Thanks Ben for reviewing and sharing the post (and to Michael for your resources) I did find it very interesting. But after reading it, giving it some thought, and reading the Aeon essay you recommended I came away quite intellectually frustrated. I think whenever some claims to have answered the hard problem, the more likely explanation is that they haven’t understood it.
(Full disclosure for me confusion, I’ve all but become a strong dualist about consciousness after many many years of being or identitfying as a physicalist. This was a result of reading the philosophical literature, but also a lot of what was a personal reflection on my own experiences through meditation practice, especially informed by Douglas Harding’s Headless Way. I basically can’t grok illusionist perspectives any more try as I might[1], so readers might better read this comment as coming from a dualist loyal opposition, rather than a balanced assessment)
Something I found particularly puzzling was in the 3rd section of the essay (beginning ‘Over the past 50 years...‘), Humphrey seems to confuse mind-brain identity theory with panyschism, which doesn’t for me bode well my expectation of his ‘solving’ of the hard problem. M-B-I to me is a strongly physicalist (if not eliminativist) position, while pansychism is by necessity dualist. [2]
The D.B. case is also an interesting one—I don’t see why it isn’t plausible to imagine that the operation (and similarly split brain cases as documented by Nagel) might lead to a second vestige of consciousness as cut off from you as that of your family, friends, and coworkers. Except this fragment doesn’t have control of motor or speach functions, how horrible! It can only pass information onto the ‘dominant’ one.
The case of whether Humphrey is right about Octopi not playing is outside of my domain of expertise but initially I am sceptical. But again just because we know that we (humans) are conscious in a certain way, why ought we to imagine that consciousness must only exist in this way? I’m not sure it follows, and there seem to be gaps like this in his arguments that actually cover up important parts of his case.
Two examples of the above to end off my comment:
In the Aeon article Humphrey states that sensations (i think he means qualia) are ideas. I agree! And these ideas exist. It feels very hard to explain how they exist in a physicalist or reductionist story, and attempts to explain often fail to the ‘Moorean’ argument for phenomenal realism.[3]
In Figure 2 he shows a simplified, 4-step diagram of how a brain might create an ‘attractor state’ of phenomenalisation. This is a clear story but seems to me to lead to eliminativist illusionism. The hard question is this, why is this attractor state experiencing phenomenality, and not just a p-Zombie? And it seems that, as all physicalist theories go, Humphrey has no answer to this.
And so help me I have tried! I’ve directly read Dennett, Frankish, and Kammerer! But they all just seem so obviously wrong when they make clear claims; or annoyingly slippery and vague when they don’t. Imo Chalmers blows them all away.
Kammerer reviews this argument here and states it fails. But I just found it a convincing refutation of his own illusionism! I suppose one man’s modus ponens really is another’s modus tollens
In the Aeon article Humphrey states that sensations (i think he means qualia) are ideas. I agree! And these ideas exist. It feels very hard to explain how they exist in a physicalist or reductionist story, and attempts to explain often fail to the ‘Moorean’ argument for phenomenal realism.
Couldn’t they just be beliefs? There are various (physicalist+reductionst-compatible) accounts of belief here. (I’m not sure if that’s what Humphrey intended, though.)
The hard question is this, why is this attractor state experiencing phenomenality, and not just a p-Zombie? And it seems that, as all physicalist theories go, Humphrey has no answer to this.
I think Humphrey is an illusionist and so would dny that it’s experiencing phenomenality and that the hard problem needs to be solved (instead, illusionists dissolve it). However, a complete illusionist theory should explain how beliefs of phenomenality arise (e.g. how these attractor states cause these beliefs); that’s the “hard problem” for illusionists. From what I’m reading in this post and comments, it seems he doesn’t explain that. So, whether interpreted as realist or illusionist, it seems there’s still an important gap.
