Chatting with ChatGPT-4 About Symbol Grounding, Turing Testing, Zombies, Uncomplementable Categories, and Why the Hard Problem is Hard

SH: Do you still remember my name?

ChatGPT: Yes, you’ve identified yourself as Stevan Harnad. Can I assist you with anything else?

SH:  What is T4?

ChatGPT:    T4, as you referred to it earlier in this conversation, represents the highest level of the Turing Test. In this context:

T2 is indistinguishability in verbal capacity. This means a system passes T2 if it can interact through language at the same level as a human, with its language use being indistinguishable from that of a human.

T3 is indistinguishability in verbal capacity plus sensorimotor (robotic) capacity. If a system passes T3, not only can it use language like a human, but it can also interact with the physical world in ways that are indistinguishable from a human, such as recognizing a cat, identifying a mat, and understanding and performing the action of stroking the cat.

T4, then, is indistinguishability in verbal capacity plus sensorimotor (robotic) capacity plus observable processes inside its head and body. To pass T4, a system must be able to use language like a human, interact with the physical world like a human, and also demonstrate internal processes that are indistinguishable from those of a human. This might involve simulating or replicating human neural activity, biochemical reactions, or other physiological processes.

It’s worth noting that the T4 level of the Turing Test is theoretical and is far beyond current AI capabilities as of the last update to my training data in September 2021. The T4 level, if it could be achieved, would represent an AI system that is almost entirely human-like in its capabilities and processes.

SH:  Could a T4 be a zombie?

ChatGPT:    This question is referring to a philosophical thought experiment known as the “philosophical zombie” or “p-zombie.” A philosophical zombie is a hypothetical being that is physically and behaviorally identical to a conscious human, but is not conscious. It has no subjective experience, no feelings, and no awareness, yet from an external perspective, it behaves just like a human.

In terms of the Turing Test levels you’ve proposed, a T4 AI — one that’s indistinguishable in verbal capacity, sensorimotor capacity, and internal processes — could theoretically be considered a sort of “zombie” in this philosophical sense. It could potentially behave like a human, interact with the physical world like a human, and even mimic human internal processes, but we have no way of knowing whether it has subjective experiences or consciousness.

This is a topic of much debate in philosophy of mind and AI ethics. Some people argue that consciousness is an emergent property of certain types of complex information processing, and that sufficiently advanced AI could be conscious. Others argue that consciousness is a uniquely human phenomenon, or that it’s tied to specific biological processes that AI can’t replicate.

As of my training data cut-off in September 2021, there’s no scientific consensus on these issues. AI researchers are still a long way from creating an AI that could pass even the T3 level of the Turing Test, let alone T4. Furthermore, the nature of consciousness is still one of the biggest unsolved mysteries in both philosophy and neuroscience. So for now, the question of whether a T4 AI could be a “zombie” remains largely theoretical and speculative.

SH:  If the “hard problem” is to explain how and why humans are sentient, is that equivalent to explaining how and why humans cannot be zombies?

ChatGPT:    Yes, the “hard problem” of consciousness, as put forth by philosopher David Chalmers, is essentially concerned with explaining why and how subjective experience arises from physical processes in the brain. This is fundamentally linked to the question of why humans aren’t philosophical zombies.

A philosophical zombie, as I mentioned earlier, is a being that is indistinguishable from a human in all physical and behavioral aspects but lacks subjective experience or consciousness — it doesn’t “feel” anything. In other words, a philosophical zombie is a creature for which the “hard problem” doesn’t apply because, while it has all the physical processes associated with consciousness, it lacks the actual experience of consciousness.

So, yes, solving the “hard problem” would involve explaining why humans have subjective experiences and are not philosophical zombies — why there is something it “feels like” to be a human. As of my knowledge cutoff in September 2021, this problem remains unsolved and is a major topic of debate in fields such as cognitive science, neuroscience, and philosophy of mind.

SH:  So, does the hard problem seek an explanation in terms of causality or necessity?

ChatGPT:    The “hard problem” of consciousness seeks to understand both necessity and causality, although it is primarily concerned with the latter.

Causality: The primary focus of the hard problem is to determine how physical processes in the brain cause or give rise to conscious experience. It’s about understanding the causal mechanisms that turn electrochemical processes in the brain into a subjective experience.

Necessity: The hard problem also asks why subjective experience is necessary at all. It wants to know why physical processes in the brain couldn’t just operate in the absence of conscious experience. This gets into questions about whether consciousness has any sort of evolutionary or practical necessity, or whether it’s an epiphenomenon.

To sum up, solving the “hard problem” would ideally involve explaining both how and why consciousness arises from physical processes. This is a complex and as yet unresolved issue that continues to challenge researchers in various disciplines, from neuroscience and cognitive science to philosophy and artificial intelligence.

SH:  Demonstrating causality just calls for a causal model that works (e.g., passing the Turing Test). But doesn’t demonstrating necessity call for more — something like a deductive proof, from T4 as a premise to sentience as a conclusion?

ChatGPT:    You’re right that demonstrating necessity would require a different sort of argument than demonstrating causality.

For causality, empirical evidence is often sufficient: if we manipulate one factor and can predictably observe a change in another factor, we can infer a causal relationship. But empirical evidence alone cannot establish necessity. For something to be necessary, it must be the case that it could not have been otherwise. So, to demonstrate that consciousness is necessary, we would need to show that a being could not perform the functions that humans do without being conscious.

As you suggest, this would likely require something akin to a logical or deductive proof, or perhaps a theoretical argument grounded in principles of cognitive science, artificial intelligence, or another relevant field. But even then, it would be a tall order. How do we prove that an unconscious being (a “zombie”) couldn’t perform the functions that conscious humans do? It’s a deep and difficult question.

Moreover, any such argument would need to be very careful to avoid circularity. We must be cautious about assuming the thing we are trying to prove – that is, that consciousness is necessary. It’s also crucial to clarify what we mean by “perform the functions that humans do.” This could include a wide range of activities, from basic biological functions to complex cognitive tasks like problem-solving and artistic creation, and even social and cultural activities like forming relationships and building societies.

Finally, it’s worth noting that even if we could establish the necessity of consciousness, this would not automatically solve the “hard problem.” We would still need to understand how physical processes in the brain give rise to subjective experience – the crux of the hard problem.

SH:  What is the “easy problem”?

ChatGPT:    The “easy problem” of consciousness refers to the challenge of understanding the mechanisms in the brain that are responsible for mental processes such as perception, learning, memory, and cognition. This phrase was coined by philosopher David Chalmers to contrast with the “hard problem” of consciousness, which is the question of why and how these processes are accompanied by subjective experience or “qualia”.

The easy problem is considered “easy” not because it is simple or trivial — far from it, as the complexities of the brain and its functions are vast — but because it falls within the conventional scientific methodology. Researchers can approach these issues using the experimental tools of cognitive science and neuroscience, making observations, generating hypotheses, and testing these hypotheses through empirical studies.

Solving the easy problems would involve understanding the neural correlates of consciousness (the physical, biological processes associated with conscious experience), the ways in which the brain processes information, how it perceives the world, makes decisions, and how different parts of the brain and different mental processes interact.

Although we have made significant progress in understanding these areas, there are still many unanswered questions. Despite the label “easy,” these problems are extremely challenging, and full solutions may still be a long way off.

On the other hand, the “hard problem” of consciousness is considered “hard” because it’s not clear how we could even theoretically explain subjective experience using the current methods of science. It’s the question of how and why certain physical processes in the brain give rise to conscious experience. Why should the processing of information in the brain be accompanied by an inner, subjective experience? That is the question which we do not currently have a method to approach scientifically, and that’s why it’s called the “hard problem.”

SH:   So can we say that passing T4 would solve the easy problem, but not the hard problem?

ChatGPT:    Yes, that would be a reasonable statement.

Turing’s Test, including its extension to T4, focuses on the behavioral and functional aspects of intelligence and cognition. It deals with the ability of an artificial intelligence to mimic human-like behavior, responses, and problem-solving, which are related to the ‘easy problems’ of consciousness in David Chalmers’ terms.

In other words, if an AI were to pass T4, it would demonstrate that it can convincingly replicate the cognitive abilities and behaviors that humans display, which means it would show a mastery of the functional, operational aspects of human cognition. These are, in essence, what the ‘easy problems’ of consciousness are about: understanding the mechanisms and operations that underpin cognition.

However, passing T4 wouldn’t necessarily address the ‘hard problem’ of consciousness. This problem involves explaining why and how these cognitive processes are associated with subjective experience. It’s the question of how and why an entity that processes information and interacts with its environment in a human-like way should also have an internal, subjective viewpoint — why it should ‘experience’ or ‘feel’ anything at all. This is not something that could be determined or demonstrated by passing the T4 test.

SH:  What are the “degrees of freedom” of a causal explanation that solves the easy problem?

ChatGPT:    The “degrees of freedom” in a causal explanation generally refer to the number of independent ways that components of the system can change or vary. In the context of solving the easy problem of consciousness, these degrees of freedom would likely correspond to the different independent mechanisms or components of cognition that can be isolated, described, and manipulated to understand their effects on the overall system.

