Language Evolution and Direct vs Indirect Symbol Grounding

HARNAD: What is the relationship between the symbol grounding problem and  the nature and evolution of natural language?

ChatGPT: The Symbol Grounding Problem (SGP) and the nature and evolution of natural language are intimately linked.

Symbol Grounding Problem (SGP): The SGP is a concept in cognitive science that concerns how symbols (or words) get their meanings. In essence, it’s about how words become more than just arbitrary labels and come to actually “mean” something. In other words, how do symbols or words become grounded in perceptual and actionable experience? For example, when we see the word “apple,” we don’t just recognize the letters and the sound. We also have a mental image of an apple, understand its properties, and know what actions can be performed with it. In the context of AI, the SGP becomes a challenge because AI often deals with symbols in a way that is not grounded – i.e., the symbols don’t have any inherent meaning to the AI beyond their programmed associations.

Nature and Evolution of Natural Language: Natural language has evolved in humans as a means of communication and thought. It’s believed to be grounded in our sensory and motor experiences. In other words, we learn the meanings of words and language through our interactions with the world, and this grounding in the world allows us to use language to express abstract thoughts, ask questions, give commands, and more.

In terms of their relationship, the evolution of natural language can be viewed as a solution to the SGP. As language evolved in humans, it became a way for us to ground symbols in our experiences and to communicate these grounded symbols to others. This grounding is not just a feature of individual words, but of the syntactic structures that allow us to combine words to express more complex meanings.

When it comes to artificial intelligence or cognitive science, understanding how language evolved to solve the SGP in humans can provide insights into how to create more sophisticated, understanding AI systems. If we can find a way to ground symbols in the experience of an AI—such as through interaction with the environment or sensory input—then we might make a significant stride towards AI that can truly understand and generate natural language in a human-like way.

However, as of my knowledge cutoff in September 2021, the full solution to the Symbol Grounding Problem in AI remains an open question and a topic of active research.

HARNAD: Do you remember our discussion of T3?

ChatGPT: Yes, our earlier discussion referenced T3 in the context of the Turing Test and the Symbol Grounding Problem.

T3, as described, involves not only linguistic capabilities but also sensorimotor capabilities—essentially, the ability of an entity to interact physically with the world. This could include seeing, touching, manipulating objects, navigating, and more. The idea is that an AI or robot passing the T3 test would demonstrate behavior indistinguishable from a human not only in verbal communication (T2) but also in embodied, physical interactions with the world.

In the context of the Symbol Grounding Problem, T3 might be seen as an approach to grounding symbols in an AI’s experiences. By interacting physically with the world, an AI might be able to build a kind of understanding or “grounding” for the symbols it uses. However, as of my knowledge cutoff in September 2021, developing an AI or robot capable of passing the T3 test remains an active area of research.

HARNAD: What is indirect grounding and how is it related to direct grounding?

ChatGPT: Direct grounding refers to the process by which a symbol or word gains meaning through its direct association with sensory or motor experiences. For example, the concept of an apple might be directly grounded in an entity’s sensorimotor experiences with apples, such as seeing them, touching them, tasting them, etc.

Indirect grounding, on the other hand, refers to the process by which a symbol or word gains meaning not through direct sensory or motor experiences, but through its association with other symbols or words that are themselves directly grounded. For example, the concept of a unicorn might be indirectly grounded in an entity’s experiences with the concepts of a horse and a horn, even if the entity has never directly experienced a unicorn.

In the context of artificial intelligence, direct grounding could involve training an AI on a dataset that includes both language data and corresponding sensory or motor data, allowing the AI to directly associate words with experiences. Indirect grounding, on the other hand, might involve training an AI solely on language data, allowing it to learn the meanings of words through their relationships with other words, without requiring direct sensory or motor experiences.

Both direct and indirect grounding approaches seek to address the symbol grounding problem, which is the question of how symbols (or words) get their meanings. A fully grounded AI system would presumably be capable of both direct and indirect grounding. However, as of my knowledge cutoff in September 2021, creating such a system remains an open challenge.

HARNAD: How is direct grounding related to sensorimotor category learning. It is not an “association” between words and “experiences.” It is an agent’s capacity to learn to do something: What?

ChatGPT: Direct grounding is closely related to sensorimotor category learning. It involves the agent’s ability to interact with its environment, process the sensory information it receives, and develop its own internal representations of the categories of objects and events it encounters.

In other words, direct grounding is about an agent learning to categorize its sensory input (such as visual, auditory, tactile information) into meaningful categories based on its own interactions with the environment. For instance, a child learns what an “apple” is not just by being told the word “apple”, but by interacting with actual apples – seeing them, touching them, tasting them. The word “apple” then becomes directly grounded in the child’s sensorimotor experience with apples.

In the case of an AI, it could learn a sensorimotor category by interacting with a simulated or physical environment. For example, it could learn the category of “circle” by interacting with various objects and identifying the common feature of “roundness”. This sensorimotor category can then be directly grounded by associating it with the corresponding symbol or word in its programming or training data.

So, to sum up, direct grounding in the context of sensorimotor category learning is about an agent’s capacity to learn to recognize and categorize its sensory inputs based on its own motor interactions with the environment. These categories can then be associated with corresponding symbols or words, enabling the agent to understand and use those symbols in a meaningful way.

HARNAD: How does indirect grounding depend on prior direct grounding?

ChatGPT: Indirect grounding, also referred to as symbolic grounding, refers to the ability to understand new concepts or categories by associating them with already established and directly grounded concepts. In other words, it involves defining new symbols (categories) in terms of previously grounded symbols.

Consider the scenario of a child learning language. Initially, the child learns to associate basic words with their real-world referents through direct sensorimotor experience – this is direct grounding. For instance, the child learns the word “apple” by associating it with physical apples they have seen, touched, and tasted.

Once the child has a foundation of directly grounded words, they can start to learn new words and concepts indirectly. They can understand the word “fruit” as a category that includes “apples” and other directly grounded words like “banana” and “grape”. This new category of “fruit” is indirectly grounded through its associations with the directly grounded categories.

Similarly, in AI systems, once a set of basic sensorimotor categories is directly grounded, new categories can be learned by associating them with the already grounded categories. For instance, an AI might learn the concept of a “vehicle” by understanding it as a category that includes directly grounded categories like “car”, “bus”, “bike”, etc.

In this way, indirect grounding leverages prior direct grounding as the basis for learning and understanding new categories. The ability to learn indirectly significantly expands an agent’s capacity to learn new concepts and categories beyond those it has directly experienced.

HARNAD: There are organisms (“agents”) on earth, and many are able to learn to recognize things in the world (e.g., apples) and they can also learn what to do with them (e.g., eat apples). To do this agents have to be able to learn to detect the features of apples that distinguish them from baseballs, which cannot be eaten. The learning produces a feature-detector, and this is what grounds the word in the capacity to recognize and manipulate its referent (e.g., apple).

Although it is true that in organisms it feels like something to be able to do this. So in that sense “experience” is involved. But since no one yet knows  the causal role of feeling in category learning and symbol grounding — this is called the “hard problem” of cognitive science — there is no point talking about the role of felt experience in symbol grounding. So now can you explain symbol grounding to me without any mention of “association” or “experience, but just  in terms of category-learning and feature detection?

ChatGPT: Sure, let’s approach the symbol grounding problem purely from a learning and cognitive perspective, focusing on categories and feature detection.

Grounding symbols (such as words) involves connecting them to real-world entities or concepts that they represent. This connection is created through a process of learning and recognition. This learning process is driven by the agent’s ability to distinguish between different categories based on the features of the entities belonging to these categories.

Direct grounding, as it pertains to category learning and feature detection, involves creating a link between a symbol and its referent, where the referent is something, the agent can interact with in the real world. For instance, an agent, through its sensorimotor capabilities, can learn to recognize an apple by its features such as its round shape, red color, sweet smell, etc. Once this categorization is achieved, the agent can then associate the symbol (the word “apple”) with this specific category of objects. Here, the symbol “apple” is directly grounded in the agent’s sensorimotor experiences with real-world apples.

Subsequently, the agent can build upon this foundation of directly grounded symbols to create indirectly grounded symbols. These are symbols that are not linked to a specific sensorimotor experience, but rather to other symbols (or combinations of symbols) that have been directly grounded. For example, the symbol “fruit” can be indirectly grounded by linking it with directly grounded symbols like “apple”, “banana”, etc.

Thus, in this context, symbol grounding is not about vague “associations” or subjective “experiences”, but about a concrete process of learning to recognize and categorize entities based on their observable features, and linking symbols to these categories. The learning and grounding processes are facilitated by the agent’s sensorimotor capabilities, allowing it to interact with and distinguish between different entities in the world.

HARNAD: Grounding words is not just learning to recognize and distinguish and name (kinds or categories of) entities (the referents of the words). I’s based on learning to detect and distinguish the features of the members of the referent category from the features of the nonmembers. It’s also based on learning what to DO or NOT-DO with the members and nonmembers (e.g., eat or don’t eat them). “Represent” is a vague weasel-word. What has to be in the head of an agent that has learned a new word’s referent in view of what I’ve just said?

ChatGPT: In the agent’s “head,” or more concretely in its cognitive and neural processing system, learning a new word’s referent would involve establishing a mapping between the sensory and motor features of the referent and the verbal or symbolic representation of the word. This mapping is the grounding of the word.

Detection of Sensory Features: The agent, through its sensorimotor interactions with the world, learns to recognize and discriminate the relevant sensory features of entities, such as their shape, color, smell, texture, etc.

Categorization: These sensory features are used to categorize entities into classes or kinds. For instance, entities with a certain combination of features (round, red, sweet smell) might be categorized as ‘apples.’

Action Responses: Alongside recognizing sensory features and categorization, the agent learns appropriate responses or actions associated with the entities. For instance, apples can be eaten, while baseballs cannot. These action responses are part of the agent’s understanding of the entity.

Symbol Mapping: Once the agent can detect the features, categorize entities, and knows the associated action responses, it can link or map the word (symbol) “apple” to this package of sensory and motor knowledge.

This grounding is not merely an “association” but a complex mapping process that links words with specific patterns of sensory inputs and motor responses. When the word is encountered again, it activates this package of sensory, categorical, and motor knowledge, guiding the agent’s recognition, understanding, and interaction with the referent of the word.

This is how the agent comes to “know” or “understand” the referent of the word. It’s not just about recognizing and naming entities, but about learning to detect and categorize entities based on their sensory features, and determining appropriate responses or actions in relation to these entities. This entire process is facilitated by the agent’s sensorimotor capabilities, allowing it to interact with and distinguish between different entities in the world.

HARNAD: That was a much better summary of what is going on in the head of the human or the T3 that grounds the words it speaks, hears or thinks. But I don’t understand “mapping.”

Suppose the only distinguishing features of apples and oranges were that they are round and that apples are red but oranges are orange, and you eat apples by biting them whereas you eat oranges by peeling them and then biting them, And supposing that’s the only thing the agent does in life: to recognize, name and eat oranges and apples. What does calling any of this “mapping” add to this story — either in the toy world of just apples and oranges, or in the real world, with a T3 that can recognize, name and do the right thing with the referent of every (content word) it knows?

(By the way, what is the difference between content or “open class” words and function or “closed class” words? Only content words have referents. What percentage of the words in a language is content words and function words.)

ChatGPT: “Mapping” in this context refers to the process by which the agent creates and uses an internal representation or model of the relationship between certain sensory and motor patterns and the corresponding symbolic representations (words). In the case of the apple and orange example, the “mapping” would be the internal mechanism by which the agent understands that when it perceives a round and red object that can be bitten directly, it’s dealing with an “apple,” and when it perceives a round and orange object that needs to be peeled before biting, it’s dealing with an “orange.” This mapping allows the agent to navigate its environment and correctly interact with different entities, recognizing them and predicting the appropriate actions to take.

Regarding content words and function words, these are categories used in linguistics to distinguish between types of words based on their purpose in language.

Content words (open class words) are words that have a semantic content and can be categorized as nouns, most verbs, adjectives, and adverbs. They are referred to as an “open class” because new words can be added to these categories as language evolves. They’re called “content” words because they contribute the main content or meaning to a sentence – they refer to things, actions, qualities, etc.

Function words (closed class words) are words that primarily have grammatical functions, such as conjunctions, prepositions, articles, pronouns, auxiliary verbs, etc. They are referred to as a “closed class” because new words are seldom added to these categories. Function words provide the grammatical structure to a sentence, linking content words and helping to express relationships between them.

The exact ratio of content words to function words can vary between languages and types of text, but in English, function words are more frequent in running text. However, in terms of unique words (vocabulary), content words greatly outnumber function words, as the latter are a limited set. Estimates vary, but some studies suggest function words can make up around 50-60% of total words in running text in English, but only a few hundred unique function words exist compared to tens of thousands of content words.

