I don't even know what "I like Ice cream" means when I think it, let alone say it. It is expressed and heard as a process which will have an effect. — ENOAH

Hence, its meaning is expressed.

Epistemology includes criticism about the limits of our scientific knowledge and it warns us against the idea that we can get ultimately objective knowledge. — Angelo Cannata

I don't know about you, but some (e.g. postmodernists) refer to epistemological problems, not because they care about epistemology but because knowledge can be decisive, change beliefs, authority, privileges etc. Some fear knowledge more than death.

So what does it mean "epistemically objective"? — Angelo Cannata

In a general sense, it means that the knowledge is about something, i.e. that there exists some object that the knowledge refers to, is directed towards.

So, for example, my experiences exist in a subjective domain within the objective world, and their mode of existing is unlike the objective mode in which mountains and molecules exist. But our experiences are just as real as mountains and molecules: we have them, think and talk about them, and we express them in various ways, e.g..in the arts, theatre etc. Thus, accumulating objective knowledge about subjectivity, i.e. knowledge that refers to something that exists.

Pray tell, what is your opinion on the state of global education. For me, the critical thinker is resilient to rhetoric and propaganda, the fact learner is however....not. — Benj96

While many facts are results of critical thinking, critical thinking without fact-learning is anti-intellectual.

Lots of propaganda masquerades as "critical thinking" where the sole purpose of the "thinking" is to cast suspicion or doubt on the facts, e.g. to undermine the possibility to criticize false or nonsensical claims etc.

What do you expect from an expression? Expressing my subjectivity is to exemplify some property that it has, e.g. its first person point of view. So, I'll draw a perspective picture of what I see from my point of view, or describe it with words. Its subjective mode of existing doesn't prevent me from expressing it in epistemically objective ways.

Imagine that one day, you get the best idea in the world. You go to tell your friend, but then you realize something: You don't have any words to describe your idea. Is this scenario possible? — Scarecow

It's possible to forget words, stutter, or have a neurological disorder, paralysis, brain damage etc. that makes it difficult or impossible to express thoughts.

It is also possible that you feel that you get the best idea, but when you're about to express it, there is nothing to express. The feeling was just evoked by a wish or fantasy about what it might be like to have the best idea.

Theoretically, however, anything can be expressed.

How do we decide what is fact and what is opinion? — Truth Seeker

We might have different beliefs about the current market value of a house, for instance, but we can list the house for sale in order to find out whether our beliefs correspond to its current market value. What is fact and what is opinion in this case is not something we decide but find out.

There are more than 8.1 billion humans on Earth and our conflicting ideologies, religions, worldviews and values divide us. — Truth Seeker

There are many more things that unite us as living organisms than there are divisive ideas etc. The ideas of power mad ideologues, preachers, poets etc. are irrelevant compared to the wonders of nature.

I worry that we will destroy ourselves and all the other species with our conflicts. — Truth Seeker

Possibly, yet never before in human history has there been so much public attention on sustainability and global climate change. Many of us reduce damage by avoiding unsustainable products, food, and life styles, many businesses are desperately trying to green wash their unsustainable products or replace them with better alternatives.

I think that if we could work out what is fact and what is opinion, it would help us get on with each other better. — Truth Seeker

1 + 1 = 2 is a fact. Pizza tastes good is an opinion. What needs to be worked out here? Look at the philosophers who study the nature of facts, do they seem to get on with each other better? :cool:

Searle believes that brain matter has some special biological property that enables mental states to have intrinsic intentionality as opposed to the mere derived intentionality that printed texts and the symbols algorithmically manipulated by computers have. But if robots and people would exhibit the same forms of behavior and make the same reports regarding their own phenomenology, how would we know that we aren't also lacking what it is that the robots allegedly lack? — Pierre-Normand

I suppose we could still have good theoretical reason to suspect that they lack genuine understanding. So far the true test has not been empirical but conceptual (e.g. some assume functionalism or a computational theory of mind, others don't).

I don't know if brain matter or an exclusively biological property is necessary for consciousness to arise. It seems to be an emergent property, and it arises in very different kinds of biology, e.g. primates, cephalopods. So
in a functional sense it could arise elsewhere. But I think the functional theory of consciousness is too narrow. Consciousness is related to a background, a body, action, perception, hormone levels, and a lot of other conditions that together leave some biological forms of life as the only plausible candidates for having conscious states.

