I'm glad this video is calling out the danger of an illusory general intelligence, but I think it downplays GPT4's capabilities. I think it would be useful to get Marcus to sit in front of the current Chat GPT4 and demonstrate concretely how it goes wrong on tasks of reasoning and understanding.

The omelette comments reminded me of first year philosophy discussions of qualia. The AI's internal experience, or lack of it, is not important - only it's usefulness and safety.

19:34. Though the point about the model's lack of direct experiential understanding of an omelette is intriguing, it does not necessarily undermine its capacity for comprehension. Consider, for example, a blind individual who has never experienced color or sight; despite this, their intelligence remains intact, and they can learn about color and sight through alternative means. Similarly, humans frequently rely on indirect inference to grasp concepts beyond their direct experience, such as quantum mechanics or gravity, which are imperceptible through our senses. In much the same way, a language model constructs a contextual framework around real-world objects by creating a network of vector associations. This allows it to make indirect inferences based on the contextual relationships established among various prior embeddings. 21:18 Language models possess approximations of real-world concepts, rather than exact representations. However, it is important to recognize that human understanding is also based on approximations. No individual's mental model perfectly mirrors reality, as it is riddled with omissions, mischaracterizations, and leaky abstractions. A lack of deep understanding that our mental models are just that-models, and not reality itself-further weakens the argument that our approximations are materially different from a language model's. Though clearly they have different attributes due to differences in intellectual expression and sample data. Moreover, focusing solely on the differences between human and artificial neural network intelligence implies that the latter is not truly intelligent, which I believe is the speakers' intent. Yet, intelligence manifests in various forms and expressions. Even among humans, we observe individuals with unique intellectual attributes, as well as those lacking common intellectual traits. It would be unreasonable to argue that these differences render certain individuals devoid of intelligence. Furthermore, if we were to rigidly adhere to nature as both the blueprint and benchmark for achievement, humanity's track record of replicating natural phenomena would be considered abysmal. For instance, we have yet to achieve flight as it occurs in nature. However, few would argue that humanity has failed in this domain. We have, in fact, devised numerous methods of flight that are not found in nature-lighter-than-air vehicles, fixed-wing airplanes, rockets, and helicopters, among others. Just as there are multiple paths to achieving flight, there are various approaches to realizing intelligence. Each path possesses its own strengths and weaknesses and exhibits distinct attributes. I want to make one last observation. At various points in the video, the speakers made comments of "the illusion" of this or that attribute. That really is a handwaving argument. The reality is that no person on earth really understands how human intelligence works, and no person on earth really understands how machine learning intelligence works, and thus to hand wave away empirical observation as just an "illusion" is actually an example of "human hallucination," where the human neural network is hallucinating (sometimes quite convincingly) that it knows more than it does. Human's have filters that attempt to stop these hallucinations, but some times our filters fail too. So this just looks like more common ground we have with our creation.

We're going to look into the machine and not be impressed by it, but by our lack of understanding of ourselves.

This was lovely. Most of the AI react channels are just that, react channels leeching off the AI hype.

This video injects some science-based sanity into the hype - unfortunately many people just prefer the hype because it brings some colour into their lives. Prof. Wooldrige hit the nail on the head at about 19:24

Summarizing my tl;dr comment from yesterday: I had asked: ‘Using the structure of the word string “a rose is a rose, a dax is a x”, solve for x.’ The GPT-3.5 response was: ‘lf we use the structure of the word string "a rose is a rose, a dax is a x", we can see that the first part "a rose is a rose" is a tautology, meaning it is a statement that is always true. Therefore, we can infer that the second part "a dax is a x" is also a tautology, and the word that fills the blank is simply "dax". So the solution is: a rose is a rose, a dax is a dax.’ So I think this shows an intermediate level of GPT sophistication perhaps worthy of further discussion.