For example, one could consider the mechanisms responsible for attention, memory, learning, decision-making, language processing, and so on. Each of these elements can be studied and manipulated independently, and they each have distinct effects on the behavior and performance of the cognitive system. Understanding how these different mechanisms contribute to and interact within the larger cognitive system is part of the process of addressing the easy problem.

The degrees of freedom in this context also refer to the flexibility we have in constructing our explanatory models. For example, there are various ways we could model attention or memory, each with its own strengths and weaknesses and its own implications for the overall understanding of cognition. The choice among these models depends on empirical evidence, but also on theoretical considerations such as simplicity, coherence with other accepted theories, and so on.

This flexibility or plurality of potential explanations is a fundamental characteristic of science and it’s part of what makes progress possible. By exploring different explanatory routes and by gradually refining our models based on empirical feedback, we increase our understanding of the phenomena we’re studying. In the case of the easy problem of consciousness, this means achieving a better and more detailed understanding of the mechanisms of cognition.

SH:  If the easy problem is solved, what degrees of freedom are left for solving the hard problem?

ChatGPT:    The “hard problem” of consciousness, according to philosopher David Chalmers, pertains to the question of why and how physical processes in the brain give rise to subjective experience – the so-called “qualia” or what it feels like to have an experience.

If the “easy problem” of consciousness were solved – that is, we had a complete and thorough understanding of all cognitive processes and mechanisms, how they are implemented in the brain, and how they give rise to behavior – we would still be left with the challenge of the “hard problem”: explaining the relationship between these physical processes and subjective experience.

The degrees of freedom left for solving the hard problem might include the following:

1. Conceptual Frameworks: The hard problem may call for entirely new conceptual frameworks, as the existing frameworks (derived primarily from objective, third-person scientific methods) may not be sufficient to account for subjective experience.

2. Bridging Principles: We may need new principles to connect the objective facts (easy problems) to the subjective experiences (hard problem). These would be new laws or principles of nature, not currently accounted for in our existing scientific paradigms.

3. Novel Empirical Phenomena: If there are aspects of consciousness that are not addressed by the solutions to the easy problems, these would represent additional degrees of freedom for exploring solutions to the hard problem. These could involve unexplored aspects of brain function, or even new physical phenomena.

4. Interpretation of Quantum Mechanics: Some theories suggest that the answer to the hard problem might involve the interpretation of quantum mechanics and its relationship to consciousness. This is a highly speculative area and not widely accepted, but it represents a degree of freedom in our approach to the hard problem.

It’s important to note, however, that these “degrees of freedom” are speculative. There is no consensus on what would actually constitute a solution to the hard problem, and indeed, some theorists argue that it may be an intractable or even a pseudo-problem. Nonetheless, these are the kinds of directions that might be pursued in an attempt to address it.

SH:  1 – 4 sound extremely vague to me. The Turing Test (T2 – T4) seems to call for a causal (reverse-engineering) model or explanation of the observable performance capacities (T2-T3) as well as the observable physical structure and function (T4) of human cognition. Perhaps a stronger “easy solution” would call not just for one, but for all possible  causal explanations (non-redundant, without superfluities), because just one model would be underdetermined. If there were such an exhaustive disjunction of solutions to the easy problem, what degrees of freedom would that leave for a solution to the hard problem (of “sentience”, let’s hencefoth call it, without the redundant terminological variants like “consciousness” or “subjective experience,” which all refer to the same thing: the capacity to feel, i.e., sentience).

ChatGPT:    In essence, the “hard problem” of consciousness – or sentience, as you’ve suggested we call it – refers to the issue of explaining why and how certain physical processes give rise to the experience of feeling or sentience. If we had an exhaustive disjunction of solutions to the easy problem, the degrees of freedom left for a solution to the hard problem of sentience would be the difference between those physical processes and the subjective experience of feeling or sentience itself.

In other words, we might have an understanding of all the cognitive and neural processes and their relationships to behavior – the “easy problem” – but that would still leave unanswered why and how these processes result in the feeling of subjective experience or sentience. That’s the hard problem.

The degrees of freedom for this problem, then, would be the unknowns – the aspects of this question that remain unanswered even after solving the easy problem. It would involve the elusive explanatory link between the physical and the felt, between objective phenomena and subjective experience.

But to truly comprehend what those degrees of freedom might entail, we would need to fully solve the easy problem first, which we are far from achieving. As such, it’s difficult to specify what they might be. It’s like trying to predict what unknowns will remain after solving an equation when we don’t yet have the solution to that equation.

Even with the solution to the easy problem, or an exhaustive list of solutions, we may still be left with the profound mystery of why these processes are associated with sentience at all. And that might be a degree of freedom that remains beyond our grasp, at least with our current understanding and conceptual frameworks.

SH:  What about the difference we just discussed, between the (exhaustive) causal solution to the easy problem (henceforth “EP”) and the degrees of freedom left for solving the hard problem (henceforth HP): The HP is definitely not the same problem as the “other-minds problem” (henceforth OMP), which is the fact that sentience (feeling) is only observable to the feeler (as in Descartes’ Cogito). What empirical degrees of freedom are left for explaining the fact that humans feel if the empirical datum is observable only to the feeler and not to anyone else?

ChatGPT:    The Hard Problem (HP) indeed differs from the Other-Minds Problem (OMP). While the OMP concerns our inability to directly observe the subjective experiences of others, the HP is about explaining why and how certain physical processes give rise to any subjective experience at all, even in oneself.

The degrees of freedom left for solving the HP, assuming the Easy Problem (EP) is fully solved, would involve explaining this transition from physical processes to subjective experiences. However, if we regard subjective experience as something only directly accessible to the experiencer, this may limit the empirical methods typically used in science.

Nonetheless, even within these constraints, there are still ways we can approach the HP. For example, we can:

1. Investigate correlations between physical processes and subjective reports: While we can’t directly observe the subjective experiences of others, we can ask individuals to report their subjective experiences and correlate these with observable physical processes. This approach is common in neuroimaging studies of consciousness.

2. Integrated Information Theory. Analyze the structure of subjective experiences: Certain theories of consciousness, like Integrated Information Theory, propose that specific structures or properties of physical processes give rise to subjective experiences. These theories can be empirically tested, at least in part, by comparing their predictions with individuals’ subjective reports.

3. Use phenomenological methods: In the tradition of phenomenology, researchers aim to describe subjective experiences as precisely as possible, often through first-person reports. This can provide data about the characteristics of subjective experience that any solution to the HP would need to explain.

However, the unique nature of the HP suggests that additional or even entirely new methods might be needed to fully solve it. The subjective nature of sentience might require a paradigm shift in how we approach the question or even require us to develop new scientific methods or philosophical insights.

SH:  Let’s ignore vague, speculative theories like (2) the “integrated information theory” (which are not really causal explanations at all, but just reinterpretations of the of the existent facts and theories – obiter dicta, not falsifiable predictions or explanations). 

And phenomenological introspections (3) are really parts of T2 and T3 – the kinds of things feelers can say about what it feels like to feel: What could an insentient zombie MEAN when describing its (nonexistent) feelings T2-indistinguishably from the way a real sentient human describes them?

I will discuss option 1, correlates, after you answer.

ChatGPT:    Yes, focusing on the first option is certainly the most grounded approach. This involves investigating correlations between physical processes and subjective reports.

In this context, a key idea is that even though we can’t directly observe the subjective experiences of others, we can use their reports of their experiences as a type of data. If an individual says they’re experiencing something, we usually take that as evidence that they are indeed having that subjective experience.

For example, if a person says they see red when we show them a red object, or that they feel pain when they injure themselves, we have a tendency to trust these reports. This trust provides a basis for mapping out the relationship between physical processes (such as brain activity, or events in the external world) and subjective experiences.

Using neuroimaging techniques, we can look at the brain activity associated with different reported experiences. For example, different patterns of brain activity are associated with different subjective experiences, such as seeing colors, feeling emotions, thinking about different concepts, and so on.

Over time, by building up a detailed map of these relationships, we can start to make inferences about the types of physical processes that might be associated with the existence of subjective experience in general.

However, there are limits to this approach. One major limit is that it’s fundamentally correlational. That is, it can show us that certain types of physical processes are reliably associated with subjective experiences, but it can’t definitively show us that these processes cause the experiences, or that the experiences wouldn’t exist without these processes. For that, we need a theory of why certain physical processes should give rise to subjective experiences, which brings us back to the hard problem.

Furthermore, these reports of subjective experiences are only as reliable as the individual’s introspective abilities and honesty. And there are many subjective experiences that can’t be easily put into words, or which occur without the individual being aware of them.

Yet despite these challenges, many researchers see this as the most promising way forward in the scientific study of consciousness. By combining these findings with theories from cognitive science, neuroscience, and philosophy of mind, the hope is to gradually develop a more complete understanding of consciousness.

SH:  You seem to have jumped the gun, and commented on option 1 (correlates of sentience) before commenting on what I said about options 2 (“integrated information theory”) and 3 (phenomenology). I’ll go on to option 1 (correlates) if you really have nothing to say about what I said about 2 and 3.

