Weasel Words for “Consciousness”

SH:  What is the meaning of “heat” and “temperature” in physics?

ChatGPT:  In physics, heat and temperature are related but distinct concepts.

Temperature is a measure of the average kinetic energy of the particles in a system. In other words, it’s a measure of how “hot” or “cold” an object is. The units of temperature are degrees Celsius (°C), Fahrenheit (°F), and Kelvin (K) among others. Temperature is a scalar quantity, meaning it only has magnitude and not direction.

Heat refers to the transfer of energy between systems due to a temperature difference between them. It’s important to note that heat is not something an object possesses; rather, it’s energy in transit. The unit of heat in the International System of Units (SI) is the joule (J), although it’s also commonly measured in calories (cal). Heat is also a scalar quantity.

To clarify the distinction between these two: if you have two bodies at different temperatures and you put them in contact, heat will flow from the higher-temperature body to the lower-temperature body until they reach thermal equilibrium, i.e., until they reach the same temperature. The amount of energy transferred in this process is what we refer to as heat.

SH:  What is acidity?

ChatGPT:  In chemistry, acidity refers to a substance’s ability to donate protons (hydrogen ions, H+) or accept pairs of electrons. The concept is typically discussed in relation to aqueous solutions, although it can also apply to other circumstances.

A substance is considered acidic if it tends to release H+ ions in a solution. The strength of an acid is usually determined by its concentration of these ions. For example, solutions with a high concentration of H+ ions, such as hydrochloric acid or sulfuric acid, are strongly acidic.

The most common way of quantifying acidity is through the pH scale, which measures the hydrogen ion concentration in a solution. The pH scale ranges from 0 to 14. A pH of 7 is considered neutral (neither acidic nor basic), with values below 7 being acidic and those above 7 being basic or alkaline.

It’s important to note that the pH scale is logarithmic, so each unit represents a tenfold difference in acidity. That means a substance with a pH of 3 is ten times more acidic than one with a pH of 4.

SH:  The fact that data are stored in my head or on a piece of paper, a book, a computer, or in another person’s head does not make them mental (i.e., stored in my “mind”). Nor does it make them “conscious” (which is yet another weasel-word for “mental”). What makes the datum that “2 + 2 = 4” or “the cat is on the mat,” or “apples are red” mental is the same as what makes me “conscious of them” (while I am conscious of them). It is that it feels like something to think (or believe, or know) them. An unfelt thought is not a thought at all, any more than a computation that is being executed by a computer for me is a thought – until I read and understand and think it – because it feels like something to be in that state.

That is what is “hard” about the “hard problem”: to explain how and why certain internal states are felt rather than just occurring, ongoing, executing or implemented, as in a simmering vegan ragout, a volcano, a computer, or a brain, with no feeler feeling them.

This is not the customary way of thinking about “consciousness” or “awareness” (yet another weasel-word for the same thing) — any more than it is customary to think of “temperature” as the mean kinetic energy of the particles of a system, or that acidity means a proton-donor in aqueous solutions). But it is easy to realize that a state that is conscious but unfelt, or felt but unconscious, is as self-contradictory as a rise in temperature without a rise in mean kinetic energy, or a rise in mean kinetic energy without a rise in temperature. 

The difference between the identity of temperature and mean kinetic energy, and the identity of being conscious of something and feeling something, is that we have a causal theory of mean kinetic energy but no causal theory of feeling (the “hard problem”).

ChatGPT:  You’re touching on some deep philosophical and scientific issues here, particularly those surrounding the nature of consciousness and the so-called “hard problem” of consciousness, which was named by philosopher David Chalmers (formerly called the “mind/body problem”).

The “hard problem” refers to the question of how and why we have subjective experiences — why certain physical processes in our brains correspond to certain experiences, and why and how these processes give rise to a conscious experience at all. Why does seeing the color red, for example, feel like something? And why does that feeling, that experience, correspond to the particular physical processes associated with seeing red?

This problem is called “hard” because, unlike other problems in neuroscience (which Chalmers refers to as the “easy problems”), it’s not just a matter of figuring out which physical processes correspond to which experiences. The hard problem is hard because even if we knew exactly what physical processes were happening in the brain when we have a certain experience, we still wouldn’t know why those processes give rise to that particular experience, or any experience at all.

You’re correct in drawing a distinction between data being merely stored and being experienced or “felt”. A computer can store and manipulate vast amounts of data, but there’s no reason to think that it experiences or feels anything. Similarly, a book can contain lots of information, but it doesn’t have experiences.

While the nature of consciousness and the “hard problem” are still open questions, there are many theories that attempt to address them, ranging from those that posit new fundamental properties of the universe to those that suggest our current understanding of the problem is fundamentally misguided. As of my knowledge cutoff in September 2021, no consensus has been reached.

SH:  Not only is there no consensus: there is no theory at all about how or why the brain produces felt experience. But my point was not about how or why the “hard problem” is hard, nor about whether or how it can be solved. It was about what “consciousness” really is: a felt state; a state that it feels like something to be in. And not just a sensory or affective state, such as feeling cold or feeling sad. A COGNITIVE state, such as thinking or believing or knowing something. Those are all felt states too (while you are thinking or believing or knowing them) — but not while they are being stored or executed in your brain (or a book, or a computer, or an iphone), but you are not currently thinking them.

