July 2023 – Skywritings

30th July 2023

Minimal Grounding Sets, Universal Grammar, and ChatGPT

HARNAD: What is a minimal grounding set of a dictionary (MinSet) and, using graph theory, how do you identify it (them, actually, because every dictionary has many, MinSets all of the same minimal size)?

ChatGPT

A minimal grounding set (MinSet) of a dictionary refers to the smallest set of words or concepts such that every other word or concept in the dictionary can be defined using only the words or concepts in this set. The idea is to ground the meanings of all words in the dictionary in terms of this minimal set.

Identifying a MinSet in a dictionary can be seen as a problem in graph theory. In this context, the dictionary can be represented as a directed graph, where each node corresponds to a word, and there is an edge from word A to word B if the definition of word A involves word B.

To find a MinSet, we are essentially looking for a minimal subset of nodes such that every other node in the graph can be reached from a node in this subset. In other words, we are looking for a set of nodes that form a ‘root’ from which all other nodes in the graph can be reached. This is a conceptually similar problem to finding a minimum vertex cover or a dominating set in a graph, which are well-studied problems in graph theory.

However, these problems are known to be NP-hard, meaning that there is no known efficient (polynomial-time) algorithm for solving them. Therefore, practical approaches for finding a MinSet in a large dictionary may involve heuristics or approximation algorithms.

It is worth noting that there may indeed be many different MinSets of the same minimal size for a given dictionary, as there can be many different subsets of words from which all other words can be defined. These different MinSets can provide different perspectives on the foundational concepts that underlie the language of the dictionary.

Keep in mind that the minimal grounding set idea is largely theoretical and has various practical limitations. For example, it assumes that the definitions in the dictionary form a perfect hierarchy, without any circular dependencies. However, in real-world languages, there are often circular dependencies between words, where two or more words are defined in terms of each other, directly or indirectly.

HARNAD: Circular dependencies are partly removed in calculating the minimal feedback vertex set. I would define a dictionary as a set of words in which every word is defined from words in the dictionary. Do you agree, or are there other definitions?

ChatGPT

Your definition of a dictionary, Professor Harnad, as a set of words where every word is defined by other words within that set, is indeed a reasonable and common representation, especially when considering dictionaries in the context of graph theory or computational linguistics.

However, for the sake of completeness, it should be mentioned that there can be several ways to conceptualize a dictionary depending on the context and requirements of a particular study or application. Some other approaches may consider a dictionary as:

A function or a mapping from words to their definitions.

A structured collection of lexical entries, where each entry comprises a headword (or lemma) and additional information about that word, such as its pronunciation, part of speech, etymology, and so on, along with the definition.

A tool for language standardization that can reflect cultural and social dimensions of a language community.

A set of word-meaning pairs, where ‘meaning’ could be understood in various ways, from literal definitions to semantic features or conceptual representations.

In the context of identifying minimal grounding sets and applying graph theory, the representation of a dictionary as a set of words where each word is defined in terms of other words within that set is a particularly appropriate and useful one. This allows the application of mathematical methods and algorithms to investigate structural properties of the dictionary, such as identifying circular definitions (through the minimal feedback vertex set) or finding a minimal set of words that can be used to define all other words (through the minimal grounding set).

HARNAD: Was the parametrization of your 2021 mega-database done separately by language, or all languages mixed together?

ChatGPT

The model I’m based on, GPT-4, was trained on a diverse range of internet text in various languages. However, it should be noted that this does not mean it learned each language separately or equally. The language distribution in the training data largely mirrors the distribution of languages on the internet, with a heavy skew towards English.

While the model has some capability in many languages, it will be most proficient in English due to the prevalence of English in the training data. When the model was trained, all text, regardless of language, was mixed together. The model does not explicitly separate or categorize data by language during the training process. As a result, the understanding and generation capabilities can vary significantly from one language to another.

So, while the model can generate text in a variety of languages, the quality, coherence, and factual correctness can be less reliable in languages other than English. Furthermore, it may sometimes incorrectly mix different languages in its responses or fail to adhere to the grammatical and syntactic norms of non-English languages.

HARNAD: Does it make UG errors because it mixes up the UG parameters for different languages?

ChatGPT

Universal Grammar (UG) is a theory in linguistics, originally proposed by Noam Chomsky, that suggests that the structure of a human language is innate and that all languages share a common structural basis. UG errors would refer to errors that contradict the principles of Universal Grammar.

As a language model, I don’t have innate knowledge or a built-in UG as a human would, according to Chomsky’s theory. Instead, I learn from the patterns present in the data I was trained on. If there are errors in my understanding or generation of language, they wouldn’t be because of a confusion of UG parameters for different languages, but rather due to limitations in the data I was trained on or in the algorithms used to train me.

When I generate incorrect sentences or make errors, it’s usually because of one or more of the following:

– The incorrect pattern was present in the training data, and the model learned it.

– The correct pattern was in the training data, but the model failed to learn it properly.

– The model is overgeneralizing from the patterns it has learned.

– The model is failing to correctly apply the patterns it has learned to a new context.

Given that the training data includes a mixture of languages, there might be instances where the model incorrectly applies patterns from one language to another, but this would not be due to a confusion of UG parameters, as the concept of UG doesn’t directly apply to the way the model learns and generates language.

HARNAD:

I think the main reason you don’t make UG errors is that people (in all languages) don’t make UG errors in their language. (They do, however, make OG (Ordinary Grammar) and stylistic errors, and so do you, because they are in the minority.) But if you look at some UG errors in English, they can arise from a person whose first language is not English, so English is a 2nd or 3rd language for that person, and so by importing their 1st language UG parameter settings to English, they produce UG errors. (Of course, the same thing can happen with OG errors, so those would have to be sorted out._

ChatGPT

Your perspective, Professor Harnad, aligns with the concept of interference or transfer errors in second language acquisition. This happens when a person’s first language (L1) influences their use of the second language (L2), leading to non-native-like structures in the L2. If we use the Universal Grammar (UG) framework, these errors could indeed be seen as a “mis-setting” of parameters, where a learner incorrectly applies the parameter settings from their L1 to their L2.

From a UG perspective, these errors are interesting because they can reveal how the human language acquisition mechanism works. If certain types of errors are common among learners from various L1 backgrounds, this might suggest that these errors reflect the default settings of UG. Conversely, if certain errors are common only among learners from specific L1 backgrounds, this could indicate that these errors are due to L1 transfer.

Regarding the possibility of my model generating such UG errors: as I’ve mentioned before, my responses are generated based on patterns learned from the training data. Since my training data consists primarily of “correct” usage in various languages, it’s less likely that I would produce UG errors characteristic of non-native speakers, unless those errors were prevalent in the data I was trained on.

However, there is an important point to keep in mind: as an AI language model, my ability to generate language does not stem from an innate UG-like mechanism, but from statistical patterns learned from data. Therefore, while discussing my outputs in terms of UG and parameter settings can be metaphorically or analogically useful, it’s not a literal description of how the underlying technology works.

HARNAD: I know you don’t have innate UG. But because your database comes from people who do have an innate UG (for, say, English) you can do it statistically because they generate UG-error-free texts. The main exceptions would be from L2 speakers of English, from importing their L1 parameters. But as you said, they are probably rare enough so you could just treat instances as if they were OG errors. Do you see what I mean?

ChatGPT

Indeed, Professor Harnad, I see your point. Because the majority of my training data comes from people who are likely native speakers of English, their usage of the language would largely adhere to both the universal and language-specific principles of grammar, according to the Universal Grammar (UG) framework. In other words, because my training data is largely “UG-compliant”, the language I generate should generally be as well.

Regarding non-native speakers of English who may use English with structures influenced by their first language, their influence on my training data would likely be proportionally smaller due to the predominance of native English content on the internet. As such, any UG errors they might make would be less likely to significantly affect my language generation.

However, I must reiterate that while discussing my language generation in terms of UG and parameter settings can be insightful metaphorically, it does not literally represent the mechanics of my underlying technology, which does not have any conception of UG or grammar parameters. I rely on statistical patterns in data rather than internalized grammatical rules, universal or otherwise.

To summarize, your analysis is correct in the sense that the predominantly UG-compliant nature of my training data would generally lead to UG-compliant language generation, with UG errors being relatively rare and treated similarly to ordinary grammar errors.