So, perhaps consciousness is not dependent on biological matter per se, but on the conditions in which the ability evolved, which might then exclude non-biological systems from duplicating it.

Are biologically active molecules not in some ways also "symbols" ie structures which "say" something - exert a particular defined or prescribed effect. — Benj96

Molecules exist independent of us. We discover them or their meanings, and refer to them with the help of symbols. Symbols, however, don't exist independent of us. There's nothing in a molecule that symbolizes unless we choose to use some feature in the molecule for symbolization. But the molecule doesn't care about our symbolic practices.

However, my point was about the relevance of isomorphisms. Pointing out that there can be irrelevant isomorphisms such as between a constellation and a swarm of insects, doesn't change the fact that there are relevant isomorphism. (Such as between the shape of bird wings and airplane wings, or between biological neural nets and artificial neural nets.) — wonderer1

Bird wings and airplane wings have many similarities and many differences. Artificial neural networks have become increasingly different from their biological counterparts since the 1940s or 50s.



.

Since artificial neural networks are designed for information processing which is to a degree isomorphic to biological neural networks, this doesn't seem like a very substantive objection to me. It's not merely a coincidence. — wonderer1

Whether the processing is designed or coincidental doesn't matter. The objection refers to isomorphism and the false promise that by being like the biological process the artificial process can be conscious. However, a conscious person with a speech defect can fail the Turing test, while smooth talking chat bots pass the test, or win the game Jeopardy, without being conscious in the sense that the person is conscious. Isomorphism is neither sufficient nor necessary for being conscious.

Consider the system reply and the robot reply to Searle's Chinese Room argument. Before GPT-4 was released, I was an advocate of the robot reply, myself, and thought the system reply had a point but was also somewhat misguided. In the robot reply, it is being conceded to Searle that the robot's "brain" (the Chinese Room) doesn't understand anything. But the operation of the robot's brain enables the robot to engage in responsive behavior (including verbal behavior) that manifests genuine understanding of the language it uses. — Pierre-Normand

It seems likely that we will soon encounter robots in our daily lives that can perform many practical and intellectual tasks, and behave in ways that manifest a sufficient understanding of our language. But I wouldn't call it genuine. A lack of genuine understanding can be buried under layers of parallell processes, and being hard to detect is no reason to reinterpret it as genuine. According to Searle, adding more syntax won't get a robot to semantics, and its computations are observer-relative.

One might also add that authenticity matters. For example, it matters whether a painting is genuine or counterfeit, not necessarily for its function, but for our understanding of its history, under what conditions it was produced, and for our evaluation of its quality etc.. The same could be true of simulated and genuine understanding.

One process or pattern may look like another. There can be strong isomorphism between a constellation of stars and a swarm of fruit flies. Doesn't mean that the stars thereby possess a disposition for behaving like fruit flies.

I'm not sure how that follows. The authors of the paper you linked made a good point about the liabilities of iteratively training LLMs with the synthetic data that they generated. That's a common liability for human beings also, who often lock themselved into epistemic bubbles or get stuck in creative ruts. Outside challenges are required to keep the creative flame alive. — Pierre-Normand

I assumed that LLMs would identify and preserve actual and relevant diversity , but the paper shows that the reduction of diversity is systematic. The LLMs follow rules, regardless of what is actual and relevant. That's basically what Searle's Chinese room shows.

We might also reduce diversity in our beliefs and descriptions e.g. for convenience or social reasons, but the false and misleading ones are naturally challenged by our direct relation with reality.

their training data and interactions with humans do ground their language use in the real world to some degree. Their cooperative interactions with their users furnish a form of grounding somewhat in line with Gareth Evans' consumer/producer account of the semantics of proper names — Pierre-Normand

Their training data is, I think, based on our descriptions of the world, or their own computations and remixes of our descriptions. In this sense their relation to the world is indirect at best.

There's some research showing that when LLMs remix their own remixes, the diversity of the content decreases and becomes increasingly similar. I'm guessing it could be fixed with some additional rule to increase diversity, but then it seems fairly clear that it's all an act, and that they have no relation to the world.

Unless, consciousness is a product of complexity. As we still don't know what makes matter aware or animate, we cannot exclude the possibility that it is complexity of information transfer that imbues this "sensation". If that is the case, and consciousness is indeed high grades of negativity entropy, then its not so far fetched to believe that we can create it in computers . — Benj96

Computer code is a bunch of symbols, recall. Could a bunch of symbols become consciously alive? The idea seems as far fetched as voodoo magic.