Yeah I’m not quiet sure what Humphrey means by belief here (thanks for the link!). But then I don’t really know what I mean by ‘belief’ to be honest! I’m not sure I can define it without evoking my own phenomenal perspective, whether directly (a flash of inspiration) or via thought and introspection (trying to update my current beliefs with new evidence) - and I think that’d already put me at odds with physicalists/illusionists
I do think Humphrey is an illusionist (even if he doens’t like the term) and view him as somewhat adjacent to Frankish. I think that the ‘meta-problem of consciousness’ isn’t quite what I’m hinting at (though it is a problem) - I’m taking my phenomenal experiences as true. Dualists (like myself) need to try and get them to accord with our understanding of the physical world, but I think illusionists need to explain why I’m experiencing anything at all rather than just reporting I am. We probably have very different intuitions on this, but part of the reason I’ve become more ‘dualist’ over time is that I found that I never had a good response to this criticism when I was a materialist/physicalist, so in the end I accepted it as a worthy criticism that disproved my original ideas.
Finally, I’ll note this isn’t the first time we’ve had a Forum discussion about consciousness[1] - maybe it’s something we could explore in a dialogue if it’s something you think would be a valuable use of our time and potentially useful for those reading on the Forum? It definitely touches on a number of EA cause areas.
I think illusionists need to explain why I’m experiencing anything at all rather than just reporting I am
We need to first decide what we mean by ‘experience’. I think there are two broad approaches (interpretations) of illusionism, which I described here and which could give us two different broad characterizations of ‘experience’:
In the first, beliefs (illusions) of phenomenality/mysteriousness/nonphysical essence/etc. themselves could be what distinguishes what’s experienced from what’s not experienced. These beliefs need not be verbalized (whether in inner speech or reported) and could be of a more intuitive kind, like Graziano’s attention schema or Humphrey’s ipsundrum are meant to capture.[1] They might just be representations or models “depicting” phenomenal properties. See also my footnote here on Graziano’s Attention Schema Theory. So, these beliefs would explain why you’re experiencing anything at all.
In the second, the physical properties that dispose us to have such beliefs could be what distinguishes experiences. This could be a kind of placeholder, but I suspect Frankish and Dennett would say that any reactive patterns and discriminations count, at least to some minimal degree.[2] So, thermometers and bacteria could be minimally experiencing things, too, and that you’re reacting and making any discriminations at all would explain why you’re experiencing anything at all. Those with blindsight could still have visual experiences, but in a way that’s not accessible for standard verbal report and possibly of a more simple/minimal kind.
I suspect there’s no real fact of the matter which approach is “right”, but I’m more inclined towards 1.
If you have something else in mind by ‘experience’, I could try to respond to that.
Finally, I’ll note this isn’t the first time we’ve had a Forum discussion about consciousness[1] - maybe it’s something we could explore in a dialogue if it’s something you think would be a valuable use of our time and potentially useful for those reading on the Forum? It definitely touches on a number of EA cause areas.
I might be interested in having a (recorded) call, and then we can release it, the (edited) transcripts and/or notes. I spend way too long writing comments (including this one, and others on this post), so I think I shouldn’t commit to a text-based discussion.
That being said, I’m not sure how useful this would be for other people, compared to them just reading writing by or listening to Graziano or Frankish. It was Graziano’s papers (2021, 2022, some clarifications in 2020) that made illusionism click for me,[3] and I suspect I couldn’t do a better job in explaining illusionism than to just linkpost or quote him, as well as Kammerer, 2022 (or just the short summary in Shabasson, 2021, section 9), which helps illustrate how the illusion could be so persistent.
I think the basic argument that convinced me roughly goes like this, based on Graziano (2021, 2022), and from a draft I wrote but never posted:
Our claims of conscious experience result from the depiction/representation of information processed in our brains as having properties we believe as common to our conscious experiences, like phenomenality, subjectivity, qualitativeness or a nonphysical essence. There must be information in our brains depicting these properties, because without such information, we wouldn’t consistently talk about these properties in the first place. Of course, maybe the information processing appears to have these properties precisely because it actually has these properties, and that’s a realist position. However, the depiction itself and access to it by systems necessary for belief formation would be enough, and that’s the illusionist position. There’s no need to posit the actual existence of these properties, and in my view, there’s currently no plausible explanation for the actual existence of these properties.