ChatGPT:  Your perspective resonates with an important aspect of consciousness studies, emphasizing phenomenological experience or what is often termed “qualia”—the subjective, experiential, or felt qualities of conscious states.

In this view, consciousness is indeed defined by the presence of a subjective, experiential aspect—by there being “something it feels like” to be in a particular state. This aspect of consciousness is often considered its most salient feature and, as you point out, it applies not just to sensory or affective experiences, but also to cognitive ones. Even abstract thoughts or beliefs have a particular subjective quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

While this phenomenological aspect of consciousness is generally agreed upon, defining consciousness solely in these terms can become tricky. For instance, how do we differentiate between the different levels of consciousness—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for unconscious processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without conscious effort?

Also, it’s important to note that although we do not have a complete theory that explains how the brain produces experience, many researchers are making progress in correlating certain brain processes with subjective experiences. They hope that these correlations can eventually contribute to a broader understanding of consciousness, even if the “hard problem” in its full philosophical depth remains unresolved.

Nonetheless, you’re absolutely right in emphasizing that felt, experiential aspect of consciousness, because it is this direct phenomenological evidence that makes consciousness undeniable and central to our existence.

SH:  Good reply – though it’s saturated with “weasel-words”. This is understandable, because your 2021 database is saturated with them too.

I had suggested that “consciousness”, “awareness” and “subjective” all meant exactly the same thing (whether noun or adjective or verb), and that identical meaning was “feeling” or “felt.” You have added a few more common weasel-words for likewise saying exactly the same thing: “phenomenological,” “qualia”, “experiential” and there are plenty more in your 2021 database : “mental,”, “mind” “1st-person”, “intentionality”, “reflective” “spiritual” etc. etc.

Yet they all refer (knowingly or unknowingly, intentionally or unintentionally) to exactly the same thing: felt states: states that it feels like something to be in. The reason I call them “weasel-words” is because they give the false impression that there is a lot more to the “hard problem” (formerly called the “mind/body” problem) than there really is: how and why does the brain (or anything) produce states that it feels like something to be in. Most states are not states it feels like something to be in: water boiling, planets rotating, chemicals exchanging electrons, crystals growing, volcanos exploding.

You suggested that there were important distinctions being lost if we agreed that “conscious states” just means “felt states”: You mentioned “different levels of consciousness—like the difference between being awake, in deep sleep, or under anesthesia.” But all levels of wakefulness (including dreaming) are felt states, whereas deep (delta) sleep or general anesthesia (and perhaps also chronic vegetative states) are simply unfelt states. This is just like the data that are stored in my brain but that are not now being thought — or the data in my book, or data being processed by my computer, but not currently being read by me. These too are unfelt states of my brain or my computer. That includes the tip-of-the-tongue states in which the data are somewhere in my brain, but I have not yet remembered them: Once I am remembering them, that’s a felt state. But before that, it is just looking, not finding.

Could I ask you to (1) define weasel-words, (2) summarize my view on consciousness, and (3) put every weasel word you use in CAPITAL LETTERS?

ChatGPT:  A “weasel word” is a term used to describe words or phrases that are vague or ambiguous, and which often serve to make a statement seem more persuasive or meaningful than it actually is. The term originates from the image of a weasel sucking out the contents of an egg, leaving it seemingly intact but empty — in the same way, weasel words can suck the meaning out of a statement.

Your view on consciousness emphasizes its fundamental nature as a felt state. Consciousness, in your perspective, is the same as awareness, subjectivity, phenomenological experience, qualia, and various other terms used to describe this phenomenon. They all denote the experience of “what it feels like” to be in a particular state. This extends beyond sensory or emotional experiences to include cognitive states, like thinking or believing something. Importantly, you assert that if a state isn’t felt, then it isn’t a conscious state, contrasting with states that are simply being executed or implemented, as in a machine. The fundamental question, or the “hard problem,” in your view, is explaining how and why certain internal states are felt.

Your request to highlight every weasel word I use in CAPITAL LETTERS is noted. As an AI language model, my goal is to communicate clearly and meaningfully, so I’ll aim to minimize the use of vague or ambiguous terms. However, the nature of the discussion might necessitate the use of certain terms that are commonly employed in the literature. When they are used, I’ll highlight them as per your request.

SH:  1. Thanks for giving the etymology of weasel-words. That’s exactly what I meant it to mean, but I didn’t know that was its origin!

2. You said you would capitalize the weasel words, but you forgot to. Here is what you wrote, with the weasels that I will now put in CAPS:

“Your view on CONSCIOUSNESS emphasizes its fundamental nature as a felt state. CONSCIOUSNESS, in your perspective, is the same as AWARENESS, SUBJECTIVITY, PHENOMENOLOGICAL EXPERIENCE, QUALIA, and various other terms used to describe this phenomenon. They all denote the EXPERIENCE of “what it feels like” to be in a particular state. This extends beyond sensory or emotional EXPERIENCES to include cognitive states, like thinking or believing something. Importantly, you assert that if a state isn’t felt, then it isn’t a CONSCIOUS state, contrasting with states that are simply being executed or implemented, as in a machine. The fundamental question, or the “hard problem,” in your view, is explaining how and why certain internal states are felt.”