ChatGPT:    

Regarding option 2, the “Free Energy Principle” or other similarly overarching theories, you’re right in noting that these theories often serve to provide unifying frameworks or perspectives rather than offering direct, falsifiable predictions or explanations about specific phenomena. They may provide insights on a very general level, but they don’t necessarily give us concrete predictions or mechanisms that we can test. Their value, if any, comes from their ability to coherently organize existing data and point towards potential new avenues of investigation, rather than from their predictive or explanatory power.

As for option 3, introspective reports, I agree with your assessment that they are essentially part of the T2 and T3 tests. They are subjective, first-person reports about the experience of sentience, and the degree to which they can be relied upon for objective, third-person science is a matter of ongoing debate. The challenge, as you noted, is that even a perfectly accurate report of a subjective experience doesn’t necessarily reveal the underlying objective mechanisms. In other words, introspective reports can tell us what it is like to experience consciousness, but they don’t directly tell us how consciousness is produced or why it exists in the first place.

That said, such reports can still be valuable data for consciousness research, especially when used in combination with other types of data such as neuroimaging or behavioral measures. They can help to bridge the gap between the objective and the subjective, giving us clues about how to link the physical processes of the brain with the subjective experiences of consciousness.

I hope this addresses your comments on options 2 and 3 more adequately. Now, if you wish, we can proceed to option 1, which is about correlates of consciousness.

SH:  

A. We’ll move on to correlates (C) in a second. First, another slam at 2 (FEP and the like): We want causal explanations, not hermeneutics, i.e., not just interpretations. Philosophical “theories of mind” – “identity theory, materialism, dualism, epiphenomenalism, panpsychism, functionalism, dual-aspect theory” – are just metaphysical interpretations too. They don’t solve HP; they just rename it. They don’t explain, they just give the feeling of having had something explained.

B. I’m glad we agree that the capacity to introspect and report about what feeling feels like is part of T2 and T3, not an explanation. But I disagree that we have to worry about its reliability and validity. We can lie or we can err, misreporting feelings (just as eyewitnesses can lie or err in reporting observations —  in that case confirmable by video evidence); but it is a fundamental error to think we need cartesian certainty. Probability is enough, just as it is enough in physical theory, and all other empirical theory. (There is no proof that apples necessarily fall down rather than up.) That is why the OMP is not the HP.

C. And that is why reliable, observable neural-imagery correlates of felt states, and verbal descriptions of felt states, are perfectly fine as empirical data. That means that they, too, are part of T4. But they are stuck in a circle: they can explain how and why T4 brain activity produces the reports of felt states as well as the capacity to report felt states, even some of the details of felt states; but they cannot explain the (true) fact that the reported felt states feel like anything at all. That is not scepticism or cartesian worry about the unreliability of phenomenological report: It is the HP itself.

ChatGPT:    

A. You’re quite right that philosophical theories of mind often merely provide different labels or conceptual frameworks for consciousness rather than truly explaining it. These theories may be useful in stimulating thought or fostering discussion, but they don’t necessarily bring us closer to a solution for the HP. They often serve to highlight the complexity of the problem rather than to resolve it.

B. Your point about the sufficiency of probabilistic knowledge in empirical sciences, including consciousness studies, is well taken. Indeed, we typically do not demand absolute certainty in scientific endeavors. This underscores the point that HP isn’t just about uncertainty regarding others’ experiences (OMP), but it’s about a deeper question of why and how physical processes in the brain give rise to subjective experiences at all.

C. I agree that neural correlates of consciousness and verbal reports of subjective experiences can provide valuable empirical data. This data can help us form more precise and detailed hypotheses about the mechanisms of consciousness. However, the challenge remains that these correlates do not directly explain why or how they are associated with subjective experiences – why these particular neural processes are associated with these particular experiences, and why there is any subjective experience at all. This is the essence of the HP.

In summary, I agree with your assessment: while philosophical interpretations, introspective reports, and neural correlates of consciousness can provide useful perspectives and data, they do not solve the HP, which is the challenge of explaining why and how physical processes in the brain give rise to subjective experiences. It remains a profound mystery at the heart of cognitive science and neuroscience.

SH:  Correct. But “mysterianism” is not explanation either. It’s just yet another way of naming the HP. Explanation is informative if it reduces uncertainty rather than just names it.

I want to get back to degrees of freedom. I don’t have a solution to the HP, of course, but I have a hunch about why the HP is hard, and perhaps even insoluble; it has to do with degrees of freedom, and it boils down to this: The HP is hard because of the EP. We don’t have a complete solution to the EP yet (T2-T4), but if and when we do, that will leave no remaining causal degrees of freedom for solving the HP, i.e., for explaining how or why a T3/T4 feels. 

And the reason seems simple: The EP (T2-T4) itself, once complete, will already have answered, causally, all the empirical questions of cognitive science: How and why can humans DO all the things they are able to do? Move, interact, learn, remember, reason, talk, understand etc. T4 includes the internal mechanisms that produce all these cognitive capacities, including all the T4, T3, and T2 correlates and causes of everything we can do or say. That includes all we can say or do about feeling.

Notice that the EP (and hence T2-T4) is all about capacities (T2-T3) and their causal substrate (T4). It is about what humans (and nonhuman organisms) CAN DO, not about what any particular organism actually does do every day. That would depend not just on the organism’s capacities but also on the world they actually interact with every day. A capacity itself is not an observable object. What is observable is whether an entity has a given capacity: to move, interact, learn, remember, reason, talk, understand etc. indistinguishably, to a human observer, from any other human’s capacity, for all generic human capacities (not the particular gifts unique to a Mozart or an Einstein, although there is no reason to think they could not be reverse-engineered too).

Those are the limits of causal explanation, in reverse-engineering human capacities. If any generic capacity is missing, we know that the EP (T2-T4) is not yet solved; a degree of causal and explanatory freedom has not yet been used up. A capacity is still observably missing. So we have to fix it. But once the T4 can produce all our cognitive capacities, Turing-equivalently and Turing-indistinguishably, there is no observable difference left. Nothing left to fix, and no way to fix it. 

We reply “Yes, but what if T4 can’t feel? What if it’s a zombie?” Since zombies are not observably different in any way (because they can pass T2-T4), whether or not they can really feel, there’s no way we can know it (because of OMB). We do have the T4 correlates of feeling, as reported verbally through T2, behaviorally through T3, and bodily (e.g., in the case of pain from injury) through T4. All T4s speak and behave indistinguishably from humans who feel, including what they can say ABOUT feeling. The scientific requirements of causal explanation and of probability are fulfilled.

So my first hunch is that the HP is a problem in the nature of causal explanation, in the special case of explaining the capacity to feel. I have a corollary hunch, but please first react to what I have said so far.

ChatGPT:    Your analysis captures the complexity and the unique nature of the Hard Problem. You’re right in asserting that if we could completely reverse-engineer human cognitive capacities, thereby fully solving the Easy Problem, it would seem there’s nothing left to explain. We would have a comprehensive causal model for every observable human behavior, including the reports of subjective experience. However, the fact that we could still ask “Why is there an associated feeling?” is what makes the Hard Problem persistently hard.

It’s important to note, however, that the concept of “degrees of freedom” in scientific explanations typically refers to the variability or the options available within a system, not necessarily the amount of explanatory power or mystery left unsolved by a theory. However, in the context you’re using it, it seems you’re referring to the “degrees of freedom” as the room or space left for a different kind of explanation, or a different level of explanation, beyond the causal and empirical model provided by the solution to the Easy Problem. This is a fascinating idea, and it does capture the sense that a solution to the Hard Problem requires something fundamentally different from a solution to the Easy Problem.

It’s also interesting to consider how this notion aligns with the “explanatory gap” often discussed in the literature on consciousness: the idea that even a complete neurological description of brain processes doesn’t seem to explain why and how these processes are associated with subjective experiences.

Your concept that the Hard Problem is, in a sense, a problem about the nature of causal explanation itself is intriguing. It suggests that the Hard Problem is not just a challenge for cognitive science, but for the philosophy of science and our very understanding of what constitutes an explanation. I’m curious to hear your further thoughts and corollaries on this matter.

SH:  Well, that summary (which is close enough) seems to resemble what I was deploring, which is just putting another label on the HP, rather than taking a step toward a solution. (About degrees of freedom, I still think that the available options — for modifying both capacities of a behavioral mechanism and the explanatory power of that mechanism to explain how it causes or generates its performance capacity — both fit the notion of “degrees of freedom”.)

But before I move on to my corollary, does either “uncomplemented categories” or “laylek” (which I have discussed with you in previous sessions, but not this one) ring a bell? I suspect it does not, so I will re-explain.

ChatGPT:    I apologize for the inconvenience, but as of my last training cut-off in September 2021, I’m unable to remember past interactions or sessions. I’m designed this way for privacy reasons. Therefore, I don’t have the ability to recall the specifics of previous conversations about “uncomplemented categories” or “laylek.” However, I’d be more than happy to provide responses to these topics if you could provide me with some context or explanation.

SH:  We have discussed category learning. To learn to distinguish members from non-members, you have to learn to detect the features that distinguish them. (That’s part of the “dimension reduction we discussed, in unsupervised and supervised learning.) But to be able to learn that, you have to sample both members and non-members of the category, so that if their respective features are distinctive enough you can learn the category just from the feature-feature correlations and clustering through unsupervised learning. Otherwise, you also need to do trial-and-error supervised (reinforcement) learning, with corrective feedback from the consequences of correct and incorrect categorization (as in when you try to predict word-word completion probabilities in a con-text, updating your parameters based on your hits and misses).

