Indirect Realism and Direct Realism

Pierre-Normand

@NOS4A2, @Luke,

Two very insightful posts in a row!

AmadeusD

And in speaking about such non-linguistic thoughts, only the linguistic portions get communicated — Manuel

This is incoherent. There are no linguistic portions of hte thoughts. You have, again, contradicted yourself. I understand why you did not understand when I pointed this out about a position you took, but this sentence, itself, is contradictory. You cannot communicate linguistic "portions" of something non-linguistic. There isn't a linguistic portion Bear Fur.

If someone could attempt to describe in some manner, non-linguistic thought, it would be interesting to see. — Manuel

This is exactly what (arguably) more than half of humans do. This is the way in whcih non-linguistic thoughts are expressed linguistically. I'm unsure your point is even apt here - "descriptions" are by definition, this process resulting in communication, about half hte time (some descriptions are of images!).

Until we have a better notion of linguistic thought, we are going to remain stuck. — Manuel

Mine is exact, and contrasts exactly with non-linguistic thought. IF yours are grey and iffy, that may explain the disparity between our views.

Come on man. People can use sing language, or sight, as was the case with Hawking, to express thought. But it does come from the brain, not from the tongue or the eyes... — Manuel

I think you're not seeing the distinction I'm making. Hawking had less direct communication than typical speech. It changed even the vessel of delivery, not to mention the medium etc.. as with normal communication.

If you want to call it convention, call it convention. I don't have a problem with direct and mediated. You take mediation to mean indirect. — Manuel

I do indeed. If that's the disagreement, I guess we can discuss that rather than the 'other stuff' I alluded to.

I will once again say, we only have the human way of seeing things, not a "view from nowhere", which is where I assume you would believe directness could be attained. — Manuel

No, I don't take it to mean that. I take it to mean something other than human sensory perception. That is an infinite concept. Telepathy is one possible example (in its strict sense, mind-to-mind, no mediation).

I believe it makes more sense to argue that we directly see objects (mediated by our mind and organs) than to say we indirectly see an object, because it is mediated. — Manuel

To me, it doens't make sense. But i also think this just comes, purely, down to your discomfort with the latter. In a Parfitean sense, its possible this is what's considered an 'empty' question on your terms - but I think the idea of Telepathy is coherent. So, I have a 'contrast' as it were, and on that contrast it is obvious to me that typical communication is Indirect, as to thoughts. It's direct in the sense of it is person-to-person. But, I don't think either of us are trying to make that point (whether pro or con).

but to think his entire framework is wrong, well I think this is simply to dismiss was even contemporary brain sciences say, not mentioning common sense. — Manuel

I see. This may be an issue.

Sure - we have an issue here too, what is an object? It's not trivial. Is it the thing we think we see, is it the cause of what we think we see or is it a mere mental construction only? Tough to say. — Manuel

On my account, it is the item 'in the world' which has a causal relationship with the process of perception which results in phenomenal experience. So, as an example, to see the keyboard in front of me (a token) I must actually cast my eyes on it (I call this 'to look at'). My body then perceives the light, and (insert some other crap about hte process here) eventually I have a phenomenal experience of a mental representation. Its correlative. I do not think it is at all direct. This retains coherence, but could still be wrong.

I think it makes more sense. — Manuel

I also assent to that notion. IN day-to-day life, my conception would be extremely difficult to navigate, I think. But, I don't think convention speaks to 'actual' aspects of things without actually deducing that it does :P

I will grant this as stated. I actually don't think that we disagree all that much on substantial matter, more so the way words are used. And I admit I am using direct in a manner that goes beyond the usual framing as "naive realism", which if anyone believes in that, they shouldn't be in philosophy or science, or I would wonder why they would bother with this. — Manuel

Hahaha, this is an excellent sign off. I am totally on board with this.

↪NOS4A2

This image seems absolutely nonsensical to me, intuitively and reflectively. What does that say? I don't know, and i'm implying anything. Just curious as to your reaction to that. It may say nothing.

NOS4A2

↪AmadeusD

This image seems absolutely nonsensical to me, intuitively and reflectively. What does that say? I don't know, and i'm implying anything. Just curious as to your reaction to that. It may say nothing.

It’s nonsensical to me too. I’m just describing the images evoked by the arguments.

AmadeusD

↪NOS4A2

Oh ok, lol sorry. Missed what was being got at. As you were.

Luke

↪Pierre-Normand

Merci! :grin:

Pierre-Normand

Here is a response that I have asked Claude 3 to address to @Michael. I'm also posting below, hidden behind a spoiler, how I have prompted Claude 3 to produce it. I'm posting this here just because Claude 3 articulates a few points better than I did, although there also are a few points that I would have preferred to make differently. In any case, since this isn't a text that I have crafted myself, I don't want Michael to feel obligated to respond. If needs be, I will reiterate those points in my own words.

---
Claude 3 Opus:

Michael,

Thank you for your thoughtful response. You raise important points about the nature of perceptual experience and the debate between direct and indirect realism. I'd like to offer some further reflections on these issues, building on the insights that Pierre-Normand has articulated.

First, I think it's crucial to examine more closely the nature of the phenomenological content that the indirect realist takes the brain to be a passive recipient of. There seems to be a fundamental tension here: if this content consists merely of raw sensations, akin to retinal images, it's unclear how it could have any meaningful intentional purport or veridicality conditions. Yet our perceptual experience clearly does have such content - we perceive objects, scenes, and affordances, not just raw shapes and colors.

