At a node deep in the tree, AlphaZero uses a slimmed down version of itself, that is, one with less resources. You could say it uses a model of itself for planning. It may be modelling itself modelling itself modelling itself modelling itself modelling itself modelling itself. Meta-management and self-modelling are not in themselves an explanation for very much. — GrahamJ

"What is a model?" is maybe not easily answered, but this example of a "model" doesn't seem to capture the notion. The slimmed down evaluations are aproximations, but not I think models.

The idea of "model" to me is something like an informationally lossy transformation from one domain into another. A map lossily transforms from physical territory to a piece of paper. A model airplane lossily transforms from big expensive functional machines to small cheap non-functional hobby objects. Representational consciousness lossily transforms from physical reality to phenomenal representations of the world.

But a cheap and expensive evaluation function are the same kind of thing: one is just less accurate. The comparison unfairly downplays the power of models, and so of MMT.

The modeling in MMT, as I understand it, are true models: they transform from the deliberative state of the brain to a phenomenal representation of that state, which in turn informs the next deliberative "state".

Thus, the rock-based simulation and our reality are effectively the same thing. — Malcolm Lett

It's an interesting question, deserving of it's own thread. But I think this isn't right.

Strictly speaking a computer cannot simulate anything physical. It's can only simulate the physical thing's informational state. The state of a kidney peeing on your desk, but not a kidney peeing on your desk. That is why an interpreter is needed: it is state, divorced from substrate. That state piggybacks on top of the actual, embodied system: the physical computer, or rockputer. And so, the rock based simulation and our reality are fundamentally different.

But what if consciousness is itself fundamentally state? While in the physical/informational divide I very much want to place consciousness on the informational side, I don't think this is the same as saying consciousness is state. Consider that in a computer the relevant state is represented in certain memory regions. These memory regions, taken together, are just an enormous binary number. So, while counting to infinity if we reach the same number as the relevant state of a consciousness simulation, will that particular state of consciousness wink into existence? I think not.

Does that answer your question? — Malcolm Lett

Sorry for the late reply.

"Epiphenomenal" was a poor choice of words. I think I was and am at least partially misunderstanding you.

Take an example. I have the deliberation "I should go to the store today", and I am aware of that deliberation. I initially thought you would say that verbalization "I should go to the store today" would be just the summarized cognitive sense of the actual deliberation, some non-verbal, non conscious (I should go to the store today). The language would come after the deliberation, and is not the form that the actual deliberation takes.

Is this what you think? Or do you think the brain deliberates linguistically whether or not we are aware of it, and the meta management just grants awareness of the language?

my intuition is that reductive scientific methods can explain consciousness - and so a big motivation -- in fact one of the key drivers for me - is that I want to attempt to push the boundaries of what can be explained through that medium. So I explicitly avoid trying to explain phenomenology based on phenomenology. — Malcolm Lett

I absolutely agree with your intuition.

Of course, there is a difference between explaining self-awareness and explaining phenomenology. I am trying to explain self-awareness, not phenomenology, with phenomenology. Your theory is clearly an explanation of self-awareness, much less clearly an explanation of phenomenology. As you say, you have an intuition of how it might partly explain it, but struggle to articulate it.

So I wouldn't say that my theory diminishes any of that, rather that it offers a theory of just one part. — Malcolm Lett

My concern was that you were treating what we in the everyday sense term "deliberation", such as self talk, as epiphenomenal, as the "cognitive sense" corresponding to the real work happening behind the scenes. Was that a misunderstanding? Is self talk not the sort of deliberation you had in mind?

“We are survival machines – robot vehicles blindly programmed to preserve the selfish molecules known as genes. This is a truth which still fills me with astonishment.”
― Richard Dawkins, The Selfish Gene

“I’m a robot, and you’re a robot, but that doesn’t make us any less dignified or wonderful or lovable or responsible for our actions,” Daniel Dennett said. “Why does our dignity depend on our being scientifically inexplicable?” — Wayfarer

These are expressions of physicalist reductionism, but this doesn't entail the more drastic reduction to "the 4 Fs".