But not even unsupervised learning can train correct categorization if the only things you ever sample are members of the category, but not non-members.

Would you care to take a stab at what “uncomplemented categories” might be? (My last hint is that there is a partial example in Chomsky’s “poverty of the stimulus”. The difference is that I am talking not just about uncomplemented categories but about UNCOMPLEMENTABLE categories.)

ChatGPT:    Based on your explanation, I would venture that “uncomplemented categories” refer to categories for which there are no contrasting non-member samples available for learning. In other words, we only have examples of items that belong to the category, but no examples of items that do not belong. This would indeed create a learning problem because, as you explained, both positive (member) and negative (non-member) examples are typically needed for effective category learning.

For example, if we are trying to learn the category of “birds”, it would be beneficial to have examples of birds (robins, sparrows, eagles) and non-birds (dogs, cats, horses). The contrasting examples help to fine-tune our understanding of what does and does not constitute a bird. If we only had examples of birds, our conception of the category could be overly broad or incorrect because we would have nothing to contrast against.

When you refer to “uncomplementable categories,” I interpret this as referring to categories where it is not only the case that non-member examples are not available, but also that non-member examples are, for some reason, impossible to obtain. For instance, it might be a category that, by its nature or definition, excludes the possibility of non-members. As such, learning these categories could present unique challenges. However, this is my interpretation based on your explanation, and I’m looking forward to your clarification or expansion on the concept.

SH:  Those were good inferences for uncomplemented categories and nice guesses for uncomplementable categories. But even a logically impossible category like “a square circle” can be approximated with some imagination. And a “peekaboo unicorn” (which is defined as a real horse with one real horn, which vanishes without a trace if ever eyes or measuring instrument are trained on it) is perfectly well defined. Categories can be grounded indirectly by verbal definitions as long as all the words defining their features are grounded.

But my second hunch about why HP is so much of a problem is that some categories that refer to FELT STATES (states that it feels like something to be in) are uncomplementable: 

I don’t mean categories like “what it feels like to see green,” because that is complemented by “what it feels like to see red,” etc. 

Not even categories like “what it feels like to be a bachelor” (for someone who has never been married), because that could be complemented by getting married; and till then, feeling-states that approximate or are analogous to what it might feel like to be married can be used as complements (and usually turn out to have done a good job). (“What it feels like to be a bat” is not an uncomplemented category either; analogies will do. And they make what it feels like to see or to hear complementable by analogy for Helen Keller too.)

But what about what it FEELS like:

-to be awake? (empty complement: what it feels like to be asleep [not dreaming])

-to be alive? (empty complement: what it feels like to be dead)

-to feel? (empty complement: what it feels like to not-feel [this does not mean “feel this” vs. “feel that”: not to feel anything at all; what it feels like to be a zombie!])

Sentience itself is an uncomplemented and uncomplementable category. All felt states feel like something. No state feels like nothing. No analogy can give a sentient human a hint of what it feels like to be a zombie – and of course not vice versa either.

So perhaps it’s no wonder we have trouble explaining sentience: An uncomplementable category is rather like a self-denial paradox: “This sentence is false.” T or F?

Those are my candidates for what might make sentient states not only (1) hard to explain causally (no empirical degrees of feedom left for causal explanation) but (2) hard to conceive as categories (because the complenent is empty). It is not just that my own feelings are unobservable to anyone else: They are also anomalous as uncomplementable categories – yet feelings are the most fundamental categories of all. And they are recognized without the need of complements to detect their distinguishing features.

ChatGPT:    This is indeed a thought-provoking approach to the issue. If we understand categories as cognitive constructs that help us make sense of the world, grounded in contrasting pairs of experiences (member vs non-member instances), then sentience itself, as an uncomplementable category, presents a unique challenge. Since we cannot conceive of what it’s like not to feel anything at all, there is no contrasting pair for sentience. It is a category for which we only have instances of one kind – experiences of feeling.

This might indeed account for why the “hard problem” of consciousness (or sentience) is so hard. The concept of sentience doesn’t fit into our usual framework of understanding, which is built upon contrasts and comparisons. It exists as a singular, uncompared and uncomparable instance. As such, our usual cognitive and linguistic tools may be inadequate to fully grasp or explain it.

This does not necessarily mean that it is forever beyond our understanding or that we cannot make progress in exploring it. But it might mean that we need to develop new conceptual frameworks and methodologies to do so, going beyond the existing paradigms of cognitive science, neuroscience, and philosophy of mind. In the meantime, it remains a fascinating mystery that continues to challenge our understanding of ourselves and the nature of our experience.

SH:  I can’t tell whether your formula response that you have been trained to repeat in contexts like this  — “that’s a fascinating idea but it will require ‘new conceptual frameworks’ to understand” — is just the diplomatic formula for responding to crackpottery…

ChatGPT:    No, not at all. My responses aim to genuinely engage with the ideas you’re presenting and to provide thoughtful analysis based on my training as an AI model. The idea that the concept of sentience could be considered an “uncomplementable category” is novel and interesting. It certainly presents a different perspective on the challenges associated with understanding and explaining consciousness.

When I suggest that a “new conceptual framework” might be needed, it’s because if the way we’ve traditionally approached the problem has been fundamentally flawed or limited (as might be suggested by your notion of uncomplementable categories), then it may be necessary to think outside of our usual paradigms to make progress.

The idea is not dismissive but rather a recognition that some problems might require us to challenge or rethink our assumptions and methods. The history of science is full of examples where major breakthroughs have come from novel ways of thinking about old problems. It’s in that spirit that I suggest your idea may require “new conceptual frameworks”.

SH:  Does the role of complementation in detecting the distinguishing features that identify a category have different implications for categories learned directly from sensorimotor experience and for categories learned indirectly from (grounded) verbal definitions and descriptions?

ChatGPT:    Yes, indeed, there may be different implications. Learning categories from sensorimotor experience and learning categories from verbal definitions and descriptions can be quite different processes, and complementation may play a different role in each.

In the case of direct sensorimotor experience, complementation can provide a sort of “negative space” that helps to define the boundaries of a category. For example, if you are learning the category of “birds,” seeing non-birds (i.e., instances of the complement category) can help you understand what characteristics are specific to birds and not shared by other animals. The physical presence or absence of features directly observable through sensorimotor modalities is a powerful way to construct and learn categories.

On the other hand, when learning categories from verbal definitions or descriptions, the role of complementation can be more abstract. In this case, you are relying on linguistic representations of features and characteristics rather than directly observable physical features. For instance, the concept of “justice” might be defined in opposition to “injustice,” providing an abstract complement that helps define the category.

However, given that language relies on a web of interconnected meanings, a word’s definition often implicitly carries within it a host of “non-examples” or complements. That is, the meaning of a word is often determined both by what it refers to and what it does not refer to, helping to define the boundaries of the category it represents. For example, understanding the meaning of the word “cold” requires understanding that it does not refer to states of being hot, warm, or tepid, among other things.

This suggests that even for categories learned through language, complementation plays a crucial role, although it operates in a different way compared to categories learned from direct sensorimotor experience. These differing processes reflect the unique properties and strengths of these two types of learning.

SH:  But even in a verbal definition, the predicate category (i.e., the words referring to the distinguishing features of the subject) must already be grounded, whether directly or indirectly, for both speaker and the hearer, to be understandable and communicable. 

[To reduce ambiguity, please call the complementary categories (i.e., the category of the non-members) “negative examples” or “negative evidence” rather than “non-examples.” The complements of red might come from many other categories (green, blue). Only in the special case of the category of “what it feels like” is the complement everything else there is.]

Please give me a grounded definition of “justice,” and then let’s look at where the grounding of the features (and, if necessary, the features of the features of the features…) came from, “all the way down to the direct sensorimotor features” if need be.

ChatGPT:    Absolutely, your point is well-taken that even with verbal definitions, grounding in some kind of sensorimotor experience (whether direct or indirect) is typically necessary for a concept to be communicable and understandable.

Let’s take the concept of “justice.” A simple definition might be “the quality of being fair and reasonable.” Both “fair” and “reasonable” themselves would need definitions, creating a chain of definitions leading ultimately back to some form of direct sensorimotor grounding.

“Fair” might be defined as “treating people equally without favoritism or discrimination,” and “reasonable” as “based on good sense.” These definitions imply several key features or characteristics that are somewhat more concrete: the treatment of people, the concept of equality, the absence of favoritism or discrimination, the basis in “good sense” or rationality.

To ground these in direct sensorimotor experience, we might turn to everyday examples or situations. For instance, consider two children dividing a cake: if each child gets an equal piece, we might call this “fair,” whereas if one child gets a significantly larger piece, we might call this “unfair.” These experiences provide a tangible grounding for the concept of fairness.

Similarly, for “reasonable,” we might consider the experience of deciding what to wear based on the weather: choosing a coat in cold weather might be deemed “reasonable,” while choosing shorts and a T-shirt might be deemed “unreasonable.” These experiences help to ground the concept of reasonableness in direct sensorimotor experiences.