However, some things may make me unusually likely to accept illusionism:
I suspect my direct intuitions about physical phenomena and consciousness are relatively weak, and I’m unusually inclined towards abstraction, so I’ve found little to count against illusionism for me. That consciousness just seems phenomenal, and red seems to be qualitative just doesn’t count very strongly to me.
I have a very strong presumption in favour of physicalism,[4] and every non-illusionist physicalist theory doesn’t seem to me to offer a serious attempt to solve the hard problem, so the best option seems to be to dissolve it, hence illusionism. It sounds like you went the other way towards dualism through your dissatisfaction with physicalist theories, and I’d guess Chalmers did, too.
Dogs presumably do not think there is something it is like to be them, even if there is. It is not that a dog thinks there isn’t anything it is like to be a dog; the dog is not a theorist at all, and hence does not suffer from the theorists’ illusion. The hard problem and meta-problem are only problems for us humans, and mainly just for those of us humans who are particularly reflective. In other words, dogs aren’t bothered or botherable by problem intuitions. Dogs – and, for that matter, clams and ticks and bacteria – do enjoy (or at any rate benefit from) a sort of user illusion: they are equipped to discriminate and track only some of the properties in their environment.
They were also the first explanations of illusionism I’d read. I haven’t settled on Graziano’s AST in particular, but it seems like a promising direction.
But also, other than panpsychism, where could we possibly draw a line for the presence and absence of the extra nonphysical property/properties? I can’t imagine there being any plausible responses.
Or, if panpsychist, how could these properties possibly combine in ways that correspond to what our brains are doing and our specific judgements? Maybe some kind of property dualism?
I also can’t imagine there being any plausible account of how the nonphysical affects the physical (or else we would already have identified it and adopted it into our physical ontology), so I’d be stuck with epiphenomenalism.
So, if not an illusionist, I’d have to be a (property dualist) epiphenomenalist, and it seems there would be no way to empirically distinguish such accounts from their illusionist counterparts, which just drop the nonphysical stuff. And whether or not there are different ethical implications between them, I can’t imagine them being that decisive in practice. The difference just doesn’t seem that interesting anymore, but I favour the metaphysically more parsimonious illusionism.
FWIW, I haven’t read much Chalmers, and I learned about property dualism after illusionism already became intuitive to me.
I tend to think that questions about which organisms or systems are conscious mostly depend on identifying the physical correlates of consciousness, and understanding how they work as a system, and that questions about panpsychism, illusionism, eliminativism, or even Calmer’s Hard Problem don’t bear on this question very much. I think there’s probably still a place for that philosophical debate because (1) there might be implications about where to look for the physical systems and (2) as I said to Michael earlier, illusionism might change our perspective on whether we assign special moral value to conscious experience at all. But I think (1) is marginal, and (2) is sort of a long shot.
In contrast, I think empirical and scientific investigation can help us understand a lot about which systems are conscious, and about what sort of conscious experiences they have, so I think most morally cruxy questions of consciousness are scientific and empirical.
Consequently, I wasn’t too bothered by Humphrey side-stepping this issue, although I basically agree he did, because he offered solid theory and empirical investigation that suggests further empirical tests that might help us make progress on understanding consciousness in animals and other systems.
The D.B. case is also an interesting one—I don’t see why it isn’t plausible to imagine that the operation (and similarly split brain cases as documented by Nagel) might lead to a second vestige of consciousness as cut off from you as that of your family, friends, and coworkers. Except this fragment doesn’t have control of motor or speach functions, how horrible! It can only pass information onto the ‘dominant’ one.