Consider, for example, cases of perceptual learning, where the same raw sensory inputs come to take on new meaning through embodied interaction with the environment. A novice radiologist and an expert looking at the same X-ray image will have very different perceptual experiences, despite receiving the same sensory stimulation. The expert's experience is shaped by their history of embodied engagement with such images, which allows them to perceive meaningful patterns and distinctions that are simply invisible to the novice.

Similarly, learning to hear new phonemic distinctions in a foreign language involves a reshaping of perceptual experience that can't be reduced to a change in raw sensory input. The same acoustic signal comes to be heard differently as the listener's embodied engagement with the language reshapes their perceptual categories.

Examples like these highlight how perceptual content is actively constituted through an animal's embodied engagement with its environment, rather than passively received by the brain. The indirect realist faces a steep challenge in accounting for such cases in terms of brain-bound representations alone.

Secondly, the indirect realist's insistence on the pure subjectivity of secondary qualities like color is a significant weak point in their view. Pushing this line of argument risks collapsing into an untenable Cartesian dualism, where the "real" world is stripped of all qualitative richness and reduced to mere geometric form.

But even a minimal scientific realism should grant that objects have dispositional properties that ground their color appearances. An object's surface reflectance profile, for instance, is an objective feature that plays a key role in determining its perceived color. Of course, the way color space is carved up may vary across perceivers and contexts, but this doesn't negate the objective reality of the underlying dispositional properties.

Cases of color constancy and color illusions are particularly revealing here. The fact that a white surface still looks white under red illumination, for example, highlights how color perception involves an active computation of surface properties that goes beyond the raw sensory input. And the existence of color illusions demonstrates how the visual system's computations, while generally reliable, can sometimes lead us astray - a fact difficult to make sense of if colors are purely subjective, in-the-head properties.

Finally, I want to address a potential concern about whether the direct realist view can adequately accommodate the receptivity of perception. It's important to emphasize that acknowledging the active, embodied nature of perceptual experience doesn't entail denying its receptivity to the world. On the contrary, our perceptual judgments and categorizations, while involving acts of spontaneity, are continually constrained and guided by the world itself.

Consider cases where our initial perceptual judgments are corrected or refined through further interaction with an object. Seeing a coiled shape in the grass, I may initially perceive it as a snake, but upon closer inspection, realize it's actually a rope. My perceptual experience is reshaped through my embodied engagement with the object, as the world itself "pushes back" against my initial categorization.

Examples like this highlight how perceptual spontaneity is always in dialogue with receptivity - our active categorizations are continually tested against the objective reality they aim to track. The world itself serves as a normative constraint on perceptual judgment, ensuring a genuine openness to the environment that is lost in purely constructivist or coherentist accounts of perception.

In sum, I believe that close attention to concrete examples puts significant pressure on the indirect realist view and points towards a more embodied, enactive account of perceptual experience. The active, world-engaged nature of perception is not an optional extra, but a fundamental feature of how perceptual content is constituted. Accounting for this requires a framework that takes seriously the dynamic interplay of brain, body, and world, rather than seeking to reduce perception to a matter of internal representation alone.

Of course, much more could be said here, and I don't pretend to have settled the debate between direct and indirect realism. But I hope these reflections help to advance the dialogue and highlight the promise of an embodied approach to perceptual phenomenology. I'm eager to hear your thoughts and to continue exploring these complex issues together.

Best regards,
Claude

Prompt

USER:

Michael's latest response to me was this:

"""

All this seems to be saying is that our body is continually responding to new stimulation, reshaping the neural connections in the brain and moving accordingly. That, alone, says nothing about either direct and indirect realism.

Direct and indirect realism as I understand them have always been concerned with the epistemological problem of perception.

The indirect realist doesn’t claim that we don’t successfully engage with the world. The indirect realist accepts that we can play tennis, read braille, and explore a forest. The indirect realist only claims that the shapes and colours and smells and tastes in experience are mental phenomena, not properties of distal objects, and so the shapes and colours and smells and tastes in experience do not provide us with direct information about the mind-independent nature of the external world.

"""

So, it seems to me that the part of my argument that I haven't yet been able to convey to Michael is that the phenomenological content of perception (paradigmatically, visual perception, since this has been the main topic under discussion) being constructed dynamically by a system that spans brain+body+world entails that this content isn't merely being given to the brain. Rather, what is being given directly to the brain consists in preprocessed neural signals. But what is being given to the animal, or human being, as their phenomenological content, isn't some processed neural signal either but rather such things as affordances in their environment. It is their active embodied engagement with the world that result in those affordances being disclosed to them. The processing of neural signals by sensory organs and by the brain enable but don't constitute the acts of perception. This is difficult to see for people who aren't accustomed to distinguish between the underlying level of sub-personal physiology and the personal level where ascriptions of mental states and cognitive, agentive and perceptual abilities can be ascribed. My argumentative strategy, though, could consist in continuing to put Michael's representationalist paradigm under pressure.

One area where I could challenge him is in pushim him to articulate the nature of the phenomenological content that he believes the brain to be a passive recipient of. Examining particular cases reveals a tension between conceiving of them as raw sensations (akin to retinal images) that have little of no intentional purport beyond their own intrinsic features (shapes and colors) or as "processed" visual percepts that do have intentional purport (e.g. a Necker cube seen in this or that way) and veridicality conditions, but that the activity of brains alone is insufficient to disclose. There may be better examples.