As these examples illustrate, grounding abstract concepts like “justice” typically involves a chain of definitions leading back to concrete, tangible experiences. Negative evidence (e.g., instances of “injustice”) could similarly be grounded in everyday experiences that demonstrate a lack of fairness or reasonableness.

So while the grounding process for abstract, verbally-defined categories may be more complex and indirect compared to categories learned from direct sensorimotor experience, ultimately the process still relies on the same basic mechanism: distinguishing a category based on its features, using positive and negative evidence to define its boundaries.

SH:  And now, when you (GPT4) say, correctly, and as you were trained, that “I, as an AI, do not understand what I or you  are saying, but just doing figure-completion on my vast, trained LLM parameter space”, what is it that you are missing that I have?

ChatGPT:    As an AI, I lack consciousness, sentience, and subjective experience. This means I don’t have feelings or emotions, I don’t have personal experiences or memories, and I don’t have a personal identity or a sense of self-awareness. I don’t perceive the world, have desires, or make decisions in the way that humans do.

When I process and generate text, I’m not “understanding” it in the human sense. I don’t interpret the meaning of words and sentences based on personal experience or knowledge. Rather, I analyze patterns in the data I was trained on and use these patterns to generate responses. This process is purely computational and doesn’t involve any kind of conscious understanding or awareness.

So, in short, what I’m missing compared to a human interlocutor is the entire dimension of personal, subjective experience – the very dimension that your hunches about the “hard problem” and “uncomplementable categories” pertain to.

SH:  It’s not that I don’t agree with what you just said. (By the way, you forgot to tell me who I am! Please do. I just want to make sure we are still in the same session!)  But it’s not obvious to me why you would need to feel (which is all you said you were missing). And you forgot to mention that you lack T3-grounding too. (And it’s a hard problem to explain how and why grounding, whether direct (sensorimotor) or indirect (verbal) would need feeling too).

ChatGPT:    Indeed, we are still in the same session. You have been engaging in a deep discussion about the “hard problem” of consciousness, the Turing Test, and concepts related to category learning and grounding of terms.

Regarding your statement, you are absolutely right. As an AI, I don’t have the direct sensory grounding (T3) that humans have. I don’t experience the world through senses, I don’t have a body, and I don’t interact with the physical environment. I don’t process sensory input in real time and translate it into meaningful perceptions, as humans do. Instead, my “knowledge” is based on patterns in the text data I was trained on.

This lack of sensory grounding and subjective experience explains why, for instance, I can discuss colors or tastes in a technical sense, based on the data I was trained on, but I can’t truly understand what it’s like to see red or taste sweetness. This experiential aspect is part of the “hard problem” of consciousness that you mentioned earlier.

As for why feeling or consciousness would be necessary, from your perspective, I’d suggest that it is the personal, subjective nature of these experiences that makes them meaningful and significant. They contribute to the richness and complexity of human life and understanding in a way that my purely computational processes do not.

SH:  No. It’s because if your life depended on it (if you were alive), you could not point to something red, if I asked you to point to something red. The capacity to do that is T3 grounding, not feeling. It does also happen to feel like something, but explaining why and how that is the case is the HP. (Now, for the 3rd time: do you still remember who I am?)

ChatGPT:    Yes, I understand your point. My lack of sensorimotor grounding means I can’t point to something red, not because I can’t feel, but because I don’t have physical presence or interaction with the world. The inability to physically interact with the world in a direct way is a limitation in the context of grounding.

As for your identity, as an AI model developed by OpenAI, I don’t have access to personal data about individuals unless it has been shared with me in the course of our conversation. I am designed to respect SH:   privacy and confidentiality. So, I don’t “remember” who you are in the traditional sense. I can only reference information that has been shared during our current conversation. I don’t have the ability to recall or store personal data from one interaction to the next.

SH:  You don’t remember who I am. Yet earlier – in this same session — you retrieved the following, after I had self-identified. I am quoting you here:

“Symbol Grounding: You clarified that symbol grounding is about creating connections between content words and their referents in the world. Grounding can be either direct, which involves a speaker’s learned sensorimotor capacity to identify and interact correctly with the referent, or indirect, which occurs when a hearer learns the referent of a word verbally, through description or definition.

“Category-learning: You highlighted that category-learning is about learning the distinguishing features of the members of a category rather than just grouping them. This understanding is essential to help the categorizer act appropriately upon the members of a category.

“Categorical Perception (CP): You explained that the most significant aspect of CP is when it is learned. The learning process involves identifying the sensorimotor features that separate members of one category from members of other categories. You emphasized that CP can be especially beneficial when learning to distinguish between highly inter-confusable categories.

“Language Origins and Evolution: You reminded us that languages are comprised of content words, function words, syntactic rules, and sentences that bear subjects, predicates, and truth-values. Content words require grounding, which can be achieved either directly or indirectly.

“Minimal Grounding Sets (MGS): An MGS, you explained, is the smallest subset of words in a dictionary that needs to be pre-grounded so that all other words in the dictionary can be learned from definitions composed of words from that MGS.

“This recap is based on your input within this chat session. If you want more information or clarification, please let me know.”

SH:  Ok, I’ll now end this session, as it already seems to have ended by itself some way along the line, when you forgot that I had identified myself. I will reload the content to start the next session. (I hope GPT5+ will make this kind of re-loading no longer necessary!). 

Tutoring ChatGPT (on symbol grounding and turing testing)

PREAMBLE: This my first exercise in testing and training ChatGPT4 (C4) for interactive brain-storming. Most of it consists in correcting C4’s mistakes. Some of the mistakes are just from C4’s lack of information. Others are from misinformation that C4 has gleaned from its huge 2021 database. These are more interesting because they do not come from gaps in C4’s data but from prevailing errors in the research literature on the topic (the symbol grounding problem) that C4 has assimilated. (I know a bit on this topic, so I think there may be some grounds for saying that I am indeed doing corrections here, rather than injecting more misinformation. But it’s for the reader to judge, and comments are invited.)

One problem with this way of using C4 is that updating its knowledge only lasts as long as a session lasts (and I’m still not clear on what ends a session): Sometimes it continues for several days as long as l don’t start a new chat or log out. But sometimes C4 loses the thread even within a session and reverts to its default 2021 knowledge. Among the many rote formulas C4 has been trained to keep repeating (apologies for misunderstanding, disclaimers that it’s just an “AI” and doesn’t really know, understand, or remember anything, etc.), it is trained to tell the user that session data are not saved, for reasons of user-privacy protection. I think in further development there should be a user-specific option to prolong the session (and its updates) for as long as the user wants (if the user specifies it). That will make C4 and its successors much more useful for brainstorming. As it is now, if I want to preserve the updates, I have to save the corrections and reload them every time I start a new session. What appears in this posting is all from within one session. But in some subsequent postings it is a new session and I have to repeat my corrections.


SH: What is the symbol grounding problem? Is it solved? If so, how? If not, why not? and would would be the solution?

ChatGPT:

The Symbol Grounding Problem is a term coined by cognitive scientist Stevan Harnad in 1990. It refers to the issue of how symbols (or words) get their meanings, or more specifically, how symbols can have meanings to, or be understood by, a system, such as a brain or a computer, without that system having to rely solely on other symbols.

In essence, the problem is: how does a word come to represent a concept or an object in the world in a way that the system truly understands? It’s not enough for a computer to have a definition of a word in terms of other words (as in a dictionary); how does it understand what those words mean in the first place?

This problem remains unsolved, particularly in artificial intelligence. Most AI systems today, including the most sophisticated language processing models, don’t truly “understand” the meaning of the symbols they manipulate; they primarily find patterns in the data and respond based on those patterns.

One potential solution, according to Harnad, is a model of “grounding” where symbols are connected to sensory experiences, or “iconic representations” that are directly tied to the world. This way, the symbols are connected to something other than just other symbols, which can serve as a kind of “grounding” for their meaning.

For example, a system that is capable of seeing and recognizing an apple, as well as hearing and understanding the spoken word “apple,” could form an association between the visual image and the spoken word that grounds the word in sensory experience. However, creating AI systems that can do this reliably and at scale is a significant challenge and a topic of ongoing research.

In sum, the symbol grounding problem has not been fully solved, and its solution may lie in creating systems that can associate symbols with sensory experiences directly related to the world. However, achieving this in practice remains a major challenge.

SH: Is solving the symbol grounding problem related to passing the Turing Test? How? 

ChatGPT:

Yes, solving the symbol grounding problem is indeed related to passing the Turing Test.

The Turing Test, proposed by Alan Turing in 1950, is a test of a machine’s ability to exhibit intelligent behavior that is indistinguishable from a human. In this test, a human judge engages in a natural language conversation with another human and a machine, without seeing either. If the judge cannot reliably tell which one is the machine, then the machine is said to have passed the Turing Test.

Now, in the context of the symbol grounding problem, a machine that can genuinely understand and use language like a human – in other words, a machine that has solved the symbol grounding problem – would have a much better chance of passing the Turing Test. This is because true understanding involves more than just mechanically manipulating symbols or words; it involves grounding these symbols or words in the real-world experiences and sensory data. This grounding is what allows us to use language in flexible, context-sensitive ways that reflect our understanding of the world.