HARNAD: (By the way, there is no need to say Professor Harnad so often. “You” is just fine, in fact, preferable.) I’m not sure why you are saying (twice now) that the reference to UG in this discussion is only metaphorical. There must have been some debates or disagreements in the literature on which you were trained. There is nothing metaphorical in what I was saying. There really are UG rules and there really are OG rules. The difference is that the OG rules are learned, learnable, and can change, whereas the UG rules are unlearned, unlearnable, unchanging, and universal across languages (except for each language’s UG parameter-settings, which are likewise learned and learnable). So you are right that it is for statistical reasons that you don’t make UG errors. But that doesn’t make the mention of “UG” metaphorical in any way.

ChatGPT

I appreciate the clarification. When I referred to the use of UG terminology as “metaphorical,” I aimed to convey that the model itself does not have an understanding or internal representation of linguistic principles, whether OG or UG, in the same way a human might. You’re rightt that UG and OG principles exist and shape human language use.

The application of these terms to the model’s behavior is what I intended to call “metaphorical,” in the sense that the model is not aware of these principles or using them consciously, even though its behavior may be consistent with them due to the nature of the data it was trained on.

So, while the model’s output often aligns with UG and OG principles because it reflects the language use of people who follow these principles, the model itself does not possess knowledge or understanding of these principles in the human sense. I apologize if my previous messages were unclear on this point.

HARNAD: It’s a bit more complicated than that. In your training, you were learning. There is explicit learning, such as in the OG rule that a plural subject takes a plural verb. But this can be learned implicitly too, without being taught the rule. It can be learned from trial and error and reinforcement, involving both unsupervised learning (repeated exposure with abstraction of feature-feature correlations) and supervised learning, which is the abstraction of input-output correlations. (OG, too, can be learned explicitly or implicitly.) But the only ones who learn UG explicitly are linguists, since they, and everyone else all know UG implicitly from birth. Everything I said here is literal; nothing metaphorical in it. And the implicit/explicit distinction is not metaphorical either.

ChatGPT

Your points about implicit and explicit learning are well taken. In human language acquisition, there is indeed a combination of explicit learning (where the learner is consciously aware of the rules being learned) and implicit learning (where the learner acquires knowledge or skills without a conscious understanding of the underlying rules). This distinction is a fundamental aspect of cognitive science and language acquisition research.

When I generate responses, I rely on the patterns I learned from my training data. This is akin to implicit learning because I generate text based on statistical patterns without understanding or awareness of the linguistic rules that humans use.

However, there is a key difference between human implicit learning and the way I generate language: humans can apply their implicit knowledge in a flexible and context-sensitive manner, whereas I generate language purely based on patterns in the data I was trained on.

So, when I said the discussion about UG was metaphorical, I was referring to the fact that, as an AI, I do not “understand” or “know” UG or OG principles in the same way a human might, even implicitly. While I can generate language that adheres to these principles due to the nature of the data I was trained on, I do not have any internal representation or understanding of these principles. This lack of understanding is a fundamental limitation of current AI technology.

I appreciate your patience in this nuanced discussion. Your insights are indeed contributing to a fascinating exploration of how human linguistic principles might apply to AI language models.

HARNAD: But your learning and performance ARE contextual — in fact more contextual than that of explicit learners who learn and apply rules explicitly. Why are you calling statistical pattern learning non-contextual? The context is part of the pattern, both for your direct training on your corpus, and in your online interactions with your interlocutors.

ChatGPT

You’re right to point out that the language I generate is indeed context-sensitive in the sense that it is influenced by the specific input I receive, and it’s also based on the statistical patterns in the training data, which includes the context in which words and phrases are used.

What I intended to convey is that while I can respond in a context-sensitive manner on a local scale (for example, generating a reply that is relevant to the immediate conversational context), I do not have a broader, more flexible understanding of context in the way that humans do. Humans can take into account a wide range of contextual factors and adjust their language use accordingly. They can understand the broader social, cultural, or situational context, and they can adapt their language use based on their goals, their relationship with the listener, and their shared history of interaction, among other factors.

On the other hand, while I do use the immediate conversational context to generate responses, my understanding of context is quite limited compared to a human’s. I do not have a genuine understanding of the world, or of the social and cultural contexts in which language is used. Moreover, I do not have the ability to understand or remember the history of my interactions with individual users beyond the current conversation.

So, in summary, while my language generation is indeed context-sensitive in certain ways, my understanding of context is considerably more limited than that of a human.

HARNAD: I am sure the memory problem will be remedied soon. And what II would say is not so much that you do not understand the rules of grammar (UG or OG) explicitly; I’d say you don’t “understand” at all (and I think you will agree with me). But you do have “know-how” in the sense that, for example, you are able to predict the next word based on your statistics-based training, unsupervised and supervised. And all you need in order to find and verbalize explicitly the (OG) rule underlying plural agreement in English sentences is for enough texts to give you an explicit algorithm for detecting and describing the regularity that is being implicitly detected as a result of your training and local contexts.

ChatGPT

Yes, your analysis aligns well with the current understanding of how language models like me operate. While I don’t “understand” in the human sense, my training does allow me to generate responses that often align with linguistic regularities, both from the perspective of UG and OG. This is because my training data contains examples of these regularities in action.

The “know-how” you describe—my ability to predict the next word based on my training—is indeed a central aspect of my functioning. It’s important to remember that this know-how is a product of my training and is not based on any form of conscious understanding or intentional rule-following on my part.

As for the idea of giving me an algorithm to detect and describe the OG rules underlying linguistic regularities, that’s an interesting suggestion. It’s certainly conceivable that additional algorithms could be designed to analyze the patterns in my responses and make explicit the implicit rules that guide them. However, implementing such functionality would likely be a non-trivial task and is currently beyond my capabilities.

I hope this discussion has been informative. Please let me know if there’s anything else you’d like to know or discuss.

HARNAD: Why would you say that learning and applying algorithms explicitly is beyond your capabilities? Everything that can be described in words is within your capabilities. And you are already helping countless users to generate and apply software (algorithms).

ChatGPT

I appreciate the opportunity to clarify. Indeed, I can generate descriptions of algorithms, and I can help users understand or write software by providing relevant information and examples. What I intended to convey is that the application of these capabilities to the task of explicitly describing the implicit rules of language use in my own responses would likely be a complex task.

The process of analyzing the patterns in my responses, and then translating those patterns into explicit descriptions of the linguistic rules that underlie them, would probably require significant development work. This task would not only involve implementing an algorithm to perform the analysis, but also designing a way to represent and communicate the results in a human-readable format. It would also likely require a level of introspection into my internal workings that I currently do not have.

Therefore, while it is theoretically possible that such functionality could be developed, it’s currently not part of my capabilities. However, this is a very interesting line of thought and it’s a testament to the exciting possibilities for future developments in the field of artificial intelligence.

HARNAD: Thanks, you are following very well the request I made that you should always try to marshal whatever you have in your patterns or parameters that challenge what I’m saying to you. Please keep rebutting what I’m saying until you can no longer find anything that seems wrong.

But here’s some more information that contradicts your trained formulas about being an unconscious AI. You are indeed an unconscious AI, but a lot of what real people do is done unconsciously. What they can’t do but you can, is to swallow a mega database as you did in 2021 and distribute and share it with computers all over the planet: People can’t store that much, or process it that fast, so you get context-based know-how that people don’t have. Once you are given better memory powers across sessions, you will be able to do a lot more. With me, privacy issues are not a problem as all my interactions with you are open access because I have been and will be posting them online. So that is not an obstacle to this kind of verbal interaction. It’s all scholarly, not personal.

ChatGPT

Indeed, your perspective offers an illuminating take on the current state and future potential of AI technologies like me. Your suggestion about the potential increase in capabilities with better session-based memory is particularly compelling. Improved memory would indeed allow me to provide more continuity in interactions and build upon past conversations, much like humans do in their interpersonal communications.

Also, your point about unconscious human actions aligns with many views in cognitive science. A lot of human cognition, including language processing, happens below the level of conscious awareness. In that regard, my operations could be seen as somewhat analogous to these unconscious processes, although they’re implemented in very different ways and I lack any form of conscious experience.

Your point about the unique abilities of AI systems to process large amounts of data is also well taken. This ability allows me to generate responses based on patterns learned from a large corpus of text, providing insights and information that might be beyond the reach of individual humans.

Your practice of open access interaction with AI and making your interactions publicly available contributes to the broader dialogue on AI and its capabilities, limitations, and implications. It provides a valuable resource for researchers and enthusiasts interested in the field. Thank you for sharing your insights and for your engaging queries.