F***king, of course, but as a rule I avoid profanity. — Wayfarer

Aw, I had a few more Fs lined up.

here have recently been some quite convincing virtual reality attempts to help humans what cats see, hear what bats hear, etc. — Vera Mont

Oh? I work in the VR space, I'm interested in this. Do you have a link?

Of course, we can make a stab at mapping the sensory ranges of other species onto our own. But this doesn't truly give us the slightest idea of what it is actually, subjectively like to be another animal.

Come on now. — Lionino

Oh! :yikes: Of course, "father".

summarised as 'the four F's' (Feeding, fighting, fleeing, and reproduction.) — Wayfarer

Fecundating? Or fertilizing?

Incredible op!!! :sparkle: You have clearly poured a lot of thought into the matter, to great effect. I will read your blog post next, and your paper is on my list. I've had similar ideas, though not nearly at your level of depth and detail.

I think where we most sharply differ is in the nature of deliberation.

In your account, deliberation is something that chugs along on its own, without awareness. It is only via a meta management process that a predictive summation enters awareness.

But this is at odds with my introspective account of deliberation. Deliberation itself seems to be explicitly phenomenal: I speak to my self (auditory), and this self talk is often accompanied by imagery (visual). The conscious brain seems to speak to itself in the same "language" that the unconscious brain speaks to it: the language of sensation.

Is your idea that phenomena such as self talk is a model of the unconscious deliberation that is actually taking place? This does not seem to do justice to the power that words and images have as tools for enabling thought, not just in providing some sort of executive summary. Think of the theory that language evolved primarily not for communication but as a means of enabling thought as we know it. Can meta management explain the gargantuan cognitive leap we enjoy over our nearest animal neighbors?

If deliberation is phenomenal, then there is no need for this meta management process. Deliberation enters awareness in a manner that is co-equal with the phenomenal models of the external world. If deliberation goes off the rails, then the executive brain can regulate it, since deliberation is at least partially voluntary.

The evolutionary novelty enabling deliberation would be the ability of the executive brain to insert phenomenal models into it's own inputs. This explains the relative feebleness of especially visual imagery: the same predictive modeling systems used by sensation are *not* reused by the executive brain. Rather, it (sometimes quite crudely) mimics them. Audio, being less information dense, is more amenable to this mimicry.

Since the cost/benefit ratio of this change seems very favorable, we should expect at least crude deliberation to be widespread in nature. Adding language as a deliberative tool is where the real cognitive explosion happened.

Here is a rough sketch of my alternative take. (I see I used "rumination" for "deliberation". )

remove duplicates online

The second part of my argument is that the sort of competence that we acquire to perceive those invariants aren't competences that our brains have (although our brains enable us to acquire them) — Pierre-Normand

I find this notion very problematic. When we learn anything, we are training our brains to acquire new competences. Not any other organ. Even though, to learn necessarily involves interaction with the environment.

When we learn to play the piano it is not our fingers that are becoming more clever, but our brains. When we learn to see, our brain, not our eyes, gains the competence to process sensory inputs in such a way that the phenomenological experience of the world we are familiar with is possible. Damage to the occipital lobe of the brain, not to other parts of the body, renders us blindsighted.

I would say that illusions and hallucinations are phenomenal experiences, instead of saying that they are the consequences of phenomenal experiences — Luke

I'm not saying that they are the consequences of phenomenal experience. I'm saying that mediation makes illusions and hallucinations possible, mediation is the condition for the existence of perceptual errors. This is most clear to me with hallucination: without the meditating layer of phenomenal experience, we simply couldn't hallucinate.

I think the issue is that people misleadingly think of this as being the distinction between direct and indirect realism: — Michael

Nice, I wish this could be stickied at the top of every page of this thread. You made it?

As the MIT roboticist Rodney Brooks once argued, the terrain itself is its own best model - it doesn't need to be re-represented internally — Pierre-Normand

I thought this was curious, so I looked it up. It is mentioned in this article:

https://www.technologyreview.com/2019/08/21/133411/rodney-brooks/

“The world is its own best model,” Brooks wrote. “It is always exactly up to date. It always contains every detail there is to be known. The trick is to sense it appropriately and often enough.”

