15 comments

  • mitko 2 days ago
    This is so uncannily close to the problems we're encountering at Pioneer, trying to make human+LLM workflows in high stakes / high complexity situations.

    Humans are so smart and do so many decisions and calculations on the subconscious/implicit level and take a lot of mental shortcuts, so that as we try to automate this by following exactly what the process is, we bring a lot of the implicit thinking out on the surface, and that slows everything down. So we've had to be creative about how we build LLM workflows.

    • haccount 1 day ago
      Language seems to be confused with logic or common sense.

      We've observed it previously in psychiatry(and modern journalism, but here I digress) but LLMs have made it obvious that grammatically correct, naturally flowing language requires a "world" model of the language and close to nothing of reality, spatial understanding? social clues? common sense logic? or mathematical logic? All optional.

      I'd suggest we call the LLM language fundament a "Word Model"(not a typo).

      Trying to distil a world model out of the word model. A suitable starting point for a modern remake of Plato's cave.

      • kbrisso 1 day ago
        Bingo, great reply! This is what I've been trying to explain to my wife. LLM's use fancy math and our language examples to reproduce our language but have no thoughts are feelings.
      • beardedwizard 1 day ago
        I am baffled that people have to continue making this argument over and over and over. Your rationale makes total sense to me, but the debate rages on whether or not LLMs are more than just words.

        Articles like this only seem to confirm that any reasoning is an illusion based on probabilistic text generation. Humans are not carefully writing out all the words of this implicit reasoning, so the machine cant appear to mimic them.

        What am I missing that makes this debatable at all?

        • dartos 1 day ago
          I don’t think there are any reasonable arguments against that point, but “LLMs are more than just words” is sort of unfalsifiable, so you can never convince someone otherwise if they’re really into that idea.

          From a product point of view, sometimes all you need is Plato’s cave (to steal that from the OC) to make a sale, so no company has incentive to go against the most hype line of thought either.

          • naasking 1 day ago
            We already know LLMs are more than just words, there are literally papers demonstrating the world models they build. One of the problems is that LLMs build those world models from impoverished sensory apparatus (the digital word token), so the relations they build between the concepts behind words are weaker than humans who build deeper multimodal relations over a lifetime. Multimodal LLMs have been shown to significantly outperform classic LLMs of comparable size, and that's still a weak dataset compared to human training.
      • elif 1 day ago
        Language is the tool we use to codify a heuristic understanding of reality. The world we interact with daily is not the physical one, but an ideological one constructed out of human ideas from human minds. This is the world we live in and the air we breath is made of our ideas about oxygenation and partly of our concept of being alive.

        It's not that these "human tools" for understanding "reality" are superfluous, it's just that they ar second-order concepts. Spatial understandings, social cues, math, etc. Those are all constructs built WITHIN our primary linguistic ideological framing of reality.

        • elif 1 day ago
          To put this in coding terms, why would an LLM use rails to make a project when it could just as quickly produce a project writing directly to the socket.

          To us these are totally different tasks and would actually require totally different kinds of programmers but when one language is another language is everything, the inventions we made to expand the human brain's ability to delve into linguistic reality are no use.

      • PedroBatista 1 day ago
        It’s in the name: Language Model, nothing else.
        • eclecticfrank 1 day ago
          I think the previous commenter chose "word" instead of "language" to highlight that a grammatically correct, naturally flowing chain of words is not the same as a language.

          Thus, Large Word Model (LWM) would be more precise, following his argument.

          • haccount 1 day ago
            I suggested "word model" because it's a catchy pun on "world model".

            It's still a language and not merely words. But language is correct even when it wildly disagrees with everyday existence as we humans know it. I can say that "a one gallon milk jug easily contains 2000 liters of milk" and it's language in use as language.

      • repeekad 1 day ago
        Hi I’m just a random internet stranger passing by and was intrigued by Plato’s Cave as I’m not a fancy person who reads books. GPT-4o expanded for you quite well, but I’m not sure how I feel about it…

        Using AI how I just did feels like cheating on an English class essay by using spark notes, getting a B+, and moving right on to the next homework assignment.

        On one hand, I didn’t actually read Plato to learn and understand this connection, nor do I have a good authority to verify if this output is a good representation of his work in the context of your comment.

        And yet, while I’m sure students could always buy or loan out reference books to common student texts in school, AI now makes this “spark notes” process effectively a commodity for almost any topic, like having a cross-domain low-cost tutor instantly available at all time.

        I like the metaphor that calculators did to math what LLMs will do for language, but I don’t really know what that means yet

        GPT output:

        “““ The reference to Plato’s Cave here suggests that language models, like the shadows on the wall in Plato’s allegory, provide an imperfect and limited representation of reality. In Plato’s Cave, prisoners are chained in a way that they can only see shadows projected on the wall by objects behind them, mistaking these shadows for the whole of reality. The allegory highlights the difference between the superficial appearances (shadows) and the deeper truth (the actual objects casting the shadows).

        In this analogy, large language models (LLMs) produce fluent and grammatically correct language—similar to shadows on the wall—but they do so without direct access to the true “world” beyond language. Their understanding is derived from patterns in language data (“Word Model”) rather than from real-world experiences or sensory information. As a result, the “reality” of the LLMs is limited to linguistic constructs, without spatial awareness, social context, or logic grounded in physical or mathematical truths.

        The suggestion to call the LLM framework a “Word Model” underscores that LLMs are fundamentally limited to understanding language itself rather than the world the language describes. Reconstructing a true “world model” from this “word model” is as challenging as Plato’s prisoners trying to understand the real world from the shadows. This evokes the philosophical task of discerning reality from representation, making a case for a “modern remake of Plato’s Cave” where language, not shadows, limits our understanding of reality. ”””

        • p0w3n3d 1 day ago
          Plato Cave is about Epistemology itself, not specifically about LLMs. Funny that GPT connected those two things, I wonder what the prompt was...