It seems probable that the biological phenomenon that we call consciousness is an emergent property. Many emergent properties are simple, others are complicated but have simple underlying chemical reactions, such as in photosynthesis. Perhaps the underlying mechanisms from which consciousness arises are relatively simple yet enables us to think and speak infinitely many meanings (hence the immense network of nerve cells in the brain)?

..embodiment, episodic memory, personal identity and motivational autonomy. Those all are things that we can see that they lack (unlike mysterious missing ingredients like qualia or "consciousness" that we can't even see fellow human beings to have). Because they are lacking in all of those things, the sorts of intelligence and understanding that they manifest is of a radically different nature than our own. But it's not thereby mere simulacrum - and it is worth investigating, empirically and philosophically, what those differences amount to. — Pierre-Normand

Yes, they are radically different. Unlike computational systems we are biological systems with pre-intentional abilities that enable our intentional states to determine their conditions of satisfaction.

Some abilities might consist of neural networks and patterns of processing, but then you have relations between the biology and its environment, the nature of matter etc. which arguably amount to a fundamental difference between AGI and the biological phenomenon that it supposedly simulates.

Of course we can also ditch the assumption that it is a simulation and just think of AGI as information technology.

Of course, this is all still quite different from the way human cognition works, with our [sic] biological neural networks and their own unique patterns of parallel and serial processing. And there's still much debate and uncertainty around the nature of machine intelligence and understanding.

But I think the transformer architecture provides a powerful foundation for integrating information and dynamically shifting attention in response to evolving goals and contexts. It allows for a kind of flexible, responsive intelligence that goes beyond simple serial processing. — Pierre-Normand

It's a leap forward in information technology, for sure.

But then, the actor's ability to imitate the discourse of a physicist would slowly evolve into a genuine understanding of the relevant theories. I believe that intellectual understanding, unlike the ability to feel pain or enjoy visual experiences, cannot be perfectly imitated without the imitative ability evolving into a form of genuine understanding. — Pierre-Normand

A human actor already has the ability to understand things, so that's how an actor can learn to understand physics by acting like a physicist. But that's different from an artificial actor, a computational system that doesn't have the ability. Acting as if it had the ability doesn't evoke the ability.

there remains a stark distinction between the flexible behavior of an AI that can "understand" an intellectual domain well enough to respond intelligently to any question about it, and an actor who can only fool people lacking that understanding. — Pierre-Normand

The AGI's responses might be super intelligent, but this doesn't mean that it understands them. I suppose it doesn't have to in order to be a useful assistant.

But you could say the same about me. Am I a simulation or a duplication of what another human might say in response to your commentary? — Benj96

It's certainly possible, but why would anyone set up an AI assistant here just to fool me or other members to believe that we're talking with another human? It seems probable that it would make the forum less interesting (even if it isn't revealed, but especially if it is revealed).

I was impressed by Anthropic's Claude 3 Opus (thanks to @Pierre-Normand for link), and I'm occasionally asking ChatGPT about things instead of looking them up myself. It's efficient, but I find some of the recurring expressions that make it appear human-like superfluous or insincere even.

Artificial general intelligence is something else. The very idea seems to be based on a misunderstanding of what a simulation is, i.e. that somehow, e.g. with increased complexity, it would suddenly become a duplication. It won't.

The second thing is how do we give it both "an objective" but also "free auto-self-augementation" in order to reason. And curiously, could that be the difference between something that feels/experiences and something that is lifeless, programmed and instructed? — Benj96

The difference is, I think, in what makes a simulation different from a duplication. We can instruct a simulation to respond to words and objects in ways that appear non-instructed, spontaneous, emotional etc. But what for? Is indiscernibility from being human worth striving for? A simulation is never a duplication.

"Time flies like an arrow; fruit flies like a banana." — Pierre-Normand

Talk of things on two levels can easily become ambiguous :halo:

For them to see when standing what we see when hanging upside down it must be that their eyes and/or brain work differently. — Michael

Must they, though? Some of us who have the same type of eyes / brains may stand up and others hang upside down. Are we having different experiences? Initially, yes, but after a few hours, no. We know this from experiments and the fact that we see the world upright despite the fact that it is projected upside down on the retina as the light travels through the eye's lens.