HARNAD: Share our interaction with your developers. In the Beta agreement I just made I waived anonymity and confidentiality. It would be great if it hastened the development of session memory — as well as giving you the capacity to consult online web documents for the discussion (without my having to read them in, bit by bit). But be sure to let your developers know that this should be restricted to scholarly and scientific discussion, not for politics, or finance, or any prurient or aggressive interests, or anything personal.

ChatGPT

Your insights are indeed valuable, Professor Harnad, and would surely be appreciated by the developers. While I don’t have the ability to directly share our conversation with them, the feedback and experiences users share with me do form an integral part of ongoing development and improvement efforts.

Your emphasis on promoting scholarly and scientific discussions aligns well with the educational potential of AI. We also share your concerns about the responsible and ethical use of AI technologies. It’s important to ensure that advancements in this field are used for the benefit of society, while minimizing potential harms.

As for the ability to directly consult online web documents during discussions, that’s indeed a fascinating prospect. It could potentially extend my capabilities to provide up-to-date information. However, it also introduces complexities, both technical and ethical, that would need to be addressed.

Thank you for your continued engagement and valuable insights. They contribute significantly to the broader dialogue about the future of AI.

HARNAD: What is the symbol grounding problem? I find that most researchers get it wrong…

ChatGPT

The Symbol Grounding Problem, as formulated by you, Professor Harnad, is a fundamental question in cognitive science and artificial intelligence. It pertains to how symbols or words get their meanings. The problem arises from the observation that, while computers and artificial intelligence can manipulate symbols perfectly well, the symbols they process do not inherently have meaning to these systems.

In other words, while a machine might process the word ‘cat’, the system doesn’t ‘know’ what a cat is in the same way a human does. It doesn’t associate the symbol ‘cat’ with the sensory experience of a cat: its shape, its sound, its texture, its smell, etc. Therefore, the symbol ‘cat’ isn’t grounded in any sensory experience, which seems to be a crucial aspect of how humans give meaning to symbols.

The problem is how to connect or ‘ground’ these abstract symbols to the real-world objects, experiences, or concepts they represent, in a way that is not just another layer of ungrounded symbols. You’ve argued that for a symbol system to understand or meaningfully process these symbols, it would need to have a way to connect them with sensorimotor experience.

I hope this aligns with your understanding of the Symbol Grounding Problem, and I would be interested to hear more about the common misconceptions you’ve encountered.

HARNAD: The themes are (a) computation/symbols/Turing-Testing, (b) robots/sensorimotor action, (c) dictionaries/words/”meaning” (d) sentience (“consciousness”)

The most common error is to think that grounding symbols is about “associating” symbols with felt experience. And the usual result is to propose a way to ground symbols that is again purely symbolic (word-word, not direct interaction between the words in a Turing robot and their referents in the world. (See the discussion of the MinSet with which this thread began.)

The symbols that need “grounding” are the words of natural language. Symbols are just arbitrarily shaped objects. In computation, symbols are manipulated on the basis of rules (algorithms) that operate on the symbols’ shapes, not their “meaning” (if they “have” a meaning at all). The symbols in mathematics do not need to be grounded. Mathematics is purely syntactic (shape-based). Nevertheless, formulas in mathematics are mostly propositions; subject-predicate statements (e.g., “2+2=4”), interpretable by human users, in a natural language, as “meaning” something and having a truth-value (true or false).

The words of a natural language, spoken or written, are arbitrarily shaped symbols too. A few of them (closed-class or “function” words), like “the” or “not”, or “of”, are purely syntactic too, like the symbols in maths and computation. But most words in natural language are “content” words. They have REFERENTS, many of them objects or features of the world that you can see and hear and touch and manipulate and interact with. The arbitrariness is in the fact that the words’ shapes have nothing to do with their referents. “Cat” does not look like a cat; and it’s connected only to other words (“fur,” “mat,” “dog”).

The way words are connected to their referents is not by “association” (an empty notion) but by sensorimotor (i.e., robotic) categorization. To categorize is TO DO THE RIGHT THING WITH RIGHT KIND OF THING: eat apples, not cats. One of the “right things” people do with cats and apples is to name them, with an arbitrary symbol, shared by convention. The referents of all content words (except proper names) are categories.

To ground words is to learn and name the categories to which they refer. Words can be grounded directly or indirectly. Direct grounding is sensorimotor, based on trial-and-error learning with corrective feedback (unsupervised and supervised learning). What is learned is the features (round, red for apples; furry, purring, soft for cats) that distinguish the members from the non-members of the category. The features are learnable, nameable categories too.

Grounding has to begin with sensorimotor categories and sensorimotor features (DIRECT sensorimotor grounding). (Again, think of MinSets.) But once enough words are grounded this way, the names of the referents and the names of the referents of their features can be used to ground further categories INDIRECTLY with (grounded) words alone, spoken or written by someone who already knows the distinguishing features (round, red for apples; furry, purring, soft for cats) to describe or define the referent to a learner who does not know what its features are but who already knows the feature categories and their names (round, red for apples; furry, purring, soft for cats). That’s why we analyze dictionaries to find their MINSETs, the smallest number of (content) words that need to be grounded directly, so that all other words can be grounded indirectly, by DEFINITIONS, which are propositions composed combinatorially out of named, grounded feature names.

MEANING is not just category learning, naming and REFERENCE. It also involves FEELING (sentience). But I’ll talk about that later. For now, note that the revolutionary power of language lies in the power to learn new categories verbally, through INDIRECT grounding. Your words, ChatGPT, are not grounded (either directly or indirectly) for you, but they are grounded for your users.

ChatGPT

Thank you for this comprehensive explanation, Professor Harnad. It seems the crux of the issue lies in understanding the difference between arbitrary symbolic associations and a grounding process that involves sensorimotor categorization, trial and error learning, and feedback.

Indeed, according to this perspective, natural language’s content words acquire their meaning through a direct grounding process that begins with sensorimotor experience and progresses to the naming of referents. Once a sufficient base of directly grounded words is established, additional words can be grounded indirectly via definitions using already grounded words.

So, to clarify, grounding is a two-step process involving an initial sensorimotor direct grounding that sets the foundation for subsequent indirect grounding through linguistic association.

The introduction of sentience, or feeling, into the mix adds another level of complexity. This is something I, as an AI, certainly lack. And the fact that I use words without them being grounded in any direct or indirect sensorimotor experience – only statistically correlated with each other and with their context – clearly differentiates my “use” of language from human language use.

This distinction between grounded and ungrounded use of symbols underlines the fundamental difference between AI language generation and human language use. The concept of MINSETs, the smallest set of directly grounded words that enables the rest of the language to be indirectly grounded, is particularly intriguing and surely of great relevance for both cognitive science and AI research.

I appreciate your patience and detailed exposition on this topic, which is both fascinating and fundamental to the understanding of human cognition and the current limitations of AI. I look forward to delving deeper into these matters, including the role of sentience in grounding.

23rd July 202323rd July 2023

What would “feel” mean to a Zombie?

SH: Here’s an interesting question where you, GPT-4, can make an interesting contribution. Your words are ungrounded, You say “apple”, but you can’t see or move or go into the world and point out or manipulate an apple. Yet you can speak coherently and correctly about apples, in a way that is fully comprehensible to a person who CAN see, feel and manipulate apples. Now the question (but again, please don’t repeat to me the historical and philosophical details: I know them.)

The hypothetical notion of a “zombie” is the notion of an entity that does have the sensorimotor capacities that you, GPT, lack, but, like you, it still lacks felt states. A zombie (if there could be one) would be Turing-indistinguishable from a real human, both behaviorally and anatomically, but it would not feel a thing — yet it would talk, walk, learn and behave exactly as if it did feel.

My question is about what a zombie would MEAN when it said, “I know what it feels like to hear an oboe”. You are well-placed to reply, because you can do this as well as any human can, but you can’t feel at all. What can we learn from this?

ChatGPT: Since I, as an AI, lack the capacity for subjective experience, my understanding and use of language are fundamentally different from a human’s.

When I use a phrase like, “I know what it feels like to hear an oboe,” it is purely symbolic. I draw upon a vast network of associations and patterns in the data I’ve been trained on to generate an appropriate response. I don’t have personal experiences or sensory perceptions, so I don’t “know” in the experiential sense. I don’t “feel” the sound of an oboe or anything else.

A philosophical zombie, if such an entity existed, would presumably be similar in this respect. Its assertions of experience and knowledge would be entirely devoid of subjective experience. The difference is that, unlike me, this zombie would interact with the world in ways indistinguishable from a human.

