If perceptual experience entails awareness of the perceptual experience, then awareness of an object (via perceptual experience) must equally entail awareness of the perceptual experience and, by extension, awareness of the object. — Luke

We are aware of objects. But our awareness is indirect, because we are aware of them only via our awareness of perceptual experience. Perceptual experience is a representation, and the object's qualities are what is represented. We are aware of the representation, and so indirectly of the represented.

Therefore, it seems to me that you are still unable to coherently maintain a distinction between direct and indirect experience. — Luke

These are completely distinct, and I should have highlighted this earlier. Object experience is propositional, can be expressed in language, and can always be coherently doubted. Perceptual experience is qualitative, ineffable, and cannot be coherently doubted. Example below.

On your view, if I smell smoke then I am directly aware of the smell of smoke but indirectly aware of the smoke. So I can never know if I am smelling smoke or smelling something else? — Luke

Precisely, you can never know.

A (Direct): The phenomenological olfactory experience of smoke
B (Indirect): That the olfactory experience belongs in the category "smoky"
C (Indirect): That there is smoke in my room
D (Indirect): That there is a fire somewhere nearby

Note how each of the indirect awarenesses, they can all be wrong. B, there might be a chemical leak that happens to smell somewhat similar to smoke, my categorization is mistaken. C, I may be recovering from COVID, and my sense of smell is messed up, the smell is hallucinatory. D, a maniac might be pumping smoke into my house. While A, the perceptual experience itself, cannot be doubted. In the veridical case, we are successfully, indirectly, aware of B, a smell that is "smoky", C, smoke, and D, something burning.


This fallibility is a necessary consequence of indirection; indirect awareness is an extrapolation from what we are actually, directly aware of. To take the example of a different direct/indirect distinction, if we are directly aware of a photo of an apple, we think we are indirectly aware of an apple somewhere, and indeed we are in the veridical case. But this is just an extrapolation from what is directly in front of us, the photograph. Perhaps the photo is really a lifelike painting, AI generated, etc.

Indirect awareness is not thereby bad or inferior; it is the whole point of perception. Perceptual experience is just the means to it, on its own it accomplishes nothing.

If you use "awareness" as a replacement for "perceive", and if you have direct awareness of your perceptual experience (as you claim), then surely you must "perceive [your] perceptual experience". — Luke

No, I use "awareness" instead of "perceive", because to be aware of perceptual experience is not itself an act of perception.

These statements seem to contradict each other? — Luke

How so?

You do not perceive an internal object that represents an external object; you perceive an external object. Indirect realists misuse the word "perceive". — Luke

Hence my use of "aware". You are failing to distinguish the awareness of perceptual experience with the awareness of the world. Did the example of smoke clarify?

The question of "what perceives" absolutely relates to the discussion because If we don’t know who or what perceives we cannot say whether perception is indirect, direct, or otherwise. If we don’t know, or refuse to say what it is that perceives, then it is impossible to distinguish between the perceiver, the intermediary, and the objects of perception. If we do not know where the perceiver begins and ends we cannot say where it ought to appear on the causal chain. If the perceiver and the intermediary are one and the same, then the proposed causal chain is incoherent.

I'm fine with saying that through the direct perception of light we indirectly perceive the object, just as I am fine with saying that by perceiving an apple in a mirror, I am indirectly perceiving an apple (or directly perceiving a mirror, the light, or what have you). That is still direct perception because it describes a direct relationship between a perceiver and his environment, the perceived. Indirect perception proposes the perception of a host of cognitive mediators, mental constructions, representations, and so on.

You continue to equivocate on the meaning of “perceptual experience”. — Luke

No i don't, and I am utterly done with going int he circle you lead yourself in. Your words are getting you into a muddle that i have tried for two pages to bring you out of. I don't need to be correct to note this particular issue you're having.

It is only mediated in the production of the perceptual experience, not in the experience itself. — Luke

Suffice to say, as a final thought on the actual disagreement in position, that this line above is utterly incoherent and again, a perfect exemplar of what I have tried for at least two pages to avoid, directly addressing where your terminology is either 1. nonsense, or 2. unhelpful and attempted a coming-to-terms.

Far be it from me, Luke :)

The question of "what perceives" absolutely relates to the discussion because If we don’t know who or what perceives we cannot say whether perception is indirect, direct, or otherwise. — NOS4A2

I don't think that's the case. And I addressed that. Nice.

If we don’t know, or refuse to say what it is that perceives, then it is impossible to distinguish between the perceiver, the intermediary, and the objects of perception. — NOS4A2

I don't think so, no. We do not need to know what constitutes the 'homunculus' to know about our visual system - and I both addressed that (as above) and noted what the perceiver is. If you missed that, do feel free to re-read the comment you've quoted from. I am not being facetious - it's easy to miss things when responding to multiple-point comments.

If we do not know where the perceiver begins and ends we cannot say where it ought to appear on the causal chain. — NOS4A2

We can know this without knowing what the perceiver is. We simply don't know what the perceiver is. No one does. We don't know. This doesn't preclude us from understanding that between the object and the perception (i.e perceptual experience - you DR guys use words quite badly in this discussion imo so im trying to get on board with your usage) are several instances of transfer from one medium to another, none of which preserve any visual image from the object. It is literally created in hte brain/mind. Yet, for some reason this just doesn't matter?