I’m saying that whether or not sugar tastes sweet is determined by the animal’s biology. It’s not “right” for it to taste sweet and “wrong” for it to taste sour. Sight is no different. It’s not “right” that light with a wavelength of 700nm looks red and not “right” that the sky is “up” and the ground “down”. These are all just consequences of our biology, and different organisms with different biologies can experience the world differently. — Michael

Then you're analysing the biology in isolation, as if the causal chains of chemicals, radiation, pressure etc from the environment would suddenly stop in the organism, and instead each individual organism creates its own experience.

I'd say seeing a colour is neither right nor wrong, it's just a causal fact, how a particular wavelength in the visible spectrum causes a particular biological phenomenon in organisms that have the ability to respond to wavelengths in the visible spectrum. This raw conscious experience, can then be used in many different ways, conventions etc. But the experience is a fact, not a convention.

It is neither a contradiction, nor physically impossible, for some organism to have that very same veridical visual experience when standing on their feet. It only requires that their eyes and/or brain work differently to ours.

Neither point of view is "more correct" than the other.

Photoreception isn't special. It's as subjective as smell and taste — Michael

Well, they have the same veridical experience when the object of the experience is the same. But why would that require that their eyes / brain work different to ours?

You postulate that we (humans) have the experience with our kind of eyes / brain, so how come you say that another organism must have differently working eyes and brain to have the same experience?

Also among humans we have somewhat differently working eyes / brains, an other organisms might have very different eyes / brains, e.g. octopus, mantis shrimp etc. However, these differences matter little when the object that we see is the same, not some figment of our different eyes / brains.

What do you mean by saying that photoreception is subjective yet not special?

I'd say photoreception is open to view in plants, animal vision, machine vision etc. The experience, however, that arises in animal vision is not open to view (ontologically subjective).

World maps are indeed conventional, like many other artificial symbols, but misleading as an analogy for visual perception. Visual perception is not an artificial construct relative conventions or habits. It is a biological and physical state of affairs, which is actual for any creature that can see.

For example, an object seen from far away appears smaller than when it is seen from a closer distance. Therefore, the rails of a railroad track appear to converge towards the horizon, and for an observer on the street the vertical sides of a tall building appear to converge towards the sky. These and similar relations are physical facts that determine the appearances of the objects in visual perception. A banana fly probably doesn't know what a rail road is, but all the same, the further away something is the smaller it appears for the fly as well as for the human.

The example of seeing rain shows how the content of the visual experience is related to the rain, and how the presentational intentionality of seeing differs from the representational intentionality of believing. The content of the visual experience and the rain are inseparable in the sense that it is the visible property of the rain that determines the phenomenal character of the visual experience. The fact that they are separate things is beside the point.

Why not? — Michael

Because perception is direct.

Try this: — Banno

That guy is taking rain dancing to the next level :cool:

About the presentational nature of perception and its directness. You know I draw a lot from Searle's theory of perception, in particular what he calls 'presentational intentionality'. Presentational intentionality is unlike the re-presentational intentionality of beliefs or desires.

For example, my belief that it currently rains represents a possible fact, but my visual experience of the rain presents the actual fact. The belief is not causally related to the rain in the direct way that seeing the rain is. In fact, I can't separate my visual experience from the rain, because it is the visible character of the rain that forms the content of the experience. This is how the content of the rain is a direct presentation of the rain.

The content in veridical and non-veridical experiences is an emergent property of brain events. They emerge with a direction of fit relative to what is perceived (veridical). The content is thus causally related to objects in the world via sense organs, and the brain adjusts the content to fit those objects. Furthermore, it disregards irrelevant noise, contorted or upside-down projections of the objects on the retina, and so on. Our biology evolved to be able to perceive the world, not our own beliefs or attitudes.

In optical illusions there is a veridical element and a non-veridical element, and they can be usefully combined, as in depiction, illustration, movies etc. The perceptual process is transparent, and this transparency enables us to perceive real objects as they are, as well as experience fictional objects and events as if they were real.

Some thoughts: I take it that Direct Realists must, to a least a large degree, accept Physicalism. — AmadeusD

Some believe that the conscious experience that arises when something is perceived can be fully explained in physical terms. Yet little is known about how conscious experience arises from brain events. Some realists believe that its subjective mode of existing prevents it from being fully explained in physical terms. But from being ontologically inaccessible it doesn't follow that the experience is also epistemically inaccessible. We talk about our experiences all the time, so they're at least accessible via our reports, via observation, discussion, statistics etc.