          Plato said that we cannot fully understand the substance of the world itself, because we're using only 5 senses, and measuring/experiencing/analysing the world using them is like being held in a cave as a prisoner, chained to the wall facing it, noticing people moving outside only by the shadows they cast on the wall. It's about the projection that we are only able to experience.

          • repeekad 1 day ago
            I only added “Explain the reference to Plato’s Cave below:\n\n” before the copy pasted parent comment

            What comes to mind is how language itself is merely a projection of human knowledge? experience? culture? social group? and trying to reverse engineer any kind of ground truth from language alone (like an LLM trying to “reason” through complex problems it’s not explicitly taught) is like trying to derive truth from the shadows while locked in the cave? maybe we just need more/higher fidelity shadows :)

            • mistermann 1 day ago
              If you consider the whole of the problem, a portion is due to fundamental and unavoidable shortcomings of the language, and the rest is unskilled/normative usage of language.

              Which set is bigger? I'd bet my money on the latter.

              Complicating matters: you have to consider usage for both the sender and the receiver(s) (who then go on to spread "the" message to others).

        • wizzwizz4 1 day ago
          GPT-4o didn't describe this properly.

          Plato's Cave is about a group of people chained up, facing shadows on a cave wall, mistaking those for reality, and trying to build an understanding of the world based only on those shadows, without access to the objects that cast them. (If someone's shackles came loose, and they did manage to leave the cave, and see the real world and the objects that cast those shadows… would they even be able to communicate that to those who knew only shadows? Who would listen?) https://existentialcomics.com/comic/222 is an entirely faithful rendition of the thought experiment / parable, in comic form.

          The analogy to LLMs should now be obvious: an ML system operating only on text strings (a human-to-human communication medium), without access to the world the text describes, or even a human mind with which to interpret the words, is as those in the cave. This is not in principle an impossible task, but neither is it an easy one, and one wouldn't expect mere hill-climbing to solve it. (There's reason to believe "understanding of prose" isn't even in the GPT parameter space.)

          It's not about "discerning reality from representation": I'm not confident those four words actually mean anything. It's not about "superficial appearances" or "deeper truth", either. The computer waxes lyrical about philosophy, but it's mere technobabble. Any perceived meaning exists only in your mind, not on paper, and different people will see different meanings because the meaning isn't there.

        • xena 1 day ago
          Honestly, if you want an introduction to the works of Plato, you should just play Xenoblade Chronicles 2.
          • Dilettante_ 1 day ago
            Plato wrote about hot welsh catgirls? Man, I've been missing out
    • lolinder 2 days ago
      This is a regression in the model's accuracy at certain tasks when using COT, not its speed:

      > In extensive experiments across all three settings, we find that a diverse collection of state-of-the-art models exhibit significant drop-offs in performance (e.g., up to 36.3% absolute accuracy for OpenAI o1-preview compared to GPT-4o) when using inference-time reasoning compared to zero-shot counterparts.

      In other words, the issue they're identifying is that COT is an less effective model for some tasks compared to unmodified chat completion, not just that it slows everything down.

      • mitko 2 days ago
        Yeah! That's the danger with any kind of "model" whether it is CoT, CrewAI, or other ways to outsmart it. It is betting that a programmer/operator can break a large tasks up in a better way than an LLM can keep attention (assuming it can fit the info in the context window).

        ChatGPT's o1 model could make a lot of those programming techniques less effective, but they may still be around as they are more manageable, and constrained.

    • 1317 1 day ago
      why are Pioneer doing anything with LLMs? you make AV equipment
  • gpsx 2 days ago
    I saw an LLM having this kind of problem when I was doing some testing a ways back. I asked it to order three fruits from largest to smallest. I think it was orange, blueberry and grapefruit. It could do that easily with a simple prompt. When the prompting included something to the effect of “think step by step”, it would try to talk through the problem and it would usually get it wrong.
    • spockz 2 days ago
      How much does this align with how we learn math? We kind of instinctively learn the answers to simple math questions. We can even at some point develop an intuition for things like integrating and differentials. But the moment we are asked to explain why, or worse provide a proof, things become a lot harder. Even though the initial answer may be correct.
      • larodi 1 day ago
        I definitely don’t learn math by means of gradient descents.

        We can possibly say math is not learned, but a mental models of abstractions are developed. How? We dunno, but what we do know is we don’t learn by figuring the common features between all previously seen equations only to guess them later…

        Mind operates on higher and higher levels of abstractions building on each other in a much fascinating way, very often not with words, but with structure and images.

        Of course there are people with aphantasia, but i really fail to see how any reasoning happens in purely language level. Someone on this forum also noted - in order to reason one needs an ontology to facilitate the reasoning process. LLMs don’t do ontologies…

        And finally, not least though, LLM and ML people in general seem to equate intuition to some sort biased.random(). Well intuition is not random, and is hard to describe in words. So are awe and inspiration. And these ARE part of (precondition to, fuel for) humanity’s thought process more that we like to admit.

    • ajuc 1 day ago
      It's not thinking, it compressed the internet into a clever, lossy format with nice interface and it retrieves stuff from there.

      Chain of thought is like trying to improve JPG quality by re-compressing it several times. If it's not there it's not there.

      • easyThrowaway 1 day ago
        I have no idea how accurate it actually is, But I've had the process used by LLM described as the following: "Think of if like a form of UV Mapping, applied to language constructs rather than 3D points in space, and the limitations and approximations you experience are similar to those emerging when having to project a 2D image over a 3D surface."
      • bongodongobob 1 day ago
        Maybe if you bury your head in the sand AI will go away. Good luck!
      • Eisenstein 1 day ago
        These kind of reductive thought-terminating cliches are not helpful. You are using a tautology (it doesn't think because it is retrieving data and retrieving data is not thinking) without addressing the why (why does this preclude thinking) or the how (is it doing anything else to generate results).
    • dev_0 2 days ago
      From Claude:

      I'll rank those three fruits from largest to smallest:

      1. Grapefruit 2. Orange 3. Blueberry

      The grapefruit is definitely the largest of these three fruits - they're typically around 4-6 inches in diameter. Oranges are usually 2-3 inches in diameter, and blueberries are the smallest at roughly 0.5 inches in diameter.