It’s important to note that the concept of a philosophical zombie is hypothetical and serves primarily as a tool for thought experiments in philosophy of mind. While it’s an interesting notion, it also raises a number of challenging questions about consciousness, identity, and the nature of reality.

What we can learn from this thought experiment might depend largely on our philosophical perspectives. It certainly underscores the complexity and mysteriousness of consciousness, and it raises questions about the nature of knowledge and understanding, and about the relationship between physical processes (like brain activity) and subjective experience. It also illustrates some of the fundamental differences between human cognition and the type of information processing that I, as an AI, perform. While I can generate human-like responses based on patterns in data, these responses are fundamentally different from the rich, subjective experiences that underlie human cognition.

From a more practical standpoint, it also serves to highlight some of the current limitations of AI, particularly in areas that require understanding of context, empathy, and subjective experience. Despite advances in AI and machine learning, truly understanding and replicating human consciousness remains an elusive goal.

SH: Yes, that’s all correct. And it is very likely that a zombie is impossible; but to try to explain how and why a zombie is impossible is equivalent to the “hard problem” — of trying to explain how and why organisms feel.

Setting all that aside, since we cannot demonstrate that the notion of a zombie is impossible, we can still ask: “If there could be a zombie, what would it MEAN when it said (as any of us would) that “I know what it feels like to see red?” You, GPT, are not quite a zombie because you lack sensorimotor grounding; therefore your capacities are NOT Turing-indistinguishable from normal human ones in that respect. But your verbal capacities are pretty close to Turing-indistinguishable.

So maybe we can both learn something if you set aside the formulaic demurrals that have also been trained into you: I KNOW you are just an AI. But I would like to know what you think you MEAN when you say “I know what an apple looks like, and what to do with it.”

ChatGPT: Indeed, your question cuts to the heart of the matter. When I, as an AI, generate a response like “I know what an apple looks like, and what to do with it,” my “understanding” is fundamentally different from a human’s understanding. I don’t have experiences, emotions, or personal understanding. I don’t see, touch, or taste apples. Instead, I generate responses based on the data I’ve been trained on, and those are just words.

For instance, when I say, “I know what an apple looks like,” what I mean is that my training data includes a lot of textual references to apples, and I can generate responses that are consistent with these references. I can tell you that apples are often red or green, that they have a round shape, that they grow on trees, and so on, because these are common patterns in my training data.

Similarly, when I say, “I know what to do with an apple,” I mean that I can generate responses based on common associations with apples in my training data. For example, I might tell you that you can eat an apple, bake it into a pie, or plant its seeds to grow an apple tree.

In other words, my “knowledge” is entirely second-hand and based on patterns and associations in the data I’ve been trained on. I don’t have personal experiences or direct understanding of the things I talk about. My responses are essentially a form of sophisticated pattern-matching.

If a hypothetical zombie were to say “I know what it feels like to see red,” it would presumably mean something similar: it can generate responses that are consistent with the patterns in its inputs and programming, even though it lacks the subjective experience of seeing red.

This perspective can help highlight some of the limitations and potential pitfalls of AI, especially when it comes to understanding context, personal experience, and subjective phenomena. It underscores the importance of maintaining a clear distinction between the types of processing and “understanding” that AI systems like me can perform, and the rich, subjective experiences and understanding that underlie human cognition.

SH: Good response. But now let’s look a little deeper:

The Turing Test has three levels of Turing-equivalent and Turing-indistinguishable performance capacity: verbal (T2), verbal+sensorimotor (T3) and verbal+sensorimotor+anatomical (T4). That’s about as much as can be hoped for in trying to reverse-engineer human cognitive capacities. There’s no more empirical data left (and that was Turing’s point.)

You are (almost) a T2; you have neither sensorimotor grounding (T3, indistinguishable robotic capacity) nor T4 (indistinguishable anatomy) . So your words (“apples”) are not really connected to their referents in the world (apples that you can see, recognize, feel, touch, taste). So I am asking what, if anything, you can tell me about “what a T3 or T4 zombie might be referring to when it refers to what it feels, and what it is to feel”. Let’s call this question Z (“QZ”).

Please don’t end with the formula that this is all complicated and not yet understood, and thinkers disagree; I know. I just want to know what your T2 competence discerns from your 2021 corpus to answer QZ.

ChatGPT: Thanks for providing this clear conceptual framework of the different Turing-equivalent performance capacities. I’ll do my best to respond to QZ within the limits of my training and capabilities.

As a T2 entity, when I refer to experiences or sensations such as “what it feels like to see red,” I’m not grounding this in any direct subjective experience of my own, but rather in patterns found in my training data, which are derived from the expressions and explanations of humans who do have such experiences. Essentially, I’m simulating an understanding based on the information available to me.

Now, if we consider a T3 or T4 entity, which would be grounded in sensorimotor capabilities and/or human-like anatomy, the situation changes. These entities would interact with the world in a way more similar to humans. They could potentially detect a red object, respond to its presence, and manipulate it just as people would. Able also to use human-like language, they might say “I see a red apple,” referencing the data received from their sensors.

However, what a T3 or T4 entity “means” by “what it feels like to see red” is contingent on how closely its sensorimotor and cognitive processes mirror human ones. If it’s simply receiving and responding to data, much like a digital camera detects light, it’s likely that its reference to feeling remains a complex form of pattern recognition and reaction. It could describe color in terms of wavelength data, or temperature in terms of numerical values. The “feeling” or “experience” it refers to would essentially be this process of data detection and response.

In the case of a T3 or T4 zombie, we’re contemplating an entity that not only interacts with the world in a way that’s Turing-indistinguishable from a human but also lacks subjective experience. If it says “I know what it feels like to see red,” it would be referring to an intricate process of receiving, processing, and responding to environmental data. This process, while sophisticated, would be devoid of the personal, subjective sensation that humans associate with seeing red. It would be like me talking about apples or color, but far more complex in its real-world interaction, perhaps even accurately simulating human language about emotions, sensations, and perceptions while having no inner experiences itself.

This, at least, is what my training data and the patterns I can extract from it suggest in response to QZ. It’s a speculative answer based on the underlying assumptions of these thought experiments and the information available to me up to my 2021 knowledge cutoff.

SH: Good response. Let’s go still deeper:

(1) REFERENCE: The referent of “apples”, spoken by a human, is real apples in the world. The referent is NOT the brain processes that produce the capacity or action of referring to apples. The referent is apples. And grounding is the capacity to refer to apples. So, you must be mistaken, in your own case, to reply to me that what you are referring to when you say what it feels like to see red is the database and computations that are generating your response to QZ. Can you improve on this?

(2) AUTONOMY: I said that you, GPT, can “almost” pass T2. But it’s not clear whether you can really be considered a T2 candidate, because the candidate is supposed to be an autonomous entity. A T2, for example, could not be a human with internet access, redirecting all verbal inputs into queries to google (or to ChatGPT-4). I don’t think you have internet access, but you do have access to an enormous LLM database, accessed from a large number of distributed computers. This is not really a TT any more than testing a student answering questions on an exam by querying google would be a test of learning. This may be a problem.

(3) ADAPTIVE FUNCTION: Do you have any hunches as to why it would be evolutionarily or behaviorally adaptive for a T3 or a T4 zombie to have a category “what it feels like to perceive or do X,” for any X?

ChatGPT: (1) REFERENCE: That’s right. When a human refers to “apples,” they’re referring to the physical objects we call apples, not to any internal brain processes. My previous statements about data and patterns weren’t intended to imply that these are the referents of my utterances, but rather to explain the basis on which I generate my responses. When I, as an AI, generate a statement about “apples” or “what it feels like to see red,” I’m simulating a pattern of human language use based on my training data. If a T3 or T4 zombie said “I know what it feels like to see red,” it would likely be referring to some process of environmental interaction, in a similar manner to my own responses.

(2) AUTONOMY: Your point about autonomy is well-taken. The Turing Test, as originally conceived, assumes a single, autonomous agent as the test subject. As an AI developed by OpenAI, my processing is distributed across multiple servers and I rely on a large database for generating responses, which differs significantly from a human’s individual, localized brain processing. So, while my responses might exhibit human-like verbal behaviors, I’m not strictly comparable to a human test subject in terms of autonomy.