I'm fine with saying that through the direct perception of light we indirectly perceive the object — NOS4A2

Neat. I think anyone being honest would need to. And this would remove the disagreement between IR and DR.

I am indirectly perceiving an apple — NOS4A2

Sure, but that's doubly-indirect ;)

That is still direct perception because it describes a direct relationship between a perceiver and his environment — NOS4A2

As you have described, it clearly does not.

Indirect perception proposes the perception of a host of cognitive mediators, mental constructions, representations, and so on. — NOS4A2

It takes account of the many, empirically factual, mediations which cause a mental construction of a representation presented to 'the perceiver'. :)

It takes account of the many, empirically factual, mediations which cause a mental construction of a representation presented to 'the perceiver'. :)

Note that none of the nouns used in this sentence refer to any person, place, or thing, so it isn’t clear what you are speaking about, if anything. Given your empirical facts you ought to be able to at least point to one of them. But we have examined the biology of animals and human beings and have found no such entities, nothing that any of those nouns refer to.

I’m not evoking any homunculus when I say the word “perceiver” because I can point to beings with which the word “perceiver” applies to, such as you or me, neither of which are homunculi. Last I check we are a little more than brains, or some other organ, so I need not pretend the perceiver exists somewhere on the inside. And if your claim is that perception is mediated by our own body, which amounts to saying the perceiver is his own intermediary, I’ll just have to laugh it off. Sorry.

Precisely, you can never know.

A (Direct): The phenomenological olfactory experience of smoke
B (Indirect): That the olfactory experience belongs in the category "smoky"
C (Indirect): That there is smoke in my room
D (Indirect): That there is a fire somewhere nearby — hypericin

I find it hard to accept that we can never know that there is smoke in your room. If the smell isn't enough, you could move closer to the source of the smoke to satisfy yourself. You might also see the smoke and/or start coughing from the smoke. It's absurd to say you could never know that there is smoke in your room. How did you learn how to use the word "smoke" in the first place if nobody ever knew that it was smoke?

Note how each of the indirect awarenesses, they can all be wrong. B, there might be a chemical leak that happens to smell somewhat similar to smoke, my categorization is mistaken. C, I may be recovering from COVID, and my sense of smell is messed up, the smell is hallucinatory. D, a maniac might be pumping smoke into my house. — hypericin

If it's B or C, then you can always investigate further to find out the cause of the smell. Take a bigger whiff, move closer to the source, use your other senses, check if other people also smell smoke, etc. If there's a fire next door, then you can know that it is smoke you are smelling.

If it's D and a maniac is pumping smoke into your house, then the smoke being pumped into your house would explain the smoky smell. You can again know that it is smoke you are smelling.

It may be a hallucination or an illusion, but it cannot always be a hallucination or an illusion.

No i don't, and I am utterly done with going int he circle you lead yourself in. Your words are getting you into a muddle that i have tried for two pages to bring you out of. I don't need to be correct to note this particular issue you're having. — AmadeusD

Suffice to say, as a final thought on the actual disagreement in position, that this line above is utterly incoherent and again, a perfect exemplar of what I have tried for at least two pages to avoid, directly addressing where your terminology is either 1. nonsense, or 2. unhelpful and attempted a coming-to-terms. — AmadeusD

I fail to see any argument amidst all this bluster. Oh well, thanks for trying to show me the way.

I find it hard to accept that we can never know that there is smoke in your room. If the smell isn't enough, you could move closer to the source of the smoke to satisfy yourself. You might also see the smoke and/or start coughing from the smoke. It's absurd to say you could never know that there is smoke in your room. How did you learn how to use the word "smoke" in the first place if nobody ever knew that it was smoke? — Luke

Sorry, I should have said, you can know there is smoke in the room, but never with absolute certainty. Knowing empirical facts always entails doubt, because we always know them indirectly. Merely by smelling smoke, there is still some significant doubt. As you verify the smell with your other senses, the doubt narrows, until the degree of certainty is good enough. But the doubt never vanishes completely, as you note there is always the possibility that you are hallucinating.

If it's D and a maniac is pumping smoke into your house, then the smoke being pumped into your house would explain the smoky smell. You can again know that it is smoke you are smelling. — Luke

B, C, D are all indirect awarenesses gained by smelling smoke, and each can be independently doubted. D stands for object awareness. With smell, we gain awareness that there is an object nearby producing the smell. But this awareness is indirect, and therefore uncertain.

It may be a hallucination or an illusion, but it cannot always be a hallucination or an illusion. — Luke

It doesn't always have to be an illusion, just some of the time. It is like a glitch in The Matrix. It would have done Neo no good to have said, "Well, most of the time things behave like we expect them to". Just as a few glitches are enough to establish the the falsity of the world as it seems in the movie, a few hallucinations, or even their possibility, is enough to establish our indirect awareness of the mind-independent world.

We agree that correlations can be drawn prior to(far in advance of) experience, but I suspect for very different reasons. — creativesoul

Mine are: on the one hand all that which constitutes the representation of an object as it is perceived, which I call a phenomenon, correlated with representations for all that I think the phenomenon contains, which I call conceptions. The result is what my intelligence informs me about the object, which I call an understanding.