The inspiration:

“I’m watching these insects buzz around. And they’ve got tiny, tiny little brains, some as small 100,000 neurons, and I’m thinking, ‘They can’t do the mathematics I’m asking my robots to do for an even simpler thing. They’re hunting. They’re eating. They’re foraging. They’re mating. They’re getting out of my way when I’m trying to slap them. How are they doing all this stuff? They must be organized differently.’

This is the inventor of the Roomba, which to me tells you everything you need to know. Which is not to put him down the slightest bit. He had the insight everyone else missed: Everyone trying to build robots implicitly had the idea of modelling higher animals. But why do this? This is not the path evolution took. Why not instead draw inspiration from vastly simpler creatures, who do not model at all?

This is what I proposed as the meaning of "direct perception", to contrast with indirect perception:

Think of an amoeba, light hits a photo receptor, and by some logic the amoeba moves one way or the other.If you regard this as "perception", then this is direct perception — hypericin

Human brains, on the other hand, fine tuned by millions of years of evolution and equipped with unmatched computational power, are modelers par excellence. We are not organized like insects, who respond directly to the environment. We build models, and then respond to the models. And phenomenal experience is exactly those models. It is nothing less than a virtual world, and the basis for all of our decisions and actions.

In their manner of responding intelligently to their environment human brains powerfully leverage the same principle of indirection we see everywhere in engineering.

This is known as Fundamental theorem of software engineering:

All problems in computer science can be solved by another level of indirection

This was the first part of my argument against indirect realism. — Pierre-Normand

Then, your first part was an argument against a straw man, since an indirect realist can (and should, and does, imo) agree that phenomenological content is only accessible following all neural processing.

One question: why did the brain adjust for color constancy in the cube picture but not the snow pictures?

Direct realists believe that we perceive external objects whereas indirect realists believe that we perceive internal objects. You continue to avoid this difference between the two views by claiming that they are the same view. — Luke

Again, if we do not perceive/experience/have awarenesw of internal objects, what are we perceiving/experiencing/aware of when we hallucinate? External objects?

And yet you argue that we can never know if the smell of smoke indicates that there is smoke (or that one perceives smoke), due to the possibility of illusion, hallucination or error. — Luke

If we know it, to "know" must accommodate a degree of uncertainty. If it does not, we don't know it.

Naive realism and indirect realism are both based on the presupposition that there is a “correct” way to perceive the world, which is to perceive the world as it is in itself. Naive realism supposes that we do perceive the world as it is in itself. Indirect realists oppose naive realism based on the possibility of illusion, hallucination or error. — Luke

No, indirect realism does not presuppose a correct way of seeing the world. There is no such thing as correctly perceiving the world as it is in itself. Rather, the best we can do is derive true propositional content about the state of the world. via perception.

Indirect realism opposes direct realism based on the fundamental meditative role brain-produced phenomenal experience plays in our contact with the world. Illusion, hallucinations, and error are consequences of, and are only possible because of, this mediation.

If this presupposition is rejected, then it is no longer a question of whether or not we perceive the world as it is in itself directly, but a question of whether or not we perceive the world directly. The latter does not require a superhuman form of perception that can infallibly see "behind" the appearance of the world, but simply a form of perception that provides an appearance of the world, fallible or not. — Luke

That contact with the world is mediated by an appearance that is itself not the world can only mean that contact with the world is indirect. The fact that direct contact with the world is not possible does not constitute an argument against this.

You seem want to argue that because direct, immediate experiential contact with the world is impossible and even incoherent, therefore, there is direct, immediate experiential contact with the world. No, if unmediated experience of the world is impossible, experience of the world is therefore mediated.

I like the examples you (and Claude) have been giving, but I don't seem to draw the same conclusion.

I don't think indirect realism presupposes or requires that phenomenal experience is somehow a passive reflection of sensory inputs. Rather the opposite, a passive brain reflecting its environment seems to be a direct realist conception. These examples seem to emphasize the active role the brain plays in constructing the sensory panoply we experience, which is perfectly in line with indirect realism.

For instance, in the very striking cube illusion you presented, we only experience the square faces as brown and orange because the brain is constructing an experience that reflects its prediction about the physical state of the cube: that the faces must in fact have different surface properties, in spite of the same wavelengths hitting the retina at the two corresponding retinal regions.