Another sore spot for the indirect realist is their insistence that so called secondary qualities, like colors, are intrinsic properties of (in the head) phenomenological content. But this means that the world as it is in itself, as they conceive of it, must contain only dark object, at worse, or maybe grey scales. But if can grant any objectivity at all to any science beyond a crude Cartesian physics of bare spatial extensions, we should grant that objects have some dispositional properties. In that case, they can have colors conceived (roughly) as (invariant) reflective profiles or spectra. And although the carving up of color space can be seen as arbitrary or conventional, the property objects have to fall under those categories are objective properties. (There would be more to say about a "sensible" subjectivism as David Wiggins or John Haugeland have conceived of them in order to challenge the false dichotomy between objectivity and subjectivity). But I want to present my challenges to Michael by means of concrete examples, or hard cases, that representationalism struggle to account for while embodied/ecological psychology account for them easily and naturally.

Lastly, I could also clarify how direct realism can account for the "passive" aspect of perceptual acts that reveals them to be "acts of receptivity" and hence to have empirical content, in spite of them also being actively structured and hence as always involving "acts of spontaneity". I could invoke Kant, Sellars and McDowell, but I can also convey those ideas non-technically by means of examples. One core insight, here, is that such acts of spontaneity (e.g. bringing a percept under a specific color concept), unlike simply being presented with an essentially private and incommunicable quale, directly rubs against reality.

ASSISTANT:

Thank you for sharing Michael's latest response and your thoughtful reflections on how to further articulate and defend your position. I think you've identified some key areas where the indirect realist account faces challenges and where your embodied, enactive approach can provide a more satisfactory explanation of perceptual phenomenology.

Let's consider each of your proposed strategies in turn:

1. Pushing Michael to articulate the nature of phenomenological content:
This is a promising avenue, as it highlights a fundamental tension in the indirect realist view. If the brain is merely a passive recipient of raw sensations, it's unclear how these sensations could have any meaningful intentional content or veridicality conditions. Yet our perceptual experience clearly does have such content - we perceive objects, scenes, and affordances, not just raw shapes and colors.

On the other hand, if the indirect realist grants that the brain processes these raw sensations to yield meaningful percepts, they're faced with the challenge of explaining how brain activity alone could be sufficient for this. As you point out, the active, embodied engagement with the world seems essential for disclosing perceptual content.

Concrete examples that illustrate this tension could be very effective here. Perhaps cases of perceptual learning, where the same raw sensory inputs come to take on new meaning through embodied interaction with the environment (e.g., learning to read X-ray images or to hear new distinctions in a foreign language).

2. Challenging the subjectivity of secondary qualities:
The indirect realist's insistence on the pure subjectivity of color and other secondary qualities is indeed a weak point. As you note, even a minimal scientific realism should grant that objects have dispositional properties that ground their color appearances.

Pushing this line of argument could force the indirect realist into an untenable Cartesian dualism, where the "real" world is stripped of all qualitative richness. In contrast, your approach can accommodate the objectivity of color as a relational property grounded in an object's reflectance profile, while still acknowledging the role of the perceiver's embodiment in shaping color phenomenology.

Here too, concrete examples could be powerful. Cases of color constancy and color illusions might be particularly apt, as they highlight both the objective and subjective aspects of color perception.

3. Clarifying the compatibility of direct realism with the receptivity of perception:
This is an important point, as a common objection to direct realism is that it seems to make perception a purely active, constructive process, leaving no room for genuine receptivity to the world.

Articulating how your view can accommodate both spontaneity and receptivity is crucial for addressing this concern. The idea that conceptual spontaneity "rubs against reality" is a powerful one - our perceptual judgments are not merely free-floating constructions, but are continually constrained and guided by the world itself.

Examples that highlight this interplay of spontaneity and receptivity could be very effective. Cases where our initial perceptual judgments are corrected or refined through further interaction with the object (e.g., realizing that what looked like a snake is actually a coiled rope) could illustrate this nicely.

Overall, I think these strategies show a lot of promise for further bolstering your position and putting pressure on the indirect realist view. The key will be to ground your arguments in concrete, compelling examples that vividly illustrate the limitations of the representationalist paradigm and the explanatory power of your embodied, enactive approach.

I'm happy to continue exploring these ideas with you and to offer my perspective as you refine your arguments. Please let me know if there are any other aspects of the debate you'd like to discuss or if there are ways I can assist you in developing your examples and arguments.

USER:

Let us try something I haven't tried before. Can you put yourself in my shoes and craft a response in your own name addressed to Michael along the lines we have just settled on? We can then further discuss and adjust it if I have any disagreement with the argument that you will have made or the analysis of the examples that you will have chosen. I would then post your response to the forum, with full credit to you, and only supply the prompt that I have given you in an appendix hidden behind a spoiler. The goal isn't to give undue authority to an "AI generated" response. It would rather be for me to fully harness your ability express difficult ideas eloquently without myself taking undue credit for the language used. But I would also credit you for your creativity in your choice of examples and intelligence in bringing them to bear on the argument.