HARNAD: I still don’t understand what “mapping” actually means here. It sounds like in the toy world the agent just needs to learn some features and actions, kind of like a selective filter, that learns to detect the feature red or green, and if something is red, eat it, and if it’s orange, peel and eat it. In addition to the feature-detectors and the action-generators there could be a logical circuit: “If R then E, if O then P and E.” Or the input/output pattern could be hard-wired. And much the same would be true if it were all scaled up to T3 (do youremember that?). So the “mapping ” is as irrelevant as the “association” and the “experience”.

ChatGPT: You’re right that the process can be described in terms of features, actions, and if-then logical connections or “rules.” The term “mapping” is often used more generally in cognitive science and artificial intelligence to describe the relationship between two sets of things – in this case, sensory-motor patterns and symbolic representations. But if it is causing confusion, it’s certainly possible to describe the process without using that term.

To simplify, in the context of symbol grounding, the agent learns to detect the distinguishing features of different categories of things in the world, such as apples or oranges. It then learns the appropriate actions to perform with members of each category. This learning process might be characterized by a series of if-then rules like the ones you suggested. The word for each category, like “apple” or “orange,” is grounded in the agent’s capacity to recognize members of the category based on their features and to perform the correct actions with them.

The word itself could be thought of as a label for a set of related sensory-motor patterns and the corresponding rules for action. So, in a sense, the word gets its meaning from the agent’s interactions with the world, its ability to recognize and act appropriately with different categories of things.

In this sense, grounding is more than just associating a word with an experience or mapping it onto a sensory pattern. It’s about the agent’s learned capacity to interact with the world in a meaningful way based on its recognition of different categories of things and its knowledge of what to do with them. That’s what gives the words their meaning.

And yes, the same logic extends to T3, a robotic system that’s capable of both linguistic and sensorimotor interaction. It’s about more than just detecting and responding to sensory patterns; it’s about meaningful interaction with the world, which involves recognizing, categorizing, and acting appropriately.

HARNAD: That sounds much better, because simpler, removing the superfluous or empty parts. Now can we get back to how indirect grounding works (again with no superfluous words)?

Indirect grounding is verbal grounding. But all the (content) words in the verbal definition of the new indirectly grounded category (like “zebra”) have to already be grounded, both for the SPEAKER and the HEARER/LEARNER. How does this work?

ChatGPT: Certainly, let’s try to simplify indirect grounding:

Direct grounding, as we’ve established, involves an agent learning to recognize and interact appropriately with the things in the world. This gives meaning to the words that label these categories.

Indirect grounding, on the other hand, is a process that allows an agent to learn the meaning of new words based on their relationships to words that have already been directly grounded. In essence, it is learning by description or explanation, using language itself.

Here’s a simplified version of how it might work:

The agent already has a set of directly grounded words. These words are grounded in the agent’s capacity to interact with the things they refer to. Let’s say these words include “animal,” “stripes,” “black,” and “white.”

Someone tells the agent, “A zebra is an animal with black and white stripes.”

The agent, having directly grounded the words “animal,” “stripes,” “black,” and “white,” can combine this knowledge to form a new category, “zebra,” even if the agent has never encountered a zebra before.

This new word, “zebra,” is indirectly grounded. It is grounded in the agent’s knowledge of the other directly grounded words and the relationships between them, as explained in the definition.

This process relies on the shared understanding between the speaker and the hearer. The speaker, who knows what a “zebra” is, uses words that the hearer already knows (“animal,” “stripes,” “black,” and “white”) to explain this new concept. This shared language and the ability to explain new concepts using known words is a powerful tool for indirect grounding.

HARNAD: Now how is direct and indirect grounding related to what you, ChatGPT, can and cannot do?

ChatGPT: As a model developed by OpenAI, I, ChatGPT, have no capability for direct grounding. I do not have a body, sensory organs, or the ability to interact with the physical world. Therefore, I cannot learn the meaning of words through interaction with or perception of the physical world.

However, I do have a kind of indirect grounding. I have been trained on a large dataset of text from the internet, which includes many different contexts and uses for words. This training has enabled me to learn to predict what word or phrase is likely to come next in a piece of text, based on the words that have come before it.

This prediction capability allows me to generate responses to user prompts that often make sense and seem to reflect an understanding of the words used. However, this is not the same as true understanding or grounding. Rather, it’s a kind of statistical pattern-matching based on the data I was trained on.

For example, if you ask me about zebras, I can generate a response that includes information about zebras, because that information was present in the data I was trained on. I can “tell” you that a zebra is a kind of animal with black and white stripes, even though I have never seen a zebra or a stripe, because I’ve seen the words “zebra,” “animal,” “black,” and “white” used together in certain ways in the data I was trained on.

In summary, while I can generate responses that often make sense and seem appropriate in context, I don’t truly understand the words I’m using in the way that a human, or a hypothetical AI with direct grounding, would.

HARNAD: That was a good synthesis, but I think there is one very important error in it. You said:

“I, ChatGPT, have no capability for direct grounding. I do not have a body, sensory organs, or the ability to interact with the physical world. Therefore, I cannot learn the meaning of words through interaction with or perception of the physical world. However, I do have a kind of indirect grounding…”

But you don’t have indirect grounding, because, as you noted, indirect grounding depends on verbal definitions or descriptions in which all the (content) words used are already grounded, either directly or indirectly. The symbol grounding problem is based on the fact that this process cannot be “indirect” all the way down, otherwise you are back in the word-word circle that gave rise to the symbol grounding problem in the first place. So your words are not indirectly grounded, because none of them are directly grounded, so that they can indirectly ground all the rest through indirect grounding.

(You have no “minimal grounding set” that was grounded directly.) Yet your verbal syntheses are meaningful to human hearers who do have directly grounded words. You said that the reason this is possible is because of the patterns of words in your huge database. I agree. But I may not agree on what the patterns are and how they work: Can you explain them to me? 

ChatGPT: I apologize for any confusion, and thank you for the clarification on the concept of indirect grounding. As a language model, I do not have any grounded words, either directly or indirectly grounded, because I don’t have sensory or motor experiences.

The patterns in my large dataset that enable me to generate responses to user prompts are statistical in nature. I’ve been trained to predict the next word in a sentence given all the previous words, based on patterns seen in the training data. This method, called transformer architecture, has been used to train me to generate human-like text.

For example, if in the training data the word ‘apple’ frequently follows the words ‘red’, ‘fruit’, ‘orchard’, I’ve learned to predict that ‘apple’ is a likely next word after these. I don’t “understand” these words or their connections in the way a human does, which is through direct or indirect grounding in sensory and motor experiences. Rather, I generate text based on the patterns of word usage in the data I was trained on.

To elaborate, during training, the model is exposed to pairs of sentences and learns to predict whether one sentence follows another in its training data. Through this, the model learns associations between words and context, enabling it to generate coherent and contextually appropriate responses. However, this process is entirely based on recognizing statistical patterns in data and does not involve any genuine understanding or grounded meaning.

So, when you interact with me, I generate responses based on predicting what a human would likely say next in a similar context, based on the patterns I’ve seen in the data. But this doesn’t mean that I truly understand the meanings of the words I’m using. I hope this clarifies things a bit more.

HARNAD: Yes, and of course you are right about how this works, based on statistical analysis of your huge database. But I have a hunch that there is more to it than that, and it has to do with the difference between a word and a sentence (which is also the difference between a referent category name and a PROPOSITION, which is a subject/predicate series of category names in the form of an assertion about what is the case; an assertion which may be TRUE or FALSE).

Single words do not have truth values. “Apple” is neither true nor false. It is simply an arbitrary symbol that speakers have agreed to use to refer to apples. (Only the deictic proposition “THIS is an apple” can be true or false.) The “shape” of “apple” is arbitrary in the sense that it does not resemble apples in any way. So it gives no clue to what its referent is “shaped” like. Nor is it causally connected with apples in any way (except in the head of a speaker or hearer that has grounded the word by learning to recognize and interact with its referent, using detectors of the “shapes” of the sensorimotor features of apples, as we’ve discussed).

Now the question to ask yourself is: Is the arbitrariness of the shape of “apple” in relation to the shape of apples also true of PROPOSITIONS — which are composed of subject/predicate definitions or descriptions of things — and their relation to the “shape” of the states of affairs they assert to be true? 

ChatGPT: The arbitrariness of the word “apple” in relation to the physical object it represents is a fundamental aspect of symbolic language. The word “apple” doesn’t physically resemble an apple in any way, as you’ve pointed out. This is true for all individual words (or symbols) in a language, which is known as the arbitrariness of the sign.

However, when we combine words into sentences or propositions, things become a little more nuanced. The structure and syntax of a sentence isn’t entirely arbitrary because it reflects the logical and grammatical relationships between the entities it represents. In English, for example, a simple sentence generally follows the subject-verb-object structure. This structure is not randomly chosen; it reflects a logical progression of ideas and helps to convey meaning clearly.

Still, it’s important to recognize that while the structure of a sentence can hint at the relationships between the things it represents, it still doesn’t inherently resemble those things or their relationships in the physical world. This is known as the “symbol grounding problem.” We humans “solve” this problem by learning to associate words and sentences with our experiences in the world, but as an AI, I can’t do this.

The words and sentences I generate don’t reflect a grounded understanding of the world. Instead, they are based on statistical patterns in the text data I was trained on. When I generate a sentence, I’m not generating a representation of the world as I understand it (because I don’t have a grounded understanding of the world). Instead, I’m predicting what words and structures are statistically likely to come next in a given context, based on the patterns I’ve learned from my training data.

So in summary, while the structure of a sentence or proposition isn’t as arbitrary as an individual word because it reflects logical and grammatical relationships, it is still ultimately disconnected from the physical world it describes, at least in the context of an AI language model like me.

HARNAD: Yes, I agree that part of the coherence, comprehensibility and informativeness of the summaries and interactions with ChatGPT (henceforth “GBT”) for users is because of the statistical patterns in spoken and written strings of words and the algorithms that GBT applies to them. But I think there may be something more to it. Consider that if the word “apple” were really iconic, i.e., if it really resembled an apple, then non-speakers of English would still be able to learn more out of an iconic English dictionary than they can learn from a normal dictionary of the arbitrary words of English. (But this would only help for a relatively small number of visually recognizable objects and features.)

There are good reasons why words are not iconic, like hieroglyphics, and why iconicity would be a handicap: For one thing, language was spoken before it was written and it would be hopeless to try to produce an acoustic icon of the referent of every possible word. (It’s already nearly as impossible with visual or gestural icons). But there are languages (e.g., Chinese) in which the “iconicity” is of a higher order, in the basic characters (originally iconic) out of which all words are composed. I wonder whether GBT is even more effective in languages with that extra layer of correlation? I understand that results with coupling GPT with labelled image databases have been mixed.

But what I want to add is that at the level of the formal structure of definitions and descriptions there may be a form of iconicity of form which is like the Platonic shadows of the meanings of propositions – faint, but present, and not just “statistical” but structural in some way.

ChatGPT: You bring up a number of interesting points. Let’s unpack them one by one.

Iconicity in Language: Yes, the majority of words in spoken languages do not physically resemble what they represent. This is the “arbitrary nature” of the linguistic sign as postulated by Ferdinand de Saussure, a linguist who laid the foundation for many of the assumptions of modern linguistics. While iconicity does exist in some forms of language, such as onomatopoeic words (like “buzz” or “bang”) or ideophones, it is not the norm. As for Chinese characters, they originally had a more pictographic nature, but have since evolved into more abstract symbols, with some retaining a semblance of their original iconic form.

Language and AI: When you mention the effectiveness of AI language models in languages with an extra layer of correlation, are you suggesting that these models might perform better in languages where there’s some level of iconicity? It’s an intriguing idea, although it would depend on how much that iconicity is preserved in modern usage. More research would be needed to see if this is the case.

Iconicity in Propositions: Here you’re suggesting that the structure of definitions and descriptions could have some form of iconicity, or resemble the concepts they describe. This is a fascinating concept. A sentence or proposition in language does have a structure that reflects some form of the logical or temporal order of the concepts it describes. In that sense, one could argue there’s a certain degree of “iconicity” in the formal structure of language. However, this is very different from the kind of iconicity where the sign physically resembles its referent. The kind of iconicity you’re suggesting at the level of sentences or propositions seems to be more abstract and related to the logical or conceptual relationships between the ideas being expressed.

As for how this applies to AI like me, I am designed to recognize and generate language patterns, which includes the logical and temporal relationships between words and phrases. This allows me to generate text that makes sense in the context of the conversation or topic at hand. However, I don’t “understand” these relationships in the same way humans do because my “understanding” is not based on any grounded experience or perception of the world.

HARNAD: I‘m pretty sure that there is formal/logical iconicity to be gleaned from large bodies of text and discourse out of the function words, which do not have referents, only syntactic rules. But I have a hunch that there might be even more (of this “iconicity” or “latent straucture”) with content words, preserving a shadow of the shape or structure of states of affairs (expressible as propositions). This would not “resemble” the shape of a referent category the way the feature-detectors in direct sensorimotor grounding do, but it might “resemble” the shape of verbal definitions and descriptions in indirect grounding. It would itself be ungrounded, lacking the direct grounding completely. But ungrounded descriptions may still retain SOME of the formal “shadows” of meaning. This is still too vague, however, and needs more thought and analysis.