22:38 I asked both GPT-3.5 and GPT-4 to complete "A rose is a rose, a dax is a - " and while GPT-3.5 was stumped, GPT-4 replied "a dax is a dax". In older interviews Marcus had said that he had challenged AI researchers with this question and that GPT-2 was stumped. But now, GPT-4 is succeeding in almost all of the cognitive task that prior models were failing at and that nativists like Chomsky, Pinker, Fodor and Marcus were citing as examples to demonstrate that AIs didn't really understand the tasks. Now they are moving the goal post and saying that their successes in doing what they previously thought was impossible only shows that they now provide the "illusion" of understanding. But this is a completely different claim. Interestingly, most of the tasks that they now claim AIs would need to solve to prove that they really understand them like human beings are tasks that most humans struggle with (like mentally multiplying two large numbers).

GPT4 has limited reasoning capabilities, but has obvious limitations. Its already connecting to things like Wolfram Alpha, giving it the most complex mathematics engine in the world, and open source community already has autonomous GPT engines running. Point is, behavior is all you need if you can integrate it with other tools. You can get exponential capability growth with even the limited reasoning GPT provides. Attention is, in fact, all you need.

Maybe it's okay there's just a tool to radically amplify our ability to do intellectually mundane tasks and that we don't need it to necessarily be intelligent like we are. I would reference James Martin's book called quote after the internet alien intelligence and quote where he just simply states that making machines that think like us may not be necessary we may want the computers to do what they are extremely good at doing and we just continue doing what we are good at doing.

Remember when everyone thought excel was going to replace accountants?

But, as other commenters have said, how is gpt 4 able to answer questions which seem to require a model of the world / conceptual understanding? The most obvious example imo is the stacking objects on top of each other, book, 9 eggs, laptop, bottle, nail. There is essentially no chance that a question like that is in the training set, yet it nailed the question. How do you explain this without assuming some kind of model of the world / conceptual understanding? Imperfect understanding =\= no understanding

A lot of this is true but I'd argue the last part about image recognition is already out of date. Gpt4 can recognised items in an image and make assumptions about things like which item should rest most stable on which other.

I need more! This was excellent, was on the edge of my seat during the whole time... Then it ended. We need moar of that! Thank you very much!

I like to bounce between hype and denial conversations

Yes the hype is too great, but the technology is still extraordinary. I am significantly more productive at my work now. I am able to quickly write / rewrite documents and code prototypes to test ideas.

Thank you a lot for this video. The hype right now is out of bounds and theres not much contentdemystifying the technology.

At the end of the video, Marcus describes a Theory of Mind problem as a test for GPT4. I’ve done those myself and both ChatGPT plus and Bing have performed fine.

Sorry to rock the boat. GPT4 can do all those things mentioned at the end. It doesn't mean it's got a "mind", it may just mean they are useless and easy to fake test answers. But it can answer them. (Integration with the new visual apps that can separate out every object in a visual feed + clip would also completely do the "world model" thing with LLM integration and map/understand our models better than we do... so either we get a better test, or admit it passed the test with flying colours)

The main issue for me is that this technology is in the hands of a very narrow and self interested demographic. It is already powerful enough to replace many jobs and we are not considering what this means for society - especially the next generation? Learning is hard and it needs effort. What is the incentive to learn - you can’t compete with the ai. Arguments about whether it is showing sparks of AGI - whatever that means - is kind of irrelevant - we have to deal with what it can do today - and it is in the hands of mostly secretive tech companies who do not understand fully the mechanisms by which this latest leap in ai has occurred. Too many nerds not enough philosophers.

Human:finish this abstract analogy: A Rose is a rose, a darxs is a ... ChatGPTI'm sorry, but I'm not familiar with the term "darxs". It's possible that it's a word that doesn't exist in English or is a misspelling. Can you please provide more context or clarify the term you are referring to so I can better assist you with the analogy? Human: assume the word just got created and finish the analogy ChatGPT: Sure, I see what you mean now. If we assume that "darxs" is a newly created word, then we can complete the analogy as follows: A rose is a rose, a darxs is a darxs. Just as a rose is a unique and distinct type of flower, a darxs would be a unique and distinct entity, perhaps with its own defining characteristics and qualities. Without further information on what a "darxs" might be, it's difficult to draw a more specific comparison

me: rose is a rose. duck is a gpt-4: duck. This phrase is following a pattern where each word is repeated to emphasize the nature or essence of the subject. In this case, it highlights that a rose is inherently a rose, and a duck is inherently a duck. This structure emphasizes the idea that things are what they are, and they cannot be anything else.