That was my reaction when I first read about split-brain patients. I now doubt it’s all that horrible. First, there’s been plenty of research of split-brain patients and I don’t think anyone has discovered signs of distress from split-halfs that are cut off from speech expression; those halves do have other ways of communicating, e.g., through signs. Second, in humans, much of distress is governed physiologically, and so (1) we would be able to detect physiological signs of stress, but more importantly (2) even if there’s a conscious half of a split-brain which can’t express itself, its mood-state might be normal because it shares a body with the other half, and so the two jointly set mood, and the system overall might not be in distress. Finally, even if consciousness isn’t illusory, conscious will often is; much more of our decisions are determined subconsciously than we think, and if the illusion still holds, the loss of conscious control might not even be perceived.
Thanks Ben for reviewing and sharing the post (and to Michael for your resources) I did find it very interesting. But after reading it, giving it some thought, and reading the Aeon essay you recommended I came away quite intellectually frustrated. I think whenever some claims to have answered the hard problem, the more likely explanation is that they haven’t understood it.
(Full disclosure for me confusion, I’ve all but become a strong dualist about consciousness after many many years of being or identitfying as a physicalist. This was a result of reading the philosophical literature, but also a lot of what was a personal reflection on my own experiences through meditation practice, especially informed by Douglas Harding’s Headless Way. I basically can’t grok illusionist perspectives any more try as I might[1], so readers might better read this comment as coming from a dualist loyal opposition, rather than a balanced assessment)
Something I found particularly puzzling was in the 3rd section of the essay (beginning ‘Over the past 50 years...‘), Humphrey seems to confuse mind-brain identity theory with panyschism, which doesn’t for me bode well my expectation of his ‘solving’ of the hard problem. M-B-I to me is a strongly physicalist (if not eliminativist) position, while pansychism is by necessity dualist. [2]
The D.B. case is also an interesting one—I don’t see why it isn’t plausible to imagine that the operation (and similarly split brain cases as documented by Nagel) might lead to a second vestige of consciousness as cut off from you as that of your family, friends, and coworkers. Except this fragment doesn’t have control of motor or speach functions, how horrible! It can only pass information onto the ‘dominant’ one.
The case of whether Humphrey is right about Octopi not playing is outside of my domain of expertise but initially I am sceptical. But again just because we know that we (humans) are conscious in a certain way, why ought we to imagine that consciousness must only exist in this way? I’m not sure it follows, and there seem to be gaps like this in his arguments that actually cover up important parts of his case.
Two examples of the above to end off my comment:
In the Aeon article Humphrey states that sensations (i think he means qualia) are ideas. I agree! And these ideas exist. It feels very hard to explain how they exist in a physicalist or reductionist story, and attempts to explain often fail to the ‘Moorean’ argument for phenomenal realism.[3]
In Figure 2 he shows a simplified, 4-step diagram of how a brain might create an ‘attractor state’ of phenomenalisation. This is a clear story but seems to me to lead to eliminativist illusionism. The hard question is this, why is this attractor state experiencing phenomenality, and not just a p-Zombie? And it seems that, as all physicalist theories go, Humphrey has no answer to this.
And so help me I have tried! I’ve directly read Dennett, Frankish, and Kammerer! But they all just seem so obviously wrong when they make clear claims; or annoyingly slippery and vague when they don’t. Imo Chalmers blows them all away.
Galen Strawson actually has an interesting argument that physicalism must collapse into pansychism.
Kammerer reviews this argument here and states it fails. But I just found it a convincing refutation of his own illusionism! I suppose one man’s modus ponens really is another’s modus tollens
Couldn’t they just be beliefs? There are various (physicalist+reductionst-compatible) accounts of belief here. (I’m not sure if that’s what Humphrey intended, though.)
I think Humphrey is an illusionist and so would dny that it’s experiencing phenomenality and that the hard problem needs to be solved (instead, illusionists dissolve it). However, a complete illusionist theory should explain how beliefs of phenomenality arise (e.g. how these attractor states cause these beliefs); that’s the “hard problem” for illusionists. From what I’m reading in this post and comments, it seems he doesn’t explain that. So, whether interpreted as realist or illusionist, it seems there’s still an important gap.