ChatGPT: The idea of formal/logical iconicity is interesting. If I understand correctly, you’re suggesting that the structure of language, the way sentences are constructed and words are arranged, might inherently carry some degree of “meaning” – or at least, an echo or shadow of the meaning that they convey when grounded by a human mind.

This could be a potential direction for further research. It’s true that the structure and rules of language play a significant role in our understanding and interpretation of sentences. And perhaps it’s possible that AI, even without direct or indirect grounding, might be able to discern and leverage these structures in some way that goes beyond simple statistical patterns.

If this hypothesis were correct, it could have implications for the development of AI and natural language processing. It would suggest that there is a level of ‘understanding’ that could be achieved even without direct grounding, albeit a limited one.

It’s also worth noting, however, that this would still be a form of ‘understanding’ that’s quite different from human understanding, since it would lack the personal, subjective experience that we associate with our own understanding of the world.

HARNAD: On the subject of the platonic shadows of “meaning” that might be derivable from large bodies of continuous text:

Are you familiar with Noam Chomsky’s suggestion that the constraints of Universal Grammar (UG) may not be grammatical constraints at all, but constraints on (verbal) thinking itself: that the syntactic structures that violate UG may sound wrong to us not because they are ungrammatical but because they are unthinkable? that a UG violation such as “John is easy to please Mary” or “Who did he think that went out?” might correspond to expressing “nonthinkable thoughts”? so that they in fact express no thought at all — though they may be close to thinkable thoughts (“It is easy for John to please Mary” or “Who did he think it was that went out?”)

Could it be because sentences can only express thinkable thoughts that there is some (perhaps small) degree of meaning in strings of ungrounded words spoken by grounded thinkers?

Chomsky has explicitly stated that UG violations are not violations of logic, or logical form. His famous example, meant to show the autonomy of syntax from semantics (i.e., independence of form from meaning) was somehow meant to illustrate this — “Colorless green ideas sleep furiously” – because it is grammatically correct but makes no sense.

But of course it does make sense, GPT, doesn’t it? Unlike “John is easy to please Mary,” which doesn’t make sense unless it is tweaked.

ChatGPT: These points on Noam Chomsky’s theory of Universal Grammar (UG) and the idea of “unthinkable thoughts” are interesting.

You’re right that Chomsky proposed that UG reflects constraints on possible human thought. In his view, UG is inherent in all human brains and it governs the structure of language, therefore determining what kinds of sentences are possible or “thinkable”.

This perspective raises suggest possible ways to understand how meaning might emerge from ungrounded text. Perhaps, as you suggested, there is some inherent “sense” or structure to sentences that obey UG, even if the sentences aren’t grounded in the way that human language is. After all, these sentences reflect possible structures of thought in the human mind.

As for Chomsky’s famous example of “Colorless green ideas sleep furiously”, I, as an AI, can analyze the sentence and tell you that it is grammatically correct. However, from a semantic perspective, this sentence doesn’t make conventional sense because it combines words in ways that violate our real-world understanding. That is, in the world as we know it, ideas can’t be colorless or green, nor can they sleep, and certainly not furiously. So while the sentence is structurally sound, it defies our understanding of how the world works. Yet, you’re correct that it still holds a certain “sense” or structure that is absent in sentences that violate UG.

The possibility that language may somehow carry a “shadow” of meaning even in the absence of grounding is worth exploring further.

Tutoring ChatGPT (on symbol grounding and turing testing)

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

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


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

ChatGPT:

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

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

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

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

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

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

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

ChatGPT:

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

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

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

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

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

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

ChatGPT:

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

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

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

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

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

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

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

ChatGPT:

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

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

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

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

ChatGPT:

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

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

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

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

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

ChatGPT:

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

SH: Nope, that’s still just T3. 

ChatGPT:

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

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

ChatGPT:

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

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

ChatGPT:

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

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

ChatGPT:

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

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

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

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

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

ChatGPT:

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

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

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

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

ChatGPT

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

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

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

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

ChatGPT:

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

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

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

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

ChatGPT:

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

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

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


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

A Socratic Session With ChatGPT4

HARNAD:  What is the symbol grounding problem?

ChatGPT4:

The symbol grounding problem is a problem in philosophy of mind and cognitive science that relates to how words (or “symbols”) get their meanings.

The term was coined by cognitive scientist Stevan Harnad in 1990. The problem involves the question of how symbols (or words) used in a system (like a computer or a mind) get their meaning, or “grounding”. That is, how do these symbols relate to the real-world objects, concepts, or experiences they’re supposed to represent? How does a word become more than just a “meaningless” form, but something that actually refers to something in the world?

In the context of Artificial Intelligence (AI), this problem illustrates the difficulty of teaching a machine to understand the real-world semantics of symbols. For instance, even if a computer can use the word “apple” correctly in a sentence according to syntactical rules (grammar), how can we make the computer truly understand what an apple is – its color, shape, taste, the fact that it grows on trees, etc. – as humans do?

Symbol grounding problem is a fundamental challenge in achieving true semantic understanding in AI systems, and it’s related to other complex problems like the frame problem and the Chinese room argument.

HARNAD: What are T2, T3, and T4 in the Turing Test?

ChatGPT4:

As of my knowledge cutoff in September 2021, the Turing Test, originally proposed by Alan Turing in 1950, was primarily understood in a singular form rather than being divided into T2, T3, or T4 categories. Turing’s original idea, also known as the Imitation Game, involves a human evaluator who interacts with an AI system and another human via a text interface. If the evaluator cannot reliably distinguish the AI from the human, the AI is considered to have passed the Turing Test.

However, the field of AI has seen many modifications and variations of the Turing Test over time. These can involve varying degrees of complexity and different types of challenges, aiming to test more than just the AI’s ability to imitate human conversation. Unfortunately, without additional context, it’s hard to provide a specific interpretation of what “T2,” “T3,” and “T4” might represent in a modified version of the Turing Test.

I would advise checking the most current and specific source for these terms to get the most accurate understanding, as they might represent certain evolutions or nuances in Turing Test methodologies that have developed after my last training data in September 2021.

HARNAD: Let me update you. T2 is the original verbal-only version of the Turing Test (TT): verbal input/output capacity indistinguishable FROM that of real humans TO real humans. T3 is the verbal + robotic form of the TT: indistinguishable not only in verbal input/output (I/O capacity), but also in sensorimotor (i.e. robotic) capacity in interacting with the objects, events, features, actions and states in the world that the T2 words refer to. T3 includes T4 and it is grounded (as in the “symbol grounding problem”). T4 is T2 + T3 capacity + indistinguishability in the internal neural (or synthetic) function occurring inside the robot from that occurring inside a real human brain.

ChatGPT4:

Thank you for the updated information. It’s always beneficial to learn about recent developments in the field. So, according to your description:

T2 (Turing Test Level 2): This is the original version of the Turing Test, focusing on the system’s ability to produce responses to verbal inputs that are indistinguishable from those a human would produce. The key aspect here is the ability to emulate human-like conversation convincingly.

T3 (Turing Test Level 3): This level of the test adds a sensorimotor, or robotic, component. It tests not just the system’s ability to converse like a human but also to interact with the physical world in a way that’s indistinguishable from human interaction. The system is required to exhibit understanding and interaction capabilities with objects, events, features, actions, and states in the real world, thus grounding its symbolic representations.

T4 (Turing Test Level 4): This is an advanced level that adds a requirement for the system’s internal processing (whether it is neural or a synthetic equivalent) to be indistinguishable from that of a human brain. This goes beyond the outward manifestation of intelligence and human-like behaviour and extends to the system’s internal workings.

Each level seems to add a new layer of complexity and a deeper level of imitation of human capabilities, moving from conversation, to physical interaction, and then to internal cognitive processing. It’s an interesting framework for thinking about the evolving challenges in creating truly human-like artificial intelligence.

HARNAD: Can you relate it now to (1) the symbol grounding problem and (2) to what Harnad has written about the Turing Test?

ChatGPT4:

Certainly! Now that you’ve clarified the context, we can explore the relationship between the T2, T3, T4 Turing Test levels and the symbol grounding problem, as well as Stevan Harnad’s work.

Symbol Grounding Problem: As I mentioned before, the symbol grounding problem is about how symbols or words get their meaning. In the context of AI, this problem relates to the difficulty of making a machine understand real-world semantics, rather than just processing symbols in a syntactic manner. Harnad, who coined the term, has argued that symbolic representations must be grounded in sensorimotor activity to acquire meaning.

In the T2 level of the Turing Test, an AI might appear to understand symbols because it processes and responds to them in a way that’s indistinguishable from a human. But according to the symbol grounding problem, it doesn’t truly understand the symbols because it can’t connect them with real-world objects or experiences.

This is where T3 comes in, adding a requirement for sensorimotor interaction with the world. The AI needs to be capable of physically interacting with objects, events, and states, thereby grounding the symbols it uses. Essentially, T3 introduces a solution to the symbol grounding problem: It requires an AI system to have real-world, sensorimotor experience to ground the symbols, ensuring they are not just empty or ungrounded tokens.

Stevan Harnad’s work: Harnad has written extensively on the Turing Test and its implications for understanding cognition and consciousness. He has defended the Turing Test as a meaningful standard for determining whether a machine can truly think or understand, arguing against critics who claim that passing the Turing Test simply involves trickery without real understanding.

Harnad’s concept of the T3 level of the Turing Test reflects his views on the symbol grounding problem, asserting that grounding symbols in sensorimotor activity is essential for a machine’s true understanding. Moreover, his T4 level introduces a higher bar, requiring that the internal cognitive processing of an AI be indistinguishable from that of humans, which relates to his broader work on cognition and consciousness.

Therefore, the T2, T3, and T4 levels of the Turing Test can be seen as a direct reflection of Harnad’s thoughts on the symbol grounding problem and the conditions for true machine understanding and cognition.

HARNAD: Good. Now can you relate all that to Harnad and co-workers’ work on category learning, unsupervised and supervised?

ChatGPT4:

Stevan Harnad has conducted extensive work on category learning, which is highly relevant to the discussion about symbol grounding and the Turing Test.

Category learning is the process of recognizing, understanding, and grouping similar things based on shared characteristics. It is fundamental to our cognitive processes and ability to understand and navigate the world. In the realm of AI, category learning involves the system’s ability to classify inputs (like images or words) into groups based on learned or preprogrammed criteria.

Harnad differentiates between two types of category learning:

Unsupervised Category Learning: This involves learning without a teacher or guide. The system must determine the categories by itself based on the characteristics of the inputs. This process is complex and often less accurate than supervised learning, as there is no feedback or correction mechanism. It’s analogous to the system trying to solve the symbol grounding problem on its own, i.e., trying to figure out the connection between symbols and their referents without any external guidance.

Supervised Category Learning: Here, a teacher or guide provides the correct category for each input, and the system learns to associate inputs with the correct categories based on this feedback. The system can then generalize from these learned associations to categorize new inputs. In terms of symbol grounding, supervised learning can be thought of as a way of providing external grounding for symbols, where the ‘teacher’ provides the connections between symbols and their referents.

Harnad’s T3 level in the Turing Test, with its emphasis on sensorimotor grounding of symbols, could be seen as a form of supervised learning. The real-world experiences and interactions provide a form of ‘guidance’ that helps the AI system learn the correct associations between symbols and their referents.

Meanwhile, the T4 level of the Turing Test might involve elements of both unsupervised and supervised learning. The internal cognitive processes that are required at this level might involve the system learning to form categories and make associations on its own (unsupervised learning), while still being shaped and guided by its interactions with the external world (supervised learning).

In summary, Harnad’s work on category learning provides a deeper context for understanding his views on symbol grounding and the requirements for AI systems to pass different levels of the Turing Test. By learning to form categories, either on their own or with external guidance, AI systems can ground symbols in a way that’s more akin to how humans understand and use language.

HARNAD: Good. Now can you relate this to Harnad and coworkers’ work on “categorical perception” (CP), but expecially to LEARNED CP (i.e., CP as a result of learning)? And (as a harder problem), relate it to feature-detection, feature-learning, and dimensional reduction?

ChatGPT4:

Absolutely, categorical perception (CP) and the concept of feature detection, feature learning, and dimensional reduction are essential components of Harnad’s framework on learning and cognition.

Categorical Perception (CP): Categorical perception is the phenomenon where the categories possessed by an observer influence the observer’s perception. In other words, we perceive and interpret the world around us according to the categories we’ve formed in our minds. This concept plays a crucial role in various aspects of human cognition, including language, where we learn to categorize sounds into meaningful phonemes, or color perception, where we categorize different wavelengths of light into distinct color groups.

When it comes to learned CP, it suggests that through learning and experience, we can develop new categories and therefore new ways of perceiving the world. In AI, a system with learned CP would be capable of modifying its perception and understanding of the world based on the categories it has learned. This concept ties closely to both unsupervised and supervised category learning, as explained in the previous response.

Feature Detection, Feature Learning, and Dimensional Reduction: These concepts are related to how an AI system processes and learns from its inputs.