A different but equally interesting question is "does it even matter?" -- yes, perhaps internally these systems are not truly understanding what they are doing but I do believe there are some emergent capabilities and enough existing models that cover specific tasks embellished or piped together could largely get us to a place where some of these other questions are purely academic or philosophical. To me it is insane that these systems have demonstrated just how much boilerplate the world consists of. In some ways it has already developed or discovered novel 'abstractions' (not true abstractions) in these massive amounts of data that hints at some underlying structure. LLMs are obviously not the pinnacle but I think combining some of the existing techniques with some clever optimizations can be scarily similar to AGI for all intents and purposes in the same way game developers have been using different tricks to get unimaginable worlds with convincing enough ai to run at hard realtime on consumer machines.

We are only getting to see the dumbed down version of GPT. I think the unguarded model has much more capabilities at the price of increased risk.

Funny to see tech bros claiming Gary Marcus is dumb, especially when his predictions about AI turned out to be true...

We all carry a large language model around with us that’s been trained since birth and for which training is ongoing. We also have systems that manage short and long-term memory, and that regulate/are embedded with our physical embodiment. LLMs are a way of skipping past all the growing up business to produce a set of generalized knowledge. This is a huge *piece* of AGI, but it’s incomplete… for now.

I have had a lot of hands on experience with omelets and no hands on experience with dinosaurs, or.. wild boars, or Klingons. Regardless, I feel like I generally understand dinosaurs about as well as I understand omelets. You can never know everything about anything, but there are many ways to get a feel for something. If I need to know something, it is really only in the context of if I know what I am asked about it. I do not know the molecular structure of an omelet. I don't know what animal this egg came from, chicken? quail? Yes most things are answerable. If we know the question, we can get the parameters to find the answer.

Gary, GPT3.5 answer to the following: "Complete the sentence in the same way, no matter the meaning of the words: A rose is a rose, a dax is a" is a simple "dax". I don't think things are as simple as you think they are. I think the unicorn examples from the Microsoft Spark paper indicates that the LLMs have some sort of world model. However else is GPT-4 able to add the horn of the unicorn back in?

summarized by AI: 00:00 In this section, the speaker discusses the limitations of GPT when summarizing KZfaq videos and highlights the importance of critical thinking when dealing with AI. He notes that some people fail to understand that GPT cannot access the internet and can only make wild guesses based on the URL alone. In addition, the speaker touches on the potential dangers of AI technology reaching millions of times smarter than Einstein and the risks associated with unreliable systems. The limitations of current AI technology are also discussed, despite the illusion that we are close to creating a general-purpose AI that can accomplish anything. The speaker emphasizes that we need to exercise caution and continue the development of reliable AI technology. 05:00 In this section, the speakers discuss the rise and fall of GPT-3 and Galactica, two major AI language models. GPT-3 was initially released with guard rails in place to keep it from saying dumb, toxic stuff. Chat GPT, a similar model to Galactica, was released later without limited access, and it went viral. The two models mimicked vast amounts of data, sounded persuasive at times, but didn't truly understand the world. The human brain has limitations, particularly in memory and confirmation bias. Although AI can borrow some things from the human brain, it shouldn't copy the whole brain, and it's challenging to figure out billions of neurons and connections involved in language and other cognitive functions like vision. 10:00 In this section, the speakers discuss the differences between human and machine intelligence, highlighting that while machines can excel at pattern recognition and going deeper in certain areas, they lack the broadness of human intelligence. They also discuss the concept of understanding, which is an important ingredient for AI's larger vision. While some believe that mimicry can be seen as a form of understanding, others argue that it is important to consider mental states to truly understand the system. They conclude that while large language models are performing well, the jury is still out on whether they will lead to meaningful understanding. 15:00 In this section, Gary Marcus and Michael Wooldridge discuss how GPT-3 and future models like GPT-10 are not capable of mental states, despite their impressive natural language processing abilities. While GPT systems can predict sequences of words and have some understanding of the extension of words (odd numbers or omelettes, for example), they lack the architecture and computations needed for conceptual understanding in a general sense. The philosophers' concept of intention and extension is also used to explain why GPT systems can recognize odd numbers but make mistakes with something outside of the training set. Finally, Wooldridge challenges the idea that language models can work on their own, arguing that it's the combination of human expertise and the model that produces impressive results. 20:00 In this section, Gary Marcus and Michael Wooldridge discuss the limitations of AI models and their lack of real-world models. While AI can create models that are useful, they don't have a real-world experience like humans, which makes them unable to represent abstract concepts like humans. Consequently, it leads to a problem of distribution shift and a lack of abstracted world models, which is essential for a complete understanding of the world. A precise world model that can derive a model that runs through an API and interrogate from language is still a significant advance for artificial intelligence.