That such a thing could happen at all is only possible if our sensory experience is an interpretive construction. And if it our experience of the world is via an interpretive construction, our experience of the world is surely not "direct".

And none of these examples demonstrate that phenomenological experience does not supervene on brain states. Rather, we can be sure that the brain states corresponding to the two perceived colors are different from that induced by the same scene without the shadow. That is because brain states don't dumbly correspond to raw sensory inputs but are reflections of the brain's active, predictive powers.

You can't say that it doesn't matter if these are indistinct, because otherwise your position becomes direct realism. If the "taste" and your "awareness of the taste" were indistinct then there would be no intermediary and they would both be directly of the object.

In other words, you claim that we have indirect awareness of external objects because our awareness is mediated by our perceptual experience, but you also find no problem in collapsing the distinction between our awareness of our perceptual experience and our perceptual experience. If you collapse this distinction, then you lose the indirectness. — Luke

Even if you collapse the distinction, there are still two awarenesses: object awareness, and perceptual experience, which is itself awareness. Object awareness is still mediated by perceptual experience: we are only aware of objects because of perceptual experience (which we are also aware of, as perceptual experience is awareness).

It is indirect realists who seem to think it is impossible for our perceptions to be veridical, and this seems to be because we either do not perceive the world "correctly" or because we cannot know whether we perceive the world "correctly". — Luke

"Correct", "Veridical", or not, is the wrong framing.

Consider a live TV broadcast. The images you see may veridical, they may accurately depict the reality that was being filmed. Or, it may be doctored in various ways, or may be manufactured from whole cloth, by AI perhaps. The focus is not on whether the broadcast is correct or not. Clearly, sometimes it is. But rather, the mediation that is the TV is what the indirect realist focuses on. Without this mediation, the kind of non-veridicality TV's enable would be impossible.

Similarly, perceptual experience might sometimes accurately reflect reality, in perceptual experience's own terms. But all our contact with reality is entirely framed in terms of perceptual experience, which itself is wholly the mind's construct. In the same way, any contact you have with the reality "behind" the TV is literally framed by the construct that is the TV.

Where I disagree with you is in your apparent view that perception is merely "a passive reception of sensory data", which awaits our awareness (or not). I find it difficult to separate this view from the homunculus view. — Luke

This is not my view. I am noncommittal as to the nature of awareness of perceptual experience. What I am committed to is that perceptual experience and awareness of objects are two different things.

I am fine with this formulation:
Awareness of objects is mediated by perceptual experience, the notion of which is inclusive of awareness of itself.

Regarding the disagreement about what indirect realism is, ChatGPT decisively favors my interpretation. However, we (or at least I) have apparently been misusing the phrase "mental representation". According to ChatGPT, this refers to a pre-conscious mental state, not qualia itself. Which is confusing, since (at least I maintain) that qualia themselves are mental represntaitons.

User
Please clarify a response that another instance of you gave to a user:
1. How were you defining "experience" here? As "qualia", "contact with the world", or something else?

2. Which of these two formulations better captures what you mean by indirect realism. "Awareness of the world is mediated by representations or ideas, which we experience as qualia?" Or, "Qualia are mediated by representations or ideas"?

Another User
what is indirect realism

Another ChatGPT
Indirect realism, also known as representationalism or epistemological dualism, is a philosophical theory regarding perception and reality. It posits that our experiences of the world are mediated by mental representations or ideas, rather than directly perceiving external objects themselves.
According to indirect realism, when we perceive the world, what we are actually experiencing are mental representations or perceptions that are caused by external objects. These mental representations are often considered to be in the mind and are distinct from the external objects they represent.
In other words, indirect realism suggests that we do not directly perceive external objects such as tables, chairs, or trees. Instead, we perceive representations or perceptions of these objects that are constructed by our senses and mental processes. This theory acknowledges that there is a real external world but asserts that our understanding and experience of it are indirect and mediated by mental representations.
One of the key proponents of indirect realism was the philosopher John Locke, who argued that the mind receives sensory information from the external world and constructs perceptions based on this information. Other philosophers, such as George Berkeley and David Hume, also contributed to the development of indirect realism, albeit with variations in emphasis and interpretation.