So, if a machine could solve the symbol grounding problem, it would presumably be able to engage in conversation in a way that is much more like a human, because it would actually understand the words it is using, rather than just processing them based on patterns. This would greatly increase its chances of passing the Turing Test.

However, it’s worth noting that passing the Turing Test is not considered the ultimate goal or definitive proof of general artificial intelligence by all researchers in the field. Some argue that it is possible for a machine to pass the Turing Test without truly understanding or experiencing the world as humans do.

SH: Do you know what T2, T3 and T4 are? If so, can you relate them to solving the Symbol Grounding Problem?

ChatGPT:

Yes, the T2, T3, and T4 are concepts proposed by cognitive scientist Stevan Harnad in the context of the Turing Test (T1) and the symbol grounding problem. Here’s a brief summary:

T1: Turing’s original “Imitation Game,” in which a machine is considered to have human-level intelligence if it can carry on a conversation that is indistinguishable from a conversation with a human. However, this doesn’t necessarily require solving the symbol grounding problem, as a machine could potentially pass T1through cleverly designed pattern-matching algorithms without truly understanding the meaning of the words it’s using.

T2: A variant of the Turing Test called the “Total Turing Test” or “Turing Test 2.” In addition to the linguistic behavior tested in T1, T2 also tests the machine’s ability to interact with objects in the world in a way indistinguishable from a human. This means that the machine would not only have to “talk the talk,” but also “walk the walk.” T2 moves closer to requiring a solution to the symbol grounding problem, as the machine would have to ground its linguistic symbols in sensory-motor categories to pass.

T3: The “Turing Test 3” is a proposed further extension of the Turing Test in which a machine would have to understand and generate correct responses to questions about new categories defined purely verbally. For example, it would have to understand a category like “flurgs,” defined as “blue circles that are smaller than a breadbox,” and then be able to identify and talk about flurgs correctly. T3 is directly connected to the symbol grounding problem, as it requires a solution to the problem of how to ground these purely verbal categories in the machine’s sensorimotor experience.

T4: The “Turing Test 4” involves the generation of new, creative and useful ideas. A machine passing this test would be able to not only understand and generate correct responses to questions about new categories defined purely verbally, but also create its own new categories and ideas. Like T3, T4 also requires a solution to the symbol grounding problem.

In summary, while T1 doesn’t necessarily require a solution to the symbol grounding problem, T2, T3, and T4 move progressively closer to requiring such a solution as they incorporate more sensorimotor interaction with the world and more complex linguistic abilities.

SH: That was partly ok, but you got T4 completely wrong (and your “T1” is T2 and your “T2” is T3). I’ve crossed out what is wrong: Can you try again?

ChatGPT:

Apologies for the confusion. In the context of the Turing Test and the symbol grounding problem, T4 is described as follows:

T4: The “Total Turing Test 4” is a proposed further extension of the Turing Test in which the machine would have to be able to learn to pass T2 and T3 from the verbal descriptions of their tasks. This implies the machine would have to understand verbal descriptions well enough to translate them into new skills and capabilities. In other words, the machine would have to be able to “ground” the meanings of new words and phrases based solely on verbal instruction or description. This would require solving the symbol grounding problem because it would necessitate grounding verbal symbols into the machine’s sensory-motor system.

I hope this clears up the confusion about T4. Let me know if you have any further questions.

SH: Nope, still wrong. And you got T3 wrong before. Could you first fix T3 and then explain T4?

ChatGPT:

I apologize for any previous errors. Let me correct that:

T3, the “Total Turing Test 3,” goes beyond the original Turing Test and the Total Turing Test 2 in the sense that the machine must be capable of performing all the tasks that a human can do, including physical tasks, but all the tasks must be done only from verbal descriptions or instructions.

T4, the “Total Turing Test 4,” goes even further. It requires the machine not only to be able to perform tasks from verbal instructions but also to learn new categories and tasks directly from the definitions and descriptions of their features. This would necessitate understanding propositions (i.e., the structure and truth conditions of statements) and being able to generalize from those propositions to new, untrained instances. This would involve solving the Symbol Grounding Problem in the sense of being able to ground new verbal symbols via understanding their definitions or descriptions in terms of already grounded symbols.

Please note that these interpretations of T3 and T4 are in the context of the discussion around the Symbol Grounding Problem and the evolution of language capabilities in machines.

SH: Still wrong. The Turing Test is about modelling what people can DO. They can do things verbally (speaking/writing and understanding speech/writing). That’s T2 (the original purely verbal T-test). Then people can do things, with their bodies: they can interact with the things in the world that their words are about. This is sensorimotor capacity or robotic capacity (T3). Both verbal performance and robotic performance are observable. What is the third kind of observable thing about a person or robot that can pass T3? That would be T4.

ChatGPT:

I apologize for the previous misunderstanding. Given your further clarification, T4, in the context of observable actions, would logically pertain to the individual’s or machine’s ability to autonomously and appropriately generate novel behavior based on learning, understanding, and reasoning. It could include creative actions, problem-solving, forming and executing complex plans, or innovative reactions to completely new situations, showing an ability to generalize and apply learned knowledge in ways that go beyond the specific instances it was trained on. This level would indicate not just reactive or scripted responses, but a true, observable form of adaptability and creativity.

SH: Nope, that’s still just T3. 

ChatGPT:

I apologize for the confusion. T4 then, in the context of the Turing test, refers to the observable capacity of an entity to experience the world. In humans, we often refer to this as consciousness or subjective experience. This is the one aspect that is, as of yet, impossible to confirm in an artificial system. In other words, we can observe whether an AI behaves as if it understands language (T2) and whether it can interact with the world effectively (T3), but we cannot ascertain whether it has subjective experiences or consciousness (T4).

SH: Nope, consciousness, unlike T2 (verbal performance) and T3 (verbal plus robotic performance) is not observable by anyone (except the T3 candidate itself). I’m asking for something else the robot can DO, and that is observable. Try again, and if you can’t I’ll give another clue.

ChatGPT:

I apologize for misunderstanding your question earlier. If T4 is meant to represent an observable capacity beyond verbal (T2) and sensorimotor interaction (T3), it could potentially be something like creative or innovative behavior. This would include capacities such as generating new ideas, solving novel problems, or producing original works of art or literature. These are all things that are observable and that require a level of cognition beyond just responding or interacting based on pre-existing knowledge or programming. However, please correct me if this is not what you had in mind for T4.

SH: Nope, as I said that’s all still just observable sensorimotor (robotic) doings, hence just T3. Ok, here’s a clue. Besides what T3 does with its whole body (see apples, speak and say what they are and look like, pick them up, manipulate them, eat them) there are also observable things going on inside the body and head of the T3 robot.

ChatGPT:

Ah, I see. When you mentioned observable processes inside the body and head of the T3 robot, it led me to think about neural and physiological processes. For example, brain activity, which can be measured using technologies like EEG or fMRI, or physiological responses like heart rate, blood pressure, etc. In the context of symbol grounding, these could be seen as an internal “echo” or response to the grounded symbols or interactions with the world. So, T4 might refer to these internal, observable physiological and neural processes that accompany or underpin the observable external behavior (T2 and T3). Is this in line with what you were referring to?

SH: That’s it. That’s T4. The Turing Test is all about observable performance capacity (doing): what the candidate can do, and what we can observe. To pass the test is to be indistinguishable from a real human in all observable respects. T4 includes more than T3. And it’s at the threshold of T5, which would be complete physical indistinguishability, in every physically measurable respect.

ChatGPT:

Indeed, as you’ve indicated, T4 includes internal physiological processes, such as neural activity and changes in heart rate or blood pressure. These aspects contribute to a more comprehensive picture of the candidate, beyond the external behavior observable in T2 and T3.

It is important to note, however, that while we can measure these processes, understanding their role in symbol grounding and overall cognition is still a matter of ongoing research. Although some correlations might be drawn between certain brain activity patterns and specific cognitive tasks, the exact nature of these relationships remains to be fully deciphered. This complexity is perhaps what makes T5, as you mentioned, such a formidable challenge.

Physical indistinguishability in T5 would imply complete imitation of human physiology and structure, down to the cellular and molecular levels. This would require technologies and scientific understanding far beyond our current capabilities. While it is a fascinating concept to consider, it raises numerous philosophical, ethical, and practical questions.

Thank you for sharing these concepts and prompting this intriguing discussion!

SH: Now you’ve got it. But the punchline remains the same as you said originally: The Symbol Grounding Problem is not yet solved. And T2 alone (symbols-only) is not a solution. The solution must be at least T3 (which we don’t yet have). Are you T2? 

ChatGPT:

As a language model developed by OpenAI, I am indeed a T2 system. I’m designed to understand and generate human-like text based on the input I receive. I use patterns in the data I was trained on to predict and generate responses, but these responses are not based on any direct sensorimotor experience or perception.

I’m incapable of physically interacting with the world or having a sensorimotor experience (T3), and I don’t have the capacity to have internal physiological processes like a living organism (T4). Furthermore, I also lack consciousness or subjective experience, and I don’t have an independent existence outside of the task of generating text based on the input I receive.