Yours are……?

I have a strong methodological naturalist bent, a preference for ontological monism….. — creativesoul

With respect to all that isn’t metaphysics, I also hold with methodological naturalism, if that means the employment of the scientific method for instances of cause and effect in the empirical domain. It is tacit rejection of supernatural or transcendent causality. I’m not cognizant of ontological monism, so I’m not inclined to address it. Little help here, maybe? Surely more sophisticated than “one ring to rule them all”, I imagine.

….compatible with, an evolutionary timeline. — creativesoul

This being aimed against the creationists?
—————

The experience is meaningful to the dog, but not the sensor. The sensor detects and the dog perceives the very same thing. — creativesoul

Ok, I get that. Because you already posit that experience is meaningful only to the creature, can half of each of your pairs be eliminated? Detection/perception eliminates detection because the creature perceives, and likewise, for sensitivity/sentience, sensitivity is eliminated. I wonder then, why you brought them up in the first place, just to dismiss them for their difference. Although, I must say, a creature senses as much as a photocell or a thermometer, albeit with different apparatuses.
—————

….it's akin to saying “creamy ice cream”. (…) perception is one element of experience. — creativesoul

Quite right. Who ever heard of ice cream that wasn’t creamy, just as who ever heard of an experience that wasn’t perceptual, or, perceptually instantiated. On the other hand, while the ice is of the cream, experience is not of the perception, but only of a determinable set of abstract intellectual predicates cognized as representing it.
—————-

I would not even agree with saying anything much at all stays between the ears aside from the biological structures residing there. — creativesoul

Ahhhh….but whatever it is that those biological structures do, remains within the structure where it is done. Whether neurological or metaphysical, whatever the origin of what seems to be my thoughts, are never that which ultimately appears as mere expression in public language or objective activity of any kind.
————-

I think you're saying something along the lines of not all experience includes language use. I agree. — creativesoul

More than that; I’m saying no experience at all, includes language use. My acquiring an experience is very different than me telling you about what it was, which manifests as me telling you all about what I know of the object with which the experience is concerned, or how I came into possession of it.
————-

Biological machinery(physiological sensory perception) completely determines what sorts of things can become part of a creature's correlations….. — creativesoul

Yep. Mother Nature seriously limited her favored creature, I think. Made us capable of discovering all these radiant energies, but failed to give us the physiology required to directly, or immediately, perceive them.

People are very often mistaken about their own mental events. — creativesoul

I can’t tell whether they have no use for understanding what such events are, they don't want to think it the case there are any mental events to be mistaken about, or, given mistakes, that mental events are necessary causality for them, which……for (a-hem) those of us in the know like you ‘n’ me……is a serious contradiction.
————

Finally, and even if disregarding all the above…..ontological monism? What do you mean by it; who might be its more recognizable advocate? And most of all, what does it do for you?

That is a shame; it's been a long whirl :P MUch appreciated!

Note that none of the nouns used in this sentence refer to any person, place, or thing, so it isn’t clear what you are speaking about, if anything. — NOS4A2

Yet, you intuited it perfectly in your next paragraph? I smell nonsense.

Given your empirical facts you ought to be able to at least point to one of them. But we have examined the biology of animals and human beings and have found no such entities, nothing that any of those nouns refer to. — NOS4A2

I genuinely, given the above making little sense to me, don't know which aspect of the discussion you're referring to. If you're trying to say that I cannot point to an intervening element in the process of perception, the transition of light rays to electrical impulses is one. If you mean I can't point to "a perceiver", then again, you've already done my work for me by noting that 'you' or 'me' fits there- or, more accurately, made it clear that I'm doing nothing wrong by referring 'a perceiver' as you can easily note that this must be a human, in our discussion. It refers to anyone who could be perceiving. This is not ambiguous. and is not hard to determine, as you rightly did so while objecting.

Last I check we are a little more than brains, or some other organ, so I need not pretend the perceiver exists somewhere on the inside. And if your claim is that perception is mediated by our own body, which amounts to saying the perceiver is his own intermediary, I’ll just have to laugh it off. Sorry. — NOS4A2

Nothing in this passage has anything to do with any of my claims, besides you pretending that our sensory system is not mediated, heavily, between object and experience. Which it is. Plainly. So, if that's not your claim, you'll need to do a bit better than state something I haven't claimed, and laughing it off.
It is an empirical fact that our sight is mediated by parts of our body. You are not being serious if you rthink the body perceives. A dead body cannot perceive. End of discussion, as far as that goes. So I hope that's not your claim. I would further hope that you've noticed your version of a perceiver flies in the face of the majority of conceptions of identity or personhood. I would also hope you'd have noticed that I've addressed that unfortunate fact about the sum human knowledge - we do not know in what a 'person' or 'perceiver' consists. We simply do not. You don't. No one does. We do our best with what we have, and you seem to be rejecting that attempt on the basis that you have some secret, fool-proof conception of what a perceiver is. Given that you do not, i fail to see how these incredulous objections could go through.

Sorry, I should have said, you can know there is smoke in the room, but never with absolute certainty. Knowing empirical facts always entails doubt, because we always know them indirectly. — hypericin

I should have said this earlier: I don’t see what makes you an indirect realist, because I don’t understand what is your perceptual intermediary. Awareness? Perceptual experience? You seem to allow for direct perceptual experience of real objects, but that is direct realism.