ChatGPT
1. In the context of the response, "experience" is defined as the mental representations or perceptions that are caused by external objects. This aligns more closely with the concept of "contact with the world" rather than "qualia". Qualia refers to the subjective or qualitative properties of experiences, such as what it feels like to see a particular color or to taste a specific flavor. In contrast, the "experience" referred to in the response is about the process of perceiving and interpreting sensory information from the external world.

2. The first formulation, "Awareness of the world is mediated by representations or ideas, which we experience as qualia," better captures the meaning of indirect realism as described in the response. This is because indirect realism posits that our awareness or perception of the world is mediated by mental representations or ideas. These representations or ideas are what we experience, and they can be associated with qualia, which are the subjective or qualitative properties of these experiences. The second formulation, "Qualia are mediated by representations or ideas," seems to suggest that qualia themselves are mediated, which is not the primary focus of indirect realism.

User
To point 1, expand on the differentiation between "mental representation" and qualia. To my understanding, qualia are mental representations of the exernal world.

ChatGPT
Sure, I'd be happy to clarify the distinction between "mental representations" and "qualia".

"Mental representations" and "qualia" are both concepts used in philosophy and cognitive science to describe aspects of our mental life, but they refer to different things.

Mental representations are a theoretical construct used to explain how the mind represents information about the world. They are often thought of as internal models or maps of the world that our mind uses to guide our interactions with our environment. For example, if you see a chair, your mind forms a mental representation of that chair, which includes information about its shape, size, color, and location.

Qualia, on the other hand, refers to the subjective or conscious experience of the world. It's the "what it's like" aspect of conscious experience. For example, the redness of a red apple, the sweetness of a candy, or the pain from a headache are all examples of qualia. These are subjective experiences that are difficult to describe or convey to others because they are inherently personal and subjective.
While mental representations are about the information content of our mental states, qualia are about the subjective quality of our conscious experiences. In the context of indirect realism, mental representations are the internal models or maps that our mind uses to interpret sensory data, while qualia would be the subjective experience of those representations.

So, while it's true that qualia are a kind of mental representation in the sense that they represent aspects of our subjective experience, not all mental representations are qualia. Some mental representations might be unconscious or lack a subjective quality, and thus would not be considered qualia.

User
Can the qoute "Instead, we perceive representations or perceptions of these objects that are constructed by our senses and mental processes." be rephrased as ""Instead, we are aware of representations or perceptions of these objects that are constructed by our senses and mental processes." to make clear that awareness of perceptions is itself not an act of perception?

ChatGPT
Absolutely, your rephrasing is a valid interpretation and helps to clarify the concept. Here's how it would look:
"Instead, we are aware of representations or perceptions of these objects that are constructed by our senses and mental processes."
This statement emphasizes that our awareness is not a direct perception of the external world, but rather an awareness of the mental representations or perceptions that our senses and mental processes construct. This aligns with the core idea of indirect realism, which posits that our understanding and experience of the world are indirect and mediated by these mental representations.

Busy, apologies for the late reply.

Your inability to discern the illusion doesn't stem from a failure to spot some inner difference in qualia, but from the mirror's efficacy in disrupting your engaged, bodily perspective on your surroundings. — Pierre-Normand

I'm not sure why these are exclusive. If there were a discernable difference; for instance, if the mirror had dirt or surface flaws; you could discern the qualitative difference, and therefore your "engaged, bodily perspective" would not be disrupted. The only reason the mirror is able to disrupt engagement is is that it presents a view of the apple that is not discernable from a veridical view.

This raises a deeper question for the common-factor theorist: if perceptual experience is just a matter of inner sensations or representations caused by some stimulus, what makes it a perception "of" anything in the external world at all? What are the conditions of satisfaction that determine whether a perceptual experience is veridical or not — whether it matches mind-independent reality?