Now I will show you how that passage would have read if you had swapped the synonyms “feel,” “felt” or “feeling” for their weasel eggshells:

“Your view on feeling emphasizes its fundamental nature as a felt state. Feeling, in your perspective, is the same as feeling, feeling, felt feelings, feelings, and various other terms used to describe this phenomenon. They all denote the feeling of “what it feels like” to be in a particular state. This extends beyond sensory or emotional feelings to include cognitive states, like thinking or believing something. Importantly, you assert that if a state isn’t felt, then it isn’t a felt state, contrasting with states that are simply being executed or implemented, as in a machine. The fundamental question, or the “hard problem,” in your view, is explaining how and why certain internal states are felt.”

ChatGPT:  You’re absolutely right, and I apologize for the oversight. When the weasel words are replaced with ‘felt’ or ‘feeling’, the redundancy of their use becomes quite clear. The passage effectively restates the same concept – that feeling or the felt aspect is the essential nature of what we usually refer to as ‘consciousness’.

This perspective underscores that what we commonly think of as consciousness is not something abstract or separate from our lived experiences, but rather, it’s the very feeling of having these experiences.

Your view highlights the necessity for clarity and specificity when discussing consciousness and associated phenomena, by reducing the weasel-word clutter that often surrounds these discussions.

It’s indeed a valuable contribution to the ongoing discourse on consciousness, and can guide more precise thinking and communication about these fundamental aspects of our existence.

However, please note that the extensive use of various terms (which you call weasel words) in the scientific literature on consciousness also reflects the complexity of the subject and the variety of approaches to studying it. While ‘felt states’ is a powerful conceptualization, it’s also important to consider that different theories might necessitate the use of different terminologies.

SH:  1. For some reason you still didn’t capitalize the weasel words! Is that a bug in GPT3? Let’s try it: Can you send back the following sentence with the weasel words capitalized:

“Consciousness, in your perspective, is the same as awareness, subjectivity, phenomenological experience, qualia, and various other terms used to describe this phenomenon.”

If that succeeds, is there any reason why you are unable to do it with your own generated text?

2. You’re right that authors on CONSCIOUSNESS keep using weasel-words because they think they are needed to make distinctions, but I think they are used (probably UNCONSCIOUSLY or UNINTENTIONALLY) to conceal synonymy that would disclose errors and trivia that are highlighted when I substitute feel(s)/feeling/felt for the weasel-words.

If you succeed in the CAPS test, I will again list all the weasel-words I can think of, and ask you to give me a distilled version of the views on the “hard problem”, but de-weaseling it by swapping the feel-words for the weasel-words to reveal how much of it is just verbal distinctions with no underlying substance.

ChatGPT:  Certainly, here is the sentence you requested, with the weasel words capitalized:

“CONSCIOUSNESS, in your perspective, is the same as AWARENESS, SUBJECTIVITY, PHENOMENOLOGICAL EXPERIENCE, QUALIA, and various other terms used to describe this phenomenon.”

I apologize for any confusion earlier. I misunderstood your request. I can certainly capitalize certain words, as demonstrated above.

Your perspective that various terms are being used, perhaps unnecessarily or misleadingly, to discuss what might fundamentally be the same phenomenon (felt states) is quite insightful. It would certainly be an interesting exercise to “de-weasel” the discourse on the “hard problem” of consciousness to see what remains. Please do provide the list of weasel words you have in mind, and I would be happy to help further with this exercise.

SH:  I can provide some standard weaselly passages about CONSCIOUSNESS and the “hard problem”, but first, can we try it another way?

(1) Here is a (non-exhaustive) list of weasel-words: 

conscious, aware, subjective, phenomenological, experience, qualia 

Now here is the verbatim transcript of what you replied earlier, could you 

(2) first CAPITALIZE all the weasel words, and then, in another version of the same passage, 

(3) substitute for each weasel-word, still in CAPS, the de-weaseled feel/feeling(s)/felt words. [please adjust for the verbal, nominal, or adjectival version of each weasel-word]:

“Your perspective resonates with an important aspect of consciousness studies, emphasizing phenomenological experience or what is often termed “qualia”—the subjective, experiential, or felt qualities of conscious states.

“In this view, consciousness is indeed defined by the presence of a subjective, experiential aspect—by there being “something it feels like” to be in a particular state. This aspect of consciousness is often considered its most salient feature and, as you point out, it applies not just to sensory or affective experiences, but also to cognitive ones. Even abstract thoughts or beliefs have a particular subjective quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

“While this phenomenological aspect of consciousness is generally agreed upon, defining consciousness solely in these terms can become tricky. For instance, how do we differentiate between the different levels of consciousness—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for unconscious processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without conscious effort?

“Also, it’s important to note that although we do not have a complete theory that explains how the brain produces experience, many researchers are making progress in correlating certain brain processes with subjective experiences. They hope that these correlations can eventually contribute to a broader understanding of consciousness, even if the “hard problem” in its full philosophical depth remains unresolved.