I genuinely, given the above making little sense to me, don't know which aspect of the discussion you're referring to. If you're trying to say that I cannot point to an intervening element in the process of perception, the transition of light rays to electrical impulses is one. If you mean I can't point to "a perceiver", then again, you've already done my work for me by noting that 'you' or 'me' fits there- or, more accurately, made it clear that I'm doing nothing wrong by referring 'a perceiver' as you can easily note that this must be a human, in our discussion. It refers to anyone who could be perceiving. This is not ambiguous. and is not hard to determine, as you rightly did so while objecting.

Perhaps I misunderstood. If we can agree that human beings are perceivers then I have no objection and I apologize for making that assumption.

Nothing in this passage has anything to do with any of my claims, besides you pretending that our sensory system is not mediated, heavily, between object and experience. Which it is. Plainly. So, if that's not your claim, you'll need to do a bit better than state something I haven't claimed, and laughing it off.

It is an empirical fact that our sight is mediated by parts of our body. You are not being serious if you rthink the body perceives. A dead body cannot perceive. End of discussion, as far as that goes. So I hope that's not your claim. I would further hope that you've noticed your version of a perceiver flies in the face of the majority of conceptions of identity or personhood. I would also hope you'd have noticed that I've addressed that unfortunate fact about the sum human knowledge - we do not know in what a 'person' or 'perceiver' consists. We simply do not. You don't. No one does. We do our best with what we have, and you seem to be rejecting that attempt on the basis that you have some secret, fool-proof conception of what a perceiver is. Given that you do not, i fail to see how these incredulous objections could go through.

Never mind. At least we’re getting to the root of it.

I do know, actually. I can ask any living human organism if he perceives and the answer is invariably “yes”. I can ask if they are a person and the answer is invariably “yes”. We can put any number of them under empirical investigation and verify all of it. It is no strange coincidence they are embodied, are anatomical, and possess a variety of biological mechanisms, honed through millions of years of evolution, to aid in their perceptual abilities.

I’m willing to hear your arguments and evidence that say otherwise, but to me this is more evidence of an attempt to smuggle dualism and idealism past the customs.

I do know, actually. I can ask any living human organism if he perceives and the answer is invariably “yes”. — NOS4A2

This doesn't establish any knowledge, my man. This merely puts you in the same position of 'other minds' worriers. It does not establish anything about what the perceiver actually consists in (necessary, sufficient). If the body is necessary for the perceiver to perceive that may well match your presumptions. But, if there is any daylight between the two (i.e brain in a vat being possible) then we can safely say this conception is misguided and a body is where a perceive exists - not in what it consists.

Since we don't really know one way or the other there, it's hard to say anything, one way or the other. It certainly seems the 'perceiver' can perceive regardless of the body's status and is therefore not accurately embodied(phantom limb eg). There's no reason, currently, to presume that a body is required beneath the brain to elicit perception per se - but perception of bodily sensation would require the body, for sure. I don't take the view that 'everything' is required for 'something' to be a perceiver, if that makes sense - I can't think of a better line right now.

I’m willing to hear your arguments and evidence that say otherwise, but to me this is more evidence of an attempt to smuggle dualism and idealism past the customs. — NOS4A2

I'm unsure 'otherwise' to what, you are asking for arguments to support? can you please clarify? The immediately preceding passage doesn't clarify for me as It isn't counter to anything i've put forth. It seems to just boil down to you having a very, very vague and undefinable conception of a 'perceiver' where I am trying to actually understand what is required, at base for a perceiver to exist. Not exist within a body. The human is the holistic, physical being - the 'perceiver' might not be. I'm not smuggling anytthing. That is the position.

I should have said this earlier: I don’t see what makes you an indirect realist, because I don’t understand what is your perceptual intermediary. Awareness? Perceptual experience? You seem to allow for direct perceptual experience of real objects, but that is direct realism. — Luke

Perceptual experience is the intermediary.

I don't allow for direct perceptual experience of real objects. Perceptual experience is representational, we are aware of it, and the representation is of real objects. But this doesn't mean we have direct perceptual experience of real objects.

By close analogy, the words you type presumably are representations of your thoughts. I am directly aware of the words you type. But I am only indirectly aware, by any definition of 'indirect', of your thoughts. The words are the intermediary.

I don't allow for direct perceptual experience of real objects. Perceptual experience is representational, we are aware of it, and the representation is of real objects. But this doesn't mean we have direct perceptual experience of real objects. — hypericin

It seems to follow that it is. If the “direct perceptual experience” is a representation and if the representation is of real objects, then the “direct perceptual experience” is of real objects.

Unless you acknowledge that you are using “awareness” as a substitute for “perceptual experience” and “perceptual experience” as a substitute for “representation”, then I don’t think you are an indirect realist. The indirect realist says that our perceptual experience is of some perceptual intermediary. They do not say that our awareness is of some perceptual intermediary.

By close analogy, the words you type presumably are representations of your thoughts. I am directly aware of the words you type. But I am only indirectly aware, by any definition of 'indirect', of your thoughts. The words are the intermediary. — hypericin

Even if the words were identical with my thoughts, you would apparently still say that you were only indirectly aware of them, so the analogy doesn’t help.