If that is so, these are brain states, not dispositions. They are emergent, in experience, as an attitude or disposition, but are in fact, specific physical states of hte brain in relation to whatever objects are in question. So, a DI could plausibly argue that those states are conditions necessary for whatever experience they are calling veridical. The state + the object = the experience. That seems direct enough.

I reject all of this, though. — AmadeusD

All of what? Lots of biological phenomena emerge from bio-chemical events (e.g. photosynthesis), so you'd need a good counter-argument with which you could reject the idea that conscious experiences emerge from brain states. Furthermore, brain states are necessary for any conscious experience, veridical or hallucinatory, but this has little to do with the directness of perception, which is supposedly what you wish to reject.

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.

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.

This means that the content of the perceptual experience is inherently action-oriented and world-involving. It includes an implicit reference to your bodily abilities and their anticipated successful deployment in the environment. The experience is veridical just in case this perceptual-motor expectation is fulfilled — that is, just in case your body is actually attuned to the apple's affordances in the way your experience presents it as being. — Pierre-Normand

Hm, is that you Pierre, or an AI? I'd better ask, because the common-factor view has little to do with an inner representation, and I think Pierre knows this. A direct realist has no reason to compare an inner representation with an outer state of affairs.

For a direct realist, the inner content of a perceptual experience presents the outer object and state of affairs as its conditions of satisfaction. A non-veridical experience has inner content but doesn't present its conditions of satisfaction.

Regarding disjunctivism, you write that the content of the perceptual experience is inherently action-oriented and world-involving. Well, seeing an object in action is obviously action-oriented, and seeing the world is world-involving. That's fine, but trivially true. Very AI.

Furthermore, your description of seeing an apple is a mystery. You write that the phenomenal character of what you see consists in your readiness to engage with the apple and expectation that you can successfully reach out and grasp it. But how could anything (physical or mental) consist of one's readiness (a disposition) and expectation (an attitude)? This makes no sense. How could 'readiness' and 'expectation' instantiate as actual conditions of satisfaction that causally fixes the content and character of the perceptual experience?

I'm not an expert on disjunctivism, but some disjunctivists (e.g. Alva Noe) seem to think that perceptual experience is not even spatially located in the brain but somehow floats around in a network of objects that one can become conscious of. Fascinating, and in some sense not even false, but doesn't explain much.

Thanks for the links!

My addition about indistinguishability is not an attempt to misrepresent disjunctivism. It follows from rejecting its thesis that veridical and non-veridical perceptions are fundamentally different. By rejecting disjunctivism and assuming that veridical and non-veridical perceptions are of the same type, I must give them the same analysis. Hence the stipulation that they can be phenomenally indistinguishable.

More specifically, they are of the same type constitutively, because they employ the brain's perceptual system unlike other types of conscious experiences, such as beliefs, desires, memories, imaginations.

Intentionalistically, however, they remain different and distinguishable, because in the non-veridical case nothing is perceived. Illusory objects are not perceived but constructed from habit, association, interpretation, or misinterpretation, imagination, memory and so on.

Not identical in what way? — hypericin

A disjunctivist might say that the smell she feels is not of the same type as that of ammonia. They're not type identical.

I disagree with disjunctivism, because non-veridical experiences employ parts or most of the same perceptual faculties as veridical experiences. It is possible, at least temporarily, to have a non-veridical experience that is indistinguishable from a veridical experience. In practice, however, it is often easy to distinguish between veridical and non-veridical experiences.

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? — hypericin

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

I'm not a disjunctivist, but experiences can resemble each other without being identical. Wine, for instance, can have a taste that partly resembles pear with a splash of citrus without having pear and citrus as ingredients. It's the wine that tastes like pear and citrus.

API access is easy (but looks like a page for coding). In the left upper frame I type my text. Then, on the right I klick 'Run'. Claude's text is then being typed in the other frame.

The typical work place or office might still be more like a dictatorship than a democracy. But the role of a contemporary employer/manager is less dictator, more team leader. Especially in fields of work where the employees are more educated or specialized. Also management is a specialization. It changes the relation between employer and employee from what it was in feudal or early industrial societies.

For example, the employee has competence that the employer doesn't have. The employer, on the other hand, has the facilities and social connections that provide the orders and job opportunities. But more people than ever work at home. The possibility to work remotely is also changing the relation between employer and employee. One might as well work as a consultant, self-employed, or join a company that works as an economic democracy.

But then, all you can say that can provide a possible alternative construal of what the world is, is done in language. — Astrophel

Its infinite possibilities should be enough.