Yeah I’m not quiet sure what Humphrey means by belief here (thanks for the link!). But then I don’t really know what I mean by ‘belief’ to be honest! I’m not sure I can define it without evoking my own phenomenal perspective, whether directly (a flash of inspiration) or via thought and introspection (trying to update my current beliefs with new evidence) - and I think that’d already put me at odds with physicalists/illusionists
I do think Humphrey is an illusionist (even if he doens’t like the term) and view him as somewhat adjacent to Frankish. I think that the ‘meta-problem of consciousness’ isn’t quite what I’m hinting at (though it is a problem) - I’m taking my phenomenal experiences as true. Dualists (like myself) need to try and get them to accord with our understanding of the physical world, but I think illusionists need to explain why I’m experiencing anything at all rather than just reporting I am. We probably have very different intuitions on this, but part of the reason I’ve become more ‘dualist’ over time is that I found that I never had a good response to this criticism when I was a materialist/physicalist, so in the end I accepted it as a worthy criticism that disproved my original ideas.
Finally, I’ll note this isn’t the first time we’ve had a Forum discussion about consciousness[1] - maybe it’s something we could explore in a dialogue if it’s something you think would be a valuable use of our time and potentially useful for those reading on the Forum? It definitely touches on a number of EA cause areas.
And I’ve very much enjoyed learning from your perspective :)
We need to first decide what we mean by ‘experience’. I think there are two broad approaches (interpretations) of illusionism, which I described here and which could give us two different broad characterizations of ‘experience’:
In the first, beliefs (illusions) of phenomenality/mysteriousness/nonphysical essence/etc. themselves could be what distinguishes what’s experienced from what’s not experienced. These beliefs need not be verbalized (whether in inner speech or reported) and could be of a more intuitive kind, like Graziano’s attention schema or Humphrey’s ipsundrum are meant to capture.[1] They might just be representations or models “depicting” phenomenal properties. See also my footnote here on Graziano’s Attention Schema Theory. So, these beliefs would explain why you’re experiencing anything at all.
In the second, the physical properties that dispose us to have such beliefs could be what distinguishes experiences. This could be a kind of placeholder, but I suspect Frankish and Dennett would say that any reactive patterns and discriminations count, at least to some minimal degree.[2] So, thermometers and bacteria could be minimally experiencing things, too, and that you’re reacting and making any discriminations at all would explain why you’re experiencing anything at all. Those with blindsight could still have visual experiences, but in a way that’s not accessible for standard verbal report and possibly of a more simple/minimal kind.
I suspect there’s no real fact of the matter which approach is “right”, but I’m more inclined towards 1.
If you have something else in mind by ‘experience’, I could try to respond to that.
I might be interested in having a (recorded) call, and then we can release it, the (edited) transcripts and/or notes. I spend way too long writing comments (including this one, and others on this post), so I think I shouldn’t commit to a text-based discussion.
That being said, I’m not sure how useful this would be for other people, compared to them just reading writing by or listening to Graziano or Frankish. It was Graziano’s papers (2021, 2022, some clarifications in 2020) that made illusionism click for me,[3] and I suspect I couldn’t do a better job in explaining illusionism than to just linkpost or quote him, as well as Kammerer, 2022 (or just the short summary in Shabasson, 2021, section 9), which helps illustrate how the illusion could be so persistent.
I think the basic argument that convinced me roughly goes like this, based on Graziano (2021, 2022), and from a draft I wrote but never posted:
Our claims of conscious experience result from the depiction/representation of information processed in our brains as having properties we believe as common to our conscious experiences, like phenomenality, subjectivity, qualitativeness or a nonphysical essence. There must be information in our brains depicting these properties, because without such information, we wouldn’t consistently talk about these properties in the first place. Of course, maybe the information processing appears to have these properties precisely because it actually has these properties, and that’s a realist position. However, the depiction itself and access to it by systems necessary for belief formation would be enough, and that’s the illusionist position. There’s no need to posit the actual existence of these properties, and in my view, there’s currently no plausible explanation for the actual existence of these properties.