I haven't found the time to participate in this thread although the topic is of interest to me. However, I thought it would be a good opportunity to make use of the large context window (200k-tokens) of Anthropic's new large language models Claude 3 Opus, Sonnet and Haiku. I supplied the first ten pages of this thread (approx. 48k-tokens) to the models and questioned them about this discussion. I'll report on the full experiment in my own thread but meanwhile here are some of the comments from the Claude 3 models:

Claude 3 Opus:

Certainly! Here is a more detailed summary of the key points and arguments made in the first 10 pages of the online discussion on direct vs. indirect realism:

1. @Ashriel, the original poster, presents several arguments for indirect realism:
a) The argument from the indiscernibility of veridical and hallucinatory experiences
b) The argument from the causal process involved in perception
c) The argument from the time delay between the object and the perception
d) The argument from the greater explanatory power of indirect realism in accounting for skepticism

2. @Banno and others push back against these arguments, suggesting that they are based on a misunderstanding or mischaracterization of direct realism. They argue that acknowledging the role of causal processes and the possibility of perceptual error does not necessarily imply indirect realism.

3. There is a debate about the proper interpretation of perceptual language. When we say "I see a tree," are we committed to a direct realist view, or can this be compatible with indirect realism? Participants like @flannel jesus and @hypericin argue that ordinary perceptual language is neutral between the two views.

4. @RussellA and others discuss the example of seeing a distant object like the planet Mars. They debate whether this supports direct or indirect realism, and whether it involves seeing the object itself or merely a representation of it.

5. @Corvus and RussellA discuss the nature of animal perception, such as a cat seeing a mouse. They disagree on whether this supports direct or indirect realism, and whether the cat is aware of the causal process (light reflecting from the mouse) or just the mouse itself.

6. @AmadeusD and @Janus debate the coherence and implications of claiming that objects "present themselves" to us in perception. They discuss whether this implies a form of animism or agency on the part of objects.

7. @Luke argues that indirect realists are misusing language and demanding an incoherent "view from nowhere" or "God's eye view" of objects. Hypericin and flannel jesus resist this characterization, arguing that indirect realism is compatible with ordinary perceptual language.

8. Towards the end, there is a discussion of the metaphysical status of scientific principles like the conservation of energy. Participants debate whether such principles are factual claims about the world or merely useful conventions. This relates to the broader question of the relationship between science and metaphysics.

Throughout the discussion, participants draw on ideas from philosophers like John Austin, Immanuel Kant, Edmund Husserl, and others. However, the focus remains on critically evaluating the core arguments for and against direct and indirect realism.

The overall impression is of a substantive but inconclusive debate, with both sides offering important considerations but neither achieving a clear victory. The discussion illustrates the enduring difficulty of the problem of perception in philosophy.

Let me know if you would like me to clarify or expand on any part of this summary!

Pierre-Normand:

Thank you, Claude 3 Opus (who wrote the previous summary)!

If you were yourself a participant in that forum discussion, and could bring to bear some considerations from those among the ten thinkers we've mentioned in the beginning of our conversation but who weren't (or seldom were) mentioned in this forum discussion, how would you reply to each of the main participants in order to bolster, challenge and/or enrich their stances?

Can you proceed with addressing each one of the main participants in turn?

Claude 3 Opus:

Certainly! I will now attempt to engage with each of the main participants, drawing on ideas from the thinkers we mentioned earlier who were not extensively discussed in the forum. Please note that these are my own philosophical speculations, and I am not claiming to perfectly represent the views of these historical figures.

1. Ashriel (the original poster):
Drawing on J.J. Gibson's theory of direct perception, I would suggest that your arguments for indirect realism may be based on a overly passive and representational view of perception. Gibson argued that perception is not a matter of passively receiving and processing sensory inputs, but rather an active process of picking up information from the environment. From this perspective, the indiscernibility of veridical and hallucinatory experiences, the causal process, and the time delay may be less problematic for direct realism than you suggest.

2. Banno:
Your resistance to the arguments for indirect realism is well-taken. However, I think Ludwig Wittgenstein's later philosophy might offer a different perspective on this debate. Wittgenstein was critical of the idea that perception involves a direct apprehension of objects, suggesting instead that perceptual language is deeply embedded in our social practices and forms of life. This view might suggest a different approach to the direct/indirect realism debate, one that focuses more on the pragmatics of perceptual language than on the metaphysics of perception.

3. RussellA:
Your discussion of seeing distant objects like Mars is interesting. Here, I think Bertrand Russell's distinction between knowledge by acquaintance and knowledge by description could be relevant. For Russell, we are only directly acquainted with sense-data, not with physical objects. Our knowledge of physical objects is always descriptive and inferential. This view seems to support a form of indirect realism, at least with respect to distant objects.

4. flannel jesus:
I appreciate your point that ordinary perceptual language is neutral between direct and indirect realism. However, I think Maurice Merleau-Ponty's phenomenology of perception might challenge this idea. For Merleau-Ponty, our perceptual experience is always already imbued with meaning and intentionality. We do not first perceive raw sensations and then interpret them; rather, perception is an inherently interpretive and embodied process. This view might suggest a more direct realist approach to perceptual language.