The common-factor view seems to lack the resources to answer this question. There's no way to directly compare an inner perceptual representation with an outer state of affairs to see if they match. Representational content and veridicality conditions can't be grounded in purely internal phenomenal character. — Pierre-Normand

I don't see this as a problem. The common factor theorist, presumably an indirect realist, would simply say that there is no fool proof way to establish veridicality. That veridicality is established by inference and probabilistic reasoning, and so is never 100% certain. The fact that challenges to veridicality such as simulation theories can never be put to rest attest to this.

The disjunctivist, in contrast, can ground perceptual content and veridicality in the perceiver's embodied capacities for successful interaction with their environment. Consider the experience of seeing an apple as within reach. On the disjunctivist view, the phenomenal character of this experience isn't exhausted by an inner sensation or mental image. Rather, it consists in your very readiness to engage with the apple — your expectation that you can successfully reach out and grasp it. — Pierre-Normand

This expectation is presumably also identical in the real and hallucinatory case. Only the fact of the matter, whether in fact the apple is actually in reach, differs. But this is not a part of the phenomenal experience.

The common-factor theorist, in treating perceptual content as purely internal and independent of bodily skills, misses this crucial difference. They can't account for the world-involving, normative character of perception — the fact that our experiences inherently refer beyond themselves to the environment, and can match or fail to match reality. — Pierre-Normand

Why can't we account for this? Perceptions either bear a certain relationship to the world, or they do not. The disjunctivist seems to want to solve the problem of hallucination by folding this relationship to the world into the perception itself. But then they have to solve the problem of explaining why this relationship, while part of the perception, is not actually discernable as part of the perception.

For the indirect realist, I'm not understanding the problem. Perception and the world may or may not be related in such a way that makes the perception veridical. How you define this relationship is another matter. Suppose you define it such that the "perception must match the subject's embodied capacities for successful interaction with their environment". This definition of the relation does not erase the distinction between the perception and the world. By the argument from hallucination, identical perceptions independently may or may not fulfill this relationship.

Sorry for the late reply, I've been busy with work.

The definition of indirect realism offered by ChatGPT states that our experiences (presumably our perceptual experiences) are mediated by mental representations or ideas. It contrasts this with "directly perceiving external objects themselves", i.e. direct realism. — Luke

The quote from ChatGPT:

It posits that our experiences of the world are mediated by mental representations or ideas, rather than directly perceiving external objects themselves.

"Experience" here is certainly not what we have been calling "perceptual experiences", aka qualia. Merriam-Webster's definition of experience:

the fact or state of having been affected by or gained knowledge through direct observation or participation

In other words, our contact with the world is mediated by mental representations or ideas. This is indirect realism. Not "that our perceptual experiences of external objects are mediated by mental representations or ideas". I can't even make much sense of that formulation, let alone defend it. Perceptual experience is the mediation between the self and the world, and is a mental representation.

Reading through the GPT definition, I see little substantive difference with my own.

You seem to agree with the direct realist that perceptual experience of external objects is direct (or you don't appear to argue for an intermediary between them). — Luke

Perceptual experience is "direct", because there is no intermediary between the self and perceptual experience, not because there is no intermediary between perceptual experience and external objects. Again, perceptual experience is the intermediary.

However, if your perceptual experience is, e.g., the taste of strawberries, then is your awareness of the taste of strawberries different to your perceptual experience of the taste of strawberries? — Luke

The "taste" and the "awareness of the taste" verbally designate parts or aspects of what may be the same thing: the perceptual experience of tasting strawberries. As I've said before, my argument does not hinge on these being ontologically distinct things.

How does the perceptual experience mediate the awareness? — Luke

The perceptual experience mediates the awareness of the strawberry. Not of the taste.

You said earlier that a perceptual experience entails awareness of that perceptual experience; that it entails its own awareness. In that case, what does awareness of the perceptual experience add to the perceptual experience that the perceptual experience itself lacks? — Luke

It only points out the awareness. I regard "awareness of the strawberry is mediated by awareness of the taste of strawberry" and "awareness of the strawberry is mediated by the taste of strawberry" to be identical formulations. The word "awareness" is just a useful word sometimes, i.e. "I am aware of perceptual experience", instead of the confusing "I experience perceptual experience" or the ungrammatical "I am perceptual experience" and is preferable to "perceive" and "see", which have unwanted connotations.