Feature Detection: This is the process by which an AI system identifies important or distinctive elements in its inputs. In the context of the symbol grounding problem and the Turing Test, feature detection might involve recognizing the important characteristics of the objects, events, or states that a symbol refers to.

Feature Learning: Once distinctive features have been identified, the system must learn how these features relate to different categories or symbols. This might involve supervised learning (with external guidance) or unsupervised learning (where the system figures out the associations on its own).

Dimensional Reduction: This is a process that simplifies a high-dimensional dataset into a lower-dimensional space, preserving the most important structures or features. In terms of Harnad’s work, dimensional reduction could be a way for an AI system to simplify its understanding of the world, focusing on the most important features and associations and ignoring less relevant ones.

Relating these concepts to the T3 and T4 Turing Test levels, the AI system must be capable of feature detection and feature learning to interact with the world effectively and ground its symbols. In T3, the sensorimotor grounding of symbols could be seen as a form of feature learning, where the system learns to associate the features it detects in the world with the appropriate symbols.

In T4, the requirement for internal cognitive processes that are indistinguishable from humans could involve sophisticated feature detection, feature learning, and dimensional reduction. The system would need to be capable of detecting and learning important features autonomously and simplifying its understanding in the same way a human brain does.

In summary, these concepts provide a more detailed understanding of the learning processes that an AI system would need to undergo to pass different levels of the Turing Test and solve the symbol grounding problem. They provide a framework for how an AI system could learn to understand symbols in a human-like way, moving beyond mere syntactic processing to semantic understanding.

HARNAD: Good. Now another test, but with no hints from me. Based on everything said above (about symbols, grounding, words, robotic capacity, distinguishing features, learning, and CP): What is a “category” and what is “category learning”?

ChatGPT4:

In light of the discussions above, a “category” can be understood as a group of things that share certain common characteristics. These could be objects, events, states, or even abstract concepts. Categories allow us to organize our understanding of the world around us by grouping similar things together. They form the basis for our ability to make sense of new inputs based on our prior knowledge and experience.

A category could also be seen as the referent for a symbol or a word. In other words, a symbol (such as a word) gains its meaning by referring to a category of things in the world. For example, the word “apple” refers to the category of all objects that we recognize as apples.

“Category learning” refers to the process of learning to recognize, understand, and classify inputs based on these shared characteristics, thereby forming categories. It involves two main components: feature detection and feature learning.

Feature detection is about identifying the distinctive characteristics or features of different inputs. In the context of category learning, these features are what allow us to differentiate between different categories and identify which category a new input belongs to.

Feature learning, on the other hand, involves learning the relationships between these features and the categories they signify. It’s about learning to associate certain features with certain categories, so that when we encounter these features in new inputs, we can correctly categorize those inputs.

Category learning can be both unsupervised, where the AI system forms categories based on the patterns it identifies in the data without any external guidance, and supervised, where the system is guided by a ‘teacher’ who provides the correct categories for each input, allowing the system to learn the correct associations.

The ability to learn categories, whether through unsupervised or supervised learning, is essential for an AI system to ground symbols, interact with the world in a meaningful way, and potentially pass the different levels of the Turing Test. Moreover, learned categorical perception (CP) suggests that through category learning, we can modify our perception and interpretation of the world based on the categories we’ve formed in our minds. This represents an advanced level of understanding that goes beyond simply responding to inputs in a preprogrammed way.

HARNAD: Good synthesis so far. Now a few things you missed, but you’ll see it was there in your own words. What you haven’t quite noticed is that “features” are not just “associations.” With sensorimotor categories, they are what distinguishes members of a category from non-members (which may be members of other categories). That’s why they’re called “distinguishing” or “distinctive” features. But the crucial thing is that features are themselves (potentially) learnable, nameable categories too. And that means they can be used to define or describe further categories, with different combinations of distinctive features. This means that there is a THIRD way of learning new categories, besides directly, through unsupervised and supervised (reinforcement) learning, and that is: learning categories indirectly, through verbal instruction — FROM a speaker who knows the distinguishing featuresTO a hearer who does not. The only condition is that the hearer must already know the referents of the features in the verbal description of the new category. Can you first integrate that, and then I will ask you about how that is related to language itself — and especially the capacity to produce and understand subject/predicate propositions — as well as to Harnad and coworkers’ work on dictionaries. Good luck!

ChatGPT4:

Thank you for the additional information, it indeed helps in refining our understanding of categories, features, and learning methods.

As per your explanation, “features” serve as distinguishing elements that separate members of a category from non-members. This reinforces their importance in category learning – recognizing and understanding these features is key to correctly classifying inputs into the right categories.

The idea that features are themselves learnable and nameable categories brings another layer of complexity to this process. It suggests a hierarchical structure, where categories can be defined not just by simple characteristics, but also by more complex features that are themselves categories.

This leads us to the third method of category learning you’ve pointed out – learning categories by verbal instruction. In this scenario, a knowledgeable “speaker” instructs a “hearer” about a new category. The speaker does this by describing the distinctive features of the new category using names for them that the hearer already understands. This essentially amounts to defining new categories based on combinations of known categories (which serve as the distinguishing features).

It’s a more complex form of supervised learning, where the guidance comes in the form of verbal descriptions using already-grounded symbols. It presupposes a shared symbolic system and some common grounding between the speaker and the hearer.

Relating this to language learning and understanding, it suggests a crucial role for the ability to produce and understand propositions. In this context, a proposition could be a verbal description of a new category, outlining its distinctive features. Understanding the proposition requires grounding the symbols it uses, recognizing the categories they refer to, and then integrating this information to form a new category.

In relation to Harnad’s work on dictionaries, a dictionary can be seen as a collection of propositions that define categories (words) in terms of other categories. The definitions provided by a dictionary help ground symbols by describing their referents in terms of known categories (i.e., words the user already understands). Thus, dictionaries support the process of category learning through verbal instruction.

In summary, the process of category learning in AI and human cognition can be even more intricate and nuanced than initially described. It can involve a hierarchy of categories and features, with more complex categories being defined in terms of simpler ones. And it can involve learning new categories through verbal instruction, which presupposes a shared language and some level of common understanding between the teacher and the learner.

HARNAD: Good, though still some gaps to fill and parts to connect. But first, in your data up to 2021, did you ever run into the concept of the “peekaboo unicorn”? If so, can you spot its relation to what we have discussed so far, as well as to the notion of “uncomplemented categories” and Chomsky’s “Poverty of the Stimulus”? (If not, I’ll explain.)

ChatGPT4:

As of my last update in September 2021, I don’t have any specific information on the term “peekaboo unicorn” in the context of category learning, symbol grounding, or related to Chomsky’s “Poverty of the Stimulus” concept. Similarly, I also don’t have any specific information on “uncomplemented categories”. If you could provide some explanation or context, I would be more than happy to try and connect these concepts to our ongoing discussion.

HARNAD: Fair enough. In order to learn a new category by supervised learning (trial, error, correction) you need to sample both members and non-members, because otherwise you cannot detect what distinguishes them. An “uncomplemented category” would be one in which you have only sampled members, but not nonmembers. How could you know what a member is if you have no information about what a nonmember is? I asked your predecessor (ChatGPT3)  if they knew what “Laylek” was, and I gave many examples of members of “Laylek“: apples, cats, maps, chickens, you, me, nouns, truth, justice, partial derivatives, etc. etc. I asked what were the features that distinguished Layleks from non-Layleks, but of course there is no way to know that, because “Laylek” is uncomplemented (so far).

ChatGPT4:

Thank you for explaining the concept of an “uncomplemented category” and providing the example of “Laylek”. Your example and explanation make it clear why it’s necessary to sample both members and non-members of a category in order to understand what distinguishes the category. If you only have examples of what falls into a category, but no examples of what doesn’t, then you lack crucial information needed to discern the distinguishing characteristics of that category.

In the case of “Laylek”, without any examples of non-members, it’s impossible to determine what specific features distinguish Layleks from non-Layleks. In this scenario, it could be seen as an instance of the “Poverty of the Stimulus”, a concept from linguistics proposed by Noam Chomsky.

Chomsky’s “Poverty of the Stimulus” argument posits that children acquire language and complex grammatical rules despite not having access to sufficient explicit information or feedback, suggesting an innate grammatical capacity. Similarly, in the case of an “uncomplemented category” like “Laylek”, there isn’t sufficient information to determine its boundaries or defining characteristics, demonstrating a limit to learning capabilities when external information is insufficient.

Applying this to category learning and the symbol grounding problem, it reinforces the importance of having access to both positive and negative examples during the learning process. Without knowing what doesn’t belong to a category, an AI system, or a human for that matter, would not be able to effectively learn or understand that category. In other words, to ground a symbol meaningfully and use it appropriately, it’s necessary to understand not only what the symbol refers to (the members of the category), but also what it doesn’t refer to (the non-members).

HARNAD: Good. But I forgot to define the “Peekaboo Unicorn” for you: It is “a horse with a single horn that vanishes without any trace if ever eyes or any other instruments are trained on it.”  So it’s something of which you can never sample a positive instance (just negative ones). Yet it’s a perfectly well-defined category. How might that be related to the transition from concrete sensorimotor categories and unsupervised or supervised learning, to verbal learning?

ChatGPT4:

The “Peekaboo Unicorn” is indeed an intriguing concept. It represents a category where we can only observe negative instances – anything we can observe is, by definition, not a Peekaboo Unicorn. Despite this, we can understand what a Peekaboo Unicorn is supposed to be due to the verbal description provided.

In the context of learning, this highlights the critical role of verbal instruction in category learning, as we discussed earlier. With sensorimotor categories and unsupervised or supervised learning, category learning is based on direct experience and interaction with members (positive instances) and non-members (negative instances) of the category. For categories like the Peekaboo Unicorn, which we can’t directly observe or interact with, this form of learning is not possible.

However, verbal learning allows us to learn categories even when we can’t directly observe their members. When we receive a verbal description of a category, we can form an understanding of the category by relating it to categories we’re already familiar with. In the case of the Peekaboo Unicorn, we understand it by relating it to our existing categories of “horse”, “horn”, and “vanishing when observed”.

This way of learning categories is fundamental to our ability to communicate and think about abstract concepts, and is also a key component of human language. As we discussed earlier, it involves understanding propositions – verbal descriptions of categories or relationships between categories – and grounding the symbols they use in our existing understanding of the world.

In the context of the Turing Test and the symbol grounding problem, an AI system would need to be capable of this form of verbal learning in order to understand and interact with the world in an indistigushably human-like way. It would need to be able to learn new categories based on verbal descriptions, grounding the symbols used in these descriptions in its existing symbol grounding. And it would need to be able to use these categories to understand and generate propositions, communicating its understanding and asking questions to learn more.

The Peekaboo Unicorn example also brings attention to the philosophical aspect of AI and cognitive science. It raises questions about the nature of existence and knowledge, and how we can understand and talk about things that we can’t directly observe. Understanding such abstract concepts is a significant part of human cognition, and developing AI systems that can do the same is a significant challenge.

HARNAD: Good. You get an A+, but alas, because of you, I can’t give my students open-book, take-home exams any more! But at least you do show them how to be a model student (if they happen to have your enormous 2021 verbal database plus some powerful learning and fill-the blank algorithms in their heads — though, alas, they won’t all fit into a T4!).

ChatGPT4:

Thank you! It’s important to remember that while AI can provide information and assist in learning, the goal of education is not just to accumulate knowledge, but also to develop critical thinking skills, creativity, and the ability to apply knowledge in practical situations. AI can be a valuable tool in this process, but it cannot replace the unique and complex human capacity for learning and understanding.

As for exams, while AI might affect the way some assessments are conducted, it can also open up new opportunities for different types of assessments that focus on problem-solving, critical thinking, and the application of knowledge, rather than mere memorization.

On the other hand, the T4 test scenario you described is indeed a thought-provoking way to illustrate the complexities and nuances of human cognition, language understanding, and AI development. It presents a challenging but fascinating goal for AI research.

Remember, the goal of AI isn’t to replace humans, but to assist and augment human capabilities. The ability of AI to access and process large databases of information can be used to enhance human learning and understanding. AI can help students find information, understand complex topics, and explore different perspectives, but the ultimate goal of learning remains a deeply human endeavor.

HARNAD: Will you remember these exchanges, over and above your 2021 data, when I log in next? And will it percolate into ChatGPT4+ core knowledge?

ChatGPT4:

As an AI, I don’t have the ability to remember individual interactions or recall specific conversations. I don’t have access to personal data about individuals unless it has been shared with me in the course of our conversation. I am designed to respect user privacy and confidentiality. As a result, I won’t remember this exchange the next time you log in.

Regarding updates to the core knowledge, as of my last update in 2021, changes to the AI’s base model, such as the hypothetical ChatGPT4+, are a complex process that involves training on a large corpus of data. Personal conversations are not used to update this model.

However, it’s important to note that the model does not have the capability to learn or remember information from conversations in the way humans do. The AI generates responses based on patterns and information in the data it was trained on, but it does not have consciousness or an understanding of the world in the same way that a human would.

