arbitrarily associated >with it. Then there is nothing linking this kind of mind with any >information-processing capacity of the system. Suppose the computers >at the National Weather Service do have this kind of subjective minds, >in the same sense that trees or rocks might. These minds might be dreaming >about God; the chances that they are thinking about the weather are >negligible. One can be some form of dualist *without* believing that minds are arbitrarily associated with information-processing. My favourite theory of consciousness is sort-of-dualist, but still holds that the causal roots (really, the supervenience base) of consciousness lie in information-processing. There can be a dualistic mind-brain association without it being an arbitrary one. If we could *prove* such a theory, or any theory delineating the specific roots of consciousness in the physical, then there would no longer be an OMP. We would know precisely which entities have, or don't have, minds. Unfortunately no-one yet has done more than offer plausibility arguments for various theories. This is OK -- for all we know, that's the best we can do. But while that's the best we can do, the OMP will remain. >However, the problem turns out to be a vestigial organ of an extinct >philosophical organism, Cartesian epistemology. The question is >invariably posed in a setting where it is completely obvious, prima >facie, that the creature in question has a mind, and it presupposes >that the alternative --- that it does not ``really'' have a mind --- >makes sense. But the alternative cannot be spelled out without >presupposing dualism or solipsism. This is quite false. It's perfectly consistent to hold a quite materalist theory of mind, where subjective phenomena are identical to certain material events -- but only *certain* material events, such as ones that occur in a given biochemistry. I believe that for various reasons this is highly implausible, but it is a coherent position. -- Dave Chalmers (dave@cogsci.indiana.edu) Center for Research on Concepts and Cognition, Indiana University. "It is not the least charm of a theory that it is refutable."