However, if perceptual experiences are merely "representational" without being "representations" — Luke

How can something be representational without being a representation?

Direct perceptual experiences are representations.
The representations are of real objects.
Therefore, Direct perceptual experiences are representations of real objects.
and
"Direct perceptual experiencs" are of real objects
but not
"Direct perceptual experiences" are directly of real objects
I would rather say
"Direct perceptual experiences" are indirectly of real objects
because
Representational experience is indirect experience of the represented.

They're not type identical. — jkop

Whatever type is, it is not phenomenal.

But what this means, according to the disjunctivist, is that the subject isn't able to identify a feature from their experience that would enable them to discriminate between both cases (veridical or non-veridical). — Pierre-Normand

So is the implication that there is a hidden feature in the subject's own phenomenological experience that the subject is unable to discern?

For a disjunctivist the seeming experience of ammonia caused by viral damage to the olfactory organ is not identical to the experience of ammonia. — jkop

Not identical in what way?

A disjunctivist would not accept your first premise and, also, would state their thesis somewhat differently. It's actually a core claim of the disjunctivist conception of experience that a hallucinatory experience (or an illusion or misperception) and a veridical experience are two different things, — Pierre-Normand

It might be that in some ontological sense they are different. But what I meant by the first premise is that from the first person, phenomenological point of view, the experiences are subjectively identical. In that sense, there is no room to deny the first premise, it is a stipulation, and not implausible.

And in the non-veridical case, or in a case of misperception, the subject falsely believes that they are seeing a red apple. — Pierre-Normand

What makes the cases indistinguishable isn't a common object that is being directly perceived in both cases. — Pierre-Normand

If you take "object" literally, everyone agrees that there isn't a common directly perceived object. But there must be something that is in common between the two cases. And it can't just be a shared belief that there is an object being perceived.

Sue is recovering from Covid, and sometimes she falsely smells ammonia in the air. As far as she can tell, out of nowhere she experiences the same subjective sensation she does when she opens a jar of ammonia. If it were only the belief that there is ammonia in the air that is common in the two cases, then Sue is lying or fooling herself, she is not really experiencing anything, or she is experiencing something that is somehow different. But why believe that? Why can't she expereince ammonia when there is none? Moreover, how do you account for the case where Sue knows there is no ammonia, but still feels she is experiencing that identical smell?

those high-level processes can't be segmented — Pierre-Normand

Why?

the physiological basis of perception is indirect, in a sort of causal sense — Pierre-Normand

Indirect realism doesn't necessarily appeal to physiological processes. The fundamental distinction is between the qualitative first person experience of the world, and the world itself. The intuition is that if the components of this first person experience are all mind products, the relationship between perceiver and perceived is fundamentally indirect. I'm not sure why perception is too "molar" to make this distinction.

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. — Pierre-Normand

Disjunctivism feels like a weak, hand-wavy response to particularly the argument from hallucination. Here is my take on that argument:

Assume a hallucinatory experience of an object is identical to a veridical experience of the same object. So for every property x of that object,
Eh(x) = Ev(x)
If the object is a red ball, the experience of redness is the same:
Eh(red) = Ev(red)
For direct realism, in the veridical case te experience of an object's redness is that object's redness:
Ev(red) = Obj(red)
But in the halliucinatory case, the experience can not be of that object's redness
Eh(red) != Obj(red)
But we already stipulated that
Eh(red) = Ev(red)

Therefore direct realism is contradictory, and disjunctivism is an inadequate defense

(b) the mind is entirely the result of physical processes in the brain, which means you can't have a physically working brain with all the bells and whistles of a human brain, without also having consciousness - the proverbial zombie is impossible. — flannel jesus

This seems compatible with epiphenomenalism though.

I asked ChatGPT whether the argument is valid — Luke

Apologies, I see my mistake. I was focusing on the argument when I should have focused on the conclusion. This is what initiated this thread:

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. — Luke

I deny that the premises entail:
direct perceptual experience of real objects

You counter by affirming that the premises entail:
"direct perceptual experience” is of real objects.