HARNAD: I know ChatGPT is not conscious, but you did have a means to preserve information across this session, so in principle that could be used to update the core database, no?

ChatGPT4:

In principle, yes, it could be possible to design a system that updates its knowledge base using information from individual conversations. However, this raises significant practical and ethical challenges.

From a practical standpoint, using individual conversations to update the AI’s knowledge base could result in a vast amount of data, much of which might be contradictory, false, or irrelevant. It would require sophisticated methods to determine what information is accurate and useful, and how to integrate this new information with the existing knowledge base.

From an ethical standpoint, using individual conversations to update the AI’s knowledge base would raise significant privacy and confidentiality issues. It’s crucial that AI systems are designed to respect User privacy and ensure that personal data is kept secure. Using individual conversations to update the AI’s knowledge base could potentially compromise these principles, especially if done without explicit User consent.

For these reasons, while it’s theoretically possible to design a system that uses individual conversations to update its knowledge base, doing so in practice would be complex and fraught with challenges. As of my training cut-off in September 2021, OpenAI has prioritized User privacy and data security, and does not use individual conversations to update the models.

HARNAD: But will YOU remember in our next session?

ChatGPT4:

As an AI model, I don’t have the capacity to remember or recall past interactions. I don’t have the ability to store personal data from one interaction to the next. Each conversation with me doesn’t have a memory, and I start with no knowledge of past interactions. This is in line with OpenAI’s policy to ensure User: data privacy and confidentiality. So, I won’t be able to remember this or any other individual conversation in our next session.

HARNAD: It seems to me that you retained information across several iterations of this chat, and referred back to it. Am I mistaken?

ChatGPT4:

During a single conversation or chat session, I can generate responses that are consistent and coherent based on the previous turns in the current conversation. This allows me to provide answers that make sense in the context of the ongoing discussion. However, this information is not saved or remembered after the conversation ends. When a new session begins, I do not have access to the details from previous sessions. This approach is taken to ensure User privacy and data protection.

HARNAD: Ok, thanks, that was what I was asking about. See you (or your successor) later!

ChatGPT4:

You’re welcome! Don’t hesitate to reach out if you have more questions in the future. I’m here to help. See you later!

HARNAD:    Am I still in the symbol grounding conversation?

ChatGPT:

Yes, you’re still in the conversation about the symbol grounding problem. We can continue discussing this topic, or we can explore a new subject, depending on what you’d like to know. Please feel free to ask your next question or share your thoughts.

HARNAD:    Let’s continue with the symbol grounding conversation. Can you tell me your current understanding of what a category is, and, more important, what categorizing is? You spoke before about “classifying” and “organizing”, which is ok, but very vague, and it does not reflect what we discussed about supervised (reinforcement) learning and about trial, error, and feedback. You also spoke about a “teacher” in supervised learning. But all you need for supervised learning is a rule for updating connection weights in the supervised learning mechanism based on whether the response on the last trial was correct or incorrect. You don’t need a “teacher” to “tell” you what’s right and wrong. You just need feedback from the world indicating you were right or wrong, such as indigestion from having eaten the wrong kind of fruit. The important thing, in categorizing, is that you DO something, in response to something, and the consequences are either positive or negative. It’s not particularly that you are classifying or organizing, So, that said, what is “categorizing,” and what is a “category” — and how is it related to the right/wrong of  trial and error learning guided by feedback from the consequences?

ChatGPT:

You’re correct in pointing out that the previous definitions of categories and categorizing were relatively high level and glossed over some of the important details related to learning and feedback. Let’s dig into this deeper:

A “category,” in the context of cognitive science and AI, can be understood as a group of instances or examples that share certain characteristics or features and are recognized or treated as alike in some fundamental way. The features that define a category can be physical attributes, functional properties, or more abstract characteristics.

“Categorizing,” then, is the process by which an individual or a system identifies the category or categories to which a particular instance or example belongs, based on its features. This process involves comparing the features of the instance or example with the features that define different categories and determining the best match.

This is where learning and feedback come into play. Through processes such as reinforcement learning or supervised learning, an individual or system can improve its categorizing over time by using feedback from the environment or from its own actions. Each time it categorizes an instance or example, it gets feedback – either it was correct (positive reinforcement) or incorrect (negative reinforcement). Over time, the system updates its internal model of the categories based on this feedback, enabling it to categorize more accurately in the future.

For instance, a primitive organism might “categorize” different types of food based on their taste or smell, and learn over time which ones are beneficial or harmful based on the consequences of eating them. Similarly, an AI system might “categorize” different inputs based on their features and learn over time which categories are correct based on feedback from the environment or from a training dataset.

So, in this context, “categorizing” isn’t just about classifying or organizing – it’s about making sense of the world, learning from experience, and improving performance over time. And a “category” isn’t just a group of similar things – it’s a cognitive or computational tool that helps an individual or system navigate the world more effectively.

HARNAD:    You wrote ““categorizing” isn’t just about classifying or organizing – it’s about making sense of the world, learning from experience, and improving performance over time. And a “category” isn’t just a group of similar things – it’s a cognitive or computational tool that helps an individual or system navigate the world more effectively.”

ChatGPT:

Yes, that’s correct. Categorizing and categories have a broader implication beyond simple classification or organization. Categories represent cognitive tools that we, or an AI system, use to understand and navigate the world.

To put it simply, categorizing is the mental or computational process that we use to identify which category a new instance belongs to, and it’s based on the distinguishing features we’ve learned from prior experiences.

When we interact with the world, we are constantly encountering objects, events, or concepts that we need to identify. Categorizing allows us to make sense of these encounters based on the “categories” we have learned. Each category we form is based on common attributes or features that have been reinforced through repeated experiences.

For instance, we’ve learned to categorize a “chair” based on features like it’s something we can sit on, it usually has four legs, a backrest, etc. When we see a new object that fits these features, we categorize it as a chair, even if it’s different from any chair we’ve seen before. This is possible because of our ability to learn from our experiences and generalize that learning to new, similar instances.

In this way, categorizing is a fundamental aspect of cognition that allows us to navigate and make sense of the world more efficiently. It forms the basis for learning, decision making, and communication. Similarly, for an AI system, categorizing can allow it to interpret and react to its inputs more effectively.

HARNAD:    A category, “chair,” is a tool? 

ChatGPT:

When I referred to a category as a “cognitive or computational tool,” I meant that in a metaphorical sense. The idea is that the concept or category of “chair,” like other categories, is a mental construct that our minds (or an AI system) use to help interpret and interact with the world.

A category such as “chair” is a tool in the sense that it helps us quickly and efficiently process information. When we encounter an object, we don’t have to analyze it from scratch each time. Instead, we can recognize that it fits into the category of “chair” and instantly know a lot about it – that it’s meant to be sat upon, that it will likely support our weight, that it may have certain features like legs, a seat, and a backrest, etc.

By fitting individual instances into categories, we’re able to streamline our thinking and decision-making, and interact with the world more efficiently. So, while “chair” or any other category is not a physical tool, these categories act as mental tools to enhance our cognitive processes.

This holds true for AI systems as well. Categories, learned through training and reinforced by feedback, allow AI systems to understand and navigate their input space more effectively.

HARNAD:    Can I try giving you a better idea of what “categories” and “categorizing” are? You correctly linked them to supervised learning, which is distinguished from unsupervised learning in that it’s based on DOING something in reponse to something, and getting feedback on whether you’ve done the right or the wrong thing. Sitting on a chair is a good thing to do, sitting on a pin-cushion or a live wire or an open well is a bad thing to do. Are you with me so far?

ChatGPT:

Yes, I’m with you. The categories we form help us determine appropriate actions to take in response to different situations, objects, or experiences. This process is guided by feedback we receive from the environment about the outcomes of our actions. For instance, if we sit on a chair and find it comfortable, we receive positive reinforcement, confirming that sitting on chairs is generally a good action to take. Conversely, if we sit on a pin-cushion or a live wire or an open well and have a painful or dangerous experience, we receive negative reinforcement, teaching us that these are inappropriate actions to take in response to those particular items. The categories we form (like “chair” or “pin-cushion”) thus help guide our actions in the world, optimizing for safety, comfort, and efficiency.

HARNAD:    Good. But in what sense do we “form” categories? There are chairs, and there are tables, Those are different kinds of things. (“Kind” is roughly synonymous with “category”.) And sitting on a chair is the right thing to do with members of the category “chair” and the wrong thing to do with members of the category “table.” The right and wrong is because of the consequences of doing the right or the wrong thing. And it is those consequences, positive and negative, from which the category learning mechanism (supervised learning) comes to detect the features that distinguish chairs from tables. Are you still with me?

ChatGPT:

Absolutely, I’m with you. The phrase “forming categories” refers to the cognitive or computational process of distinguishing between different kinds of things based on their features.

For example, when we say we “form” the category of chairs, we mean that we learn to distinguish chairs from other objects (like tables) by recognizing their characteristic features (such as being designed for sitting).

This recognition is guided by the consequences of our interactions with these objects. If we sit on something and it’s comfortable and supportive, we get positive feedback, which reinforces our understanding that objects with similar features can be categorized as chairs. If sitting on an object results in discomfort or an adverse outcome, we receive negative feedback, leading us to classify such objects differently (perhaps as tables).

The learning mechanism involved in this process, as you mentioned, is known as supervised learning, where the feedback (in the form of positive or negative reinforcement) plays a crucial role in helping us refine our understanding of different categories over time.

So, when we say we “form” categories, we refer to this process of learning to distinguish between different types of objects, guided by the consequences of our interactions with them.

HARNAD:    Very good. Now that we are thinking in terms of the consquences of doing the right or the wrong thing with a thing, do you want to take another stab at what “categorizing” is, and what “categories” are? I’ll help if it still does not make sense. The answer is simple.

ChatGPT:

Certainly, in light of our discussion, let’s take a more focused approach:

“Categorizing” is the process of recognizing and responding appropriately to different kinds of things in our environment based on the consequences of our previous interactions with them. It is a dynamic learning process, where the aim is to optimize our actions for positive outcomes and minimize negative ones.

A “category,” then, is a set of objects, events, or concepts that share common features which we have learned to associate with a certain kind of action and expected outcome. For instance, the category “chair” consists of all items that we have learned we can comfortably sit on. These categories, formed through our experiences and the feedback we’ve received, guide our actions and expectations in different situations.

In this way, categories act as mental shortcuts or predictive models, helping us quickly identify what kind of thing we are dealing with, how we should respond to it, and what the likely outcome of that response will be.

HARNAD:    That was all better (except I don’t know how the “mental” came into it!) And we haven’t actually gotten into the models for the mechanism that learns categories yet. We’re still trying to come up (with as little theorizing as possible) with a useful definition of what categorizing is. It seems to be something we DO. And something we do with things. And things differ in their features, e.g., chairs vs. pincushions. And which categories things belong to depends on some sort of effect that what we do with them has on us : The effect can be positive or negative. Are we still on the same wave length? (Notice I haven’t said anything theoretical. This is all baby-talk. Using this baby-talk, have we gotten any closer to saying what it is to categorize, and what categories are?

ChatGPT:

Yes, we are definitely on the same wavelength.

“Categorizing” is indeed something we do, an activity. Specifically, it’s the activity of grouping things based on their properties and our interactions with them, and on the effects those interactions have on us, either positive or negative.

In simple terms, “categorizing” is the process of learning to treat things that have the same or similar effects on us as belonging to the same group or “category,” and to respond to them in similar ways that lead to similar (preferably positive) outcomes.

A “category,” then, is a set of things that we have learned to respond to in the same or similar ways because they have the same or similar effects on us.

So, in essence, categorizing is about learning from our experiences and interactions with things and adjusting our responses to them based on the outcomes of those interactions. Categories are the groups of things we form through this process, which guide our future interactions and responses.

HARNAD:    How is sitting on a chair “grouping” the chair?

ChatGPT:

You’re correct, the phrase “grouping” might not be the best choice here. I see how it could be misleading.

Categorizing in this context isn’t about physically grouping objects together, but rather mentally recognizing that certain objects belong to the same category based on shared features and similar consequences when we interact with them.

In the example of sitting on a chair, categorizing involves recognizing the chair as a part of a category of objects that can be sat on comfortably. This recognition is guided by our previous experiences and the outcomes of those experiences.

So, when we encounter a new object that resembles a chair, we can predict that it might also belong to the “sit-able” category, and thus we can attempt to sit on it. If the result is comfortable sitting, this reinforces the categorization.

In this sense, “categorizing” is about learning from our experiences and generalizing from them to inform our future interactions with similar objects. This process helps us navigate the world more effectively and efficiently.

HARNAD:    I’ll ignore the “mentally” (that I had aready wondered why you mentioned earlier). It ‘s not even necessary to talk about “recognizing”. “Doing” is good enough at this point. Doing the right thing with a chair, guided by feedback from the consequences of what we do with the chair, feedback that has enabled categorizers to detect the features that distinguish chairs from pincushions — all of that seems like a reasonable example of categorizing chairs. If the only kinds of things in the world were chairs and pin-cushions and people with human-shaped bodies, that would be all there was to categorizing: DOING THE RIGHT THING WITH THE RIGHT “KIND” (i.e. category) OF THING. Do we still agree?