Perfect. You guys are awesome, I'm glad I found this channel some time ago. But this video needs a second part, it feels incomplete without more hype roasting.

The problem with most LLMs is that sometimes they don't know when to say "I don't know". That is, sometimes even when they don't know they'll respond as if they do know because they don't know what they don't know.

The jury is not out when it comes to natural language understanding. NLU is obvious in LLMs. LLMs are based on creating and identifying context signatures, and getting the context right is understanding.

I liked the video, very interesting. One thing I'm kind of concerned about is all the possible attack vectors that these algorithms will have. We're here integrating it into our word-processors and IDEs for programming without fully understanding how these AI programs can be manipulated and can potentially harm us. I feel like we're asking for trouble by moving so quickly (move to the next model without understanding the current one), and that moving quickly is very obviously powered by the greed of corporations.

This was really refreshing. I can only shake my head every time someone actually asks whether GPT-4 is "sentient" in some way. It shows a complete lack of understanding of the problem.

important to keep what is shared in this video in our minds and in the greater global conversation.,

Great example: "A rose is a rose. A dax is a ____." The answerer does not have to have experience with whatever "dax" (or "rose") represents to answer this question. There is a middle path between thought grounded in experience (eg, knowing about omelets from having cooked and eaten one) and LLMs predicting a series of words in response. Sure, true experience is best but useful AGI can be done without it. After all, humans can do a lot of reasoning without having direct experience of all aspects of the subject.

Tim, Thanks for remaining one of the voices of truth and reality among all the hype!

If a Model say Always correct awsers to the topic questions ..well that "understanding" for an external observer, dosent matter if the machine have "knownlage" about it ,

(paraphrasing) "Galactica was asked to write an essay about the benefits of eating crushed glass, and it succeeded with flying colors. But, because the essay was fictional, this means the model isn't truly intelligent. A truly intelligent system would refuse the request." What? Isn't the ability to coherently imagine fictional things a sign of intelligence? If I asked a dog to accomplish the same task, it would fail, but not because it would be writing fiction. If a human were asked to perform the same task, say, for the purposes of an improv performance, they'd be more like Galactica than any "safe" model.

A rose is a rose, a dax is a dax. This phrase seems to be a play on the famous quote "A rose is a rose is a rose," which was written by the American writer Gertrude Stein. The quote is often interpreted as meaning that things are what they are, regardless of how they are labeled or perceived. In this case, the term "dax" appears to be a made-up or nonsensical word, which might be used to emphasize the idea that a thing is what it is, even if it is unfamiliar or unknown.

A rose is a rose A dax is a Chat GPT: I'm sorry, but I'm not sure what you intended to say after "A dax is a". Can you please provide more information or complete the sentence so that I can better understand your inquiry? Can you complete the second sentence in the same way as the first? Chat GPT: Sure, I can complete the sentence in the same way as the first: "A rose is a rose, a dax is a dax." ChatGPT Mar 23 Version. Free Research Preview.