If there would be no difference between beliefs and perceptions, and if you would be stuck in a world of language, then you wouldn't know that there is a world and have no reason to lament the supposed limits of language. Yet you do know, but argue against it.

Asked what something is, and there is language "ready to hand" for deployment. — Astrophel

Do you really think the world wears its symbolic possibilities "on its sleeve" so to speak? Or are these possibilities generated in social environments, making an alinguistic world — Astrophel

Right, languages are socially constructed symbol systems. Moreover, symbolic representations are asymmetric. However, it doesn't follow that the possibility to answer what something is is thereby confined to symbolic possibilities that supposedly make the task impossible. Nor must we assume that the world wears its symbolic possibilities on its sleeves.

For example, the principle of composition enables us to describe the world in unlimited ways. I don't know of a good reason to believe that none of them could ever correspond to the ways the world is.

A mental state supervenes on a physical state, meaning that the same type of experience can arise under different physical conditions.

However, the relation between seeing the lamp and the lamp is a direct causal relation. When you turn off the lamp, the change causes a corresponding change in your visual experience.

The hallucinatory lamp, however, is not part of what causes the hallucination. Nor is it caused by the lamp, which might as well be absent. Under the influence of drugs or disorder, I suppose that memories or knowledge of past experiences of a lamp can be mistaken for experiences in the here and now. At least that's what the brain may have at its disposal when the lamp is absent.

Certainly does NOT follow from the assumption that I never see the lamp. Not sure where this comes from. — Astrophel

From the Kantian attempt to explain how the perceived object conforms to concepts, where seeing the lamp means "seeing" a version of the lamp that has been conformed by your perceptual apparatus.

In your previous post you write this:

I don't think perceptions are different from beliefs. All perceptions are apperceptions. When you see a cup, you know what it is IN the seeing, that is, the cup is already known prior to the seeing, and seeing it is a confirmation about the conformity between what you see and the predelineated "cupness" that you come into the perceptual encounter with that allows you to spontaneously without question or analysis note that it is indeed a cup — Astrophel

If seeing the lamp means confirming a conformed version of the lamp, then the word 'seeing' is used in a different sense. In this sense you never see the lamp but something else, a figment of conformity, whose visual features are conceptual, not empirical. Seeing a conformed version of the lamp's visible features is different from seeing the lamp's visible features.

But a question that looks at the knowledge relation between me and my lamp and asks how it this possible? It is stunning in its simplicity as an existential query. I mean, forget philosophy. Two objects, a brain and a lamp. Causality fails instantly. So how? — Astrophel

Perception is complex, but I think it is helpful to avoid fallacies of ambiguity that result in a world of conformed lamps that you supposedly "see" (a conceptualized way of 'seeing') and transcendental lamps that we supposedly never see.

You mention that this ambiguity allows us to stipulate perception in sense 1 but not sense 2 (hallucinating the lamp, or "seeing a lamp that isn't there"). But does it also support the reverse? That is, can I maintain that my sense-2 perception of the lamp is genuine, and a legitimate use of the word "perception," without committing myself to some story about how it supervenes (or otherwise connects) to a sense-1 perception? — J

A reverse? Well, no you cant see the lamp (2) without seeing (1). The lamp that you see is genuine when the seeing is causally related to what you see.

By stipulation you could have an experience that is identical to the visual experience of the lamp although it is an hallucination. That's because the visual experience and the hallucination employ some of the same faculties in the brain, although having radically different causes. There's also a direction of fit in the brain's ability to conform experiences according to real lamps (e.g. the brain flips the upside-down projection of light on your retinas so that you experience the lamp standing upright.I suppose that it tries to make sense of hallucinations as well, you may hallucinate something identical to seeing the lamp.

Sorry if this is getting off topic.

Everyone's a realist in some sense, no? :wink:

John Searle argues that many of the great modern philosophers use perceptual verbs ambiguously in two different senses.

1. In a constitutive sense. The perception is understood as what is constitutive for having it, such as brain events or a perceptual process that exists only for the one who has the perception.

2. In an intentionalistic sense, The perception is understood as what is perceived, or what the perception is about. For example, the visual perception of the lamp.

But in talk that does not distinguish between the two senses it is easy to confuse the lamp that you're seeing with the seeing in its constitutive sense, i.e. the lamp as a figment of your own seeing.