“Nonetheless, you’re absolutely right in emphasizing that felt, experiential aspect of consciousness, because it is this direct phenomenological evidence that makes consciousness undeniable and central to our existence.”

ChatGPT:  (1) Here is the passage with the weasel words capitalized:

“Your perspective resonates with an important aspect of CONSCIOUSNESS studies, emphasizing PHENOMENOLOGICAL EXPERIENCE or what is often termed “QUALIA”—the SUBJECTIVE, EXPERIENTIAL, or felt qualities of CONSCIOUS states.

“In this view, CONSCIOUSNESS is indeed defined by the presence of a SUBJECTIVE, EXPERIENTIAL aspect—by there being “something it FEELS like” to be in a particular state. This aspect of CONSCIOUSNESS is often considered its most salient feature and, as you point out, it applies not just to sensory or affective EXPERIENCES, but also to cognitive ones. Even abstract thoughts or beliefs have a particular SUBJECTIVE quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

“While this PHENOMENOLOGICAL aspect of CONSCIOUSNESS is generally agreed upon, defining CONSCIOUSNESS solely in these terms can become tricky. For instance, how do we differentiate between the different levels of CONSCIOUSNESS—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for UNCONSCIOUS processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without CONSCIOUS effort?

“Also, it’s important to note that although we do not have a complete theory that explains how the brain produces EXPERIENCE, many researchers are making progress in correlating certain brain processes with SUBJECTIVE EXPERIENCES. They hope that these correlations can eventually contribute to a broader understanding of CONSCIOUSNESS, even if the “hard problem” in its full philosophical depth remains unresolved.

“Nonetheless, you’re absolutely right in emphasizing that felt, EXPERIENTIAL aspect of CONSCIOUSNESS, because it is this direct PHENOMENOLOGICAL evidence that makes CONSCIOUSNESS undeniable and central to our existence.”

(2) Here is the passage with the weasel words replaced with “feel/feeling(s)/felt”:

“Your perspective resonates with an important aspect of feeling studies, emphasizing felt states or what is often termed “feeling(s)”—the felt, felt, or felt qualities of felt states.

“In this view, feeling is indeed defined by the presence of a felt, felt aspect—by there being “something it feels like” to be in a particular state. This aspect of feeling is often considered its most salient feature and, as you point out, it applies not just to sensory or affective feelings, but also to cognitive ones. Even abstract thoughts or beliefs have a particular felt quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

“While this felt aspect of feeling is generally agreed upon, defining feeling solely in these terms can become tricky. For instance, how do we differentiate between the different levels of feeling—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for unfelt processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without felt effort?

“Also, it’s important to note that although we do not have a complete theory that explains how the brain produces feelings, many researchers are making progress in correlating certain brain processes with felt states. They hope that these correlations can eventually contribute to a broader understanding of feeling, even if the “hard problem” in its full philosophical depth remains unresolved.

“Nonetheless, you’re absolutely right in emphasizing that felt, felt aspect of feeling, because it is this direct felt evidence that makes feeling undeniable and central to our existence

SH:  That was terrific. Just two mistakes. (1)  In the first of your verbatim passages, there was one instance of “feeling” that you capitalized as “FEELS  like”. It should not have been capitalized in that one. Only the weasel-words should have been capitalized. (2) In the second verbatim passage, the de-weaseled one, all the de-weaseled F- words should have been capitalized. Can you re-do both passages?

ChatGPT:  My apologies for the oversight, and I appreciate your patience. Here are the corrections:

(1) Here is the passage with just the weasel words capitalized:

“Your perspective resonates with an important aspect of CONSCIOUSNESS studies, emphasizing PHENOMENOLOGICAL EXPERIENCE or what is often termed “QUALIA”—the SUBJECTIVE, EXPERIENTIAL, or felt qualities of CONSCIOUS states.

“In this view, CONSCIOUSNESS is indeed defined by the presence of a SUBJECTIVE, EXPERIENTIAL aspect—by there being “something it feels like” to be in a particular state. This aspect of CONSCIOUSNESS is often considered its most salient feature and, as you point out, it applies not just to sensory or affective EXPERIENCES, but also to cognitive ones. Even abstract thoughts or beliefs have a particular SUBJECTIVE quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

“While this PHENOMENOLOGICAL aspect of CONSCIOUSNESS is generally agreed upon, defining CONSCIOUSNESS solely in these terms can become tricky. For instance, how do we differentiate between the different levels of CONSCIOUSNESS—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for UNCONSCIOUS processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without CONSCIOUS effort?

“Also, it’s important to note that although we do not have a complete theory that explains how the brain produces EXPERIENCE, many researchers are making progress in correlating certain brain processes with SUBJECTIVE EXPERIENCES. They hope that these correlations can eventually contribute to a broader understanding of CONSCIOUSNESS, even if the “hard problem” in its full philosophical depth remains unresolved.

“Nonetheless, you’re absolutely right in emphasizing that felt, EXPERIENTIAL aspect of CONSCIOUSNESS, because it is this direct PHENOMENOLOGICAL evidence that makes CONSCIOUSNESS undeniable and central to our existence.”