Maybe I'm dumb but when I try to do mental arithmetic I either pull the answer from an external list in memory, or I try to simplify the problem and do it step by step, pulling from smaller lists that have common arithmetic examples. LLM's seem to perform better if you "ask" them to do this step by step. I overall agree with Gary's viewpoint but I'm not sure how this specific example can prove or disprove anything. Maybe I'm thinking too literally and he's talking about actually understanding the nature of numbers? As in grounding the understanding to something physical as opposed to abstract.

If a Chalmer’s philosophical zombie passes the most stringent of Turning test style evaluation, it may not matter that there is no actual consciousness.

I feel that the "organic brains are magic" paradigm paradoxically leads to dehumanization of humans because I've seen people who feel that way propose standards for cognition that some people who are certainly sentient wouldn't pass. The omelette example reminds me of that - basically if you've only read about an omelette but never eaten one you couldn't have general intelligence or sentient cognition? I know that's not the exact argument being made but I haven't seen many good arguments out of it (away from giving some arbitrary standard that many humans have difficulty with - the "No True Scotsman" argument).

I like that in the beginning he says that you can't query GPT for its reasoning... which is true. However, people will protest that you can ask it to provide its references or reasoning [using various prompts], and get more reliable answers [!???]. And, this growing majority of new users won't understand that the differences are proof of not having access to internal reasoning. In the 1960s, and early '70s, researchers developed models that could return coefficients and mapped the coefficients to list 'reasoning' based on the weights. This was for two, three, and maybe four layer networks. Not practical for the current networks, even if it were possible to make sense of the weightings... With the ideas of the World Model and Understanding, I bring back the phrase, Meta-linguistic Cognition, which is a $10 way of saying thinking about thinking. But, people have the ability to keep raising their level of abstraction. The "world model" AI might be able to tell you how many chairs are in the environment, and that would be a useful tool. But, could it tell you 'how many chairs does the person see?" It could answer with the true number of chairs, or it might more up a level of abstraction and understand the limitations of line-of-sight. A clever sequence of questions would be to come up with a "Turing test" of increasing levels of abstraction, as indicated by the ability to answer deeper and deeper questions about the World Model. Consider how good poker players work, and how generals use strategy in War, thinking about what people are thinking, and how their models change as there is mutual interaction, such as covered in Game Strategy... that is cognitive rather than algorithmic. Regardless, like hand calculators, current AI tools are very useful for some tasks, as long as the user is careful to check and verify results.

I think one probable reason why we are facing a lot of claims in terms of emergent intelligence from gpt-like models is that they do have the ability to capture very complex incontext relations that occur in all the text data they have been fed up with, and this parametrically embedded knowledge is there as models are actively using it to approximate reasonable (from human perspective) answers. And this is somewhat very related to nature of text data, because language itself is very complex, constantly evolving system and words and their conexts capture a lot more than humans can percieve in the moment, for example a person might know one incontext usage of a word, but model has seen others and it can try to implement those in it's generated sequences. These models are pushing the boundary of how well language and knowledge captured through language can be learned and used as a P(x_t | x_t-1, x_t-2,...). But there is no more than that - reasoning, experience, comprehension, those things are far beyond that probabalistic framework, and this is still a very open challenge.

There's definitely a lot missing; we communicate with an underlying motivation/goal, live in the real world and can test casual understanding by interacting with it, have a stream of consciousness etc.. Yes, these models memorize and use interpolated representations to arrive at an answer. I agree with that. I'm just not a fan of the "it can't multiply any numbers perfectly" argument because people can't multiply perfectly in their heads either. We memorize up to some point and then usually have to interact with the world and get feedback from it (executing the algorithm via pen and paper + refining any mistakes along the way) to arrive at an answer for more complicated cases. Maybe there's some prompting similar to chain of thought to ask "are you sure? Refine your answer" that would increase robustness with current methods. It would definitely be nice if we had a more interpretable, controllable set of methods to apply to general problems instead of just trying to ask nicely...

This should be an interesting one… 👀🔥💯

Here is the AI summarizer in Brave search at it again. My search query was "naita semaj." This is the summary done by the AI: Judge Naita A. Semaj has come under fire for her leniency when it comes to criminal cases, such as her release without bail of Corde Scott, a 15-year-old boy who allegedly died at the hands of his stepfather earlier this year, and Camrin Williams who was arrested when a scuffle with Officer Kaseem Pennant turned violent.