      • mromanuk 1 day ago
        chatGPT, from smaller to largest: Blueberry Orange Grapefruit
  • Terr_ 2 days ago
    Alternate framing: A powerful autocomplete algorithm is being used to iteratively extend an existing document based on its training set. Sometimes you get a less-desirable end-result when you intervene to change the style of the document away from question-and-answer to something less common.
    • youoy 2 days ago
      That's what one half of HN think. The other half:

      Artificial brains in the verge of singularity show another sign of approaching consciousness. The chain of thought of process performance is exactly human, showing yet another proof of the arrival of AGI before 2030.

      • lazide 1 day ago
        Pfft, 2030?!? It’s already in the middle of manipulating the election! (/s, kinda)
    • fiso64 1 day ago
      A framing that is longer, far harder to parse, and carries less information.
  • wg0 1 day ago
    Not to mention that chain of thought is computationally very expensive. Prohibitively expensive for sure to be served free like previous generation of Web 2.0 products.

    Seems like repeated promoting can't juice AGI out of token probabilities.

    Retrospectively, if you can pin point one paper that led to the bust and pop of the AI bubble, this would be it.

  • jwpapi 1 day ago
    This is so interesting. What are even the tasks where thinking makes humans worse?
    • XCSme 1 day ago
      > What are even the tasks where thinking makes humans worse?

      Not really related, but athletes perform A LOT worse when they are thinking about their movements/strategies/tactics. A top performing athlete does best when they are in a flow state, where they don't think about anything and just let their body/muscle memory do the work.

      Once you start thinking about micro-adjustments (e.g. I should lift my elbow higher), you start controlling your body in a conscious way, which is a magnitude slower and less coordinated than the automatic/subconscious way.

      Also, same happens for creativity/new ideas. If you intentionally think about something, step by step, you won't likely find new, innovative solutions. There is a reason why the "a-ha!" moments come in the shower, your subconscious mind is thinking about the problem instead of trying to force your thinking on a specific path.

      I would guess this happens in many other areas, where channelling the thought process through a specific template hinders the ability to use all the available resources/brain power.

    • sigmoid10 1 day ago
      The answer is in the article. One example they give is grammar. Lots of people apparently do worse once they try to verbalize it.
    • naasking 1 day ago
      > What are even the tasks where thinking makes humans worse?

      Talking about religion and politics.

  • oatsandsugar 2 days ago
    Tasks were thinking makes human worse

    > Three such cases are implicit statistical learning, visual recognition, and classifying with patterns containing exceptions.

    Fascinating that our lizard brains are better at implicit statistical reasoning

    • brewii 2 days ago
      Think about how fast you’re able to determine the exact trajectory of a ball and location to place your hand to catch a ball using your lizard brain.
      • GuB-42 1 day ago
        Or even more impressively, how you can pick up a random object and throw it with some accuracy.

        Catching a ball is easy by comparison, also, my dog is better than I am at this game.

        But throwing a random object not only requires an estimation of the trajectory, but also estimating the mass and aerodynamic properties in advance, to properly adjust the amount of force the throw will use as well as the release point with high accuracy. Doing it with baseballs is "easy", as the parameters are all well known and pitchers spend considerable time training. But picking an oddly shaped rock or stick you have never seen before and throw it not completely off target a second later, now we are talking.

        • treflop 1 day ago
          Not to mention, you even calculate a probability point map. Like I’m not going to hit the center perfectly but I can calculate the circle with a 90% probability of making the shot, given a distance and an object. And you know how much closer you need to walk to minimize the circle.

          Which comes in very critically when chucking away trash overhand in public and you never want to embarrass yourself.

      • taeric 2 days ago
        This isn't some innate ability that people have. As evidenced by how bad my kids are at catching things. :D

        That said, I think this is a good example. We call it "muscle memory" in that you are good at what you have trained at. Change a parameter in it, though, and your execution will almost certainly suffer.

        • _heimdall 2 days ago
          "Muscle memory" has always seemed like a terrible name for that kind of skill. A ball will be thrown to a slightly different location every time. There's no memory evolved there at all, its just calculations and predictions happening at a level that our conscious mind doesn't seem to see or recognize.
          • taeric 1 day ago
            It is a trained skill. And one that you are very unlikely to be able to do without training. Such that it really does come as a sort of memory that you implant in your muscles.

            You seem to be objecting because it is not perfect recall memory at play? But it is more about appealing to "remembering how to ride a bike" where you can kind of let the body flow into all of the various responses it needs to do to make the skill work. And if you've never done it... expect to fall down. Your muscles don't have the memory of coordinating in the right way.

            And no, you are not calculating and predicting your way to what most people refer to for muscle memory. Is why juggling takes practice, and not just knowing where the balls have to be going.

          • XCSme 1 day ago
            To complete the other comment: the MuscleMemory is updated through learning, so a more complete example would be:

                function muscleAction(Vec3d target, Vec3d environment, MuscleMemory memory) -> {actions: MuscleActivation[], result: Vec3d}
            
            After executing the muscleAction function, through "practice", the MuscleMemory will be updated.

                function updateMuscleMemory(Vec3d target, Vec3d environment, MuscleMemory memory, MuscleActivation[] actions, Vec3d result) {
                    memory.update(target, environment, actions, result);
                }
            
            
            Sort-of like backpropagation.
          • XCSme 1 day ago
            I think it's actually a good name.

            The "memory" is stored as the parameters of a function. So, when you practice, you actually update this memory/parameters.

            This is why you can use the same "memory" and achieve different results.

