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