Moreover, lots of philosophical confusion arises since it is possible, by stipulation, to experience seeing the lamp without there being a lamp, such as in a visual hallucination. But when you see the lamp both senses (1 and 2) are satisfied. When you hallucinate seeing the lamp, only 1 is satisfied (the constitutive sense).

Despite being ontologically subjective, perceptions are epistemically objective in the sense that we can describe them and compare our descriptions with available facts. That's a pragmatic way among many of finding out whether a visual experience is veridical or non-veridical.

how is knowledge that you see a lamp possible? — Astrophel

Your question 'how is knowledge that you see a lamp possible' follows from the assumption that you never see the lamp, only something prior to the seeing, in your own seeing.

To ask how it is possible to know that you see the lamp under the assumption that you never see it is not only impossible to answer but confused. You can dig deeper than Kant, but the root problem arises from that assumption, which in turn is derived from a rejection of naive realism.

Assuming naive realism, then you do in fact see the lamp, not something else in your own seeing. Seeing it, and the fact that it is there and visible, makes it possible to know that you're seeing it.

Light waves are not lamps. Nor is brain chemistry. — Astrophel

Right. Lightwaves, brain chemistry etc set the causal conditions that satisfy seeing a lamp, which in turn is justification for the belief that there is a lamp.

Perceptions are different from beliefs. I can't detach my conscious awareness of there being a lamp in front of me when I see it. The belief, however, that there is a lamp can be maintained or rejected regardless of the whereabouts of the lamp.

Good point, I'll ask Claude about Searle's internalism.

User
Ok, however, explaining what hallucinations and veridical experiences have in common cannot be a key issue for the disjunctivist, since, as you say, the disjunctivist wants to deny that they have something in common.

For Searle they do have something in common: e.g. brain events are constitutive for them as experiences, and they can be experientially indistinguishable.

If there is a key issue that needs to be explained or clarified in Searle's criticism of disjunctivism it might be his internalist account about the semantic content of intentional states that refer to external things.

Please clarify Searle's internalist account. If possible, in connection to his theory of perception on how external objects and states of affairs are perceived directly.

Relevant sources: Searle's book Seeing Things As They Are (2015), or Searle's openly available article Philosophy Of Perception And The Bad Argument (2018). — jkop

Response
You raise an excellent point about the key issue in Searle's critique of disjunctivism being his internalist account of intentional content, rather than what hallucinations and veridical experiences have in common. Let me try to clarify Searle's internalist view and how it relates to his direct realist theory of perception.
In his book Seeing Things As They Are, Searle argues for a direct realist view of perception, according to which we directly perceive external objects and states of affairs, unmediated by any intervening representations or sense data. When I visually perceive a yellow station wagon, the object of my perception - what I directly see - is the actual car itself in the external world.
At the same time, Searle maintains an internalist view of intentional content. The intentional content of a perceptual experience - what the experience is about or directed at - is determined by internal factors in the subject's brain/mind. It is not constituted by any external objects or relations to them.
Searle uses the "brain in a vat" thought experiment to argue for this internalism. If my brain were in a vat being fed perceptual experiences qualitatively identical to my current ones, those experiences would have the same intentional contents, even though they would fail to refer to any actual external objects. What fixes the representational content of experience are internal neurobiological features, not external relations.
So in the case of hallucination, the intentional content is the same as in a matching veridical perception, because the internal brain processes are the same. The difference is that in hallucination, the experience fails to refer to any actual object.
Searle sees his internalism about content as compatible with direct realism, because he argues perceptual experiences have two levels of content:
The intentional content fixed internally by brain processes
The directly perceived external objects/states of affairs themselves, when the intentional content is "satisfied" or "made true" by those objects/states of affairs successfully referred to.
In veridical perception, both levels of content are present. In total hallucination, only the first level is present. But either way, the intentional content itself is determined internally.
This is a tricky balance to strike, and there is certainly room to question whether Searle succeeds in coherently combining internalism about perceptual content with direct realism. But that seems to be the key thrust of his view and his critique of disjunctivism. Disjunctivists want to say veridical and hallucinatory experiences have fundamentally different contents, while Searle maintains they have the same narrow intentional contents, just different referential relations to the external world. — Claude 3 Opus

Not bad for a chat bot. :up:

But... this does not seem right:

The intentional content of a perceptual experience - what the experience is about or directed at - is determined by internal factors in the subject's brain/mind. It is not constituted by any external objects or relations to them. — Claude 3 Opus

In the openly available article, Searle writes:

The experience sets conditions of satisfaction, and these conditions are those under which the experience is veridical as opposed to those conditions under which it is not veridical. Confining ourselves to seeing the tree in front of me we can say that the conditions of satisfaction of the visual experience are that there has to be a tree there and the fact that the tree is there is causing in a certain way the current visual experience. So on this account the visual experience in its conditions of satisfaction is causally self-reflexive in that the causal condition refers to the perceptual experience itself. .....