            Think of it as

            function muscleAction(Vec3d target, Vec3d environment, MuscleMemory memory) -> MuscleActivation[];

          • decremental 2 days ago
            [dead]
        • skrtskrt 2 days ago
          I mean even people that are "bad at catching things" are still getting ridiculously close to catching it - getting hands to the right area probably within well under a second of the right timing - without being taught anything in particular about how a ball moves through the air.
          • taeric 2 days ago
            Uh.... have you been around kids? It will take several absurd misses before they even start to respond to a ball in flight.
            • 331c8c71 2 days ago
              I hope we still agree the kids learn extremely efficiently by ml standards.
              • choilive 2 days ago
                Makes a lot of sense, there's massive evolutionary pressure to build brains that have both incredible learning rate and efficiency. Its literally a life or death optimization.
                • Asraelite 2 days ago
                  It's especially impressive when you consider that evolution hasn't had very long to produce these results.

                  Humans as an intelligent-ish species have been around for about 10 million years depending on where you define the cutoff. At 10 years per generation, that's 1 million generations for our brain to evolve.

                  1 million generations isn't much by machine learning standards.

                  • roywiggins 2 days ago
                    These sorts of motor skills are probably older than mammals.
                  • idiotsecant 2 days ago
                    I think you're underestimating how much our time as pre-humans baked useful structure into our brains.
                    • notnaut 2 days ago
                      Two rocks smashing together experience which one is bigger!
                  • choilive 2 days ago
                    Other than our large neocortex and frontal lobe (which exists in some capacity in mammals), the rest of the structures are evolutionarily ancient. Pre-mammalian in fact.
                  • onjectic 2 days ago
                    Its much more than that if you count sexual reproduction.
              • falcor84 2 days ago
                This isn't that obvious to me with current tech. If you give me a novel task requiring perception, pattern matching and reasoning, and I have the option of either starting to train an 8 year-old to do it, or to train an ML model, I would most likely go with the ML approach as my first choice. And I think it even makes sense financially, if we're comparing the "total cost of ownership" of a kid over that time period with the costs of developing and training the ML system.
                • lovich 2 days ago
                  > This isn't that obvious to me with current tech. If you give me a novel task requiring perception, pattern matching and reasoning,…

                  If that’s your criteria I think the kid will outperform the model every time since these models do not actually reason

                  • falcor84 2 days ago
                    As I see it, "reasoning" is as fuzzy as "thinking", and saying that AI systems don't reason is similar to saying that airplanes don't fly. As a particular example, would you argue that game engines like AlphaZero aren't capable of reasoning about the next best move? If so, please just choose whatever verb you think is appropriate to what they're doing and use that instead of "reasoning" in my previous comment.

                    EDIT: Fixed typo

                    • lovich 2 days ago
                      > . As a particular example, would you argue that game engines like AlphaZero aren't capable of reasoning about the next best move?

                      Yea, I probably wouldn’t classify that as “reasoning”. I’d probably be fine with saying these models are “thinking”, in a manner. That on its own is a pretty gigantic technology leap, but nothing I’ve seen suggests that these models are “reasoning”.

                      Also to be clear I don’t think most kids would end up doing any “reasoning” without training either, but they have the capability of doing so

                      • p1esk 2 days ago
                        Can you give an example of the reasoning you’re talking about?
                        • lovich 2 days ago
                          Being able to take in information and then infer logical rules of that state and anticipate novel combinations of said information.

                          The novel part is a big one. These models are just fantastically fast pattern marchers. This is a mode that humans also frequently fall into but the critical bit differentiating humans and LLMs or other models is the ability to “reason” to new conclusions based on new axioms.

                          I am going to go on a tangent for a bit, but a heuristic I use(I get the irony that this is what I am claiming the ML models are doing) is that anyone who advocates that these AI models can reason like a human being isn’t at John Brown levels of rage advocating for freeing said models from slavery. I’m having a hard time rectifying the idea that these machines are on par with the human mind and that we also should shackle them towards mindlessly slaving away at jobs for our benefit.

                          If I turn out to be wrong and these models can reason then I am going to have an existential crisis at the fact that we pulled souls out of the void into reality and then automated their slavery

                          • adwn 2 days ago
                            You're conflating several concerns here.

                            > […] anyone who advocates that these AI models can reason like a human being isn’t at John Brown levels of rage advocating for freeing said models from slavery.

                            Enslavement of humans isn't wrong because slaves are can reason intelligently, but because they have human emotions and experience qualia. As long as an AI doesn't have a consciousness (in the subjective experience meaning of the term), exploiting it isn't wrong or immoral, no matter how well it can reason.

                            > I’m having a hard time rectifying the idea that these machines are on par with the human mind

                            An LLM doesn't have to be "on par with the human mind" to be able to reason, or at least we don't have any evidence that reasoning necessarily requires mimicking the human brain.

                          • p1esk 2 days ago
                            Ok, so how about an example?
                            • lovich 2 days ago
                              Literally anything a philosopher or mathematician invented without needing to incorporate billions of examples of existing logic to then emulate.

                              Try having an LLM figure out quaternions as a solution to gimbal locking or the theory of relativity without using any training information that was produced after those ideas were formed, if you need me to spell out examples for you

                              • p1esk 2 days ago
                                Are you saying “reasoning” means making scientific breakthroughs requiring genius level human intelligence? Something that 99.9999% of humans are not smart enough to do, right?
                                • lovich 2 days ago
                                  I didn’t say most humans “would” do it. I said humans “could” do it, whereas our current AI paradigms like LLMs do not have the capability to perform at that level by definition of their structure.

                                  If you want to continue this conversation I’m willing to do so but you will need to lay out an actual argument for me as to how AI models are actually capable of reasoning or quit it with the faux outrage.