However, some things may make me unusually likely to accept illusionism:
I suspect my direct intuitions about physical phenomena and consciousness are relatively weak, and I’m unusually inclined towards abstraction, so I’ve found little to count against illusionism for me. That consciousness just seems phenomenal, and red seems to be qualitative just doesn’t count very strongly to me.
I have a very strong presumption in favour of physicalism,[4] and every non-illusionist physicalist theory doesn’t seem to me to offer a serious attempt to solve the hard problem, so the best option seems to be to dissolve it, hence illusionism. It sounds like you went the other way towards dualism through your dissatisfaction with physicalist theories, and I’d guess Chalmers did, too.
But might leave out too many details of how this actually works in humans and other animals to be very satisfying.
E.g. Frankish on continuity here (54:00-57:37).
Also Dennett (2019, p. 54):
And Dennett thinks that chickens, octopuses and bees are definitely conscious.
They were also the first explanations of illusionism I’d read. I haven’t settled on Graziano’s AST in particular, but it seems like a promising direction.
Just generally.
But also, other than panpsychism, where could we possibly draw a line for the presence and absence of the extra nonphysical property/properties? I can’t imagine there being any plausible responses.
Or, if panpsychist, how could these properties possibly combine in ways that correspond to what our brains are doing and our specific judgements? Maybe some kind of property dualism?
I also can’t imagine there being any plausible account of how the nonphysical affects the physical (or else we would already have identified it and adopted it into our physical ontology), so I’d be stuck with epiphenomenalism.
So, if not an illusionist, I’d have to be a (property dualist) epiphenomenalist, and it seems there would be no way to empirically distinguish such accounts from their illusionist counterparts, which just drop the nonphysical stuff. And whether or not there are different ethical implications between them, I can’t imagine them being that decisive in practice. The difference just doesn’t seem that interesting anymore, but I favour the metaphysically more parsimonious illusionism.
FWIW, I haven’t read much Chalmers, and I learned about property dualism after illusionism already became intuitive to me.
I tend to think that questions about which organisms or systems are conscious mostly depend on identifying the physical correlates of consciousness, and understanding how they work as a system, and that questions about panpsychism, illusionism, eliminativism, or even Calmer’s Hard Problem don’t bear on this question very much. I think there’s probably still a place for that philosophical debate because (1) there might be implications about where to look for the physical systems and (2) as I said to Michael earlier, illusionism might change our perspective on whether we assign special moral value to conscious experience at all. But I think (1) is marginal, and (2) is sort of a long shot.
In contrast, I think empirical and scientific investigation can help us understand a lot about which systems are conscious, and about what sort of conscious experiences they have, so I think most morally cruxy questions of consciousness are scientific and empirical.
Consequently, I wasn’t too bothered by Humphrey side-stepping this issue, although I basically agree he did, because he offered solid theory and empirical investigation that suggests further empirical tests that might help us make progress on understanding consciousness in animals and other systems.
That was my reaction when I first read about split-brain patients. I now doubt it’s all that horrible. First, there’s been plenty of research of split-brain patients and I don’t think anyone has discovered signs of distress from split-halfs that are cut off from speech expression; those halves do have other ways of communicating, e.g., through signs. Second, in humans, much of distress is governed physiologically, and so (1) we would be able to detect physiological signs of stress, but more importantly (2) even if there’s a conscious half of a split-brain which can’t express itself, its mood-state might be normal because it shares a body with the other half, and so the two jointly set mood, and the system overall might not be in distress. Finally, even if consciousness isn’t illusory, conscious will often is; much more of our decisions are determined subconsciously than we think, and if the illusion still holds, the loss of conscious control might not even be perceived.