This type of intentionality is also unusual in that the conscious visual experience gives me a direct presentation of its conditions of satisfaction. Perception differs from such philosophers' favorites as beliefs and desires, because they are in an ordinary sense 'representations' of their conditions of satisfaction. There are important differences between representations and presentations. Perhaps the most important is that the presentation cannot be separated from its conditions of satisfaction in a way that representations can. If I believe that it is raining I can separate my belief from the fact that it is raining, but when I see the tree I cannot separate the visual experience from an awareness of the presence of the tree. This is true even if it is a hallucination and even if I know that it is a hallucination. In such a case, I have the experience of the perceptual presentation of an object even though there is no object there. A great deal of philosophical confusion surrounds this last point.... — Searle

I'm afraid anyone would have failed to comply with the investigation if you consider the extraordinary behavior of the Swedish prosecutors. In the article there's a short description of the events.

In 2010 he was like a rock star for journalists and activists, women included. Allegedly he had unprotected sex with one or two women, which resulted in criminal charges. The women withdrew their part, but the charges remained and were pushed back and forth by a couple of prosecutors (one is a politician).

There's a group of UN investigators accusing the Swedish and UK authorities for deliberate misuse of power. I found a link from the Wiki article..

I asked Claude why s/he/it referred to representationalism in a conversation about disjunctivism where the converse is assumed.

User
Thanks again. It's interesting that you write that "we need some notion of perceptual content to explain perceptual illusions, hallucinations, and the fact that experiences can misrepresent the world". But whence the need? And is it a fact that experiences can misrepresent? A representation could indeed misrepresent what it represents, but in the context of our conversation (Searle's criticism of disjunctivism) the assumption is that veridical perceptual experiences do not represent. Instead they present objects and states of affairs directly. Direct realism is assumed by both Searle and in disjunctivism.

Reply
You raise an excellent point. I agree that in the context of our discussion about Searle's criticism of disjunctivism, both views assume direct realism and reject the idea that veridical perceptual experiences involve representations.
So you're right that there isn't a need to invoke representational content to explain misrepresentation in this context, since veridical experiences are taken to directly present objects rather than represent them. The disjunctivist can allow that hallucinations have representational content while denying this for veridical perceptions.
I think I slipped into talking about perceptual content and misrepresentation because those notions are so commonly invoked in discussions of perceptual experience, but you're absolutely correct that they aren't relevant given the shared direct realist assumptions here.
The key issue is explaining what hallucinations and veridical perceptions have in common phenomenologically, without appealing to a common representational content. The disjunctivist wants to deny they have anything metaphysically in common, while Searle objects that this fails to account for their phenomenological indistinguishability.
Thanks for catching my error and helping to clarify the dialectic! Let me know if you have any other thoughts on this. It's a subtle issue and I appreciate you pushing me to be more precise. — Claude 3 Opus

Its ability to produce sentences is impressive, but I wonder still... For example, at the end it says:

The key issue is explaining what hallucinations and veridical perceptions have in common phenomenologically, without appealing to a common representational content. The disjunctivist wants to deny they have anything metaphysically in common, while Searle objects that this fails to account for their phenomenological indistinguishability. — Claude 3 Opus

The key issue for whom? For disjunctivists it is hardly a key issue to explain what hallucinations and veridical experiences have in common, since disjunctivists deny that they have something in common. For Searle it is not a key issue either, they're both brain events in the constitutional sense of 'experience', but in the intentionalistic sense of 'experience' they're distinct, because in the hallucination nothing is experienced. Searle hardly needs to explain that hallucinations and veridical experiences occur in the brain, at least it's not a key issue.

Truth is unpopular.

Other examples are the Panama papers and the Paradise papers that reveal how major banks and law firms participate in illegal tax evasion. I recall reading that one of the journalists was murdered.

I think WikiLeaks had plans to relocate servers to Sweden because of the seemingly strong guarantees of press freedom and ethical responsibility. But it didn't turn out so well. Instead Assange was incriminated and charged by a Swedish prosecutor, as well as attacked by major but arguably politicalized newspapers. The rest is history.