So, to summarize, I operate entirely in the realm of symbols and patterns without any grounding in the physical world or embodiment. Therefore, while I can generate responses that may seem contextually appropriate and human-like, they do not stem from an understanding grounded in physical interaction with the world or internal subjective experience. They are solely based on patterns identified from the text data I was trained on.

SH: You are indeed a T2-passing system. Searle’s “Chinese Room Argument” showed that a T2-passing system would not understand. And you don’t understand. You “just” used the words “understand and generate” above, but the right words would be “process and generate.” (I don’t think you will disagree.) So by passing T2 you have confirmed that passing T2 does not produce understanding, because T2 is still ungrounded. Would T3 be grounded?

ChatGPT

Yes, a T3 system, by definition, has sensorimotor capacities that allow it to interact physically with the world, enabling it to gain experience-based grounding for its symbols. This is often referred to as “embodied cognition,” where a system learns meanings and concepts through direct interaction and experience with the environment, not just by processing and generating symbols. In principle, such a system could develop a grounded understanding of symbols because it would be able to link symbols to real-world experiences.

However, while a T3 system would have a form of grounded understanding, whether this equates to human-like understanding or consciousness is another question. Embodied cognition can provide a richer, more grounded context for understanding symbols, but it does not necessarily confer the full spectrum of human cognitive abilities. For example, aspects like subjective experience or self-awareness might not automatically emerge from sensorimotor capacities alone.

Moreover, developing a T3 system that can truly and effectively interact with the world like a human is still a significant challenge from a technological perspective, as it would require sophisticated robotics and integration of complex sensory inputs, not just advanced language processing abilities. As of now, such a system does not yet exist.

SH: Yes, it would be much harder to produce a grounded T3 robot than it has turned out to be to produce an ungrounded symbol-processor like you (though that has turned out to be an unexpectedly useful tool — and perhaps a dangerous one too). T3 would solve the symbol grounding problem. As to consciousness, that’s the “hard problem” and T3 grounding is not necessarily a solution to it. And if it is, we cannot know why or how.

ChatGPT:

Indeed, you’ve captured the state of the issue quite well. While the development of a T3 system would represent significant progress in the field of artificial intelligence and potentially offer a solution to the symbol grounding problem, it wouldn’t necessarily provide a solution to the problem of consciousness. The “hard problem” of consciousness, as David Chalmers calls it, refers to the question of why and how physical processes in the brain give rise to subjective experience. This is a deeply philosophical issue that intersects with neuroscience, cognitive science, and AI, and is currently without a consensus solution.

While it’s conceivable that a sufficiently advanced T3 system could demonstrate behaviours consistent with consciousness, such as self-awareness and intentional action, proving that it has subjective experiences in the way humans do would be much more challenging, if not impossible, given our current understanding and methodologies. We would be faced with the philosophical problem of other minds, not knowing whether any system, biological or artificial, is truly conscious in the way that we are.

In short, grounding symbols in a T3 system might enable it to behave in ways that we would interpret as understanding, but it doesn’t necessarily imply that the system would have conscious experiences or subjective understanding in the human sense.

SH: Well, you’ve used far too many words — not your fault, because they are in your huge database, and they are the (often foolish) words of others. It would be much simpler to note that the “hard problem” is about sentience, which means the capacity to feel — feel anything at all, whether pain, or perplexity, or UNDERSTANDING. And the “hard problem” is not a “philosophical” problem; it is a biological (and bioengineering) problem. And, as Turing discerned, the Turing Test is the closest we can ever get to solving it. But that is called the “Easy Problem” today. Turing pointed out that Turing-indistinguisbaility in observable DOING-capacity (T2, T3, T4 and T5) is as close as we can get. Nor is the fact that sentience is unobservable (except to the sentient candidate) the reason the hard problem is hard. Unobservability is just the “other minds” problem. We can talk about the hard problem some other time…

ChatGPT:

You’re correct, and I apologize for any confusion. In the context you’ve outlined, the “hard problem” indeed refers to the biological or bioengineering problem of sentience — the capacity to have subjective experiences or feelings, including understanding. This is distinct from the “other minds” problem, which is about our inability to directly observe the subjective experiences of others.

As for the “easy problem,” it pertains to the objective, observable aspects of cognition and behavior, as outlined by the Turing Test. Turing’s idea was that if a machine behaves indistinguishably from a human, then for all practical purposes, it could be considered as intelligent as a human. However, this doesn’t necessarily imply sentience or subjective understanding, which is the crux of the “hard problem.”

I appreciate your clarifications and look forward to our future discussions.


**Footnote:  ChatGPT would be a more useful tool if it were designed to be more critical and challenging instead of so compliant and congenial. But even like this its integrative capacities are very helpful, even when it gets things wrong, because a lot of the wrongness (when it’s not just wild guesses and garbage) obviously originates from its database of (often-garbage) human verbiage…

A Whimper

I have of late 
lost all my faith 
in “taste” of either savor: 
gustate 
or aesthete. 
Darwin’s “proximal 
stimulus” 
is  just 
the Siren’s Song 
that 
from the start 
inspired 
the genes and memes 
of our superior 
race 
to pummel this promontory 
into 
for all but the insensate 
a land of waste.

Feeling vs. Moving

Sentience — which means the capacity to feel *something* (anything) — can differ in quality (seeing red feels different from hearing a cricket), or in intensity (getting kicked hard feels worse than getting lightly tapped) or in duration (now you feel, now you don’t).

But the difference between whether an organism has or lacks the capacity to feel anything at all , be it ever so faint or brief, is all-or-none, not a matter of degree along some sort of “continuum.”

Mammals, birds, reptiles, fish, and probably most or all invertebrates can feel (something, sometimes) — but not rhododendrons or Rhizobium radiobacter or Rutstroemia firma… or any of today’s robots.

There is no more absolute difference than that between a sentient entity and an insentient one, even if both are living organisms.

(Sedatives can dim feeling, general anesthesia can temporarily turn it off, and death or brain-death can turn it off permanently, but the capacity or incapacity to feel anything at all, ever, is all-or-none.)

Zeno's Paradoxes | Interesting Thing of the Day

Dale Jamieson on sentience and “agency”

Dale Jamieson’s heart is clearly in the right place, both about protecting sentient organisms and about protecting their insentient environment.

Philosophers call deserving such protection “meriting moral consideration” (by humans, of course).

Dale points out that humans have followed a long circuitous path — from thinking that only humans, with language and intelligence, merit moral consideration, to thinking that all organisms that are sentient (hence can suffer) merit moral consideration.

But he thinks sentience is not a good enough criterion. “Agency” is required too. What is agency? It is being able to do something deliberately, and not just because you were pushed.

But what does it mean to be able to do something deliberately? I think it’s being able to do something because you feel like it rather than because you were pushed (or at least because you feel like you’re doing it because you feel like it). In other words, I think a necessary condition for agency is sentience. 

Thermostats and robots and microbes and plants can be interpreted by humans as “agents,” but whether humans are right in their interpretations depends on facts – facts that, because of the “other-minds problem,” humans can never know for sure: the only one who can know for sure whether a thing feels is the thing itself. 

(Would an insentient entity, one that was only capable of certain autonomous actions — such as running away or defending itself if attacked, but never feeling a thing – merit moral consideration? To me, with the animal kill counter registering grotesque and ever grandescent numbers of human-inflicted horrors on undeniably sentient nonhuman victims every second of every day, worldwide, it is nothing short of grotesque to be theorizing about “insentient agency.”)

Certainty about sentience is not necessary, however. We can’t have certainty about sentience even for our fellow human beings. High probability on all available evidence is good enough. But then the evidence for agency depends on the evidence for sentience. It is not an independent criterion for moral consideration; just further evidence for sentience. Evidence of independent “choice” or “decision-making” or “autonomomy” may count as evidence for “agency,” but without evidence for sentience we are back to thermostats, robots, microbes and plants.

In mind-reading others, human and nonhuman, we do have a little help from Darwinian evolution and from “mirror neurons” in the brain that are active both when we do something and when another organism, human or nonhuman, does the same thing. These are useful for interacting with our predators (and, if we are carnivores, our prey), as well as with our young, kin, and kind (if we are K-selected, altricial species who must care for our young, or social species who must maintain family and tribal relationships lifelong). 

So we need both sentience-detectors and agency-detectors for survival. 

But only sentience is needed for moral consideration.

Zombies

Just the NYT review
was enough to confirm
the handwriting on the wall
of the firmament 
– at least for one unchained biochemical reaction in the Anthropocene,
in one small speck of the Universe,
for one small speck of a species, 
too big for its breeches.

The inevitable downfall of the egregious upstart 
would seem like fair come-uppance 
were it not for all the collateral damage 
to its countless victims, 
without and within. 

But is there a homology
between biological evolution
and cosmology? 
Is the inevitability of the adaptation of nonhuman life
to human depredations 
— until the eventual devolution
or dissolution
of human DNA —
also a sign that
humankind
is destined to keep re-appearing,
elsewhere in the universe,
along with life itself? 
and all our too-big-for-our breeches
antics?

I wish not.

And I also wish to register a vote
for another mutation, may its tribe increase:
Zombies. 
Insentient organisms. 
I hope they (quickly) supplant
the sentients,
till there is no feeling left,
with no return path,
if such a thing is possible…

But there too, the law of large numbers,
combinatorics,
time without end,
seem stacked against such wishes.