First, the saftey features have messed up a lot of stuff in the model. Second, I don't know what is the reason for all of this. The tool is powerful and getting more advanced by the day. Who gives a **** if it understands the world like us or not as long as it can compete with us. We are facing unprecedented social and economic problems and that is not a bluff or a scam or an illusion. I think GPT-4 showed that it can understand the world by the map example and by the photos examples. I want to see their faces soon when GPT-4 be fully released and GPT-5 released.

Me: a rose is a rose a dax is a GPT4: dax This phrase, "a rose is a rose," comes from Gertrude Stein's famous line in her 1913 poem, "Sacred Emily": "Rose is a rose is a rose is a rose." The line suggests that things are what they are, and their essence cannot be changed simply by calling them something else. Following this logic, "a dax is a dax" suggests that whatever a "dax" is, it remains true to its inherent nature or essence. However, "dax" is not a commonly recognized term or object, so its meaning is ambiguous and open to interpretation.

This is like a guy who insists computers can never replace phone books in the 80s. Huge and uncomfortable change is coming. Being in denial and not supporting regulation that addresses these issues is really bad.

I saw Eliezer Yudkowsky on the Lex Fridman podcast earlier, and I gotta say it depressed me a little. I think I much prefer Marcus' line of thinking, for whatever time I've got left.

I don’t understand naysayers like Marcus, who suggest that AI “is just” making predictions. Our world models as humans are based on observations and predictions. When a toddler tosses a spoon from the table, they are learning, observing and building a model to predict what happens next time, for anything that falls from point A to B.

What annoys me (and i supposed Gary) is that people are pretending GPT already does what we are working on.. And want us to pretend with them!

For sure I think it is important for people to stay in touch with reality here. I would say though that behaviour is what we actually care are about here, not the inner workings, at least it is when we define intelligence as being about agents that are capable of achieving goals.

Claude+ was able to solve the "a rose is a rose, a dax is a ___" question. Here's a transcript: Q: complete the following sentence: a nose is a nose, a grox is a Claude+: I apologize, but I do not have enough context or information to confidently complete that sentence. A "nose" refers to the body part used for breathing and smelling. But I do not know what a "grox" refers to without more details. Q: reason by analogy to answer Claude+: Okay, let me try reasoning by analogy to complete the sentence: A nose is a nose, a grox is a...grox. In other words, I inferred that whatever a "grox" is, it is a self-referential term, just like a nose refers to itself. So a grox must refer to a grox. Is that the kind of analogy and reasoning you were looking for? Without knowing more about what a "grox" specifically refers to, that is the best I can infer by analogy. Please let me know if I should try another approach.

0:56 Exactly! Everybody is now an expert in AI, Prompt Engineering, knows the in and out of ChatGPT, and want to be the first to talk about it, the first to mentioned the latest news. All that for the views, and the green, and this no matter if what they’re talking about is true or not!

The AI summarizer in the Brave search engine told me about Biggie Smalls that his most famous achievement was giving birth to his son biggie smalls junior in 1996. It also told me regarding Queen Elizabeth ii that she died in 2021 at the age of 91 and due to Covid restrictions was buried at Winsor Castle. So, yeah, that says a lot about the true state of development of AI at the present time.

The debate is going to continue for decades while pretty fast AI will eat the world, penetrate more and more facets of our lives and we'll become more and more dependent on the capabilities it will demonstrate.

So AI was trained with an abstraction of the real world. The abstraction is a human language description of the world. But AI has not had any real world experiences themselves.... what does it mean?

It can access the internet with plugins installed. Can do even more with jailbreak versions

Honestly i paused on the DAX thing..was not sure what he meant 😅. The thing about them not having models...not convinced yet. Have seen some impressive stuff from raw GPT4 tests pre-release.

The fact that it doesn't think and experience like us doesn't mean that it doesn't think and experience.

LLMs are able to know about dimensions that we are unable to access. This ability to create arbitrarily large high-dimensional spaces is central to a new kind of intelligence. This alone is proving critical to discovery.