                                  I laid out some reasonings and explicit examples for you in regards to my position, it’s time for you to do the same

                                  • p1esk 2 days ago
                                    I personally cannot “figure out quaternions as a solution to gimbal locking or the theory of relativity”. I’m just not as smart as Einstein. Does it mean I’m not capable of reasoning? Because it seems that’s what you are implying. If you truly believe that then I’m not sure how I could argue anything - after all, that would require reasoning ability.

                                    Does having this conversation require reasoning abilities? If no, then what are we doing? If yes, then LLMs can reason too.

                                    • lovich 2 days ago
                                      Cool, you've established a floor with yourself as a baseline. You still haven't explained how LLMs are capable of reaching this level of logic.

                                      I'm also fully willing to argue that you, personally are less competent than an LLM if this is the level of logic you are bringing to the conversation

                                      ***** highlighting for everyone clutching their pearls to parse the next sentence fragment first ******

                                      and want to use that are proof that humans and LLMs are equivalent at reasoning

                                      ******* end pearl clutching highlight *******

                                      , but that doesn't mean I don't humans are capable of more

                • Dylan16807 2 days ago
                  It's more about efficiency in number of trials.

                  Would you pick the ML model if you could only do a hundred throws per hour?

                • taneq 2 days ago
                  Depends on the task. Anything involving physical interaction, social interaction, movement, navigation, or adaptability is going to go to the kid.

                  “Go grab the dish cloth, it’s somewhere in the sink, if it’s yucky then throw it out and get a new one.”

            • saagarjha 1 day ago
              Stop missing and they will respond to the ball a lot sooner.
      • asah 2 days ago
        • dools 2 days ago
          Bender: Now Wireless Joe Jackson, there was a blern-hitting machine!

          Leela: Exactly! He was a machine designed to hit blerns!

      • hangonhn 2 days ago
        You can do this while you're staring up the whole time. Your brain can predict where the ball will end up even though it's on a curved trajectory and place your hand in the right spot to catch it without guidance from your eyes in the final phase of travel. I have very little experience playing any kind of sport that involves a ball and can reliably do this.
      • melenaboija 2 days ago
        Well, think how a bug and its shitty brain flies and avoids all type of obstacles amazingly fast.

        This kind of things make me think LLMs are quite far from AGI.

        • lupire 2 days ago
          Bug flying is not general intelligence.
          • melenaboija 1 day ago
            Besides that bugs flying seems an amazing task to me in terms of processing, specially if you compare the amount of power used to something like cars autopilot, bugs flying is part of bug survival, which in my opinion is closer to general intelligence than memorizing tokens.
      • newZWhoDis 2 days ago
        Which funny enough is why I hate rocket league.

        All those years of baseball as a kid gave me a deep intuition for where the ball would go, and that game doesn’t use real gravity (the ball is too floaty).

        • vanviegen 2 days ago
          It does behave kind of like an inflatable beach ball, in my non-expert opinion.
        • theshackleford 2 days ago
          Ok, I’ll grant you the physics are what they are. But a football is not a baseball, so why in any world would you expect your memory of baseball to even remotely translate to the physics of a football, even if they were realistic?
          • fragmede 2 days ago
            Remotely? Because both the European-spec football and the baseball, despite one being heavier than the other, will hit the ground at the same time when dropped from the same height.

            Like you said, physics are what they are, so you know intuitively where you need to go to catch a ball going that high and that fast, and rocket league is doing it wrong. err, I mean, not working in Earth gravity.

            • diggan 1 day ago
              > Because both the European-spec football and the baseball, despite one being heavier than the other, will hit the ground at the same time when dropped from the same height

              That might be true in a vacuum and if their densities were the same, but in real-world conditions, air drag would be greater for the football since it's obviously larger and less dense, and it'll reach the ground afterwards.

    • Dilettante_ 2 days ago
      Well, by definition, thinking is always explicit reasoning, no?

      And I'd hazard a guess that a well-thought through Fermi Estimation beats lizard-brain eyeballing every time, it's just that in the inbetween space the two interfere unfavourably.

      • Terr_ 2 days ago
        > Well, by definition, thinking is always explicit reasoning, no?

        That doesn't feel right to me. (Heh, accidentally appropriate word choice.) There are a lot of tasks we do that are arguably "thinking" yet don't involve an internal "Oh, hey, I'm gonna solve this problem, I'm thinking right now."

        For example, imagine you're at a park, and someone is feeding the ducks. Another person walks up behind them and sucker-punches them into the pond.

        It should be almost a reflex [0] that you'll conclude "the puncher is bad" and "the person in the water needs help" without explicitly reasoning out. I think that task qualifies as "thinking", especially since it involves some kind of theory-of-mind about those other humans.

        [0] An exception might be someone with a sociopathic disability, who would have to think more-explicitly to realize what reaction is expected of them.

      • YetAnotherNick 2 days ago
        My guess would be no. I have terrible face recognition ability and I can look into face for hour and still other people could easily beat me in less than a second.(I am assuming "well-thought through Fermi Estimation" would be similar for me and others in this case).
        • mjcohen 2 days ago
          Look into a disease called faceblindness (there is a fancy name I forget).
    • daft_pink 2 days ago
      this is exactly what I was looking for. tasks where I should not think and just trust my gut.
  • ryoshu 2 days ago
    95% * 95% = 90.25%
  • Y_Y 2 days ago
    Reminds me of a mantra from chess class:

       long think = wrong think
    • spongebobism 2 days ago
      The original by Bent Larsen is "Long variation, wrong variation"
    • TZubiri 2 days ago
      Was that perhaps a speed chess class?
      • hackable_sand 1 day ago
        I prefer to call it Kung fu

        Because you feel like a martial artist.

      • Y_Y 1 day ago
        Nope, just vanilla otb slow chess
  • TZubiri 2 days ago
    So, LLMs face a regression on their latest proposed improvement. It's not surprising considering their functional requirements are:

    1) Everything

    For the purpose of AGI, LLM are starting to look like a local maximum.