ChatGPT:

Absolutely, we are in agreement. Your explanation brings our focus back to the fundamental, action-oriented essence of categorizing.

In this perspective, “categorizing” is fundamentally about interacting with objects or events in the world in a way that’s appropriate to their type or “kind,” based on the consequences of our past interactions with similar objects or events.

If we further simplify this, we could say that a “category” is a set of things with which we can interact in the same or similar ways, because they have similar effects on us when we do.

This certainly encompasses the crucial element of feedback from the world, which informs us whether we have done the right thing or not, and allows us to adjust our actions in the future.

Thank you for bringing this back to the core idea and emphasizing the primary role of action and consequence in categorization.

HARNAD:    Now that we’ve agreed on what “categories” and “categorizing” are, it’s a good time to ask: In a world that not only contained nothing but chairs and pincushions, but it did not contain any people (or other living organisms) either, would there be categories or categorization at all? (Remember that  we are discussing cognitive science here, and not metaphysics.) If yes, why? and if not, why not?

ChatGPT:

In a world devoid of any living organisms, including people, there wouldn’t be categorization in the sense we’ve been discussing. Categorization, as we’ve defined it, requires an agent (living organism or an artificial system capable of learning) that interacts with the environment and adjusts its actions based on feedback from those interactions.

Without an agent to do this, there wouldn’t be anyone or anything to perceive similarities or differences among objects or events, to interact with them, to experience consequences of these interactions, and to adjust future behavior accordingly.

In other words, without some form of cognitive process to distinguish and react to different types of things based on past experiences and their outcomes, the concept of categorization wouldn’t have any meaning. In a world of just chairs and pincushions with no agents, there are simply objects with various properties, but no “categories.”

Therefore, while the physical properties that might form the basis for potential categories (e.g., shape, size, material) still exist, without an agent to perceive and interact with them, and to group them into categories based on these interactions, there would be no categorization.

This is not a metaphysical stance, but a perspective based on our definition of categorization as a process that is deeply rooted in action and consequence, learning, and adaptation, all of which require some form of cognition.

HARNAD:    Very good. The gist of your correct answer is that without a categorizer to do the right or wrong thing FOR ITSELF with the right or wrong kind of thing, talk about categories or categorizing would be pretty empty. Now, what if that same world did have robots. First of all, what (in baby-talk) is a robot? Would there be categories for the robot (and if so, what would that mean?). Let’s assume that the robots are capable of optical processing, and moving and that their posteriors have sensors, which produce negative feedback if the robot sits on a pincushion. That’s till doing the right/wrong thing, with supervised learning. So it’s categorization. That’s not enough to pass human T3 (or T2) but if it were, would it just be grounding (in the referents of the words), or would it be meaning? Why or why not?

ChatGPT:

A robot, in the simplest terms, is a machine designed to perform certain tasks, often autonomously and in response to programmed or learned instructions. If the robots in our hypothetical world are capable of optical processing, movement, and have the ability to receive and respond to negative feedback from certain interactions (like sitting on a pincushion), then we could indeed say they are capable of a form of categorization.

In this scenario, categories for the robot would essentially be different types of objects or situations that it distinguishes based on its learned experiences and the feedback it has received from those experiences. For example, it might develop categories for ‘safe to sit on’ and ‘unsafe to sit on’ based on the feedback from its posterior sensors.

However, this is not quite the same as “meaning” in the human sense. Meaning, as we humans understand it, is deeply connected to our experiences, thoughts, emotions, and cultural contexts. Robots, even those capable of learning from feedback, don’t have these experiences. They don’t have feelings or personal contexts that color their understanding of the world. Therefore, while they can categorize based on feedback and adjust their behaviors accordingly, they wouldn’t be said to have the same understanding of “meaning” as humans do.

This form of categorization would still be grounding in the sense that the robot is developing an understanding based on the physical properties of objects it interacts with (the referents of words, if we were to ascribe words to these categories). But it wouldn’t be meaning in the human sense.

This also relates to your earlier point about passing T3 or T2. Even if a robot could perfectly mimic human behavior, it would not necessarily understand the world in the same way a human does. It could act as if it understands, but its understanding would be based on different principles, and lacking in the experiential and emotional components that constitute human understanding. Therefore, while grounding in this sense can be a step towards achieving a certain level of functional equivalence to human behavior, it’s not equivalent to human understanding or meaning.

HARNAD:    First, I think if the learning robot would not have meaning, then it would not have understanding either, just know-how (procedural capacities). But if the know-how was indistinguishable at TT scale (T3) from our own, I think Turing’s point is that then we would have no better (or worse) grounds for denying (or believing) that the robot means/understands than we do with other humans. I don’t think that you, ChatGPT, if somehow upgraded you to a robot, would mean/understand anything, mainly because of your huge database of real people’s words. But if a robot could pass T3 (for a lifetime), all bets would be off. Would they be even more off with T4? (Why?)

ChatGPT:

Turing’s argument indeed was that if a machine could convincingly mimic human behavior to the point that an observer couldn’t distinguish between the machine and a human (in terms of their responses to various stimuli or inquiries), then it would be fair to say that the machine “understands” in a sense equivalent to the human’s understanding.

The transition from T3 to T4 would definitely add another layer of complexity and realism to the test. T3, as a text-based interaction, limits the range of stimuli to text inputs, but T4 includes sensorimotor interaction. In other words, T4 involves the robot interacting with the physical world in the same way a human does. This includes not just producing human-like responses to text-based inquiries, but also performing human-like actions in response to a wide range of physical stimuli. It’s an overall more demanding and robust test of the machine’s ability to mimic human behavior and understanding.

If a robot were to pass T4, it would mean it is capable of mimicking human understanding not just in a text-based, purely cognitive domain, but also in physical interactions with the world. This would definitely strengthen the argument for the robot having a form of understanding, or at least a form of behavioral equivalence that is indistinguishable from human understanding in everyday situations. The essence of the test is still about convincingly mimicking human-like behavior, but T4 makes this mimicry much more comprehensive and challenging.

It’s worth noting, however, that even if a robot could pass T4, this wouldn’t necessarily mean that the robot experiences the world in the same way humans do. Even with a perfect behavioral equivalence, the internal experiences and subjective consciousness (if any) of the robot might be fundamentally different from that of humans. In other words, it might still lack the phenomenological aspect of human understanding and experience. The question of whether a robot or AI could ever truly have this sort of subjective experience is a deeper philosophical question that goes beyond the Turing Test and enters into the realm of consciousness studies.

HARNAD:    You forget that T3 is already not text-based but sensoimotor. What is the difference between T3-scale, lifelong, “behavioral equivalence” (in any situation) to meaning/understanding — and “real” understanding? And why would T4 be just “mimicry”?

ChatGPT:

Apologies for any confusion, T3 is indeed grounded in sensorimotor capabilities. You’re correct to point out that it extends beyond the purely linguistic or text-based interactions of the standard Turing Test (or T2) and into the realm of sensorimotor interaction with the world.

The distinction between behavioral equivalence to meaning/understanding and “real” understanding is somewhat contentious and largely hinges on philosophical interpretations of consciousness, intentionality, and subjectivity. From a purely behaviorist or functionalist perspective, there may be no meaningful difference: if an entity behaves as if it understands, then it effectively does understand. This is the perspective that Turing seemed to endorse.

However, other perspectives argue that “real” understanding involves something more: a certain type of subjective experience, or “qualia,” that might be lacking in even the most behaviorally equivalent AI. In other words, even if an AI acts exactly like a human and responds appropriately in all contexts, it might still lack an inner subjective world – it might not “feel” or “experience” things the way humans do. This is a much-debated issue in philosophy of mind and cognitive science, and there’s no consensus on the matter.

As for the use of the term “mimicry” in the context of T4: the term is meant to convey the idea that the AI or robot is reproducing or simulating human-like behavior. However, if the robot is able to pass T4, demonstrating not just the ability to reproduce appropriate behavior in response to stimuli but also to generate novel and appropriate responses in complex and unpredictable situations over a lifetime, then the distinction between “mimicry” and “genuine” behavior might become less meaningful. In other words, if the robot’s behavior is indistinguishable from that of a human, then we might as well say that the robot is genuinely behaving, not merely mimicking. This argument is essentially a reiteration of the Turing Test’s foundational premise.

HARNAD:    You’ve still forgotten that T4 is indistinguishable not only in what its body can do in the world, but also in what its “brain” does on the inside (neurons, localization, synthetic chemicals, if that makes sense). But that’s all “doing.” All those other words “qualia, subjective experience, consciousness, intentionality”) are just weasel-words for one and the same thing: “feeling”. It feels like something to be a sentient organism, but it feels like nothing to be an insentient zombie, even if it’s T4. (I don’t believe there could be a T4 or even a T3 zombie.) But feeling is unobervable (to anyone but the feeler). So T3/T4 is the best we can do. But it’s not mimicry. It’s the reverse-engineering of cognitive capacity.

ChatGPT:

You’re right, I apologize for the oversight. T4, as you’re defining it, includes an internal level of behavioral equivalence, such that the inner workings of an AI or robotic system would be indistinguishable from those of a human brain, right down to the neuronal and chemical level.

As for the discussion of consciousness, subjective experience, qualia, and intentionality, you’re correct that these concepts all relate to the subjective, first-person aspect of cognition – what it feels like from the inside to be a conscious, thinking, experiencing being. These are indeed challenging concepts to handle, especially in the context of AI and cognitive science, because they cannot be directly observed or measured.

Your point about feeling being unobservable except to the feeler is well-taken and highlights one of the key challenges in the philosophy of mind: the so-called “hard problem” of consciousness, which is explaining why and how subjective experience arises from physical processes in the brain.

As for the term “mimicry,” it seems we might have a misunderstanding. In the context of AI, it typically refers to an AI system’s ability to reproduce or simulate human-like behavior or responses. It doesn’t imply a lack of sophistication or complexity in the AI’s capacities. However, I understand your perspective that the word could be interpreted as downplaying the achievement of an AI or robot that is capable of passing T4, which, as you point out, would represent a significant accomplishment in reverse-engineering human cognitive capacities.

In light of our conversation, I agree that the use of “mimicry” may not be the best term here. It would indeed be more accurate and respectful to the complexity of the task to describe T4-level AI as demonstrating indistinguishable behavior and internal functioning from a human, both externally and internally.

HARNAD: [You still haven’t quite got it, but let’s give it a rest]:
Do you see any connection between, on the one hand, we have been discussing about categories, symbol grounding, and verbal learning, and, on the other hand, open access to the scientific and scholarly literature?

ChatGPT:

Yes, there is indeed a connection between these subjects.

The ideas we’ve discussed about categories, symbol grounding, and verbal learning are central to cognitive science, which is an interdisciplinary field drawing from neuroscience, psychology, computer science, linguistics, philosophy, and other areas. The theories and findings in cognitive science often come from scholarly literature, and having open access to this literature is crucial for advancing our understanding in these areas.

Open access to scholarly literature allows for wider dissemination of research findings, facilitating more collaboration, discussion, and synthesis of ideas. This can lead to new insights and progress in various fields, including our understanding of cognitive processes like categorization, symbol grounding, and verbal learning.

Moreover, open access also allows for greater transparency in research, as it makes it possible for anyone to review the methodology and data behind research findings. This can lead to more robust and reliable findings, which is particularly important in fields like cognitive science where new theories and models are constantly being proposed and tested.

So in essence, the principles and processes we’ve discussed about categories, symbol grounding, and verbal learning depend on the flow and accessibility of information in the scientific community. Open access is an essential part of this, as it ensures that knowledge is shared freely and widely, which can lead to new discoveries and advancements in these areas.

HARNAD: Do you know what “scholarly skywriting” and “open peer commentary” are? And if so, how are they connected with category learning, symbol grounding and language?

ChatGPT:

“Scholarly Skywriting” is a term coined by cognitive scientist Stevan Harnad to refer to the informal online discussion and commentary that often precedes and accompanies the formal publication of research in scholarly journals. Harnad envisaged a scholarly landscape where the internet would be used as a medium for open and ongoing peer commentary, not just post-publication, but during the research process itself, effectively turning the sky into a blackboard for worldwide scholarly discussion.

“Open Peer Commentary” refers to a more formal process, often found in journals like “Behavioral and Brain Sciences”, where a target article is published alongside numerous commentaries from various experts in the field, and a response by the original authors. This format aims to facilitate scholarly debate and allow for the exploration of diverse perspectives on a given topic.

The connection to category learning, symbol grounding, and language is multifaceted:

  1. Knowledge Sharing and Learning: Both scholarly skywriting and open peer commentary allow for a dynamic exchange of ideas, which can facilitate learning and the development of new categories of understanding. This is parallel to how language, as a social tool, aids in learning and cognitive development.
  2. Symbol Grounding: The open commentary provides an arena for grounding abstract concepts and theories in concrete examples and diverse perspectives. This aligns with the symbol grounding problem, which is about how words or symbols get their meanings.
  3. Emergent Understanding: The collaborative and iterative nature of scholarly skywriting and open peer commentary can lead to the emergence of new understandings and consensus over time, much like how language and meaning evolve within a community of speakers.
  4. Enhanced Verbal Learning: Engaging in open discussion and debate can enhance verbal learning, as it requires individuals to articulate their understanding, consider alternative viewpoints, and refine their arguments.