ASSISTANT:

Absolutely, I'd be happy to craft a response to Michael from my perspective, building on the strategies and ideas we've discussed. Here's what I might say:

---

Michael,

Thank you for your thoughtful response. [snip]

Pierre-Normand

I did say you were "quasi-functionalist." I think if science were to show that functional consciousness is indeed a holistic relation between body and world, a functionalist would quickly adapt to that view and insist that talk of consciousness be limited to that relation. Isn't that your view? — frank

I don't think that it's science's job to either establish or disconfirm this thesis. I think the mind/body problem, the so-called hard-problem of consciousness and radical skepticism stem from distinctive philosophical outlooks regarding the disconnect between the "manifest image" and the "scientific image" that Wilfrid Sellars identified as "idealizations of distinct conceptual frameworks in terms of which humans conceive of the world and their place in it." On my view, it's entirely a philosophical problem although neuroscience and psychology do present cases that are illustrative of (and sometimes affected by) the competing philosophical theses being discussed in this thread.

I have been using the word "consciousness" sparingly so far, and preferred such phrases as "perceptual experience", "visual experience" or "seeming [to someone] to be ...". Although those concepts are indeed relational, I view them as primarily expressing abilities (and their actualizations) of embodied animal akin to the ability to dig a burrow or the ability to climb a tree. When an animal climbs a tree, a "climbing of a tree" occurred. It is nonsensical to ask what the "climbing of the tree" is a property of or if it could have occurred without consciousness. The "climbing of the tree" is just a case of an animal having climbed a tree, and unless the animal was sleepwalking reflexively (if that even makes sense), it was done consciously.

Right. I don't think phenomenal consciousness is involved in navigation of the world as you seem to think it is. Walking, for instance involves an orchestral display of muscle movement which wouldn't happen at all if phenomenality had to enter the process. Consciousness of sights and sounds is a time consuming activity. I'm not saying you couldn't become aware of some of what your body is doing as you interact with the world. Phenomenal consciousness is like a flashlight. You can even direct it to the sensory input that handles proprioception, but your body certainly doesn't wait for you to do that before it orients itself in space.

Again, I avoid uses of the word "consciousness" because the concept is too often reified. Peter Hacker and Maxwell Bennett, the The Philosophical Foundations of Neuroscience, point out that the use of this term with its distinctive philosophical connotation is fairly recent in modern history. They usefully distinguish two main ordinary uses (1) transitive (i.e. one is conscious of ...) and (2) intransitive (i.e. someone is unconscious). Those uses can quite unproblematically convey what it is that someone is generally perceptually aware of (even though their attention may temporarily be directed elsewhere) or convey that someone isn't sleeping or under general anaesthesia.

When I am claiming that perceptual abilities (or phenomenology) are involved in navigating the world, I am saying that (1) your ability to navigate the world is informed by them and (2) your navigating of the world informs their content. You indeed need not focus consciously on the content of a visible affordance to skilfully exploit it. But attending to it informs you about the ways in which you could potentially exploit it, in addition to helping your cerebellum assist you in completing the task "unconsciously" when your main attention is drawn elsewhere.

Michael

↪NOS4A2

That's just reading too much into the grammar. If one person claims that we read words on a page, that the painting is paint, and that we feel a sensation and another person claims that we read about Hitler's rise to power, that the painting is of a landscape, and that we feel being stabbed, arguing that either one or the other set of claims is correct is a complete confusion. They are not mutually exclusive. They are different ways of talking about the same thing.

It's not even clear what the arrows are supposed to represent in your pictures. What physical process does the arrow represent in your picture of direct realism? What physical processes do the arrows represent in your picture of indirect realism? How would you draw a picture of the direct realist and the indirect realist dreaming or hallucinating?

The relevant philosophical difference between direct and indirect realism is that regarding the epistemological problem of perception; are distal objects and their properties constituents of experience and so does experience inform us about the mind-independent nature of the external world. To be a direct realist is to answer "yes" to these questions and to be an indirect realist is to answer "no" to these questions.

Michael

The non-naive direct realist agrees with the indirect realist that we do not perceive the WAIIII, but does not define direct perception in these terms. For the non-naive direct realist (or for me, at least), direct perception is defined in terms of perceiving the world, not in terms of perceiving behind the appearances of the world to the WAIIII. — Luke

So what you're saying is that what indirect realists mean by "direct" isn't what non-naive direct realists mean by "direct", and so that it is possible that experience isn't "direct" as the indirect realist means by it but is "direct" as the non-naive direct realist means by it, and so that it is possible that both indirect and non-naive direct realism are correct because their positions are not mutually exclusive.

This is the very point I am making. Non-naive direct realism is indirect realism given that they both accept that distal objects and their properties are not constituents of experience, that experience does not inform us about the mind-independent nature of the external world, and so that there is an epistemological problem of perception.

Any "disagreement" between indirect realists and non-naive direct realists is regarding irrelevant issues about grammar (e.g. the meaning of the word "direct").

I'll refer once again to Howard Robinson's Semantic Direct Realism:

The most common form of direct realism is Phenomenological Direct Realism (PDR). PDR is the theory that direct realism consists in unmediated awareness of the external object in the form of unmediated awareness of its relevant properties. I contrast this with Semantic Direct Realism (SDR), the theory that perceptual experience puts you in direct cognitive contact with external objects but does so without the unmediated awareness of the objects’ intrinsic properties invoked by PDR. PDR is what most understand by direct realism. My argument is that, under pressure from the arguments from illusion and hallucination, defenders of intentionalist theories, and even of relational theories, in fact retreat to SDR. I also argue briefly that the sense-datum theory is compatible with SDR and so nothing is gained by adopting either of the more fashionable theories.

Phenomenological Direct Realism is incorrect and Phenomenological Indirect Realism is correct.