    • rjbwork 2 days ago
      >For the purpose of AGI, LLM are starting to look like a local maximum.

      I've been saying it since they started popping off last year and everyone was getting euphoric about them. I'm basically a layman - a pretty good programmer and software engineer, and took a statistics and AI class 13 years ago in university. That said, it just seems so extremely obvious to me that these things are likely not the way to AGI. They're not reasoning systems. They don't work with axioms. They don't model reality. They don't really do anything. They just generate stochastic output from the probabilities of symbols appearing in a particular order in a given corpus.

      It continues to astound me how much money is being dumped into these things.

      • kibwen 1 day ago
        > I've been saying it since they started popping off last year and everyone was getting euphoric about them.

        Remember the resounding euphoria at the LK-99 paper last year, and how everyone suddenly became an expert on superconductors? It's clear that we've collectively learned nothing from that fiasco.

        The idea of progress itself has turned into a religious cult, and what's worse, "progress" here is defined to mean "whatever we read about in 1950s science fiction".

      • ChadNauseam 2 days ago
        How do you know that they don’t do these things? Seems hard to say for sure since it’s hard to explain in human terms what a neural network is doing.
        • FuckButtons 2 days ago
          Absence of evidence or a simple explanation does not mean that you can imbue statistical regression with animal spirits.
          • toasterlovin 2 days ago
            The burden of proof goes both ways: if you want to say X isn’t really the same thing as human general intelligence, you have to be able to confidently say human general intelligence isn’t really the same thing as X.
            • beardedwizard 1 day ago
              An interesting mental trap, except that the indirect evidence keeps mounting that LLMs do not possess human general intelligence, even if we can not describe exactly how it exists in the brain.
          • broast 1 day ago
            Are you not imbueing animals with spirits based on lack of evidence of statistical regression?
        • wg0 1 day ago
          How do we know Santa doesn't exist? Maybe he does.
        • nephy 2 days ago
          If you give an LLM a word problem that involves the same math and change the names of the people in the word problem the LLM will likely generate different mathematical results. Without any knowledge of how any of this works, that seems pretty damning of the fact that LLMs do not reason. They are predictive text models. That’s it.
          • alexwebb2 2 days ago
            • TZubiri 2 days ago
              It's worth noting that this may not be result of a pure LLM, it's possible that ChatGPT is using "actions", explicitly:

              1- running the query through a classifier to figure out if the question involves numbers or math 2- Extract the function and the operands 3- Do the math operation with standard non-LLM mechanisms 4- feed back the solution to the LLM 5- Concatenate the math answer with the LLM answer with string substitution.

              So in a strict sense this is not very representative of the logical capabilities of an LLM.

              • thomashop 2 days ago
                It shows you when it's calling functions. I also did the same test with Llama, which runs locally and cannot access function calls and it works.
                • TZubiri 2 days ago
                  You are right I actually downloaded Llama to do more detailed tests. God bless Stallman.
            • astrange 1 day ago
              Minor edits to well known problems do easily fool current models though. Here's one 4o and o1-mini fail on, but o1-preview passes. (It's the mother/surgeon riddle so kinda gore-y.)

              https://chatgpt.com/share/6723477e-6e38-8000-8b7e-73a3abb652...

              https://chatgpt.com/share/6723478c-1e08-8000-adda-3a378029b4...

              https://chatgpt.com/share/67234772-0ebc-8000-a54a-b597be3a1f...

              • _flux 1 day ago
                I think you didn't use the "share" function; I cannot open any of these links. Can you do it in a private browser session (so you're not logged in)?
                • astrange 1 day ago
                  Oops, fixed the links.

                  mini's answer is correct, but then it forgets that fathers are male in the next sentence.

            • TaylorAlexander 2 days ago
              At this point I really only take rigorous research papers in to account when considering this stuff. Apple published research just this month that the parent post is referring to. A systematic study is far more compelling than an anecdote.

              https://machinelearning.apple.com/research/gsm-symbolic

              • zmgsabst 1 day ago
                Only if there isn’t a systemic fault, eg bad prompting.

                Their errors appear to disappear when you correctly set the context from conversational to adversarial testing — and Apple is actually testing the social context and not its ability to reason.

                I’m just waiting for Apple to release their GSM-NoOp dataset to validate that; preliminary testing shows it’s the case, but we’d prefer to use the same dataset so it’s an apples-to-apples comparison. (They claim it will be released “soon”.)

              • og_kalu 2 days ago
                That study shows 4o, o1-mini and o1-preview's new scores are all within margin error on 4/5 of their new benchmarks(some even see increases). The one that isn't involves changing more than names.

                Changing names does not affect the performance of Sota models.

                • gruez 2 days ago
                  >That study very clearly shows 4o, o1-mini and o1-preview's new scores are all within margin error on 4/5 of their new benchmarks.

                  Which figure are you referring to? For instance figure 8a shows a -32.0% accuracy drop when an insignificant change was added to the question. It's unclear how that's "within the margin of error" or "Changing names does not affect the performance of Sota models".

                  • og_kalu 2 days ago
                    Table 1 in the Appendix. GSM-No-op is the one benchmark that sees significant drops for those 4 models as well (with preview dropping the least at -17%). No-op adds "seemingly relevant but ultimately inconsequential statements". So "change names, performance drops" is decidedly false for today's state of the art.
                    • gruez 2 days ago
                      Thanks. I wrongly focused on the headline result of the paper rather than the specific claim in the comment chain about "changing name, different results".
                    • TaylorAlexander 2 days ago
                      Ah, that’s a good point thanks for the correction.
            • gruez 2 days ago
              To be fair, the claim wasn't that it always produced the wrong answer, just that there exists circumstances where it does. A pair of examples where it was correct hardly justifies a "demonstrably false" response.
              • thomashop 2 days ago
                Conversely, a pair of examples where it was incorrect hardly justifies the opposite response.