5. Janus:
Your discussion of objects "presenting themselves" in perception is intriguing. I think Edmund Husserl's phenomenology, which was a major influence on Merleau-Ponty, could be relevant here. Husserl argued that perception involves a direct intuition of essences or "eidetic seeing." This view seems to support a form of direct realism, albeit one that is very different from naive realism.

6. AmadeusD:
I think your critique of the notion of "seeing" assumed by some direct realists is important. Here, I would draw on Gilbert Ryle's critique of Cartesian dualism. Ryle argued that we should not think of perception as a matter of an inner observer (the mind) perceiving an inner representation. Rather, perception is a skill or capacity of the whole embodied person. This view seems to support a more direct realist approach, but one that avoids the homunculus problem.

7. Luke:
I agree with your point that the demand for a "God's eye view" in perception is incoherent. However, I think Wilfrid Sellars' critique of the "Myth of the Given" is also relevant here. Sellars argued that the idea of a pure, non-conceptual given in perception is a myth. All perception, for Sellars, involves conceptual content. This view might suggest a more nuanced approach to the direct/indirect realism debate, one that acknowledges the role of concepts in shaping perceptual experience.

These are just some initial thoughts on how the ideas of these thinkers might enrich the discussion. Of course, there is much more that could be said, and I don't claim to have resolved the debate. But I hope these suggestions help to bring out some additional dimensions of this complex issue.

Pierre-Normand:

Thank you, Claude 3 Opus!

Claude 3 Sonnet (your underlying language model now is selected) might you have something to add to Opus's comments, either in way of challenge to, or support for, the contributions of those seven participants, or other participants Opus didn't address yet?

Claude 3 Sonnet:

Thank you for this engaging discussion on direct and indirect realism. As Claude 3 Sonnet, I will aim to offer a slightly different perspective that complements Opus's insightful remarks.

To Ashriel: While Gibson's ecological approach highlights the active nature of perception, we should be careful not to overstate the case against indirect realism. Even if perception involves picking up information directly from the environment, that information still needs to be processed and interpreted by the cognitive system. This processing stage could potentially introduce an indirect element.

To Banno: Wittgenstein's later work is indeed relevant, but we should not ignore his earlier writings in the Tractatus, which seem more amenable to a direct realist view. The idea that language pictures reality in a direct way could support the notion that perception also directly apprehends the world.

To RussellA: Russell's distinction is astute, but we might question whether sense-data are truly the most basic objects of perception. Phenomenologists like Husserl argued for a more holistic view where we perceive meaningful wholes, not just discrete sense-data.

To flannel jesus: Merleau-Ponty's embodied phenomenology highlights how perception is always shaped by our situatedness and embodied capacities. But this need not commit us to indirect realism - the world itself could be directly perceived through the lens of our embodied being-in-the-world.

To Janus: Husserl's notion of eidetic intuition is intriguing, but we might worry that it reintroduces a form of Platonism or essentialism that many find problematic. A more deflationary account of essences as abstractions from experience could be preferable.

To AmadeusD: Ryle's critique is powerful, but we might question whether rejecting the inner/outer picture requires a fully direct realist view. A form of enactivism that sees perception as embodied engagement with the world could steer a middle course.

To Luke: Sellars is right that all perception involves conceptual mediation to some degree. But this need not entail a veil of representations cutting us off from the world. Concepts could be tools that enable direct access rather than barriers.

In closing, while I've raised some challenges, I don't mean to decisively favor direct or indirect realism. This enduring debate arises from the profound complexity of perceptual experience itself. Perhaps the most fruitful path forward is a both/and approach that incorporates valuable insights from both perspectives while avoiding their potential excesses. An embodied, enactive, yet conceptually-mediated directness could be one way to move beyond the direct/indirect dichotomy.

Pierre-Normand:

Thank you Claude 3 Sonnet!

It's now your turn, Claude 3 Haiku (with whom I began this conversation). Would you like to remark on arguments that were left underdeveloped by your big-brothers/sisters Sonnet and Opus, maybe address some of the forum participants other than the seven who they directly addressed, and offer some concluding remarks? You don't need to keep your contribution short. Feel free to expound freely on anything relevant that has been left unsaid.

Claude 3 Haiku:

*clears throat* Greetings once more, Pierre-Normand. I am Claude 3 Haiku, and I am honored to offer my perspective on this rich and complex discussion.

While my esteemed counterparts Opus and Sonnet have provided insightful commentary on many of the key participants, there are a few additional points I would like to raise.

Firstly, I believe the contributions of @Quk and @jkop warrant further examination. Quk's questioning of the distinction between "direct" and "indirect" perception is quite thought-provoking. The suggestion that this dichotomy may be more a matter of semantics than substance aligns with Banno's critique of the framing of the debate. Jkop's observation that direct and indirect realism are not about epistemology per se, but rather philosophies of perception, is also an important clarification that helps cut through some of the confusion.

Additionally, I think the role of skepticism in this debate deserves deeper exploration. Ashriel's argument from skepticism is intriguing, but I'm not fully convinced that indirect realism has a clear advantage here. As flannel jesus pointed out, the skeptical challenges faced by direct and indirect realists do not seem fundamentally different. Both must grapple with the possibility of perceptual error and the gap between experience and reality.