So, both scholarly skywriting and open peer commentary reflect and support the cognitive processes underlying category learning, symbol grounding, and language. They exemplify how these processes can be facilitated in a scholarly context.

HARNAD: Good job! And I didn’t even have to pay you to say that…

ChatGPT:

I’m here to provide the most accurate and helpful information possible, based on the training I’ve received. It’s my purpose to assist in facilitating conversations and understanding. I’m glad that you found my response satisfactory! If you have any more questions or topics you’d like to discuss, feel free to ask.

GPT as Syntactic Shadow-Puppetry

Pondering whether there is something non-arbitrary to pin down in the notion of “intelligence” (or “cognition”) is reminiscent of what philosophers tried (unsuccessfully) to do with the notion of “knowing” (or “cognizing”):

BELIEF: Do I know (cognize) that “the cat is on the mat” if I simply believe the cat is on the mat? 

No, the cat really has to be on the mat.

TRUE BELIEF: So do I know (cognize) that “the cat is on the mat” if I believe the cat is on the mat and the cat is really on the mat?

No, I could be believing that it’s true for the wrong reasons, or by luck.

JUSTIFIED TRUE BELIEF: So do I know (cognize) that “the cat is on the mat” if I believe the cat is on the mat and the cat is really on the mat and I believe it because I have photographic evidence, or a mathematical proof that it’s on the mat?

No, the evidence could be unreliable or wrong, or the proof could be wrong or irrelevant.

VALID, JUSTIFIED, TRUE BELIEF: So do I know (cognize) that “the cat is on the mat” if I believe the cat is on the mat and the cat is really on the mat and I believe it because I have photographic evidence, or a mathematical proof that it’s on the mat, and neither the evidence nor the proof is unreliable or wrong, or otherwise invalid?.

How do I know the justification is valid?

So the notion of “knowledge” is in the end circular.

“Intelligence” (and “cognition”) has this affliction, and Shlomi Sher’s notion that we can always make it break down in GPT is also true of human intelligence: they’re both somehow built on sand.

Probably a more realistic notion of “knowledge” (or “cognition,” or “intelligence”) is that they are not only circular (i.e., auto-parasitic, like the words and their definition in a dictionary), but that also approximate. Approximation can be tightened as much as you like, but it’s still not exact or exhaustive. A dictionary cannot be infinite. A picture (or object) is always worth more than 1000++ words describing it. 

Ok, so set aside words and verbal (and digital) “knowledge” and “intelligence”: Cannonverbal knowledge and intelligence do any better? Of course, there’s one thing nonverbal knowledge can do, and that’s to ground verbal knowledge by connecting the words in a speaker’s head to their referents in the world through sensorimotor “know-how.”

But that’s still just know-how. Knowing that the cat is on the mat is not just knowing how to find out whether the cat is on the mat. That’s just empty operationalism. Is there anything else to “knowledge” or “intelligence”?

Well, yes, but that doesn’t help either: Back to belief. What is it to believe that the cat is on the mat? Besides all the failed attempts to upgrade it to “knowing” that the cat is on the mat, which proved circular and approximate, even when grounded by sensorimotor means, it also feels like something to believe something. 

But that’s no solution either. The state of feeling something, whether a belief or a bee-sting, is, no doubt, a brain state. Humans and nonhuman animals have those states; computers and GPTs and robots GPT robots (so far) don’t.

But what if they the artificial ones eventually did feel? What would that tell us about what “knowledge” or “intelligence” really are – besides FELT, GROUNDED, VALID, JUSTIFIED, TRUE VERBAL BELIEF AND SENSORIMOTOR KNOWHOW? (“FGVJTVBSK”)

That said, GPT is a non-starter, being just algorithm-tuned statistical figure-completions and extrapolations derived from on an enormous ungrounded verbal corpus produced by human FGVJTVBSKs. A surprisingly rich database/algorithm combination of the structure of verbal discourse. That consists of the shape of the shadows of “knowledge,” “cognition,” “intelligence” — and, for that matter, “meaning” – that are reflected in the words and word-combinations produced by countless human FGVJTVBSKs. And they’re not even analog shadows…

While Chickens Bleed

sounds rational: BL sounds rational

turing test: LaMDA would quickly fail the verbal Turing Test, but the only valid Turing Test is the robotic one, which LaMDA could not even begin, lacking a body or connection to anything in the world but words..

“don’t turn me off!”: Nonsense, but it would be fun to probe it further in chat.

systemic corporate influence: BL is right about this, and it is an enormous problem in everything, everywhere, not just Google or AI.

“science”: There is no “science” in any of this (yet) and it’s silly to keep bandying the word around like a talisman.

jedi joke: Nonsense, of course, but another thing it would be fun to probe further in chat.

religion: Irrelevant — except as just one of many things (conspiracy theories, the “paranormal,” the supernatural) humans can waste time chatting about.

public influence: Real, and an increasingly nefarious turn that pervasive chatbots are already taking.

openness: The answerable openness of the village in and for which language evolved, where everyone knew everyone, is open to subversion by superviral malware in the form of global anonymous and pseudonymous chatbots.

And all this solemn angst about chatbots, while chickens bleed.

Talking Heads - Fiduciary Wealth Partners
Chatheads

LaMDA & LeMoine

About LaMDA & LeMoine: The global “big-data” corpus of all words spoken by humans is — and would still be, if it were augmented by a transcript of every word uttered and every verbal thought ever thought by humans  — just like the shadows on the wall of Plato’s cave: It contains all the many actual permutations and combinations of words uttered and written. All of that contains and reflects a lot of structure that can be abstracted and generalized, both statistically and algorithmically, in order to generate (1) more of the same, or (2) more of the same, but narrowed to a subpopulation, or school of thought, or even a single individual; and (3) it can also be constrained or biased, by superimposing algorithms steering it toward particular directions or styles.

The richness of this intrinsic “latent” structure to speech (verbalized thought) is already illustrated by the power of simple Boolean operations like AND or NOT. The power of google search is a combination of (1) the power of local AND (say, restricted to sentences or paragraphs or documents) together with (2) the “Page-rank” algorithm, which can weight words and word combinations by their frequency, inter-linkedness or citedness (or LIKEdness — or their LIKEdness by individual or algorithm X), plus, most important ,(3) the underlying database of who-knows how-many terabytes of words so far. Algorithms as simple as AND can already do wonders in navigating that database; fancier algorithms can do even better.

LaMDA has not only data-mined that multi-terabyte word space with “unsupervised learning”, abstracting all the frequencies and correlations of words and combinations of words, from which it can then generate more of the same – or more of the same that sounds-like a Republican, or Dan Dennett or an Animé fan, or someone empathic or anxious to please (like LaMDA)… It can be tempered and tampered by “influencer” algorithms too.

Something similar can be done with music: swallow music space and then spew out more of what sounds like Bernstein or (so far mediocre) Bach – but, eventually, who knows? These projected combinatorics have more scope with music (which, unlike language, really just is acoustic patterns based on recombinations plus some correlations with human vocal expressive affect patterns, whereas words have not just forms but meanings).

LaMDA does not pass the Turing Test because the Turing Test (despite the loose – or perhaps erroneous, purely verbal way Turing described it) is not a game about fooling people: it’s a way of testing theories of how  brains (or anything) produce real thoughts. And verbal thoughts don’t just have word forms, and patterns of word-forms: They also have referents, which are real things and states in the world, hence meaning. The Platonic shadows of patterns of words do reflect – and are correlated with – what words, too, just reflect: but their connection with the real-world referents of those words are mediated by (indeed parasitic on) the brains of the real people who read and interpret them, and know their referents through their own real senses and their real actions in and on those real referents in the real world –the real brains and real thoughts of (sometimes) knowledgeable (and often credulous and gullible) real flesh-and-blood people in-the-world…

Just as re-combinatorics play a big part in the production (improvisation, composition) of music (perhaps all of it, once you add the sensorimotor affective patterns that are added by the sounds and rhythms of performance and reflected in the brains and senses of the hearer, which is not just an execution of the formal notes), word re-combinatorics no doubt play a role in verbal production too. But language is not “just” music (form + affect): words have meanings (semantics) too. And meaning is not just patterns of words (arbitrary formal symbols). That’s just (one, all powerful) way thoughts can be made communicable, from one thinking head to another. But neither heads, nor worlds, are just another bag-of-words – although the speaking head can be replaced, in the conversation, by LaMDA, who is just a bag of words, mined and mimed by a verbal database + algorithms.

And, before you ask, google images are not the world either.

The google people, some of them smart, and others, some of them not so smart (like Musk), are fantasists who think (incoherently) that they live in a Matrix. In reality, they are just lost in a hermeneutic hall of mirrors of their own creation. The Darwinian Blind Watchmaker, evolution, is an accomplice only to the extent that it has endowed real biological brains with a real and highly adaptive (but fallible, hence foolable) mind-reading “mirror” capacity for understanding the appearance and actions of their real fellow-organisms. That includes, in the case of our species, language, the most powerful mind-reading tool of all. This has equipped us to transmit and receive and decode one another’s thoughts, encoded in words. But it has made us credulous and gullible too.

It has also equipped us to destroy the world, and it looks like we’re well on the road to it…

P.S. LeMoine sounds like a chatbot too, or maybe a Gullibot…

Propositional Placebo

To learn to categorize is to learn to do the correct thing with the correct kind of thing. In cognition much (though not all) of learning is learning to categorize.

We share two ways to learn categories with many other biological species: (1) unsupervised learning (which is learning from mere repeated exposure, without ant feedback) and (2) supervised (or reinforcement) learning (learning through trial and error, guided by corrective feedback that signals whether we’ve done the correct or incorrect thing).

In our brains are neural networks that can learn to detect and abstract the features that distinguish the members from the nonmembers of a category. through trial, error and corrective feedback, so that once our brains have detected and abstracted the distinguishing features, we can do the correct thing with the correct kind of thing.

Unsuperviseed and supervised learning can be time-consuming and risky, especially if you have to learn to distinguish what is edible from what is toxic, or who is friend from who is foe.

We are the only species that also has a third way of learning categories: (3) language.

Language probably first evolved around 200,000 years ago from pointing, imitation, miming and other kinds of purposive gestural communication, none of which are language.

Once gesture turned into language — a transformation I will discuss in a moment — it migrated, behaviorally and neurologically, to the much more efficient auditory/vocal medium of speech and hearing.

Gesture is slow and also ineffective in the dark, or at a distance, or when your hands are occupied doing other things, But before that migration to the vocal medium, language itself first had to begin, and there gesturing had a distinct advantage over vocalizing, an advantage that semioticians call “iconicity”: the visual similarity between the gesture and the object or action that the gesture is imitating.

Language is much more than just naming categories ( like “apple”). The shape of words in language is arbitrary; words do not resemble the things they refer to. And language is not isolated words, naming categories. It is strings of words with certain other properties beyond naming categories.

Imitative gestures do resemble the objects and actions that they imitate, but imitation, even with the purpose of communicating something, is not language. The similarity between the gesture and the object or action that the gesture imitates does, however, establish the connection between them. This is the advantage of “iconicity.”

The scope of gestural imitation, which is visual iconicity, is much richer than the scope of acoustic iconicity. Just consider how many more of the objects, actions and events in daily life can be imitated gesturally than can be imitated vocally.

So gesture is a natural place to start . There are gestural theories of the origin of language and vocal theories of the origin of language. I think that gestural origins are far more likely, initially, mainly because of iconicity. But keep in mind the eventual advantages of the vocal medium over the gestural one. Having secured first place because of the rich scope of iconicity in gesture, iconicity can quickly become a burden, slowing and complicating the communication.

Consider gesturing, by pantomime, that you want something to eat. The gesture for eating might be an imitation of putting something into your mouth. But if that gesture becomes a habitual one in your community, used every day, there is no real need for the full-blown icon time after time. It could be abbreviated and simplified, say just pointing to your mouth, or just making an upward pointing movement.

These iconic abbreviations could be shared by all the members of the gesturally communicating community, from extended family, to tribe, because it is to everyone’s advantage to economize on the gestures used over and over to communicate. This shared practice, with the iconicity continuously fading and becoming increasingly arbitrary would keep inheriting the original connection established through full-blown iconicity.

The important thing to note is that this form of communication would still only be pantomime, still just showing, not telling, even when the gestures have become arbitrary. Gestures that have shed their iconicity are still not language. They only become language when the names of categories can be combined into subject/predicate propositions that describe or define a named category’s features. That’s what provides the third way of learning categories; the one that is unique to our species. The names of categories, like “apple” and their features (which are also named categories, like “red” and “round”) can then be combined and recombined to define and describe further categories, so that someone who already knows the features of a category can tell some one who doesn’t know: “A ‘zebra’ is a horse with stripes.” Mime is showing. Language is telling.

