[HN Gopher] Why do LLMs have emergent properties?
       ___________________________________________________________________
        
       Why do LLMs have emergent properties?
        
       Author : Bostonian
       Score  : 54 points
       Date   : 2025-05-08 20:07 UTC (2 hours ago)
        
 (HTM) web link (www.johndcook.com)
 (TXT) w3m dump (www.johndcook.com)
        
       | cratermoon wrote:
       | Alternate view: Are Emergent Abilities of Large Language Models a
       | Mirage? https://arxiv.org/abs/2304.15004
       | 
       | "Here, we present an alternative explanation for emergent
       | abilities: that for a particular task and model family, when
       | analyzing fixed model outputs, emergent abilities appear due to
       | the researcher's choice of metric rather than due to fundamental
       | changes in model behavior with scale. Specifically, nonlinear or
       | discontinuous metrics produce apparent emergent abilities,
       | whereas linear or continuous metrics produce smooth, continuous
       | predictable changes in model performance."
        
         | moffkalast wrote:
         | That has been a problem with most LLM benchmarks. Any test
         | that's rated in percentages tends to be logarithmic, since
         | getting from say 90% to 95% is not a linear 5% improvement but
         | probably more like a 2x or 10x improvement in practical terms,
         | since the metric is already nearly maxed out and only the
         | extreme edge cases remain that are much harder to master.
        
         | K0balt wrote:
         | A decent thought-proxy for this : powered flight.
         | 
         | An aircraft can approach powered flight without achieving it.
         | With a given amount of thrust or aerodynamic characteristics,
         | the aircraft will weigh dynamic_weight=(static_weight - x)
         | where x is a combination of the aerodynamic characteristics and
         | the amount of thrust applied.
         | 
         | In no case where dynamic_weight>0 will the aircraft fly, even
         | though it exhibits characteristics of flight, I.e the transfer
         | of aerodynamic forces to counteract gravity.
         | 
         | So while it progressively exhibits characteristics of flight,
         | it is not capable of any kind of flight at all until the
         | critical point of dynamic_weight<0. So the enabling
         | characteristics are not "emergent", but the behavior is.
         | 
         | I think this boils down to a matter of semantics.
        
           | scopemouthwash wrote:
           | "Thought-proxy"?
           | 
           | I think the word you're looking for is "analogy".
        
         | foobarqux wrote:
         | The author himself explicitly acknowledges the paper but the
         | incomprehensibly ignores it ("Even so, many would like to
         | understand, predict, and even facilitate the emergence of these
         | capabilities."). It's like saying "some say [foo] doesn't exist
         | but even so many would like to understand [foo]". It's
         | incoherent.
        
           | autoexec wrote:
           | No point in letting facts get in the way of an entire article
           | I guess.
        
         | jebarker wrote:
         | Yes, this paper is under-appreciated. The point is that we as
         | humans decide what constitutes a given task we're going to set
         | as a bar and it turns out that statistical pattern matching can
         | solve many of those tasks to a reasonable level (we also get to
         | define "reasonable") when there's sufficient scale of
         | parameters and data, but that tip-over point is entirely
         | arbitrary.
        
         | Al-Khwarizmi wrote:
         | The continuous metrics the paper uses are largely irrelevant in
         | practice, though. The sudden changes appear when you use
         | metrics people actually care about.
         | 
         | To me the paper is overhyped. Knowing how neural networks work,
         | it's clear that there are going to be underlying properties
         | that vary smoothly. This doesn't preclude the existence of
         | emergent abilities.
        
       | chasing0entropy wrote:
       | There are eerie similarities in radiographs of LLM inference
       | output and mammalian EEGs. I would be surprised not see latent
       | and surprisingly complicated characteristics become apparent as
       | context and recursive algorithms grow larger.
        
         | aeonik wrote:
         | What graphs are you talking about? I've never heard of LLM
         | radiographs, and my searches are coming up empty.
        
       | unsupp0rted wrote:
       | Isn't "emergent properties" another way to say "we're not very
       | good at understanding the capabilities of complex systems"?
        
         | seliopou wrote:
         | Yes, it's a cop-out and smells mostly of dualism:
         | https://plato.stanford.edu/entries/properties-emergent/
        
         | theobreuerweil wrote:
         | I understood it to mean properties of large-scale systems that
         | are not properties of its components. Like in thermodynamics:
         | zooming in to a molecular level, you can reverse time without
         | anything seeming off. Suddenly you get a trillion molecules and
         | things like entropy appear, and time is not reversible at all.
        
         | tunesmith wrote:
         | It just means they haven't modeled the externalities. A plane
         | on the ground isn't emergent. In the air it is, at least until
         | you perfectly model weather, which you can't do, so its
         | behavior is emergent. But I think a plane is also a good
         | comparison because it shows that you can manage it; we don't
         | have to perfectly model weather to still have fairly
         | predictable air travel.
        