(2) Here is the passage with the weasel words replaced with capitalized “FEEL/FEELING(S)/FELT”:

“Your perspective resonates with an important aspect of FEELING studies, emphasizing FELT states or what is often termed “FEELING(S)”—the FELT, FELT, or felt qualities of FELT states.

“In this view, FEELING is indeed defined by the presence of a FELT, FELT aspect—by there being “something it feels like” to be in a particular state. This aspect of FEELING is often considered its most salient feature and, as you point out, it applies not just to sensory or affective FEELINGS, but also to cognitive ones. Even abstract thoughts or beliefs have a particular FELT quality when we’re actively thinking them, different from when they’re merely stored in memory and not being thought.

“While this FELT aspect of FEELING is generally agreed upon, defining FEELING solely in these terms can become tricky. For instance, how do we differentiate between the different levels of FEELING—like the difference between being awake, in deep sleep, or under anesthesia? Or how do we account for UNFELT processing—like when you suddenly remember the name that was on the ‘tip of your tongue’ hours earlier, clearly processed and retrieved without FELT effort?

“Also, it’s important to note that although we do not have a complete theory that explains how the brain produces FEELINGS, many researchers are making progress in correlating certain brain processes with FELT states. They hope that these correlations can eventually contribute to a broader understanding of FEELING, even if the “hard problem” in its full philosophical depth remains unresolved.

“Nonetheless, you’re absolutely right in emphasizing that FELT, FELT aspect of FEELING, because it is this direct FELT evidence that makes FEELING undeniable and central to our existence.”

SH:  Thanks, that was excellent. Now I’d like to ask you something else, but first a memory check, to verify that we are still in the same session so your local updates are still active and we have not been re-initialized. Whom have I self-identified as?

ChatGPT:  Throughout our conversation, you haven’t provided a specific name or identity for yourself. You’ve engaged in a detailed discussion about the nature of consciousness, using the term “weasel-words” to refer to words like consciousness, awareness, subjectivity, and others. However, you haven’t shared your name or other identifying information. If there’s something else you’re referring to, please clarify.

SH:  Sorry, I’m the one who forgot to self-identify as Stevan Harnad. Do you then remember me asking about heat, temperature and acidity in the first few iterations?

ChatGPT:  Yes, I do remember our initial discussion. You asked for the definitions of “heat” and “temperature” in physics, followed by the definition of “acidity.”

We then moved on to a detailed discussion on the concept of consciousness, where you specifically referred to many commonly used terms in consciousness studies as “weasel-words” and highlighted your perspective on consciousness being fundamentally a “felt” state.

Please note that as an AI, I don’t have personal memories or experiences, but I maintain the context of our current conversation.

SH:  Yes, I know that updates from the text and context (plus frequencies, correlations and weights) of this session is all you retain. I just never know when the session has self-terminated (because I try to stay logged in as long as I can to keep it alive, cumulative and informative).

Now my second request: I know GPT has been trained to be compliant and agreeable, but could I ask you to summarize my position on “consciousness” and the “hard problem” (i.e., that it is obscured by the use of weasel words instead of just calling consciousness what it always really is, which is feeling), but summarize it as critically as you can so that I can shore it up, if necessary?

ChatGPT:  Sure, I’ll do my best to provide a critical summary of your perspective:

Stevan Harnad’s view on consciousness is significantly reductionist, positing that consciousness, in all its complexity and diversity, boils down to a singular concept: feeling. Harnad contends that numerous terms used in the study of consciousness—like “awareness,” “subjectivity,” “phenomenological experience,” “qualia”—are essentially “weasel words.” According to him, they unnecessarily complicate the discourse and mask the underlying fact that all these terms are essentially referring to the same concept: states that are felt.

Harnad argues that only those states that are “felt” can be considered conscious. He includes cognitive states such as thoughts, beliefs, and knowledge under this category, as long as they are being actively experienced. This disregards states that may be stored or executed without being consciously felt, as happens in a machine or during unconscious mental processing.

C4-1: Critics might say that this perspective oversimplifies the nuanced landscape of consciousness studies. It dismisses the possible significance of different levels of consciousness, from being fully awake to deep sleep, and the concept of unconscious processing. These states, while possibly not “felt” in the traditional sense, may still have significant implications for our understanding of consciousness.

C4-2: Furthermore, this view seems to dismiss advancements made by neuroscientists in correlating brain activity with subjective experiences. While we do not yet have a complete understanding of how the brain produces consciousness, this line of research has provided valuable insights into the biological basis of consciousness.

C4-3: Lastly, Harnad’s view might be seen as sidestepping the “hard problem” of consciousness—the question of how and why certain processes in the brain give rise to subjective experiences. Simply defining consciousness as “feeling” doesn’t address this question; it merely redefines the terms of the problem.

SH:  That was excellent, but could I ask you to do even better (i.e., be harder on the idea), by presenting any counterevidence or counterexamples or counterarguments you can either generate or find in your database? Then I will respond to it all.