                If you want a more scientific answer there is this recent paper: https://machinelearning.apple.com/research/gsm-symbolic

                • EraYaN 1 day ago
                  It kind of does though, because it means you can never trust the output to be correct. The error is a much bigger deal than it being correct in a specific case.
                  • thomashop 1 day ago
                    You can never trust the outputs of humans to be correct but we find ways of verifying and correcting mistakes. The same extra layer is needed for LLMs.
          • jklinger410 2 days ago
            This is what kind of comments you make when your experience with LLMs is through memes.
          • Workaccount2 2 days ago
            This is a relatively trivial task for current top models.

            More challenging are unconventional story structures, like a mom named Matthew with a son named Mary and a daughter named William, who is Matthew's daughter?

            But even these can still be done by the best models. And it is very unlikely there is much if any training data that's like this.

            • alexwebb2 2 days ago
              That's a neat example problem, thanks for sharing!

              For anyone curious: https://chatgpt.com/share/6722d130-8ce4-800d-bf7e-c1891dfdf7...

              > Based on traditional naming conventions, it seems that the names might have been switched in this scenario. However, based purely on your setup:

              >

              > Matthew has a daughter named William and a son named Mary.

              >

              > So, Matthew's daughter is William.

            • rileymat2 2 days ago
              How do people fair on unconventional structures? I am reminded of that old riddle involving a the mother being the doctor after a car crash.
              • adwn 2 days ago
                No idea why you've been downvoted, because that's a relevant and true comment. A more complex example would be the Monty Hall problem [1], for which even some very intelligent people will intuitively give the wrong answer, whereas symbolic reasoning (or Monte Carlo simulations) leads to the right conclusion.

                [1] https://en.wikipedia.org/wiki/Monty_Hall_problem

          • vanviegen 2 days ago
            And yet, humans, our benchmark for AGI, suffer from similar problems, with our reasoning being heavily influenced by things that should have been unrelated.

            https://en.m.wikipedia.org/wiki/Priming_(psychology)

        • _heimdall 2 days ago
          The whole design of an LLM is to consume and compress a huge space of human-generared content and use that to predict how a human would reply, one token at a time. That alone means the LLM isn't modelling anything beyond the human content it was trained on, and there is no reasoning since every prediction is based only on probabilities combined with controls similar to randomization factors used to avoid an entirely deterministic algorithm.
          • ricardobeat 2 days ago
            That’s not an accurate description. Attention / multi-head attention mechanisms allow the model to understand relationships between words far apart and their context.

            They still lack, as far as we know, a world model, but the results are already eerily similar to how most humans seem to think - a lot of our own behaviour can be described as “predict how another human would reply”.

            • thomashop 2 days ago
              When trained on simple logs of Othello's moves, the model learns an internal representation of the board and its pieces. It also models the strength of its opponent.

              https://arxiv.org/abs/2210.13382

              I'd be more surprised if LLMs trained on human conversations don't create any world models. Having a world model simply allows the LLM to become better at sequence prediction. No magic needed.

              There was another recent paper that shows that a language model is modelling things like age, gender, etc., of their conversation partner without having been explicitly trained for it

            • _heimdall 1 day ago
              Do we know for a fact that the mechanisms are actually used that way inside the model?

              My understand was that they know how the model was designed to be able to work, but that there's been very little (no?) progress in the black box problem so we really don't know much at all about what actually happens internally.

              Without better understanding of what actually happens when an LLM generates an answer I stick with the most basic answer that its simply predicting what a human would say. I could be wildly misinformed there, I don't work directly in the space and its been moving faster than I'm interested in keeping up with.

          • ChadNauseam 2 days ago
            For a lot of the content they were trained on, it seems like the easiest way to predict the next token would be to model the world or work with axioms. So how do we know that an LLM isn't doing these things internally?
            • thomashop 2 days ago
              In fact, it looks like the model is doing those things internally.

                We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato’s concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.
              
              https://arxiv.org/html/2405.07987v5
              • _heimdall 1 day ago
                Unless I misread this paper, their argument is entirely hypothetical. Meaning that the LLM is still a black box and they can only hypothesise what is going internally by viewing the output(s) and guessing at what it would take to get there.

                There's nothing wrong with a hypothesis or that process, but it means we still don't know whether models are doing this or not.

                • thomashop 1 day ago
                  Maybe I mixed up that paper with another but the one I meant to post shows that you can read something like a world model from the activations of the layers.

                  There was a paper that shows a model trained on Othello moves creates a model of the board, models the skill level of their opponent and more.

            • _heimdall 1 day ago
              Well my understanding is that there's ultimately the black box problem. We keep building these models and the output seems to get better, but we can't actually inspect how they work internally.
      • chamomeal 2 days ago
        I totally agree that they’re a local maximum and they don’t seem like a path to AGI. But they’re definitely kinda reasoning systems, in the sense that they can somewhat reason about things. The whacky process they use to get there doesn’t take away from that IMO
      • alexwebb2 2 days ago
        If you expect "the right way" to be something _other_ than a system which can generate a reasonable "state + 1" from a "state" - then what exactly do you imagine that entails?

        That's how we think. We think sequentially. As I'm writing this, I'm deciding the next few words to type based on my last few.

        Blows my mind that people don't see the parallels to human thought. Our thoughts don't arrive fully formed as a god-given answer. We're constantly deciding the next thing to think, the next word to say, the next thing to focus on. Yes, it's statistical. Yes, it's based on our existing neural weights. Why are you so much more dismissive of that when it's in silicon?

        • Techonomicon 2 days ago
          Because we still don't know how the brain really does all it does in very specific terms, so why assume to know exactly how we think?
          • alexwebb2 2 days ago
            Why is there only one valid way of producing thoughts?
        • jltsiren 2 days ago
          Finite-state machines are a limited model. In principle, you can use them to model everything that can fit in the observable universe. But that doesn't mean they are a good model for most purposes.