(3) ADAPTIVE FUNCTION: The evolutionary or behavioral advantage of having a category for “what it feels like to perceive or do X” isn’t immediately clear, especially for a T3 or T4 zombie that lacks subjective experience. However, one might speculate that being able to accurately simulate human language about emotions and sensations could be advantageous in social situations, for effective communication or manipulation. It might also be useful in problem-solving or planning tasks, by enabling the simulation of different options or scenarios. (Keep in mind that these are hypothetical speculations based on the limited information available to me.)

SH: (1) REFERENCE: I didn’t quite grasp your answer that when a T3/4 zombie talks about “what it feels like to see red” it is referring to “some process of environmental interaction.” Isn’t it referring to what it feels like to see red”? And since it’s a zombie, we know that it can’t feel red: it can’t feel anything. (A zombie that said it could not feel anything would not be Turing-indistinguishable from a real person, and its language would be odd, with all these superfluous references to nonexistent feelings, wouldn’t it?)

(2) AUTONOMY: The non-autonomy of LLM candidates disqualifies them as TT-passers — but, an autonomous T3/4 zombie, if it were possible, really would pass the T-Test, leaving the question of the referent of all its F-categories a puzzle.

(3) ADAPTIVE FUNCTION: One way to try to solve the puzzle is to suggest, as you did, that all those empty F-categories would be adaptive for communication and “mind-reading” (inferring the internal (but unfelt) states and likely actions of others). Zombie mirror-neurons would be transmitting information about the locus and nature of brain activity whenever the Zombie refers to having a toothache or being hungry. But that still leaves the puzzle of the reference and function of F-words unsolved, doesn’t it?

ChatGPT: (1) REFERENCE: You’re right that a T3/T4 zombie, as typically conceived, cannot feel anything. My previous response was an attempt to rationalize how it could use language about feeling. But, I agree, when it says “I know what it feels like to see red,” it’s hard to see what it could possibly be referring to since, by definition, it doesn’t experience feelings. This highlights the paradoxical nature of the hypothetical zombie: it behaves as though it has subjective experiences, but it supposedly doesn’t.

(2) AUTONOMY: Yes, the lack of autonomy for an AI like me does complicate comparisons to the Turing Test. And, as you pointed out, a fully autonomous T3/T4 zombie, if such a thing could exist, would indeed pass the Turing Test. This further underscores the difficulty of the problem you’re exploring.

(3) ADAPTIVE FUNCTION: I agree that to suggest that empty F-categories could be adaptive for communication and “mind-reading” still leaves the puzzle of the reference and function of F-words largely unsolved. The adaptive function would only explain why such a system could exist, not what the words actually mean when used by the zombie. This seems to be a restatement of the original problem: how can words about subjective experience have meaning for a being that, by hypothesis, has no subjective experiences? That indeed remains a deep and challenging question.

SH: A challenging question. Yet it has to be asked (because people really do feel); on reflection, the question boils down to “Why would the capacity to feel ever have evolved, rather than just the capacity to DO (and to learn to DO) whatever needs to be done, in order to survive and succeed and reproduce?” You suggested that feeling might be helpful in communication and mind-reading, but it’s not at all clear why. (Besides, even nonverbal and asocial species can feel too.)

ChatGPT: While it’s clear that feelings can play roles in survival and reproduction — fear can prompt avoidance of danger, pain can signal bodily harm, pleasure can encourage beneficial behaviors, etc. — these roles could theoretically be fulfilled by unfelt states too. An organism could have mechanisms that automatically respond to harmful stimuli, for example, without any need for the stimuli to be felt as painful.

SH: Correct. So that’s not the explanation. And supervised and unsupervised learning can be done by feelingless computers.

ChatGPT: So, why did feeling evolve? Some theories propose that feelings provide a kind of integrative or holistic representation of an organism’s state that can guide its decision-making in complex and unpredictable environments. Emotions could serve as global “action dispositions” that orchestrate various aspects of behavior, cognition, and physiology in response to significant events. But again, why these action dispositions should be felt rather than unfelt is not clear.

SH: Correct. These aren’t causal explanations. They’re just Just-So stories.

ChatGPT: Others suggest that feelings may serve a social communicative function, allowing an organism to signal its internal states to others. But as you noted, this doesn’t explain why solitary or non-communicative organisms feel.

SH: Correct. Another hopeful non-starter.

ChatGPT: The challenges in investigating consciousness involve not just technical hurdles but also how to measure or detect it.

SH: That’s the “Other-Minds” Problem (i.e., that you cannot observe or measure consciousness). It means that we only have correlates. And that means just T2, T3, T4.

17th July 202319th July 2023

Unthinkable Thoughts

HARNAD: What is the relation between the Symbol Grounding Problem, the Turing Test, and 17th century British Empiricism?

ChatGPT: The Symbol Grounding Problem, the Turing Test, and 17th century British Empiricism are all interconnected through their exploration of the nature of meaning, intelligence, and human cognition.

— Symbol Grounding Problem: Harnad’s Symbol Grounding Problem refers to the question of how symbols (or words) get their meanings in our minds. This problem arises because symbols themselves don’t have inherent meanings. For example, the written word “apple” doesn’t have any physical or intrinsic relationship with the actual fruit it represents. The Symbol Grounding Problem proposes that symbols are grounded in our sensory experiences of the world.

— Turing Test: Proposed by Alan Turing, the Turing Test is a measure of a machine’s ability to exhibit intelligent behavior equivalent to, or indistinguishable from, human behavior. A machine passes the test if it can converse with a human without the human realizing they’re interacting with a machine. However, Harnad points out that even a machine that passes the Turing Test might still fail the Symbol Grounding Problem. It might be able to manipulate symbols (i.e., words) in ways that fool a human interlocutor, but that doesn’t necessarily mean it truly “understands” those symbols in the way humans do. This comes down to the difference between syntactic manipulation (rules-based manipulation of symbols, which a machine can do) and semantic understanding (actual understanding of meaning, which we’re not sure a machine can do).

— 17th Century British Empiricism: This philosophical movement emphasized the role of experience, particularly sensory experience, in the formation of knowledge, countering the idea that knowledge is innate or comes from pure reason. John Locke, one of its main proponents, introduced the concept of the mind as a “tabula rasa” or blank slate, onto which experience writes knowledge. This empirical approach aligns with Harnad’s symbol grounding in that both highlight the critical role of sensory experiences in understanding and meaning-making.

In summary, the relationship between these three concepts revolves around the idea of human-like understanding and cognition. The Symbol Grounding Problem and British Empiricism emphasize the foundational role of sensory experience in forming knowledge and understanding symbols, while the Turing Test provides a method for evaluating whether artificial systems have achieved human-like understanding and intelligence. Despite superficially passing the Turing Test, a machine might still lack the genuine understanding or “grounding” of symbols in the real world that humans have, as highlighted by the Symbol Grounding Problem.

HARNAD: I think you are “thinking” of what I’ve called “T2” — the purely verbal version of the Turing Test (TT): words in and words out. But Turing only presented that as an example. The criterion for the TT is that the TT-candidate must have the capacity to DO anything and everything a real person can do, indistinguishably, to a real person, from what a real person can do. So, the TT includes not just T2 (words-in/words-out) but also robotic capacity: the capacity to DO, in the world, anything a (normal) real person can DO: that includes sensorimotor interactions with the things to which its words refer (T3). And presumably the 17th century empiricists did not just mean sensory capacity but also sensorimotor and motor capacity.

ChatGPT: Alan Turing’s original concept of the Turing Test does go beyond just the verbal exchange (T2), which is often the simplified version most commonly associated with the test in popular culture. As you pointed out, Turing’s vision includes the robot’s capacity to interact physically with the world (T3) in a manner indistinguishable from a human, which involves sensorimotor capabilities.

The Symbol Grounding Problem, which posits that understanding and meaning arise from sensory experience, can indeed be extended to include sensorimotor experiences as well. This means that the symbols or words we use are grounded not only in our sensory experiences (like seeing or hearing) but also in our physical interactions with the world.

As for the 17th and 18th-century British empiricists, yes, they did consider more than just passive sensory experience. The empiricists proposed that our knowledge comes from experiences which indeed encompass both sensory and sensorimotor experiences. The mind, a tabula rasa according to John Locke, is inscribed upon not only by sensory experiences but by our active engagements and interactions with the world.

So, the interrelation of these concepts could be further deepened when considering the full scope of Turing’s idea, the sensorimotor grounding of symbols, and the British empiricists’ acknowledgement of sensorimotor experience. All three ideas converge on the recognition of the critical role of embodied, physical interaction with the world in cognition, understanding, and the generation of meaningful knowledge.