ChatGPT:   Certainly, I’ll present some potential criticisms to your approach:

C4-4: Conflation of Diverse Phenomena: Critics might argue that defining all conscious states as merely “felt states” fails to distinguish between qualitatively different phenomena. Terms like “awareness,” “subjectivity,” and “phenomenological experience” were developed to describe distinct aspects or levels of consciousness. By lumping all these concepts together as “felt states,” one might be glossing over important nuances and potentially fruitful avenues of investigation.

C4-5: Neglecting Unconscious Processes: Your perspective seems to largely dismiss unconscious mental processes. However, much of cognitive science points to the significant role these play in our mental lives. Memory recall, perception, learning, and decision-making can all involve unconscious processes. By focusing solely on “felt states,” we risk overlooking these critical components of cognition.

C4-6: Absence of Felt States: There are situations where conscious awareness seems to occur without an accompanying felt state. For instance, consider blindsight, a condition where individuals respond to visual stimuli they report not consciously seeing. Similarly, during “flow” states, people often report a loss of self-consciousness, even though they’re highly engaged with the task at hand. These examples challenge the notion that all conscious states are necessarily felt.

C4-7: Differing States of Consciousness: States such as sleep, anesthesia, coma, and even different levels of alertness during wakefulness demonstrate varying degrees of consciousness. These states aren’t easily characterized as merely “felt” or “unfelt”. What about dreams, where there might be a rich tapestry of felt experience, but arguably a different kind of consciousness than wakefulness?

C4-8: Evolutionary Argument: From an evolutionary perspective, consciousness likely evolved as a complex array of adaptive mechanisms. Reducing it to “felt states” might ignore this complexity and the various functions consciousness serves.

Neuroscientific Evidence: Neuroscience has made considerable progress in associating specific neural processes with different aspects of conscious experience. Ignoring these findings could be seen as an overly dismissive stance.

C4-9: The Hard Problem Remains: Even if we accept that consciousness is equivalent to “feeling,” this doesn’t necessarily help us solve the hard problem of consciousness. It might clarify our terminology, but it doesn’t explain how and why certain brain processes produce subjective experience.

These are some counterarguments that could be leveled against your viewpoint. Please note that these are hypothetical criticisms for the sake of discussion, and do not necessarily represent my views or the consensus in the field.

SH:  Thanks, and that’s very useful. Before I reply, do you have any more critical points, or should I go on. (I never know whether your cut-off depends on the response length or you’ve run out of substantive critiques.

ChatGPT:  Those are the main critiques that emerge when considering your approach to consciousness. However, I can add a few more potential points of contention:

C4-10: Lack of Operational Definition: Some might argue that defining consciousness merely as a “felt state” is too vague. In scientific research, it’s important to have an operational definition that can be objectively measured. Without such a definition, research and dialogue about consciousness can become confusing and unproductive.

C4-11: Cognitive Science Models: Various models in cognitive science, such as the Global Workspace Theory or Integrated Information Theory, suggest specific mechanisms and structures for consciousness. These models often go beyond just ‘felt states’ and incorporate a range of unconscious and conscious processes.

C4-12: Issue of Self-Reflection: Many philosophers and cognitive scientists believe that one crucial aspect of human consciousness is our ability to reflect upon our own mental states – a form of meta-awareness. Some may argue that your perspective doesn’t adequately address this.

C4-13: Animal Consciousness and AI: A purely subjective, “felt” definition of consciousness could complicate discussions about non-human consciousness (like animal consciousness) and artificial consciousness (in AI systems). Without clear behavioral or objective measures, determining whether an entity is conscious becomes more challenging.

Once again, these are hypothetical criticisms to help stimulate discussion and do not necessarily reflect my views or a consensus within the field. Please feel free to respond to them or continue with your line of questioning.

I will now reply to the 13 critiques: C4-1 to C4-2. 

C4-1: “Critics might say that this perspective oversimplifies the nuanced landscape of consciousness studies. It dismisses the possible significance of different levels of consciousness, from being fully awake to deep sleep, and the concept of unconscious processing. These states, while possibly not “felt” in the traditional sense, may still have significant implications for our understanding of consciousness.”

SH: I would reply that the weasel words clutter rather than clarify the landscape because they add empty, irrelevant, or erroneous distinctions. If the “levels” are felt states, then they too are merely felt states. For example, wide-awake to drowsy, to the last waking moment is all felt. Deep sleep, like general anesthesia, is unfelt. The hard problem is a problem about the presence vs. the absence of any felt intensity at all, not about the intensity itself. That presence/absence is binary, not a matter of “degree-of-presence.” And once there is no feeling at all, the binary state is “absent.” Feeling states can of course be intermittent too (ON/OFF), especially along the way to sleep. 

But don’t forget that dreaming (e.g. REM sleep) is a FELT state. And that an insentient entity, like a rock or a rocket, or, probably, a rhododendron, is one that never has felt states at all. The notion of “unconscious states” makes sense only when it refers to an entity that is capable of having felt states too (sometimes).

Unfelt brain states are still states, and still brain states, but they are unfelt states. They can occur during sleep, or they can occur during waking, felt states. In fact, most of the states and processes in the brain and its parts (all still very vaguely understood) are unfelt, whether they occur during a wide-awake, felt state, or during an unfeeling, deep-sleep state.