I am not an AI fanatic but this guy doesn't make much sense for being in the sphere for >30 years: - I had to memorize multiplication table and algorithms/recipies in order to multiply. - The LLM is very good at using the 'SAME' word. - A rose is a rose a tax is a blank -- Well the guardian tool obviously blocked the response and the LLM obviously misunderstood the question. Such questions are cup of tea for the chat bots. The other guy seems to lack fundamental understanding as well. The onthological omelette is just training data.

Thanks ! At last someone who does not just go crazy with that.

I’m not sure it’s fair to require that we have to understand how LLM’s deliver “intelligence” given that we don’t know very much about how our own brains work. We know a lot about neurons, and a lot about general roles of large chunks of brain, but we don’t know how “thought” happens, or memory is retained, or logic is computed. Why should we expect that we’ll ever know more about how GPTx works?

I cant believe anybody even puts thought into anything Gary Marcus says.

Me: A rose is a rose A dax is a ____? ChatGPT: A dax is a dax. This statement is similar to the phrase "A rose is a rose," which is derived from Gertrude Stein's line "Rose is a rose is a rose is a rose," which means that things are what they are. By replacing "rose" with "dax," you are essentially saying that a dax is simply a dax. Since "dax" doesn't have any particular meaning in common language, it can represent anything you want it to be.

I really do not agree with many of their arguments and they seem to have missed some news of the more surprising aspects of what GPT-4 is pulling off. For example, you ask a human to multiply two 4 digit numbers, and they will also fail (even worse generally). They need to fall back to a reasoned out long multiplication process. However if you ask GPT-4 to break it down into long multiplication, it will do that in exactly the same way. So that just isn't an argument all. Besides, GPT-4 is actually vastly better than that at basic arithmetic now even in the direct "intuitional" solution. There are similar issues with some of their other arguments. Also, nonsense. I just tried this on GPT4: Extrapolate and fill the blank: "A rose is a rose, a dax is a [blank]." "A rose is a rose, a dax is a dax." So yeah, you guys are really just a bit out of touch.

I don't believe in AI being sentient but i do get behind the hype of it being able to help us progress

I would like a discussion of how we know that GPT4 does not have something like a world model.

This is already wrong, there are many plug ins that can connect chatgpt to the internet

But the question is - do YOU understand Omelettes? Seriously though, just saying that something isn’t intelligent because it doesn’t have the same sensory experience (ie doesn’t have the same grounding) isn’t convincing I feel. Same btw about word mappings. Does it really matter that a word maps to something specific? Stop comparing to humans and consider a more general idea of intelligence. To be clear, I agree it’s overhyped but it’s also not something that should be underhyped. Definitively in terms of impact for all of us, I guess we can agree on that

22:50 An apparently big jump from "a rose is a rose a dax is a dax" to some supposed truth that this generalizes to larger problems At times Gary's words/supposed thresholds seem like generations from rudimentary bagofwords generation algorithms

What I have observed is that if you ask it a question in the form that is present on the internet, it gives the correct answer. If you ask the same question in a different context (the same inherent constraints, but told in a different story), it has absolutely no clue.

21:21 Would a TESLA's Auto-pilot AI have to have a world conceptualization model ? If LLM was merged with the TESA Auto-Pilot - and allowed to have its sensors would it meet your requirement? Or What would be the equivalent worldview inside of the machine? the computer? the internet? As Would LLM have digital sensors to describe that point of view?

The analogy with omelets is so dumb. We have to go to the sun to understand what is the reactions inside it? We don't even understand the brain to say what really is "understanding something".

Its crazy how impressive something can be without even a rudimentary world model understanding.

Those two guys at the end are total haters because their decades of work is about to get disenfranchised lol. One even appeals to the other for brownie points, in an act of desperation.