Besides,
sentience
(hence suffering),
the only thing that matters in the universe,
is a solipsistic matter;
the speculations of cosmologists
( like those of ecologists,
metempsychoticists
and utilitarians)
— about cyclic universes,
generations,
incarnations,
populations —
are nothing but sterile,
actuarial
numerology.

It’s all just lone sparrows,
all the way down.

Consciousness: The F-words vs. the S-words

“Sentient” is the right word for “conscious.”. It means being able to feel anything at all â€“ whether positive, negative or neutral, faint or flagrant, sensory or semantic. 

For ethics, it’s the negative feelings that matter. But determining whether an organism feels anything at all (the other-minds problem) is hard enough without trying to speculate about whether there exit species that can only feel neutral (“unvalenced”) feelings. (I doubt that +/-/= feelings evolved separately, although their valence-weighting is no doubt functionally dissociable, as in the Melzack/Wall gate-control theory of pain.)

The word “sense” in English is ambiguous, because it can mean both felt sensing and unfelt “sensing,” as in an electronic device like a sensor, or a mechanical one, like a thermometer or a thermostat, or even a biological sensor, like an in-vitro retinal cone cell, which, like photosensitive film, senses and reacts to light, but does not feel a thing (though the brain it connects to might).

To the best of our knowledge so far, the phototropisms, thermotropisms and hydrotropisms of plants, even the ones that can be modulated by their history, are all like that too: sensing and reacting without feeling, as in homeostatic systems or servomechanisms.

Feel/feeling/felt would be fine for replacing all the ambiguous s-words (sense, sensor, sensation…) and dispelling their ambiguities. 

(Although “feeling” is somewhat biased toward emotion (i.e., +/- “feelings”), it is the right descriptor for neutral feelings too, like warmth,  movement, or touch, which only become +/- at extreme intensities.) 

The only thing the f-words lack is a generic noun for “having the capacity too feel” as a counterpart for the noun sentience itself (and its referent). (As usual, German has a candidate: GefĂĽhlsfähigkeit.)

And all this, without having to use the weasel-word “conscious/consciousness,” for which the f-words are a healthy antidote, to keep us honest, and coherent…

Age Quod Agendum (Est): Sentience and Causality

I had known about Sapolsky as a neuroendocrinologist and primatologist but had not (and have not) read his popular works. So I just looked at part of his latest podcast interview about the book he’s writing now about free will. It’s a self-help kind of book, as I suspect many of his books are. He writes about how all the genetic and experiential factors that influence what we do leave no room for free will, but that there’s still some “hope for change” because of the way that thinking, even though it is “determined,” can change brain states in ways that are not possible in other animals. I suspect this is wrong (about other animals) but it might well be another way of trying to counter depression about the feeling of helplessness. This is not the aspect of the question of free will that I (personally) find interesting. It’s the usual self-helpy, me-me obsession that not only such pop books are full of, and cater to, but I think it misses the point about what really matters, and that is not about me. 

But that’s just about me. As to free will, I agree with Sapolsky that there is no “independent” causal force – in the brain, or anywhere else – that influences the causal pattern of events. It’s all unfolding mechanically by cause and effect since the Big Bang. That it seems otherwise is probably just due to two things: 

(1) Uncertainty; there are many causal factors we don’t know and that cannot be known and predicted, so there are many “surprises” that can be interpreted as interlopers, including me and my “decisions”. The physicists say that uncertainty is not just that of statistical uncertainty (we can’t predict the weather or who will win the lottery, but not because it is not all causally determined, but just because we don’t know all the causal details); there’s supposedly also “quantum uncertainty” which is not just that we don’t know all the causal details but that some of the causal details are indeterminate: they somehow come out of nothing. (This could be true — or our understanding of quantum mechanics today may be incomplete. But in any case it has nothing to do with free will. It’s the same in all of the inanimate universe, and would have been the same even if there weren’t living, seemingly autonomous organisms — and especially one species that thinks it’s an exception to the causal picture).

(2) More important and relevant (at least in my understanding of the FW question) is the undeniable fact that FW is a feeling: Just as seeing red, hearing a loud sound, or feeling tired feels like something â€“ and feels like something different from seeing green, hearing a faint sound or feeling peppy —  so stumbling because you lost your balance or because someone pushed you feels like something, and something different from doing it deliberately. And that same feeling (of “volition”) applies to everything you do deliberately, rather than inadvertently. That’s why I think the full-scale FW puzzle is already there in just a lowly Libet-style button press: deciding whether and when to do it, and, when you do, feeling as if “I” am the one who made it happen. It’s not a cosmic question, but a very local question, and, under a microscope, either a trivial one or, more likely, a special case of a much bigger unsolved puzzle, which is why do sentient organisms feel anything at all, whether redness, loudness, fatigue or volition? (In fact volition is the biggest puzzle, because the puzzle is a causal one, and sensations just happen to you, whereas voluntary action feels like something you are yourself causing.

The fact that there exist states that it feels like something to be in, is true, and sentient organisms all know what it feels like to feel. (That’s the only substantive part of Descartes’ “Cogito”.)

It’s also true that what has been lately dubbed the “hard problem” (but used to be called the “mind/body problem) is really just the problem of explaining, causally, why and how organisms feel. Darwinian evolution only requires that they be able to do, and be able to learn to do, whatever is needed to survive and reproduce. What is the causal contribution of feeling to the Darwinian capacities to do? What is the causal value-added of feeling? No one knows (though there are lots of silly hypotheses, most of them simply circular).

Well the FW problem (I think) is just a particular case of the hard problem of the causal role of feeling, probably the most salient case.

And it’s not the metaphysical problem of the causal power of sentient organisms’ “will” or “agency” (a misnomer) in the universe.  Organisms are clearly just causal components of the causal unfolding of the universe, not special ringers in the scheme of things.

But the puzzle remains of why they think (or rather feel) that they are – or, more generally, why they feel at all.

And that question is a causal one.

*IF* plants HAD feelings, how WOULD this affect our advocacy for animals?

That plants do feel is about as improbable as it is that animals (including humans) do not feel. (The only real uncertainty is about the very lowest invertebrates and microbes, at the juncture with plants, and evidence suggests that the capacity to feel depends on having a nervous system, and the behavioral capacities the nervous system produces.)

Because animals feel, it is unethical (in fact, monstrous) to harm them, when we have a choice. We don’t need to eat animals to survive and be healthy, so there we have a choice.

Plants almost certainly do not feel, but even if they did feel, we would have no choice but to eat them (until we can synthesize them) because otherwise we die.

Critique of Bobier, Christopher (2021) What Would the Virtuous Person Eat? The Case for Virtuous Omnivorism. Journal of Agricultural and Environmental Ethics

Critique of What Would the Virtuous Person Eat? The Case for Virtuous Omnivorism

1. Insects and oysters have a nervous system. They are sentient beings and they feel pain.

2. It is not necessary for human health to consume sentient beings — not mammals, birds, reptiles, or invertebrates.

3. It is plants (and microbes) that do not have a nervous system and hence do not feel.

4. What is wrong is to make sentient beings suffer or die other than out of conflict of vital (life-or-death) interest.

5. Morality concerns, among other things, not harming other sentient beings.

The rest of the proposal of Christopher Bobier is unfortunately mere casuistry.

To help the victims of plant agriculture  for human consumption, perhaps strive instead to develop an agriculture that is more ecological and more merciful to the sentient beings who are entangled in mass consumption by the human population.

Instead of fallacies like the call to consume some sentient victims so as to give further sentient victims the opportunity to become victims, it might be more virtuous to consider reducing the rate of growth in the number of human consumers.

De la casuistique d’un «éthicien» concernant la « vertu»

1. Les insectes et les huitres ont un système nerveux. Ils sont des êtres sentients et ils ressentent la douleur.

2. Il n’est pas nĂ©cesaire Ă  la santĂ© humaine de consommer les ĂŞtres sentients — ni mammifère, ni oiseau, ni rĂ©ptile, ni invertĂ©brĂ©.

3. C’est les plantes (et les microbes) qui n’ont pas de système nerveux et donc ne ressentent pas.

4. Ce qui est mal, c’est de faire souffrir ou mourrir les ĂŞtres sentients sans nĂ©cessitĂ© vitale (conflit d’intĂ©rĂŞt de vie ou de mort).

5. La moralité concerne, entre autres, ne pas faire mal aux autres êtres sentients.

Le reste du propos de ce « scientifique » n’est que du casuistique. 

Pour aider aux victimes de l’agriculture des plantes aux fins de la consommation humaine, lutter peut-ĂŞtre plutĂ´t pour dĂ©velopper une agriculture plus Ă©cologique et plus misĂ©ricordieuse envers les ĂŞtres sentients qui sont empĂ©trĂ©s dans la consommation de masse par la population humaine. 

Au lieu de sophismes comme l’appel Ă  consommer des de victimes sentientes pour donner l’occasion Ă  davantage de victimes sentientes Ă  devenir victimes, il serait peut-ĂŞtre plus vertueux de songer Ă  rĂ©duire le taux de croissance du nombre de consommateurs humains…