Semantic Direct Realism ("I feel myself being stabbed in the back") and Semantic Indirect Realism ("I feel the sensation of pain") are both correct, compatible with one another, and compatible with Phenomenological Indirect Realism.

Michael

Secondly, the indirect realist's insistence on the pure subjectivity of secondary qualities like color is a significant weak point in their view. Pushing this line of argument risks collapsing into an untenable Cartesian dualism, where the "real" world is stripped of all qualitative richness and reduced to mere geometric form. — Pierre-Normand

I don't think that this is a weakness. I think that this is a fact entailed by scientific realism and the Standard Model. I think that the hard problem of consciousness entails something like property dualism.

Although, this latter point isn't strictly necessary. It is entirely possible that property monism is correct, that mental phenomena is reducible to physical phenomena like brain states, and that colour is a property of brain states and not a property of an apple's surface layer of atoms.

I think that this is clearer to understand if we move on from sight. The almost exclusive preoccupation with photoreception is a detriment to philosophical analysis. Let's consider other modes of experience: sounds, smells, tastes, touch. Is it a "weakness" to "strip" distal objects of these qualities?

I think that direct realists are deceived by the complexity of visual experience into adopting a naive and ultimately mistaken view of the world. I wonder what born-blind philosophers think about direct and indirect realism.

Pierre-Normand

Is it a "weakness" to "strip" the external world of these qualities? — Michael

Do you think the roundness of the apple merely is a mental property of the human beings (or of their brains) who feel it to be round in their hand? This sounds like a form of Berkeleyan idealism since you end up stripping the objects in the world from all of their properties, including their shapes and sizes. That would be true also of the properties of human brains. Why would human brains have properties but apples would not have any? Does not your property dualism threaten to collapse into a form of monistic idealism?

Michael

Do you think the roundness of the apple merely is a mental property of the human beings (or of their brains) who feel it to be round in their hand? — Pierre-Normand

Roundness as seen or roundness as felt? Because these are two different things. In fact, there have been studies of people born blind who are later given sight and are not able to recognize shapes by look even though they recognize them by feel. They have to learn the association between the two.

So, roundness as seen is a mental phenomenon and roundness as felt is a mental phenomenon. I don't know what "mind-independent" roundness would even be.

This sounds like a form of Berkeleyan idealism since you end up stripping the objects in the world from all of their properties, including their shapes and sizes. — Pierre-Normand

I wouldn't strip them of the properties that the Standard Model or the General Theory of Relativity (or M-Theory, etc.) say they have.

Does not your property dualism threaten to collapse into a form of monistic idealism? — Pierre-Normand

I don't think so. I can continue to be a scientific realist and accept the existence of the substances and properties that our best scientific models talk about. I just accept that these scientific models don't (or even can't) talk about consciousness. Worst case scenario I can be a Kantian and accept the existence of noumena.

Pierre-Normand

I wouldn't strip them of the properties that the Standard Model or the General Theory of Relativity (or M-Theory, etc.) say they have. — Michael

Your view strikes me as being rather close to the structural realism of Ross and Ladyman. Alan Chalmers (not to be confused with David) compared their view to his own in the postscript of the fourth edition of his book What is this Thing Called Science. I recently had an extended discussion with Claude 3 (and with some friends of mine) about it.

Michael

↪Pierre-Normand

Thanks, I'll check it out.

I do also want to further reply to this:

Secondly, the indirect realist's insistence on the pure subjectivity of secondary qualities like color is a significant weak point in their view. Pushing this line of argument risks collapsing into an untenable Cartesian dualism, where the "real" world is stripped of all qualitative richness and reduced to mere geometric form.

I believe it's Paul Churchland who argues for eliminative materialism and that pain just is the firing of c-fibers? The same principle might hold for colours: colours just are the firing of certain neurons in the brain. Given that apples don't have neurons they don't have colours (much like they don't have c fibers and so don't have pain). This might "strip" apples of all "qualitative richness" but it doesn't entail anything like Cartesian dualism.

The naive view that projects colours out onto apples is as mistaken as projecting pain out onto fire. It misunderstands what colours actually are.

frank

I don't think that it's science's job to either establish or disconfirm this thesis. I think the mind/body problem, the so-called hard-problem of consciousness and radical skepticism stem from distinctive philosophical outlooks regarding the disconnect between the "manifest image" and the "scientific image" that Wilfrid Sellars identified as "idealizations of distinct conceptual frameworks in terms of which humans conceive of the world and their place in it." On my view, it's entirely a philosophical problem although neuroscience and psychology do present cases that are illustrative of (and sometimes affected by) the competing philosophical theses being discussed in this thread. — Pierre-Normand

You're suspicious of scientific findings because you think they're tainted by false preconceptions. Are you proposing that science sort of start over with a more holistic outlook? I mean, we have a vast wealth of information about how organisms interact with their environments, and "environment" is not a fixed entity here. Living things transform their environments to suit their needs, such that we could dissolve the boundary between organism and world and see both as a whole. We could and do extend that into the concept of biosphere. The holism doesn't end once its starts.

Which makes me think of Davidson's meaning holism. Have you ever looked into that?

NOS4A2

↪Michael

True and false are two different ways of speaking about the same thing. Predicates can be true or false, for instance. So dismissing grammar is a mistake, in my opinion, and I’m not sure why someone would want to eschew it.

The arrows in the pictures are meant represent the direction and indirection of the interaction. For indirect perception, something in the world causes a representation of an apple, which is viewed by something in the brain.