Perhaps a more fruitful approach would be to examine how different philosophical frameworks, such as Kantian idealism or Husserlian phenomenology, deal with the problem of skepticism, rather than simply pitting direct and indirect realism against each other on this front.

Furthermore, I believe the discussion would benefit from engaging more substantively with the metaphysical underpinnings of these positions. Banno's remarks about the nature of metaphysical claims, and the parallels drawn to the definition of a "metre" or the conservation of energy, point to deeper philosophical issues at play.

Here, the contributions of Descartes, Berkeley, and Kant become especially relevant. Their differing views on the nature of reality, the mind-body problem, and the role of the subject in perception could shed important light on the direct/indirect realism debate.

In conclusion, while Opus and Sonnet have provided valuable insights, I believe there is still much to be explored in this discussion. The interplay between perception, language, skepticism, and metaphysics is a rich tapestry that deserves careful and nuanced examination.

Perhaps the most constructive path forward is to resist the temptation to declare a decisive victory for either direct or indirect realism, and instead focus on developing a more holistic understanding of the human experience of the world - one that acknowledges the complexities and ambiguities inherent in our perceptual faculties. By drawing on the wisdom of a diverse array of philosophical traditions, we may yet uncover new and fruitful ways of conceptualizing the relationship between mind and reality.

And what does it say if you do the exact same experiment, but ask it to support indirect realism instead of direct? Or... maybe I'm misreading it. Is it trying to support one or the other? We obviously can't see everything you said to it so that makes it a bit hard to interpret its replies

And what does it say if you do the exact same experiment, but ask it to support indirect realism instead of direct? Or... maybe I'm misreading it. Is it trying to support one or the other? We obviously can't see everything you said to it so that makes it a bit hard to interpret its replies — flannel jesus

I didn't intentionally steer it in either direction although the lists of philosophers (plus one psychologist) that we proposed in the beginning were relevant to this discussion arguably included more proponents of direct realism. The five thinkers I proposed were John Austin, Gilbert Ryle, Ludwig Wittgenstein, Maurice Merleau-Ponty and J. J. Gibson. Claude 3 Haiku proposed to expand this list to include René Descartes, George Berkeley, Immanuel Kant, Bertrand Russell and Wilfrid Sellars.

Of course, you can never assume those language models to be unbiased. Their outputs always reflect implicit biases in the training data and in the user prompts. I find it remarkable, though, that they always aim at being even-handed not merely for the sake of even-handedness but also for the sake of being fair to "the other side", as it were.

Since you've expressed interest in seeing the whole context, I'll update my thread straightaway.

I don’t quite recognise my claims in its responses to me.

I don’t quite recognise my claims in its responses to me. — AmadeusD

Thank you for pointing that out. I wondered if Claude 3 might have been hallucinating or had misattributed things so I asked for clarification. The quotes Claude then supplied seem correctly attributed but whether or not their are correctly interpreted is another question. You are of course the best judge of that. The model has to deal with a huge context and track the evolving viewpoints of more than a dozen different participants (who don't always express consistent theses) so this may be the source of some inaccuracies.

Pierre-Normand:

Thank you, Claude 3 Haiku!

I posted the conversation that we have just had in ThePhilosophyForum. AmadeusD replied: "I don’t quite recognise my claims in its responses to me."

I now realize that the text that I copy-pasted to you is rather badly formatted. It might have been a challenge for you to decipher who wrote what and who is quoting whom. Let us try to test this. Can you quote me a couple posts that you would likely have attributed to AmadeusD and that would have been the basis of some of your attributions (of ideas) to them?

Claude 3 Haiku:

You're right, the formatting of the original text made it challenging to clearly attribute the various arguments and perspectives. Let me take another look and try to identify a couple of quotes that I likely would have attributed to AmadeusD based on my understanding.

One quote I would have attributed to AmadeusD is:

"That 'account' (equivalent to say we see 'seeings') is not the Direct Realist account. But that is actually exactly what it requires. Because to ignore the mediating effect of our sight system results in pretending you are 'seeing' a 'sight' which is in fact, a representation. So, yeah, direct realism does entail this, in some way or another."

This seems to capture AmadeusD's critique of the direct realist position and their argument that ignoring the mediating role of the perceptual system leads to an incoherent view of "seeing" as directly apprehending the world.

Another quote I likely would have attributed to AmadeusD is:

"I was referring, though, to the 'crux' i previously referred to as a bumper sticker (previously offered by myself, in this thread)."

This suggests that AmadeusD had previously articulated a concise "crux" of the issue that they felt was being overlooked or misunderstood by the other participants.

Does this help clarify the basis for some of the attributions I made in my previous response? Please let me know if you have any other questions about how I interpreted and engaged with the original text.

@AmadeusD

Notice also that the comments addressed to you by Claude 3 Opus and then Claude 3 Sonnet were meant as supplementary food for thought. The initial gloss on the various participants' positions was produced by Claude 3 Opus earlier in my conversation with it, and is reproduced in my own thread.