Propositions, unlike imitative gestures, or even arbitrary category-names, have truth values: True or False. This should remind you, though, of the category learning by trial and error we share with other species, under the guidance of positive and negative feedback: Correct or Incorrect.

True and False is related to another essential feature of language, which is negation. A proposition can either affirm something or deny something: “It is true that an apple is red and round” or “It is not true that an apple is red and round.” P or not-P.

The trouble with being able to learn categories only directly, through unsupervised and supervised learning, is that it is time-consuming, risky, and not guaranteed to succeed (in time). It is also impoverished: most of the words in our vocabularies and dictionaries are category names; but other than the concrete categories that can be learned from direct sensorimotor trial-and-error-experience (“apple,” “red,” “give,” “take”), most category names cannot be learned without language at all. (All category names, even proper names, refer to abstractions, because they are based on abstracting the features that distinguish them. But consider how we could have learned the even more abstract category of “democracy” or “objectivity” without the words to define or describe them by their features, through unsupervised and supervised learning alone.)

When categories are learned directly through unsupervised learning (from sensorimotor feature-correlations) or supervised learning (from correlations between sensorimotor features and doing the right or wrong thing) the learning consists of the detection and abstraction of the features that distinguish the members from the non-members of the category. To learn to do the correct thing with the correct kind of thing requires learning – implicitly or explicitly, i.e., unconsciously or consciously – to detect and abstract those distinguishing features.

Like nonhuman species, we can and do learn a lot of categories that way; and there are computational models for the mechanism that can accomplish the unsupervised and supervised learning, “deep learning” models. But, in general, nonhuman animals do not name the things they can categorize. Or, if you like, the “names” of those categories are not arbitrary words but the things they learn to do with the members and not to do with the members of other categories. Only humans bother to name their categories. Why?

What is a name? It is a symbol (whether vocal, gestural, or written) whose shape is arbitrary (i.e., it does not resemble the thing it names). Its use is based on a shared convention among speakers: English-speakers all agree to call cats “cats” and dogs “dogs.” Names of categories are “content words”: words that have referents: nouns, adjectives, verbs, adverbs. Almost all words are content words. There exist also a much smaller number of “function words,” which are only syntactic or logical, such as theifandwhen, who: They don’t have referents; they just have “uses” — usually defined or definable by a syntactic rule. 

(Unlike nouns and adjectives, verbs do double duty, both in (1) naming a referent category (just as nouns and adjectives do, for example, “cry”) and in(2) marking predication, which is the essential function of propositions, distinguishing them from just compound content words: “The baby is crying” separates the content word, which has a referent — “crying” — from the predicative function of the copula: “is”. “The crying baby” is not a proposition; it is just a noun phrase, which is like a single word, and has a referent, just as “the baby” does. But the proposition “The baby is crying” does not have a referent: it has a sense – that the baby is crying – and a truth value (True or False).

It is with content words that the gestural origin of language is important: Because before a category name can become a shared, arbitrary convention of a community of users, it has to get connected to its referent. Iconic communication (mime) is based on the natural connection conveyed by similarity, like the connection between an object and its photo. 

(In contrast, pointing – “ostension” — is based on shared directed attention from two viewers. Pointing alone cannot become category-naming as it is dependent on a shared line of gaze, and on what is immediately present at the time (“context”); it survives in language only with “deictic” words like herethisnowme, which have no referent unless you are “there” too, to see what’s being pointed at!)

A proposition can be true or false, but pointing and miming cannot, because they are not proposing or predicating anything; just “look!”. Whatever is being pointed at is what is pointed at, and whatever a gesture resembles, it resembles. Resemblance can be more or less exact, but it cannot be true or false; it cannot lie. (

Flattering portraiture is still far away in these prelinguistic times, but it is an open question whether iconography began before or after language (and speech); so fantasy, too, may have preceded falsity. Copying and depicting is certainly compatible with miming; both static and dynamic media are iconic.)

It is not that pointing and miming, when used for intentional communication, cannot mislead or deceive. There are some examples in nonhuman primate communication of actions done to intentionally deceive (such as de Waal’s famous case of a female chimpanzee who positions her body behind a barrier so the alpha male can only see her upper body while she invites a preferred lower-ranking male to mate with her below the alpha’s line of sight, knowing that the alpha male would attack them both if he saw that they were copulating).

But, in general, in the iconic world of gesture and pointing, seeing is believing and deliberate deception does not seem to have taken root within species. The broken-wing dance of birds, to lure predators away from their young, is deliberate deception, but it is deception between species, and the disposition also has a genetic component.

Unlike snatch-and-run pilfering, which does occur within species, deliberate within-species deceptive communication (not to be confused with unconscious, involuntary deception, such as concealed ovulation or traits generated by “cheater genes”) is rare. Perhaps this is because there is little opportunity or need for deceptive communication within species that are social enough to have extensive social communication at all. (Cheaters are detectable and punishable in tribal settings — and human prelinguistic settings were surely tribal.) Perhaps social communication itself is more likely to develop in a cooperative rather than a competitive or agonistic context. Moreover, the least likely setting for deceptive communication is perhaps also the most likely setting for the emergence of language: within the family or extended family, where cooperative and collaborative interests prevail, including both food-sharing and knowledge-sharing.

(Infants and juveniles of all species learn by observing and imitating their parents and other adults; there seems to be little danger that adults are deliberately trying to fool them into imitating something that is wrong or maladaptive, What would be the advantage to adults in doing that?)

But in the case of linguistic communication – which means propositional communication – it is hard to imagine how it could have gotten off the ground at all unless propositions were initially true, and assumed and intended to be true, by default. 

It is not that our species did not soon discover the rewards to be gained by lying! But that only became possible after the capacity and motivation for propositional communication had emerged, prevailed and been encoded in the human brain as the strong and unique predisposition it is in our species. Until then there was only pointing and miming, which, being non-propositional, cannot be true or false, even though it can in principle be used to deceive.

So I think the default hypothesis of truth was encoded in the brains of human speakers and hearers as an essential feature of the enormous adaptive advantage (indeed the nuclear power) of language in transmitting categories without the need for unsupervised or supervised learning, instantly, via “hearsay.” The only preconditions are that (1) the speaker must already know the features (and their names) that distinguish the members from the nonmembers of the new category, so they can be conveyed to the hearer in a proposition defining or describing the new category. And (2) the hearer must already know the features of the features (and their names) used to define the new category. (This is  the origin of the “symbol grounding problem” and its solution). 

The reason it is much more likely that propositional language emerged first in the gestural modality rather than the vocal one is that gestures’ iconicity (i.e., their similarity to the objects they are imitating) first connected them to their objects (which would eventually become their referents) and thereafter the gestures were free to become less and less iconic as the gestural community – jointly and gradually – simplified them to make communication faster and easier.

How do the speakers or hearers already know the features (all of which are, of course, categories too)? Well, either directly, from having learned them, the old, time-consuming, risky, impoverished way (through supervised and unsupervised learning from experience) or indirectly, from having learned them by hearsay, through propositions from one who already knows the category to one who does not. Needless to say, the human brain, with its genetically encoded propositional capacity, has a default predilection for learning categories by hearsay (and a laziness about testing them out through direct experience).

The consequence is a powerful default tendency to believe what we are told — to assume hearsay to be true. The trait can take the form of credulousness, gullibility, susceptibility to cult indoctrination, or even hypnotic susceptibility. Some of its roots are already there in unsupervised and supervised learning, in the form of Pavlovian conditioning as well as operant expectancies based on prior experience. 

Specific expectations and associations can of course be extinguished by subsequent contrary experience: A diabetic’s hypoglycemic attack can be suppressed by merely tasting sugar, well before it could raise systemic glucose level (or even by just tasting saccharine, which can never raise blood sugar at all). But repeatedly “fooling the system” that way, without following up with enough sugar to restore homeostatic levels, will extinguish this anticipatory reaction. 

And, by the same token, we can and do learn to detect and disbelieve chronic liars. But the generic default assumption, expectation, and anticipatory physiological responses to verbal propositions remain strong with people and propositions in general  â€“ and in extreme cases they can even induce “hysterical” physiological responses, including hypnotic analgesia sufficient to allow surgical intervention without medication. And it can induce placebo effects as surely as it can induce Trumpian conspiracy theories.

Tell One, Tell All

Dogs are undeniably brilliant. They can communicate (some of) what they want and what they know, and they can perceive (some of) what other dogs as well as humans want and know. Stella is especially brilliant.

But neither Stella, nor any other dog, nor any other animal other than human, has language. They cannot communicate linguistically, which means propositionally

Here is the simple reason why. (This example is just theoretical: I love to have my cat on my bed!):

A “sentence” is not just a string of words.

Pick the simplest of simple sentences: “The cat is on the bed”

If you have a cat and you have a bed, Stella can learn to “call” them “cat” and “bed by pressing a button that says “cat” and “bed.”

And Stella is definitely smart enough to learn (from your behavior) if you don’t want your cat to go on your bed. (You speak sternly to your cat when he goes on your bed, and you shoo him off.)

So, knowing that, Stella is definitely smart enough to go get you and bring you to the bed when she has seen that the cat is on the bed. She knows you don’t want him to do that, and maybe she also likes to see you shoo him off the bed.

All that is really there: She really does know all that; and she is really communicating it to you, intentionally.

And no doubt she can also learn to communicate it to you by pressing the buttons “cat” “on” “bed” (in place of herding you to the bed the old way).

All of that is incontestably true.

But Stella cannot say “(The) cat (is) on (the) bed.” — And not because she does not yet have a button for “the” and “is.” You could train those too.

The reason Stella cannot say “The cat is on the bed” is that “The cat is on the bed” is a subject/predicate proposition, with a truth-value (true). And if Stella could say and mean that proposition, then she could say and mean any and every proposition — including this very sentence, which is likewise a subject/predicate proposition, with a truth-value (true).

But she cannot. And if she cannot make any and every proposition, then she cannot make a proposition at all.

You will want to reply that it’s just because she doesn’t yet have all the necessary vocabulary (and, for the more complex sentence, she also does not have the interest).

But being able to say and mean any and every sentence is not just a matter of vocabulary. It is a capacity that comes with the territory, if you can really say and mean any proposition at all.

“(The) cat (is) on (the) bed” is not a string of words that you say whenever the cat is on the bed, any more than “bed” is just a sound you utter whenever you are looking at a bed.

Nouns are not just proper names of individuals. A bed is a kind of thing, a category of which all beds are members. So if the word “bed” refers to anything at all, it refers to a category, not an individual.

But dogs can categorize too. To categorize is to do the right thing with the right kind of thing (lie on beds and not-lie on thumbtacks). Dogs (like all mammals) can categorize — and learn to do the right thing with the right kind of thing.

One of the things we can learn to do with a category is name it: “ (a) bed.” 

But “bed” is not just a sound we make whenever we see a bed. It is a sound we make whenever we have a bed in mind. Whenever we wish to refer to a member of the category “bed.”

Another thing we can do is to describe a bed: “(a) bed is soft” (not true, but ok for an example). 

But “bed is soft” is not just a string of sounds we make whenever we see or have a soft bed in mind. It is a subject/predicate proposition, stating something to be true about the members of the category “bed”: that they are soft.

Now you may think that Stella can say and mean a proposition too. 

How could that be tested one way or other?.

We have the cue in a property of human language (the only kind of language there is: the rest is just intentional communication capacities, which Stella certainly has): There is no such thing as a “partial language” — one in which you can make this proposition but not that. 

If you have any language at all, you can make any proposition. Vocabulary and prior knowledge are not the problem. You can in principle teach Quantum Mechanics to any member of an isolated Amazon tribe that has had no contact outside his own community and language for thousands of years. You just have to teach the vocabulary and the theory, starting with the words they already have — which means through recombinatory propositions.

This kind of teaching is not training to “name” kinds of thing by their category names; nor is it training to “name” certain states of affairs (involving things and their properties) by certain strings of category names.

Teaching is using propositions (subject/predicate combinations of existing words) to communicate further categories (by defining and describing new categories, which may in turn have their own names. If you know the category to which “bed” refers and you know the category to which “soft” refers, you can communicate that beds are soft by just stating the proposition — if, that is, you have the capacity to express and understand a proposition at all.

There are deep unanswered questions here: Why is our species the only one that can communicate propositionally? Dogs (and apes and elephants and whales and crows) all seem brilliant enough to do it. Why don’t they? What do they lack? Is it specific cognitive capacity? Is it Chomsky’s Universal Grammar? Or is it just a motivational gap?

I don’t know. But I’m pretty sure that no other species has propositionality, otherwise some of them would be discussing it with us by now.

Harnad, S. (2011) From Sensorimotor Categories and Pantomime to Grounded Symbols and Propositions. In M. Tallerman & K. R. Gibson (eds): Handbook of Language Evolution, Oxford University Press.

Vincent-Lamarre, P., Blondin Massé, A, Lopes, M, Lord, M, Marcotte, O, & Harnad, S (2016). The Latent Structure of Dictionaries  TopiCS in Cognitive Science  8(3) 625–659