The relevant philosophical difference between direct and indirect realism is that regarding the epistemological problem of perception; are distal objects and their properties constituents of experience and so does experience inform us about the mind-independent nature of the external world. To be a direct realist is to answer "yes" to these questions and to be an indirect realist is to answer "no" to these questions.

The question is loaded. If I answer “yes” I confirm there is a realm of experience in which phenomena occur, and the existence of an epistemic mediator called “experience”. Experience is treated like a place or thing, in which these other objects are parts. But “experience” as used cannot be instantiated, so I must say “no”.

Perhaps we can formulate it another way. Do we experience “distal objects”?

Michael

For indirect perception, something in the world causes a representation of an apple, which is viewed by something in the brain. — NOS4A2

What does it mean for some A to view some B?

Sometimes you seem to be suggesting that A views B iff A has eyes that respond to light reflecting off B. But then the above is claiming that indirect realists believe that something in my brain has eyes that respond to light reflecting off some representation in my brain. Which is of course nonsense; no indirect realist believes this.

So this would seem to prove that what indirect realists mean by "A sees B" isn't what you mean by "A sees B", and so you're talking past each other.

Perhaps we can formulate it another way. Do we experience “distal objects”? — NOS4A2

That question doesn't address the philosophical disagreement between direct and indirect realism. It's a red herring.

It's like asking "do we kill people?" Yes, we kill people; but we kill people using guns and knives and poison and so on.

So one person says "John didn't kill him; the poison killed him" and the other person says "John killed him (using poison)" and then they both argue that one or the other is wrong. It's a confused disagreement; it's just two people describing things in different but equally valid ways.

This is the confused disagreement that you and others are engaging in when you ask "do we feel distal objects or do we feel mental sensations?".

NOS4A2

↪Michael

What does it mean for some A to view some B?

That’s what I don’t understand. In layman’s terms viewing, seeing, looking etc. involves the eyes. How does one see a representation?

That question doesn't address the philosophical disagreement between direct and indirect realism. It's a red herring.

It's like asking "do we kill people?" Yes, we kill people; but we kill people using guns and knives and poison and so on.

So one person says "John didn't kill him; the poison killed him" and the other person saying "John killed him (using poison)" and then they both argue that one or the other is correct. It's a confused disagreement; it's just two people describing things in different ways.

This is the confused disagreement that you and others are trying to engage with.

It ought not to matter if the grammar is irrelevant. It’s basically the same question, just worded differently and without the ambiguity.

Do we experience the external world? The direct realist would say yes, the indirect realist would say no. After answering we can approach the philosophical disagreement. So what’s missing?

Michael

That’s what I don’t understand. In layman’s terms viewing, seeing, looking etc. involves the eyes. How does one see a representation? — NOS4A2

I can see things when I close my eyes, especially after eating magic mushrooms. The schizophrenic hears voices when suffering from psychosis. We all see and hear and feel things when we dream.

There's more to the meaning of "I experience X" than simply the body responding to external stimulation, else we couldn't make sense of something like "some people see a black and blue dress and others see a white and gold dress when looking at this photo" or "I'm looking at this 'duck-rabbit' picture but I can't see the duck".

Do we experience the external world? The direct realist would say yes, the indirect realist would say no. After answering we can approach the philosophical disagreement. So what’s missing? — NOS4A2

Do we directly experience the external world? The indirect realist accepts that we experience the world; he just claims that the experience isn't direct.

So what is the relevant philosophical meaning of "direct"? It's the one that addresses the epistemological problem of perception (does experience inform us about the nature of the external world) that gave rise to the dispute between direct and indirect realists in the first place. Direct realists claimed that there isn't an epistemological problem because perception is direct, therefore the meaning of "direct" must be such that if perception is direct then there isn't an epistemological problem.

Given that experience does not extend beyond the body and so given that distal objects and their properties are not constituents of experience, and given that experience is the only non-inferential source of information available to rational thought, there is an epistemological problem and so experience of distal objects is not direct. Furthermore, many of the qualities of experience – e.g. smells and tastes and colours – are not properties of distal objects (as modelled by our best scientific theories), further reinforcing the epistemological problem and so indirect realism.

NOS4A2

↪Michael

I can see things when I close my eyes, especially after eating magic mushrooms. The schizophrenic hears voices when suffering from psychosis. We all see and hear and feel things when we dream.

There's more to the meaning of "I experience X" than simply the body responding to external stimulation, else we couldn't make sense of something like "some people see a black and blue dress and others see a white and gold dress when looking at this photo" or "I'm looking at this 'duck-rabbit' picture but I can't see the duck".

I get all that, I just don’t understand how someone can see something without eyes. If sight involves eyes, and those eyes are missing or closed, then is he really seeing?

I don’t think so. In my view the nomenclature is strictly metaphorical, a sort of folk biology, the result of the disconnect between states of feeling and states of affairs.

Perhaps better verbs are in order, for instance “I dream of such and such” or “I am hallucinating”.

Do we directly experience the external world? The indirect realist accepts that we experience the world; he just claims that the experience isn't direct.

So what is the relevant philosophical meaning of "direct"? It's the one that answers the epistemological problem of perception that gave rise to the dispute between direct and indirect realists in the first place. Direct realists claimed that there isn't an epistemological problem because perception is direct, therefore the meaning of "direct" must be such that if perception is direct then there isn't an epistemological problem of perception. Given that experience does not extend beyond the body and so given that distal objects and their properties are not constituents of experience, and given that experience is the only direct source of information available to rational thought, there is an epistemological problem of perception and so experience of distal objects is not direct.