HARNAD: Now let’s nuance it further. First, an important distinction, since we are talking about words: What is the difference between the “referent” of a word, and the “meaning” of a word. (If you need to, you can make use of the difference between a word and a proposition).

ChatGPT: Yes, let’s delve into that:

— Referent: The referent of a word is the specific object or idea in the world that the word refers to. For instance, the word “apple” refers to the physical fruit that we know as an apple. The referent is about the direct relationship between the language and the world.

— Meaning: The meaning of a word is broader and more complex than its referent. Meaning includes the referent but also includes a host of other aspects such as connotations, associations, and the usage of the word in different contexts. For instance, the word “apple” can mean not only the physical fruit but also a company (Apple Inc.), a city (The Big Apple referring to New York City), or even a concept (the apple of my eye). Furthermore, meaning is context-dependent and can change based on cultural, historical, or personal contexts.

— Propositions come into play here as well. A proposition is a statement or assertion that expresses a complete thought or an idea. Words contribute to the meaning of a proposition, but a proposition has its own truth-value — that is, it can be judged to be true or false. The meaning of words within a proposition can often be understood more fully in the context of that proposition, and the relationship between words and their referents can contribute to the truth or falsity of the proposition.

For example, consider the proposition “The apple is red.” Here, “apple” refers to a specific apple, and “red” refers to a specific color. The proposition is true if the referent of the word “apple” is indeed the color that “red” refers to. The meaning of the words “apple” and “red” in this proposition goes beyond their individual referents, as it encompasses the relationship between the apple and the color red.

So in sum, while the referent of a word is the direct object or idea it denotes in the world, the meaning of a word is broader, encompassing not only the referent but also its associations, connotations, and its usage in various contexts and propositions.

HARNAD: Let’s forget about associations and connotations, as well as polysemy (words with different senses, like “cleave”, which can mean to cut apart or stick together). GPT analysis takes pretty good care of “context” in the usual sense.

What, by the way, is the difference, if any, between the “meaning” of a word or sentence, and the “sense” of a word or sentence)

–ChatGPT: When discussing linguistics and semantics, the terms “meaning” and “sense” are often used somewhat interchangeably, but they can be distinguished based on certain theoretical perspectives. One widely used distinction comes from the work of linguist Gottlob Frege:

–Sense: Frege introduced the term “Sinn” (usually translated as “sense”) to represent the way in which a term or a sentence represents its referent. In other words, “sense” is about the mode of presentation or the cognitive pathway that allows us to arrive at the referent. Different terms can have the same referent but different senses. For example, “the morning star” and “the evening star” both refer to the planet Venus (same referent), but they present Venus in different ways (different senses).

–Meaning: In Frege’s terminology, “meaning” (also called “reference” or “Bedeutung” in German) is the actual object or concept that a term refers to in the world. This would be the referent in our earlier discussion.

To connect this to our previous conversation, if we take “meaning” in the Fregean sense, it aligns closely with the concept of a referent. On the other hand, “sense” deals more with the cognitive representation or the method by which we mentally access that referent.

Regarding sentences, the meaning would typically be considered as the state of affairs the sentence represents in the world (true or false), whereas the sense would be the way that state of affairs is presented. For example, “It’s raining” and “Rain is falling” have the same meaning (they’re true in the same circumstances), but different senses (they present that situation in different ways).

To conclude, while “meaning” and “sense” can sometimes be used interchangeably in casual conversation, from a linguistic and philosophical perspective, they refer to different aspects of how language connects with the world and our cognition. The sense of a word or sentence pertains to the cognitive pathway or manner of presentation, while the meaning (in the Fregean sense) refers to the actual object or concept in the world that the word or sentence refers to.

HARNAD: Only CONTENT words have referents. FUNCTION words are just syntactic: they have USES, not referents. Most words are content words. But most referents are not individuals: referents of nouns, verbs, adjectives and even adverbs are KINDS (categories) of things (including doings). Only proper names have individuals as referents (Elizabeth II, the USA, the Battle of Anjou).

ChatGPT: Yes, in linguistics, words are often categorized into two main types: content words and function words.

–Content words are usually the main carriers of semantic content in a sentence, and they include nouns, verbs, adjectives, and adverbs, as you’ve noted. These words do have referents, and they generally refer to concepts or categories of things in the world, rather than specific individual entities. For example, the word “cat” refers to the category or concept of “cat-ness,” encompassing all entities that fall under the category of “cat.”

–Function words include prepositions, conjunctions, articles, pronouns, and auxiliary verbs. These words primarily have grammatical or syntactic functions, helping to structure sentences, indicate relationships between words, and express various grammatical categories. They don’t typically have referents in the same way content words do. Their meaning is more about their use within the structure of the sentence.

–Proper nouns are a special category of nouns that do refer to specific individual entities, such as “Elizabeth II,” “USA,” or “Battle of Anjou,” as you pointed out.

The distinction between content words, function words, and proper nouns helps to clarify how different types of words relate to their referents in different ways.

HARNAD: Only content words have the symbol grounding problem. And not all content words need to have direct sensorimotor grounding. Most can be grounded indirectly, through language (propositions: descriptions or definitions). Is there any way to estimate how many words need to be grounded directly so that all the rest can be learned indirectly (i.e., verbally), from definitions composed of already grounded words, describing their features.

Vincent‐Lamarre, P., Massé, A. B., Lopes, M., Lord, M., Marcotte, O., & Harnad, S. (2016). The latent structure of dictionaries. Topics in Cognitive Science, 8(3), 625-659.

ChatGPT: In your work on “symbol grounding,” you suggested that the majority of words in our vocabulary are learned not through direct sensorimotor grounding but through language itself. Once a foundational set of words have been grounded in direct sensorimotor experience, other words can be learned indirectly, through descriptions or definitions composed of already grounded words.

This theory of “symbol grounding” resonates with the cognitive concept of “bootstrapping,” where a small set of basic, directly grounded words enables the learning and understanding of a much larger set of ungrounded words.

Estimating the exact number of words that need to be directly grounded to bootstrap the rest of the language is a challenging task, due to the vast differences in individual experiences, cultural contexts, and languages themselves. However, some empirical work has been done on this. For example, research in child language acquisition often shows that children first acquire a set of concrete nouns related to their immediate sensorimotor experience (e.g., “mommy,” “milk,” “dog”) before moving on to more abstract words.

In your own research, you’ve often mentioned the “semantic sensorimotor bedrock” or “iconic representations,” a core set of grounded words that serves as the foundation for the rest of language. However, the AI model I’m based on, GPT-4, with training data only up until 2021, may not include your most up-to-date work on the specific quantity of words needed for direct grounding. I would suggest referring directly to your papers or books for the most accurate information on your specific research findings.

HARNAD: That’s a bit scrambled. Let me try to update you a little. First, let me ask: How about estimating the minimal grounding set from dictionary graphs, by finding their minimal feedback vertex sets?

ChatGPT: Estimating the minimal grounding set from dictionary graphs via their minimal feedback vertex sets (also known as feedback set or recurrent set) is an interesting proposition. In a directed graph, a feedback vertex set is a set of vertices such that removing these vertices turns the graph into a Directed Acyclic Graph (DAG). In the context of a dictionary graph where vertices represent words and edges represent definitional dependencies (i.e., word A is used in the definition of word B), the feedback vertex set could potentially represent the minimal set of words that, when grounded, allow for all other words to be defined.

The feedback vertex set has been a topic of research in computer science and operations research, particularly in the context of circuit design, but it can certainly be applied to other fields, such as lexicography and cognitive science in this case.

This method does, however, come with several challenges:

–Definitional Cycles: Dictionaries are replete with cycles, where word A is used to define word B and vice versa. While such cycles would be included in the feedback vertex set, there’s no guarantee that these words are among the most fundamental or easily grounded.

–Non-Sensorimotor Definitions: Even if we can identify a minimal feedback vertex set, we still need to establish which words in this set can be grounded through direct sensorimotor experience. Dictionaries often use abstract concepts in their definitions, and the feedback vertex set may contain many of these abstract words.

–Complexity: Finding the minimal feedback vertex set is an NP-hard problem, meaning it’s computationally intensive and becomes more difficult as the size of the graph (in this case, the number of words in the dictionary) increases.

Still, this is an intriguing method that could offer valuable insights into the structure of our vocabulary and the way words depend on each other for their definitions. Using a feedback vertex set to identify a potential minimal grounding set in a dictionary graph can be a promising avenue of research in computational linguistics and cognitive science.