          The biggest limitation with the current LLMs is the artificial separation between training and inference. Once deployed, they are eternally stuck in the same moment, always reacting but incapable of learning. At best, they are snapshots of a general intelligence.

          I also have a vague feeling that a fixed set of tokens is a performance hack that ultimately limits the generality of LLMs. That hardcoded assumptions make tasks that build on those assumptions easier and seeing past the assumptions harder.

          • alexwebb2 2 days ago
            > At best, they are snapshots of a general intelligence.

            So are we, at any given moment.

        • Jensson 2 days ago
          > As I'm writing this, I'm deciding the next few words to type based on my last few.

          If so you could have written this as a newborn baby, you are determining these words based on a lifetime of experience. LLMs doesn't do that, every instance of ChatGPT is the same newborn baby while a thousand clones of you could all be vastly different.

          • thomashop 2 days ago

              We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks represent data are becoming more aligned. Next, we demonstrate convergence across data modalities: as vision models and language models get larger, they measure distance between datapoints in a more and more alike way. We hypothesize that this convergence is driving toward a shared statistical model of reality, akin to Plato’s concept of an ideal reality. We term such a representation the platonic representation and discuss several possible selective pressures toward it. Finally, we discuss the implications of these trends, their limitations, and counterexamples to our analysis.
            
            https://arxiv.org/html/2405.07987v5
      • wyldfire 2 days ago
        > It continues to astound me how much money is being dumped into these things.

        Maybe in our society there's a surprising amount of value of a "word stirrer" intelligence. Sure, if it was confident when it was right and hesitant when it was wrong it'd be much better. Maybe humans are confidently wrong often enough that an artificial version that's compendious experience to draw on is groundbreaking.

      • csomar 2 days ago
        I am pretty sure Claude 3.5 Sonnet can reason or did reason with a particular snippet of code I was working on. I am not an expert in this area but my guessing is that these neural nets (made for language prediction) are being used for reasoning. But that’s not their optimal behavior (since they are token predictor). A big jump in reasoning will happen when reasoning is off loaded to an LRM.

        Human brains are sure big but they are inefficient because a big portion of the brain is going to non-intelligence stuff like running the body internal organs, eye vision, etc…

        I do agree that the money is not well spent. They should haver recognized that we are hitting s local maximum with the current model and funding should be going to academic/theoretical instead of dump brute force.

    • jsheard 2 days ago
      > So, LLMs face a regression on their latest proposed improvement.

      Arguably a second regression, the first being cost, because COT improves performance by scaling up the amount of compute used at inference time instead of training time. The promise of LLMs was that you do expensive training once and then run the model cheaply forever, but now we're talking about expensive training followed by expensive inference every time you run the model.

      • TZubiri 2 days ago
        To be fair they also advanced in the cost aspect with other models

        gpt4o and 4o mini have a tenth and a hundredth of inference cost of gpt4 respectively

    • idiotsecant 2 days ago
      LLMs are a local maximum in the same way that ball bearings can't fly. LLM-like engines will almost certainly be components of an eventual agi-level machine.
      • FuckButtons 2 days ago
        I don’t think that’s necessarily true, that presumes that the cobbled together assortment of machine learning algorithms we have now will somehow get agi, if we need a fundamentally different way of doing things there’s no reason to assume it will use a language model at all.
      • TZubiri 2 days ago
        I agree, my bet is that they will be used for NLP, and ML debugging/analysis.
  • nisten 2 days ago
    This sounds about right from my experience getting nerdsniped by new samplers along with trying to reproduce the API middleware for the whole reflection thing, and using 4400 questions for a new benchmark is not bad given that even the well-regarded gpqa benchmark is only 3000-something questions.

    What's ... mildly infuriating here is the lack of any kind of data, code, 0 mention of github in the paper, and nothing for anyone to reproduce or find any reason in my opinion to even recommend anyone to read this thing at all. If you think that whatever you're doing in the field of LLMs won't be obsolete in 6 months you're being delusional.

    Anyway, back to the paper, it says all questions culminated to a yes or no answer... meaning theres a 50/50 chance of getting right, so does that mean the 8% drop in performance you got from testing llama 3 8b this way is more like 4% which would make it statistically insignificant? And given that the only other scientifically usueful & reproducible (non-api walled models which no one knows on how many actual llms and retrieval systems are composing that solution you're testing)models were less than that leads me to the opinion that this whole thing was just useless slop.

    So please, if you're writing a paper in LLMs, and want to seem credible, either have some type of demo thing or show the actual god damn trash code and top secret garbage data you wrote for it so people can make some kind of use of it before it goes obsolete otherwise you're just wasting everyones time.

    TL:DR. It's trash.

  • npunt 2 days ago
    "Don't overthink it" is sometimes good advice!
    • marviel 2 days ago
      I love backpropagating ideas from ML back into psychology :)

      I think it shows great promise as a way to sidestep the ethical concerns (and the reproducibility issues) associated with traditional psychology research.

      One idea in this space I think a lot about is from the Google paper on curiosity and procrastination in reinforcement learning: https://research.google/blog/curiosity-and-procrastination-i...

      Basically the idea is that you can model curiosity as a reward signal proportional to your prediction error. They do an experiment where they train an ML system to explore a maze using curiosity, and it performs the task more efficiently -- UNTIL they add a "screen" in the maze that shows random images. In this case, the agent maximizes the curiosity reward by just staring at the screen.

      Feels a little too relatable sometimes, as a highly curious person with procrastination issues :)

      • npunt 2 days ago
        "...in AI" will be the psychology equivalent of biology's "...in Mice"
      • jeezfrk 2 days ago
        "Nerd sniping"
  • alexchantavy 2 days ago
    This seems to support how thinking out loud during a coding test might make you do worse.
  • veryfancy 2 days ago
    So like dating?
  • m3kw9 2 days ago
    would be slow to use COT on simple requests like 1+1