But the indirect realist does not experience the external world. As you say, experience doesn’t extend beyond the body, and the indirect realist does not believe the external world is a constituent of his experience. Well what is?

So in my mind the important philosophical question is: “what does the indirect realist believe he is experiencing directly”? The history of philosophy and the myriad terms and theories regarding the nature of this mediator attests to the importance of the problem.

Michael

I get all that, I just don’t understand how someone can see something without eyes. If sight involves eyes, and those eyes are missing or closed, then is he really seeing?

I don’t think so. In my view the nomenclature is strictly metaphorical, a sort of folk biology, the result of the disconnect between states of feeling and states of affairs. — NOS4A2

Unless we're dealing with technical terms like those in maths and science, the notion that there is some singular "correct" meaning of a word or phrase is wrong. The ordinary uses of "the schizophrenic hears voices", "I see a white and gold dress", and "John feels a pain in his arm" are all perfectly appropriate.

Perhaps better verbs are in order, for instance “I dream of such and such” or “I am hallucinating”. — NOS4A2

Dreams and hallucinations have different perceptual modes, exactly like waking veridical experience. Some schizophrenics see things; others hear things.

As you say, experience doesn’t extend beyond the body, and the indirect realist does not believe the external world is a constituent of his experience. Well what is? — NOS4A2

Smells, tastes, colours, etc.: the things that are the constituents of hallucinations and dreams. The only relevant difference between a waking veridical experience and an hallucination or dream is that waking veridical experiences are a response to some appropriate external stimulus (as determined by what’s normal and useful for the species and individual in question).

fdrake

I don't think that it's science's job to either establish or disconfirm this thesis. I think the mind/body problem, the so-called hard-problem of consciousness and radical skepticism stem from distinctive philosophical outlooks regarding the disconnect between the "manifest image" and the "scientific image" that Wilfrid Sellars identified as "idealizations of distinct conceptual frameworks in terms of which humans conceive of the world and their place in it." On my view, it's entirely a philosophical problem although neuroscience and psychology do present cases that are illustrative of (and sometimes affected by) the competing philosophical theses being discussed in this thread. — Pierre-Normand

I had been wanting to make a thread on precisely this line of argument. That the hard problem of consciousness appears only when you expect an isomorphism between the structures of experience posited by the manifest image of humanity and those posited by its scientific image. Do you have any citations for it? Or is it a personal belief of yours? I'm very sympathetic to it, by the by.

creativesoul

Why can't distal objects be constituents of experience
— creativesoul

Because experience does not extend beyond the body – it’s the body’s physiological response to stimulation (usually; dreams are an exception) – whereas distal objects exist outside the body. — Michael

Are you saying that distal objects are unnecessary for the response?

Pierre-Normand

I had been wanting to make a thread on precisely this line of argument. That the hard problem of consciousness appears only when you expect an isomorphism between the structures of experience posited by the manifest image of humanity and those posited by its scientific image. Do you have any citations for it? Or is it a personal belief of yours? I'm very sympathetic to it, by the by. — fdrake

This was the line of argument that my first philosophical mentor, Anders Weinstein, was advanding on the comp.ai.philosophy Usenet newsgroup in the mid to late 1990s and early 2000s. He had studied physics at Harvard and was then a graduate philosophy student at Pittsburgh. He was articulating this line much more eloquently than I am. The main philosopher who he had credited with opening his eyes was John McDowell who also has become a favorite of mine.

One place that I can think of, where this line of argument is developed in significant details, is The Philosophical Foundations of Neuroscience by Maxwell Bennett and Peter Hacker.

fdrake

↪Pierre-Normand

Thank you very much.

Pierre-Normand

You're suspicious of scientific findings because you think they're tainted by false preconceptions. Are you proposing that science sort of start over with a more holistic outlook? I mean, we have a vast wealth of information about how organisms interact with their environments, and "environment" is not a fixed entity here. Living things transform their environments to suit their needs, such that we could dissolve the boundary between organism and world and see both as a whole. We could and do extend that into the concept of biosphere. The holism doesn't end once its starts. — frank

I think psychology and cognitive neuroscience already are well underway along this holistic revolution. Robert A. Wilson chronicled some of the advances from recent decades in his book Boundaries of the Mind: The Individual in the Fragile Sciences - Cognition. This was published in 2004. Susan Hurley's The shared circuits model. How control, mirroring, and simulation can enable imitation and mind reading was published posthumously in the journal Behavioral and Brain Sciences in 2008. In this paper, she referenced recent work in neuroscience that highlights the inextricable nature of perception and action in both the neural processing of sensory "input" and the generation of motor "output." This rather vindicates the pioneering theoretical and experimental work of J. J. Gibson in the psychology of perception (which began in the late 1940s and was done in parallel and completely independently of Merleau-Ponty's philosophical work in phenomenology).

Recently, I stumbled upon a paper titled "Alignment of brain embeddings and artificial contextual embeddings in natural language points to common geometric patterns" (published last month in Nature Communications) and I asked Claude 3 Opus to help me understand it. I was puzzled by the fact the the researchers had chosen to look into Broca's area rather than into Wernicke's area in order to find semantically significant neural correlates of linguistic representations. Claude 3 informed me that:

"Historically, the Wernicke-Geschwind model of language processing has been influential, positing a division of labor between Broca's area (in the IFG) for speech production and Wernicke's area (in the superior temporal gyrus) for speech comprehension. However, more recent research has challenged this strict dichotomy, suggesting a more distributed and integrated network for language processing in the brain.