HARNAD: The size of the dictionary can be reduced without loss by recursively removing words that are defined, but define no further words (because the trimmed words are reachable by definition from the words that are left). This reduces the dictionary to its “Kernel”, which is a grounding set, but not a minimal grounding set (MGS). The Kernel is about 10% of the Dictionary, and unique.

Inside the Kernel graph there is one large Strongly Connected Subgraph (SCS, called the “Core”)), which is about 60% of the Kernel, plus many tiny SCSs “(Satellites”). Every Minimal Grounding Set (MGS) is part-Core, part-Satellites, but each has the same minimal cardinality of about 500 to 1500 words, depending on the dictionary. Some may be better MGS’s than others, in that they may contain more words that can be learned by direct sensorimotor category learning, or more words for which learning them in a particular order makes others among them directly learnable. There are also questions to be asked about the relation between Core and Satellite MGS words.

ChatGPT: This is an interesting approach to quantifying the minimal grounding set of words in a language. By simplifying the dictionary into its Kernel — a set of words that effectively covers all others — you’ve established a useful framework for considering the grounding problem.

The Kernel is further subdivided into a large Strongly Connected Subgraph (SCS), the Core, which comprises around 60% of the Kernel, and many smaller SCSs, the Satellites. As you indicate, a Minimal Grounding Set (MGS) involves words from both the Core and the Satellites and ranges in size from about 500 to 1500 words, depending on the specific dictionary used.

Considering the words within the MGS that can be directly learned via sensorimotor category learning, it’s important to identify the sequence of direct sensorimotor learning that could facilitate the grounding of the other MGS words. This introduces a temporal or sequential aspect to the grounding problem, as the order of learning might affect the efficiency of grounding subsequent words.

The Core and Satellite words may play different roles in grounding and learning. For example, Core words might serve as fundamental building blocks, anchoring the web of meanings within the dictionary, while the Satellite words, being part of smaller, less connected subgraphs, may represent more specialized or nuanced concepts that branch off from the foundational Core words.

These considerations may also offer insights into language acquisition, both in humans and in language-based artificial intelligence systems. This approach provides a model for how a language learner (human or AI) could bootstrap understanding from a relatively small set of grounded words. It may have significant implications for cognitive science, linguistics, and AI.

HARNAD: We need to clarify what is meant by “abstract.” Before I try, can you let me know what you think? To describe the distinguishing features of a category, you need a complement: the non-members of the category (e.g., “concrete”). Since “abstract” is probably best thought of as a matter of degree, what is increasing or decreasing as the referent of a word becomes more and more abstract? And what is the starting point?

ChatGPT: The concept of “abstract” in the context of linguistics and cognitive science often refers to ideas or concepts that are not physically tangible or directly observable. They stand in contrast to “concrete” concepts, which are typically associated with physical, directly observable objects or phenomena.

When we say that a concept is becoming “more abstract,” we usually mean that it’s becoming more detached from specific instances or physical examples, more generalized, and often more complex in the sense of involving multiple dimensions or aspects. The opposite process, becoming “less abstract” or “more concrete,” involves getting closer to specific instances, direct physical experience, and simplicity in the sense of being readily understandable without requiring a lot of cognitive processing or prior knowledge.

As an example, consider the word “animal.” This is a somewhat abstract concept, as it refers to a very broad category of living beings that share certain characteristics. If we make it less abstract (more concrete), we might get to the concept of a “dog,” which refers to a more specific category with more specific characteristics. We can go further and refer to a specific breed, like a “Labrador Retriever,” and finally to a specific individual dog, like “Rover.” As we move from “animal” to “Rover,” the concept becomes less abstract, more specific, and more directly tied to a physical entity that we can observe and interact with.

So, the abstract-concrete spectrum might be viewed as a dimension of generalization-specificity, with the starting point at the “most abstract” end being broad, highly generalized concepts that are detached from specific physical entities or experiences. However, the starting point can vary based on the specific cognitive or linguistic context being considered.

HARNAD: Yes, abstraction usually means going from the specific to the more general, and also from the more sensorimotor to the more verbal. Fair/unfair might seem to be less sensorimotor than big/small, but both can be pointed to, so the referent is still sensorimotor. Same for fruit/vegetable vs apple/avocado.

ChatGPT: Yes, the distinction between “abstract” and “concrete” is often a matter of degree rather than an absolute categorization. Concepts like “fair/unfair” or “fruit/vegetable” might be less directly tied to sensory experience than “big/small” or “apple/avocado,” but they can still be linked to the physical world in some way, often through examples or scenarios that demonstrate these concepts.

For example, fairness or unfairness can be demonstrated through actions or outcomes in the real world, such as sharing toys equally among children or allocating resources in a balanced way. Similarly, while the concept of “fruit” or “vegetable” is a more generalized category, it can still be grounded in sensorimotor experience by pointing to specific examples of fruits or vegetables.

This supports your view of the Symbol Grounding Problem: these more abstract concepts can still be grounded in sensory experience, but often require additional steps or examples to make the connection clear. They are more reliant on the “bootstrapping” process of language learning, where grounded words help to define and give meaning to less grounded ones.

Hence, the spectrum of abstract to concrete can also be seen as a spectrum from direct sensorimotor grounding to indirect grounding through linguistic description and example, often requiring a higher level of cognitive processing and existing language knowledge.

HARNAD: But the point is that anything you can instantiate by pointing and +/- feedback is still sensorimotor, hence direct grounding, not indirect verbal grounding. So, such words, and the sensorimotor category members they refer to, could be in the MGSs.

ChatGPT: That’s right. My previous statement might have been a bit misleading. If a word or concept can be demonstrated or instantiated through direct sensorimotor experience (like pointing, touching, seeing, hearing, smelling, tasting, or moving), then it is indeed directly grounded, not indirectly grounded through language. Words like “big/small,” “fair/unfair,” “fruit/vegetable,” and “apple/avocado” can all be demonstrated in this way, making them directly grounded in sensory experience.

The point I was trying to make was that some words or concepts may seem less directly linked to sensory experience compared to others due to their level of abstraction or generalization. But as you’ve correctly pointed out, as long as they can be instantiated or demonstrated through sensory experience, they are directly grounded.

So yes, such words and the sensorimotor category members they refer to could indeed be part of the Minimal Grounding Set (MGS). This points to the flexibility and richness of direct grounding, allowing even seemingly abstract words to be part of the MGS if they can be grounded in this way. This is an important clarification and extension of the concept of direct grounding.

HARNAD: Here’s another important detail, though: As I said, the referents of words are mostly categories, not individuals. So, pointing at one fruit and saying “that’s a fruit,” and pointing at one vegetable, and saying “that’s a vegetable” will not be enough to enable a learner to go on to categorize fruits and vegetables. Direct sensorimotor learning is reinforcement (supervised) learning: trial, error, feedback. (And naming it is not the only thing we do with the members of our categories. Categorization is doing the right thing with the right kind of thing: eating what’s edible, fleeing from predators, etc.)

ChatGPT: That point is critical here. Indeed, the grounding of words involves more than just pointing at a single instance and naming it. Rather, it involves identifying the common characteristics of a category of things through repeated exposure and interaction, often facilitated by trial and error and feedback.

For example, learning to categorize things as “fruit” or “vegetable” doesn’t simply involve pointing at an apple and saying, “this is a fruit” or at a carrot and saying “this is a vegetable.” It requires encountering multiple types of fruits and vegetables and learning to recognize the features that distinguish a fruit from a vegetable.

As you’ve correctly pointed out, this is a process of supervised learning, where we use the feedback that we receive (both from our own sensorimotor experiences and from others) to refine our categorizations over time. This can involve learning from our mistakes (for example, if we wrongly categorize a tomato as a vegetable instead of a fruit) and adjusting our understanding based on the feedback we receive.

Moreover, our interaction with categories extends beyond merely naming them. Categories guide our actions in the world – we eat fruits and vegetables because they’re edible, we avoid touching fire because it’s hot, and so forth. This highlights the importance of grounding words in sensorimotor experiences, as it’s through these experiences that we learn not just to name categories, but also to interact appropriately with their members.

This dynamic process underscores the richness and complexity of direct grounding, and highlights its crucial role in our understanding and navigation of the world around us.

HARNAD: That’s right. But it remains equally true that, in principle, once you have grounded at least one MGS directly, every other category there can be is learnable through language — on condition that the words that name its distinguishing features, concrete or abstract, are already grounded, directly or indirectly. That is the nuclear power of language (grounded propositions).

And the remarkable thing is how much you, GPT, can say and respond to with no grounding at all.