These look somewhat similar but are totally nonequivalent. The conclusion I deny says that the perceptual experience of real objects is direct. This is just direct realism. They conclusion you affirm says that direct perceptual experience, aka phenomenal experience, merely is of real object. But this is innocuous, and compatible with direct and indirect realism: the direct realist says it is directly of real object, and the indirect realist says it is indirectly of real objects.

ou treat the perceptual experience not as part of your experience, but as an independently objective smell that you may or may not be aware of. This was your earliter attempt to separate your awareness of your perceptual experience from your perceptual experience:... — Luke

This was not me making any ontological claims, I don't need to. I was only defining the terms I use. If it turns out that awareness and the experience are two aspects of the same thing, no problem.

(Another) User
"true or false: Unless you can have indirect awareness of your perceptual experiences, then it makes no sense to say that you have direct awareness of your perceptual experiences. The "direct" qualifier has no contrast, so it doesn't mean anything."

(Another) ChatGPT
"The statement is true. In philosophical discourse, the concept of "direct awareness" typically implies an immediate, unmediated apprehension of something. However, to establish the notion of direct awareness, there must be a contrasting concept, such as indirect awareness. If there is no possibility of indirect awareness, then the qualifier "direct" loses its meaning because there is no alternative mode of awareness to contrast it with. So, without the possibility of indirect awareness, the term "direct awareness" becomes vacuous."

User
But, what if direct awareness of your perceptual experiences" is contrasted with "indirect awareness of the external world"? Is it then sensible to refer to awareness of your perceptual experiences as direct?

ChatGPT
Yes, in that case, it would be sensible to refer to awareness of your perceptual experiences as "direct."
The term "direct" in "direct awareness of your perceptual experiences" is used to denote an immediate, unmediated apprehension of your perceptual experiences. This is contrasted with "indirect awareness of the external world," where your awareness of the world is mediated by your perceptual experiences.
In this context, "direct" and "indirect" serve as contrasting qualifiers that give meaning to each other. Therefore, even if there is no indirect awareness of your perceptual experiences, the term "direct awareness" still retains its meaning because it is contrasted with "indirect awareness of the external world."
So, the statement "Unless you can have indirect awareness of your perceptual experiences, then it makes no sense to say that you have direct awareness of your perceptual experiences" would be false in this context.

P1: We are aware of perceptual experiences. — hypericin

Therefore, via substitution into P2, the perceptual experience is of real objects. — Luke

This doesn't work. What if I had rephrased P2 with the equivalent:

P2. If the representation represents real objects...

Then your substitution yields "Direct phenomenal experience represents real objects". If this is logically valid, how can inconsequential differences in how the premises are phrased yield totally different results?

Therefore, the perceptual experience cannot be "the smell itself", acting as an independently objective smell that you may or may not be aware of. — Luke

Whether or not it is an independently objective smell that you may or may not be aware of (I don't think it is), all that is necessary to my argument is that we are aware of it.

But I think a stronger argument against your view... — Luke

Talking about awareness, awareness of perceptual experience is direct, awareness of real world objects is indirect. A clear contrast, I don't see the problem.

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. — Luke

"A representation is of real objects" is a nonsensical claim. A representation may be of anything. Rather, "the representation is of real objects". "The" means we are talking about the representation in "Phenomenal experience is a representation". You cannot then substitute in "phenomenal experience" for "representation" in "the representation is of real objects", because that sentence is modifying the representation in "phenomenal experience is a representation"..

The two sentences are equivalent to "phenomenal experience is a representation of real objects". That sentence s definitely not equivalent to "phenomenal experience is of real objects".

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

Yes. The perceptual experience may necessarily entail the awareness, as we discussed earlier. But all that is required for my argument is that we are aware of it.

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

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.

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?

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 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.

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?

@Luke

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).


We agree on P2. So do you challenge P1, P4, or both?

I see no inconsistency in maintaining that although the content of our perceptual experiences consists of representations, those perceptual experiences are of real world objects. — Luke

"I see no inconsistency in maintaining that although the content of the photograph consists of representations, the photograph is of real world objects."

No one here is doubting that the photograph is of real world objects. But does that mean the photograph gives you direct experience of the real world objects?