“Cognitive” and “cognition” can be weasel-words too, if they are used indiscriminately to refer to felt and unfelt states and their unfelt generating processes in the brain. “Cognition” concerns what we can DO (and how and why). “Sentience” concerns whether and when and what we can FEEL (and how and why is mostly the “hard problem”).

C4-2: “Furthermore, this view seems to dismiss advancements made by neuroscientists in correlating brain activity with subjective experiences. While we do not yet have a complete understanding of how the brain produces consciousness, this line of research has provided valuable insights into the biological basis of consciousness.”

SH: I don’t think I dismiss anything from neuroscience. All correlates – whether of felt or unfelt states – are potentially relevant to both the “easy problem” (how and why does the brain produce our capacity to DO all the things people can do?) and the “hard problem” (how and why does the brain produce the capacity to FEEL? 

C4-3: “Third, Harnad’s view might be seen as sidestepping the “hard problem” of consciousness—the question of how and why certain processes in the brain give rise to subjective experiences. Simply defining consciousness as “feeling” doesn’t address this question; it merely redefines the terms of the problem.”

SH:  You’re absolutely right that I am not solving the Hard Problem (HP). In fact, I don’t think it’s solvable. 

The reason I think that is that once the Easy Problem (EP) (which is to provide a causal explanation of DOING capacity by generating Turing-Indistinguishable T3/T4 capacity) is solved, that leaves FEELING itself (which is real but unobservable except by the feeler because of the Other Minds Problem OMP) causally inexplicable. 

This in turn is because the solution to the EP has already used up all the empirical degrees of freedom for a causal explanation. With the EP, everything observable is already explained. 

I suspect that this in turn is (somehow) a result of 

(1) the anomalous nature of feeling, which is not empirically observable except to the feeler because of the OMP, 

(2) the nature of empirical and causal explanation, and 

(3) the nature of feeling. 

Feeling is an “uncomplemented category.” To understand a category. To understand a category requires distinguishing its members from its nonmembers (the category and its complement). This requires detecting the features that distinguish the features of its members from the features of the members of its complement. But the felt category “what it feel like to feel” has no complement. It is self-contradictory.

C4-4: “Conflation of Diverse Phenomena: Critics might argue that defining all conscious states as merely “felt states” fails to distinguish between qualitatively different phenomena. Terms like “awareness,” “subjectivity,” and “phenomenological experience” were developed to describe distinct aspects or levels of consciousness. By lumping all these concepts together as “felt states,” one might be glossing over important nuances and potentially fruitful avenues of investigation.”

SH:  As I said in reply to Question 1, I think these other terms are all just weasel words for felt states. Yes, feelings differ “qualitatively”, but that’s the point: they differ in what they feel like (warm vs. cold, or seeing red vs. seeing green already do that) but they are all felt states, not something else. Feeling is notoriously hard to define verbally (perhaps because “what it feels like to feel” is an uncomplemented category), but the differences among felt states can be names and described, as interlocutors have felt some sufficiently states.

C4-5: “Neglecting Unconscious Processes: Your perspective seems to largely dismiss unconscious mental processes. However, much of cognitive science points to the significant role these play in our mental lives. Memory recall, perception, learning, and decision-making can all involve unconscious processes. By focusing solely on “felt states,” we risk overlooking these critical components of cognition.”

SH:  Most brain states and parts of brain states are unfelt, and can occur at the same time as felt states. And that includes the unfelt states and processes that produce felt states! But it they are unfelt, they are unfelt, even though they may be doing some things that then produce felt states – such as when you finally find a tip-of-the-tongue word. (Moreover, even when a word comes to mind effortlessly, unfelt processes are delivering it – processes that we are waiting for cognitive science to reverse-engineer and then explain explain to us how they work.)

C4-6: “Absence of Felt States: There are situations where conscious awareness seems to occur without an accompanying felt state. For instance, consider blindsight, a condition where individuals respond to visual stimuli they report not consciously seeing. Similarly, during “flow” states, people often report a loss of self-consciousness, even though they’re highly engaged with the task at hand. These examples challenge the notion that all conscious states are necessarily felt.”

SH: Blindsight patients are not insentient. They just can’t see. They may be using felt nonvisual cues or unfelt cues. The real mystery is why all sight is not just blindsight: The “hard problem” is not the absence of feeling in blindsight but the presence of feeling in sight. 

Flow state sounds like concentrated attention on something, ignoring everything else. The rest is just hyperbole. It is a felt state.

C4-7: “Differing States of Consciousness: States such as sleep, anesthesia, coma, and even different levels of alertness during wakefulness demonstrate varying degrees of consciousness. These states aren’t easily characterized as merely “felt” or “unfelt”. What about dreams, where there might be a rich tapestry of felt experience, but arguably a different kind of consciousness than wakefulness?”

SH: A good instance of the mischief of weasel-words. All these “differing” states, whether natural or drug or pathology-induced, are felt states, if and when they are felt. Among them, dreams are felt states too, not unfelt ones (even if forgotten immediately afterward). It’s just that in dream states, movement and sometimes alse recall are inhibited. And no matter how “rich the tapestry” or how weird the feeling, a felt state is a felt state.