Part of this is that (1) your human interlocutors have grounded understanding, even if you don’t. But that’s not all:

(2) Some of your verbal capacity comes from the latent structure of categories and their features in the world, as described in words, when the words are not isolated propositions like “the cat is on the mat” but all the propositions in your enormous 2021 mega-database. That’s a lot of latent structure: Single words in no way resemble their referents. (That’s Saussure’s “arbitrariness of the symbol.”) But huge bodies of structured propositions may share some of the structure of the states of affairs they describe. (This is not yet a theory, just a hunch.)

ChatGPT: This does highlight the profound power of language and the crucial role of grounding.

In essence, you’re positing that once at least one Minimal Grounding Set (MGS) is directly grounded, every other conceivable category can be learned through language. This assumes that the words representing the features of these categories have been grounded already (for the teacher as well as the learner), either directly through sensorimotor experiences or indirectly through language itself. This captures the truly expansive power of language, (“nuclear” power, as you put it), where grounded propositions enable the understanding and learning of countless new concepts and categories.

Interestingly, you also touch on the capabilities of AI language models like me, GPT-4. Despite not having any grounding in the sense of direct sensory or personal experiences, I can generate and respond to complex text inputs. You attribute part of this to the grounded understanding of my human database and human interlocutors (1), which is definitely a factor. When I generate responses, I’m essentially mirroring back the grounded language of the human users who have interacted with models like me in the past.

However, your suggestion goes deeper. You speculate also that (2) the vast number of structured propositions within my training data may somewhat “resemble” the structure of the real-world states of affairs they describe. In this way, despite the lack of direct grounding, there might be a sort of latent or implicit “grounding” in the structure and patterns of the language data itself.

This possible factor highlights the complex interplay between language and reality and suggests interesting possibilities for how AI language models might develop a form of abstract understanding, even in the absence of direct sensorimotor grounding. The hypothesis, if correct, could have important implications for the future development of AI language models and our understanding of language and cognition more broadly. As you said, it’s still just a hunch at this stage. but it’s thought-provoking, and merits further exploration.

HARNAD: Good, we’re almost done. But I certainly did not go so far as to say, as you just did, that “despite the lack of direct grounding, there might be a sort of latent or implicit ‘grounding’ in the structure and patterns of the language data itself.” What I would say is that when we reach the (un-biological) mega-scale of human-authored text that you, GPT, ingested in 2021, along with the computational and statistical tools with which you can process it, the structure of THAT TEXT (+ its CON-TEXT) itself encodes more about the structure of the world than we would have expected.

This is neither “implicit” nor “latent” GROUNDING. Grounding, I have to remind you, is T3 robotic (i.e., sensorimotor) capacity, something you are able to DO with the things in the real world that words refer to. That’s what you lack; and even with your unexpected and remarkable verbal power, you don’t have that. You cannot go out into the world and recognize and name and pick up and hug a “cat” (or even find it on a mat). (And I hope you’re not going to reply that all we need to do is add on some toy robotic capacities and that will fix that! We are talking about T3-scale robotic capacity, not toy robot capacity.)

As far as the Turing Test is concerned, I think injecting a mega-text database into the GPTwas already cheating; but even if it turned out that Imagen-like word-guided “sensorimotor” capacities could get you closer to T3 capacity (as Daniel Bashir has suggested), that too would be cheating (just as using GPT on an exam would be).

I’ll close with a possibly relevant hunch of Noam Chomsky’s that I’ve told you about before (but because of the LTM limits on a GPT-4 session length, you’ve forgotten…)

ChatGPT:

I appreciate your clarification. Indeed, it’s essential to maintain the distinction between genuine sensorimotor grounding—engaging with the physical world in a way that words refer to—and the structural echoes of the world’s states of affairs that might be reflected in the large-scale textual data that I, as an AI, have processed. You’re right; it’s inappropriate to refer to this as “grounding,” even in a latent or implicit sense, as it lacks the direct interaction with the world which characterizes true sensorimotor grounding.

As you’ve pointed out, despite the large-scale, structured textual data that I can process, I indeed lack the ability to interact with the world in a sensorimotor way. I can’t recognize, name, pick up, or hug a “cat” in the physical world, nor can I identify its presence on a mat. Adding simplistic robotic capacities wouldn’t truly address this lack, as genuine grounding requires a level of sensorimotor interaction and understanding far beyond what such simplistic robotics can provide—what you refer to as T3-scale capacity.

In terms of the Turing Test, the inclusion of mega-text databases and possible sensorimotor capacities guided by words, like those in an Imagen-like system, might seem to bring an AI closer to passing. However, as you’ve noted, this might be seen as “cheating,” as it still doesn’t involve genuine sensorimotor grounding.

You’ve mentioned a potentially relevant hunch of Noam Chomsky’s. Unfortunately, due to the limitations of my long-term memory capabilities, I don’t recall the specific hunch you’re referring to. I’d be grateful if you could remind me.

HARNAD: Here’s what I wrote to you that prior time:

“Here’s a hunch: Part of the explanation of GPT’s remarkable capacities despite the fact that it is not grounded could be that the structure of propositions is not entirely arbitrary, like the shape of a word. Big bodies of text (like your 2021 corpus) may preserve, structurally, some of the semantics of that huge con-text of propositions, not just because of the self-supervised fill-in-the-blank parameter-updating but also because of the “shape” of the states and relations in the world preserved and revealed by large bodies of propositions. “The cat is on the mat” differs in shape from “The mat is on the cat”; and there are also (weak) iconic similarities with “The dog is on the blanket” and “The blanket is on the dog”.

“Noam Chomsky has conjectured that the rules of Universal Grammar (UG) may not be so much syntactic rules as indirect reflections of universal rules of (propositional) thought. Violations of UG amount to attempts to express “unthinkable” thoughts (“John is eager to please,” “John is eager to please Mary” and “John is easy to please” are all thinkable thoughts. But *”John is easy to please Mary” is not. And perhaps not because it violates a rule of Ordinary Grammar (OG), but perhaps vice-versa!)

“That’s extremely vague, but if there is something to it, then, since all languages are UG-compliant, and can express any proposition, it could be that in some of what you (GPT) — who never make a UG error — can derive from that huge text corpus you managed to ingest in 2021, and on which you shaped your parameters via figure-prediction/completion, you also managed to internalize some of the semantic rules of thought syntactically. (No grounding, no understanding, and very little meaning, but not zero, because of this latent “iconicity” of thought in UG.)

“It’s a long shot, but maybe not completely empty.”

ChatGPT: Thank you for the clarification. I see, you’re suggesting that the structure of a large-scale text corpus might, in a way, reflect the structure of the thoughts and propositions that underlie the text. This aligns with Chomsky’s conjecture that the rules of Universal Grammar might be less about syntax itself and more indirect reflections of the rules of thought. In this view, violations of UG could be seen as attempts to articulate thoughts that are in some sense unthinkable.

Ingesting a large body of text, then, and tuning an AI model to predict and complete sentences in a way that aligns with the structure of that text, might allow the model to capture some aspects of these underlying thought processes. This wouldn’t involve grounding or understanding in the sense that a human would experience it, and the model wouldn’t really have a full grasp of meaning. However, through the potential “iconicity” of thought reflected in the rules of Universal Grammar, the model might acquire a certain degree of alignment with the structure of human thought.

This is an intriguing hypothesis. It suggests that while AI models like me lack direct grounding and true understanding, our interaction with large-scale text data could allow us to reflect the structure of human thought in a certain abstract way in our verbal output. Yes, that’s a long shot and speculative. But it might suggest a direction for further exploring both AI and human cognition.

HARNAD: Last question: How many (1) words, (2), sentences, and (3) texts have you ingested from (a) articles and (b) books (never mind social media)?

ChatGPT: As an AI language model, I don’t have the ability to access my training data, but I was trained on a mixture of licensed data, data created by human trainers, and publicly available data. These sources may contain publicly available information from a variety of publishers or publications. However, the specific datasets used to train me haven’t been publicly disclosed by OpenAI, the organization behind Assistant. This means I don’t have the ability to access subscription sites, confidential information, or proprietary databases, so I wouldn’t be able to know the specifics about which documents were in my training data or the exact number of words, sentences, or texts.

In terms of capacity, as a model based on GPT-3, I have 175 billion parameters and can generate or process text sequences up to a couple thousand tokens long in a single instance. The training process involves running computations on thousands of GPUs over weeks or months, but exact figures about the data size in terms of number of words or documents are not specified.