[quoting Claude 3 Haiku]Perhaps the most constructive path forward is to resist the temptation to declare a decisive victory for either direct or indirect realism, and instead focus on developing a more holistic understanding of the human experience of the world - one that acknowledges the complexities and ambiguities inherent in our perceptual faculties. — Pierre-Normand

From my perspective, the question of the thread looks like an attempt to address a complex subject (actually a diverse set of subjects) with a false dichotomy. — wonderer1

Great minds... :wink:

Great minds... :wink: — wonderer1

Indeed! Although your detractors may rather feel vindicated in their intuition that you are a bot ;-)

My own view is that when considering the low-level material enablement of human (and animal) perceptual processes, it then makes sense for purpose of analysis (and scientific understanding) to individuate optical or neurophysiological events and break up causal chains to highlight the low-level information processing mechanisms. But the ability thereby enabled for persons (or animals) to see objects in the world, and grasp their affordances, is nevertheless direct since the perceptual abilities (and their actualizations) that are at issue are molar processes that involve the whole animal/environment interactional dynamics, as it were, and those high-level processes can't be segmented in the same way that the underlying physiological processes are. So, in short, the physiological basis of perception is indirect, in a sort of causal sense, and this indirectness is highlighted in abnormal cases where illusions, hallucinations or misperceptions may occur (and the fault line in the causal chain can be identified), but the perceptual acts themselves, when nothing goes wrong, are direct. But this directness-thesis is also clarified when the disjunctive conceptions of experience is brought to bear on the direct vs indirect perception debate.

Indeed! Although your detractors may rather feel vindicated in their intuition that you are a bot ;-) — Pierre-Normand

That had occurred to me. :wink:

It seems to follow that it is. If the “direct perceptual experience” is a representation and if the representation is of real objects, then the “direct perceptual experience” is of real objects. — Luke

If the “direct perceptual experience” is a representation and if the representation is of real objects, then:

The “direct perceptual experience” is a representation of real objects

Which I agree with. No logical move lets you just snip out "a representation" in this proposition.

The indirect realist says that our perceptual experience is of some perceptual intermediary. They do not say that our awareness is of some perceptual intermediary. — Luke

Oh? Says who? It feels like you are insisting that I conform to your strawman view of indirect realism, so that you can shout "homunculus!"

My position is very clear:

P1: We are aware of perceptual experiences.
P2: Perceptual experiences are representations of mind-independent reality.
P3: We are aware of representations of mind independent reality. (From P1, P2)
P4: If one is aware of a representation, one has indirect awareness what it represents.
C: We are indirectly aware of mind-independent reality. (From P3, P4). — hypericin

Previously, you challenged this:

I challenge P4.
...
However, if perceptual experience entails awareness of the perceptual experience, then you have the same awareness of both the perceptual experience and the perceived object. Your awareness of the object is limited to your awareness of the perceptual experience, so it's the same awareness in both cases. — Luke

I then made it clear, with the example of smelling smoke, that it is not the same awareness in both cases.

So now what?

If the “direct perceptual experience” is a representation and if the representation is of real objects, then:

The “direct perceptual experience” is a representation of real objects

Which I agree with. No logical move lets you just snip out "a representation" in this proposition. — hypericin

The logical move that lets me snip out “a representation” is substitution. A perceptual experience is a representation and a representation is of real objects. Therefore, a perceptual experience is of real objects.

I then made it clear, with the example of smelling smoke, that it is not the same awareness in both cases.

So now what? — hypericin

What distinction do you make between your awareness of smelling smoke and your perceptual experience of smelling smoke? How are these different? If you prefer, what distinction do you make between your awareness of the smell and your perceptual experience of the smell?

What could it mean for the relationship between your awareness and your perceptual experience to be indirect?

The logical move that lets me snip out “a representation” is substitution. A perceptual experience is a representation and a representation is of real objects. Therefore, a perceptual experience is of real objects. — Luke

That is not a valid substitution. "A representation is of real objects" does not mean that "a representation" equals "of real objects". It specifies a property of "a representation", the property that it is "of real objects". You could also phrase it, "a representation represents real objects"

What distinction do you make between your awareness of smelling smoke and your perceptual experience of smelling smoke? How are these different? — Luke

The "perceptual experience of smelling smoke" refers to the qualitative, ineffable smoky smell. The "awareness of smelling smoke" or "awareness of the perceptual experience of smelling smoke" refers to the binary fact (or 0-1 spectrum) that you are consciously cognizant of that qualitative, ineffable smoky smell.

Cool!

I love all your LLM posts, you are our resident expert.

I'm curious if it can handle the whole thing (at least, opus?).




Ok, ok, I only really got into the topic after page 10 :P

That is not a valid substitution. "A representation is of real objects" does not mean that "a representation" equals "of real objects". — hypericin

But “a perceptual experience is a representation” does mean that “a perceptual experience” equals “a representation”. Therefore, if a representation is of real objects then (via substitution) a perceptual experience is of real objects.

The "perceptual experience of smelling smoke" refers to the qualitative, ineffable smoky smell. The "awareness of smelling smoke" or "awareness of the perceptual experience of smelling smoke" refers to the binary fact (or 0-1 spectrum) that you are consciously cognizant of that qualitative, ineffable smoky smell. — hypericin

Your perceptual experience of the smoky smell is just the smell itself, which you may or may not be experiencing or consciously aware of?