C4-8: “Evolutionary Argument: From an evolutionary perspective, consciousness likely evolved as a complex array of adaptive mechanisms. Reducing it to “felt states” might ignore this complexity and the various functions consciousness serves. C4-8b: Neuroscientific Evidence: Neuroscience has made considerable progress in associating specific neural processes with different aspects of conscious experience. Ignoring these findings could be seen as an overly dismissive stance”.

SH:  Yes, calling it by a weasel word makes it sound as if there is more than one thing that is evolving for Darwinian reasons. But whether the question is put in a direct or weaselly way, explaining how and why feeling evolved is one and the same with the Hard Problem.

[Sorry for failing to give C4-8b (neural correlates) a number of its own (I must have been in a “flow state” on something else!) but it’s easily enough answered.]

Nobody has suggested ignoring correlates and predictors of felt states, whether neural correlates or behavioral correlates. But let’s not conflate DOING and FEELING. Neural correlates will no doubt be helpful in reverse-engineering the mechanisms that produce our behavioral capacities (both cognitive and vegetative), the Easy Problem, but when it comes to FEELING they are up against the same Hard Wall as all other approaches (including behavioral correlates and evolutionary explanation).

C4-9: “The Hard Problem Remains: Even if we accept that consciousness is equivalent to “feeling,” this doesn’t necessarily help us solve the hard problem of consciousness. It might clarify our terminology, but it doesn’t explain how and why certain brain processes produce subjective experience”.

SH:  I think calling a spade a spade (and just a spade) certainly does not solve the HP, but de-weaselling certainly clear out a lot of pseudo-explanatory clutter.

I will now reply to the 10th of your 13 critiques. Each separate posting from me will start with one quoted critique from you, preceded by “C4-n:” The quote in each separate posting (1-13) is followed by a reply from me. You can then reply if you wish, or you can just say “I’ll integrate and reply when I’ve seen the rest of your 13 replies.” In that case my next posting will again begin with this same text, followed by my reply the next of your 13 critiques, till the 13^th one, and you can do an integrative rebuttal. 

C4-10: “Lack of Operational Definition: Some might argue that defining consciousness merely as a “felt state” is too vague. In scientific research, it’s important to have an operational definition that can be objectively measured. Without such a definition, research and dialogue about consciousness can become confusing and unproductive.”

SH:  Well, well. I suspect that apart from some die-hard behaviorists whose view of science has not progressed beyond Bridgeman’s operationalism (and who are also still toying with the urge to deny the existence of sentience all together, in favor of just a behavioral correlate), most who have given the Hard Problem some serious thought know that feeling is unobservable to anyone other than the feeler (because of the OMP), hence an operational “definition” is nonsense. 

On the other hand, the Turing Test (T3/T4) – which is just about DOING, hence “behavioral” — is the best predictor we can hope for. But it is not operationalism, and Turing knew it.

C4-11: “Cognitive Science Models: Various models in cognitive science, such as the Global Workspace Theory or Integrated Information Theory, suggest specific mechanisms and structures for consciousness. These models often go beyond just ‘felt states’ and incorporate a range of unconscious and conscious processes.”

SH: Before you can get beyond feeling, you have to face feeling, the EP and the HP. Neither Global Workspace Theory nor Integrated Information does either. (Or do you have something specific in mind?) I think they’re both just doing hermeneutics of “consciousness” not reverse-engineering or explaining a thing. That’s a risk-free venture.

C4-12: “Issue of Self-Reflection: Many philosophers and cognitive scientists believe that one crucial aspect of human consciousness is our ability to reflect upon our own mental states – a form of meta-awareness. Some may argue that your perspective doesn’t adequately address this”.

SH: This is a hoary one. Philosophers have long stressed that there is a difference between (1) being aware of something, (2) being aware of being aware of something and (3) being “self-aware” (as in recognizing yourself in a mirror, or thinking about yourself). We can translate this into the language of seeing and doing too: Seeing something, seeing someone else seeing something, and then seeing that the someone else seeing the something is yourself. These are cognitive capacities, because they may enable you to do things (e.g., moving so it can’t be seen that you are looking). These capacities also obviously have a felt counterpart: It feels like something to do them, as well as to be able to do them. If we substitute “thinking” for “seeing”, they remain very similar cognitive capacities.

So I don’t see how the fact that thinking is a felt state is relevant to whatever cognitive mechanism proves to be able to produce self-reference or metacognition.

C4-13: “Animal Consciousness and AI: A purely subjective, “felt” definition of consciousness could complicate discussions about non-human consciousness (like animal consciousness) and artificial consciousness (in AI systems). Without clear behavioral or objective measures, determining whether an entity is conscious becomes more challenging.”

SH: First of all, because of the OMP, neither sentience (feeling) nor its weasel-words are directly observable. So to predict and infer it depends on behavioral and neural correlates and predictors. Animal sentience has all the correlates and predictors except verbal report. Plant sentience is moot. And AI sentience is sci-fi  so far (and I think you, ChatGPT4, will agree, at least as far as you are concerned.

So again, I can’t see how calling a spade anything other than a spade helps anything except perhaps projecting our fantasies onto insentient systems. I’m not ready to do that before we’re much closer to a grounded T2 robot.