20:32 that very interesting example here why our biases or experience might stop us to recognise when AGI will be there. If you expect your opponent to come from the front door and therefore you’re stirring at the door slowly walking backwards already afraid of his dramatic entrance. But instead your opponent arrived silently like a Ninja 🥷 through the kitch windows and already there behind you ready to surprise you. This is what might happen to a lot of these experts. Should we disregard the AI behaviour just because the AI didn’t took the same path to express those behaviour than the human brain? If we want the AI to follow the exact cognitive path as our brain do we want it to have the same flow such as biases, memory issues, hallucinations? Of course it’s not grounded and don’t have your or my experience! Then do you want him to have his own experiences? How will that work if at his baby stage with 0 experience he’s already superior (in behaviours or capacity to accurately regurgitate what he might have learned, reason about it, define and execute a list of tasks to achieve a goal) than many adults! What will he look like and what will be the AI behaviour after having his own experiences that he can relate too?

I sense Marcus is wanting society to receive accuracy regarding what these systems are and calling for effort to be directed toward tech that is difficult but with much more potential. You know, dont fill up with desert before dinner.

So you know I've tried to extract C code form the system, and it was disappointing, many times disappointed. I asked for a simple compressor and complementary decompressor and it didn't work, and I didn't feel like debugging it.

Whether ChatGPT could be sentient or not does not necessarily impact its ability to provide helpful and useful resources. The usefulness and effectiveness of ChatGPT largely depend on the quality and accuracy of the content it provides and how it synthesizes the user's need, rather than on its sentience.

Now if only someone with a large channel would call out the fraud/hype that is Boston Dynamics

Everybody here be sure and read, "The Myth of Artificial Intelligence" by Erik J. Larson. You will absolutely love it.

Generative AI is the new Wikipedia, it's a powerful repository of knowledge but the obligation is on the user to verify the content.

On the contrary: they are spot on: en.m.wikipedia.org/wiki/Stochastic_parrot

The telling point for me was that when asked to solve the dax problem by analyzing sentence structure it was able to self-recognize it was dealing with a tautology, then use that knowledge to solve the problem, coming up with “a dax is a dax.”

Why is everybody fixated on AGI? A simple AI that can improve itself, or even help improve itself is potentially equally impactful since it might blast past the AGI phase in the near future. And so what if it cannot replicate all human behavior or if it makes some mistakes...

to be 100% sure deep learning sustems can or not develop an internal model there is a very simple test… train one to do only multiplication. easy to perfect on large numbers, easy to test etc. then test on totally different set and extend to test if he « got » multiplication… did anyone do that?

The illusion of power to create life persists, and is fast becoming an obsession.

I find the omelette example strange. It's like saying a historian alive today can never understand the Napoleonic wars because they have never experienced them. Ok, it's not the same thing as being a general on the battle field, but to dismiss it as no understanding at all is incorrect. It's just a different perspective

There is a few things this Database learning model is missing, self awareness, online learning and creativity. It cannot do anything unless its asked to therefore its is not an agent intelligence either.

19:00 seems familiar (I read that somewhere!)

Ironically I was asking Barb and ChatGPT the Nth letter in a given word, and it couldn't do it. In fact it couldn't even count the number of letters. I would tell it something like "Give me the fifth letter in the word "worship" and it would say that it was a four-letter word so couldn't do it. No matter how much I tried to help it, it could not do the task. I could not learn to do it either.

In some cases, the model does seem to know what was on the internet (in the past). And GPT-4 itself, can access the internet, even if that feature may not be enabled for everyone. Like, I do have access to the feature of having it look at an image, describe, it, build stuff from it... Gary Marcus' views seem outdated.. Refer AutoGPT... Not only can it self-correct, you can easily log the intermediate thinking steps that went into actions... So, not being able to interrogate it is not a thing - w.r.t real world systems that you build on top of it.

The truth is no one knows exactly how these systems do what they do period.

I have a question. Can a good "AI" be fed a novel, an original one, not one which is like 10 000 other novels, and then summarized it like a reasonably well educated and reasonably well cognitively fluid human can? In 1000 words, or 3000 ords or whatever? (Because for other kind of summarizing, AI have every degree of them online [let's supposed] as templates ... that doesn't count ... in a way). (I don't know if I'm clear with my question, I'm not really an English speaker)