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…)
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.