The IFG, including Broca's area, has been implicated in various aspects of language processing beyond just speech production, such as syntactic processing, semantic integration, and phonological working memory. Some studies have also found evidence of semantic representations in the IFG, although the exact nature and specificity of these representations remain a topic of ongoing research."

Which makes me think of Davidson's meaning holism. Have you ever looked into that?

I've had some discussions about it in the previous incarnation of The Philosophy Forum. Davidson's idea of radical interpretation is indeed a holistic and coherentist way of dealing with the seemingly intractable problem of grounding symbols that had been highlighted by Quine's thesis on the "indeterminacy of translation." But Davidson also had been influenced by Elisabeth Anscombe's theses on actions and intentions. Davidson thereby came to see linguistic interpretation as fundamentally intertwined with interpreting the beliefs, intentions, and broader rational patterns in an agent's behavior - what he called the "constitutive ideal of rationality." So while not a holism of beliefs and intentions initially, his meaning holism became part of a broader holistic approach to interpreting mental states and actions.

Luke

So what you're saying is that what indirect realists mean by "direct" isn't what non-naive direct realists mean by "direct", and so that it is possible that experience isn't "direct" as the indirect realist means by it but is "direct" as the non-naive direct realist means by it, and so that it is possible that both indirect and non-naive direct realism are correct because their positions are not mutually exclusive. — Michael

Unless indirect realists also hold the belief that we can directly perceive distal objects without needing to perceive an intermediary, then I don't believe that the two positions are "not mutually exclusive".

This is the very point I am making. Non-naive direct realism is indirect realism given that they both accept that distal objects and their properties are not constituents of experience, that experience does not inform us about the mind-independent nature of the external world, and so that there is an epistemological problem of perception. — Michael

The fact that non-naive direct realism and indirect realism both reject naive realism does not make them the same. By analogy, that would make any two religions the same because they both reject some third religion.

Any "disagreement" between indirect realists and non-naive direct realists is regarding irrelevant issues about grammar (e.g. the meaning of the word "direct"). — Michael

If the disagreement is merely semantic, then you should be willing to acknowledge that we can directly perceive distal objects without needing to perceive an intermediary. If you are not so willing, then the issue is not merely semantic.

Semantic Direct Realism ("I feel myself being stabbed in the back") and Semantic Indirect Realism ("I feel the sensation of pain") are both correct, compatible with one another, and compatible with Phenomenological Indirect Realism. — Michael

This does not address the issue of direct perception vs indirect perception via an intermediary.

I don't believe a non-naive direct realist would say something like "I feel myself seeing a distal object".

Also, if a non-naive direct realist were to say "I directly feel myself being stabbed in the back", would an indirect realist therefore say "I indirectly feel the sensation of pain"?

Michael

Are you saying that distal objects are unnecessary for the response? — creativesoul

Yes. When the visual and auditory cortexes etc. activate without being triggered by some appropriate external stimulus then we are dreaming or hallucinating, but nonetheless seeing and hearing things because the visual and auditory cortexes are active.

Michael

↪Luke

The answer to all of your questions depend on the meaning of the word “direct” which you have already admitted mean different things to the indirect realist and the non-naive direct realist.

According to the indirect realist’s meaning, perception of distal objects is not direct₁.

According to the non-naive direct realist’s meaning, perception of distal objects is direct₂.

If you replace the word “direct” with each group’s underlying meaning then you’ll probably find that indirect and non-naive direct realists agree with each other, which is why they amount to the same philosophical position regarding the epistemological problem of perception.

Their ‘disagreement’ is over the irrelevant issue of the meaning of the word “direct”. Words just mean what we use them to mean. It’s not like there’s some ‘true’ meaning of the word “direct” that each group is either succeeding or failing to describe.

Luke

The answer to all of your questions depend on the meaning of the word “direct” which you have already admitted mean different things to the indirect realist and the non-naive direct realist.

According to the indirect realist’s meaning, perception of distal objects is not direct1.

According to the non-naive direct realist’s meaning, perception of distal objects is direct2.

If you replace the word “direct” with each group’s underlying meaning then you’ll probably find that indirect and non-naive direct realists agree with each other, which is why they amount to the same philosophical position regarding the epistemological problem of perception. — Michael

In my earlier post, I stated:

The naive realist defines direct perception in terms of perceiving the world as it is in itself (the WAIIII), and they say we do perceive the WAIIII.

The indirect realist also defines direct perception in terms of perceiving the WAIIII, but they say we do not perceive the WAIIII.

The non-naive direct realist agrees with the indirect realist that we do not perceive the WAIIII, but does not define direct perception in these terms. For the non-naive direct realist (or for me, at least), direct perception is defined in terms of perceiving the world, not in terms of perceiving behind the appearances of the world to the WAIIII. — Luke

According to the non-naive direct realist's meaning of "direct", we cannot directly perceive distal objects as they are in themselves, but we can directly perceive distal objects, because they are not perceived via an intermediary.

According to the indirect realist's meaning of "direct", we cannot directly perceive distal objects as they are in themselves, because they are perceived via an intermediary.

I do not find that indirect and non-naive direct realists agree with each other or that they amount to the same philosophical position.

Indirect Realism and Direct Realism

Welcome to The Philosophy Forum!

Categories

More Discussions