         | esafak wrote:
         | Not quite. Complex systems can exhibit macroscopic properties
         | not evident at microscopic scales. For example, birds self
         | organize into flocks, an emergent phenomenon, visible to the
         | untrained eye. Our understanding of how it happens does not
         | change the fact that it does.
         | 
         | There is a field of study for this called statistical
         | mechanics.
         | 
         | https://ganguli-gang.stanford.edu/pdf/20.StatMechDeep.pdf
        
           | HPsquared wrote:
           | Very interesting crossover!
        
           | anonymars wrote:
           | See also: stigmergy
        
         | bunderbunder wrote:
         | I've always understood it more to mean, "phenomena that happen
         | due to the interactions of a system's parts without being
         | explicitly encoded into their individual behavior." Fractal
         | patterns in nature are a great example of emergent phenomena. A
         | single water molecule contains no explicit plan for how to get
         | together with its buddies and make spiky hexagon shapes when
         | they get cold.
         | 
         | And I've always understood talking about emergence as if it
         | were some sort of quasi-magical and unprecedented new feature
         | of LLMs to mean, "I don't have a deep understanding of how
         | machine learning works." Emergent behavior is the _entire
         | point_ of artificial neural networks, from the latest SOTA
         | foundation model all the way back to the very first tiny little
         | multilayer perceptron.
        
           | andy99 wrote:
           | Emergence in the context of LLMs is really just us learning
           | that "hey, you don't actually need intelligence to do <task>,
           | turns out it can be done using a good enough next token
           | predictor. We're basically learning what intelligence isn't
           | as we see some of the things these models can do.
           | 
           | I always understood this to be the initial framing, e.g. in
           | the Language Models are Few Shot Learners paper but then it
           | got flipped around.
        
             | dmd wrote:
             | Or maybe you need intelligence to be a good enough next
             | token predictor. Maybe the thing that "just" predicts the
             | next token can be called "intelligence".
        
             | HPsquared wrote:
             | Or more generally "fitting a model to data".
        
             | Workaccount2 wrote:
             | The challenge there would be showing that humans have this
             | thing called intelligence. You yourself are just outputting
             | ephemeral actions that rise out of your subconscious. We
             | have no idea what that system feeding our output looks like
             | (except it's some kind of organic neural net) and hence
             | there isn't really a basis for discriminating what is and
             | isn't intelligent besides "if it solves problems, it has
             | some degree of intelligence"
        
               | PaulDavisThe1st wrote:
               | To return an old but still good analogy ...
               | 
               | If you want to understand how birds fly, the fact that
               | planes also fly is near useless. While a few common
               | aerodynamic principles apply, both types of flight are so
               | different from each other that you do not learn very much
               | about one from the other.
               | 
               | On the other hand, if your goal is just "humans moving
               | through the air for extended distances", it doesn't
               | matter at all that airplanes do not fly the way birds do.
               | 
               | And then, on the generated third hand, if you need the
               | kind of tight quarters maneuverability that birds can do
               | in forests and other tangled spaces, then the way our
               | current airplanes fly is of little to no use at all, and
               | you're going to need a very different sort of technology
               | than the one used in current aircraft.
               | 
               | And on the accidentally generated fourth hand, if your
               | goal is "moving very large mass over very long distance",
               | the the mechanisms of bird flight are likely to be of
               | little utility.
               | 
               | The fact that two different systems can be described in a
               | similar way (e.g. "flying") doesn't by itself tell you
               | that they are working in remotely the same way or capable
               | of the same sorts of things.
        
               | Workaccount2 wrote:
               | I think that many birds gets too sensitive when
               | discussing what "flight" means, heh
        
             | prats226 wrote:
             | If we use some metric as proxy for intelligence, emergence
             | simply means a non-linear sudden change in that metric?
        
         | gond wrote:
         | Not at all. Here is an analogy: A car is a system which brings
         | you from point A to B. No part of the car can bring you from
         | point A to B. Not the seats, the wheels, not the frame, not
         | even the motor. If you put the motor on a table, it won't move
         | one bit. The car, as a system, however does. The emergent
         | property of a car, seen as a system, is that it brings you from
         | one location to another.
         | 
         | A system is the product of the interaction of its parts. It is
         | not the sum of the behaviour of its parts. If a system does not
         | exhibit some form of emergent behaviour, it is not a system,
         | but something else. Maybe an assembly.
        
           | unsupp0rted wrote:
           | That sounds like semantics.
           | 
           | If putting together a bunch of X's in a jar always makes the
           | jar go Y, then is Y an emergent property?
           | 
           | Or we need to better understand why a bunch of X's in a jar
           | do that, and then the property isn't emergent anymore, but
           | rather the natural outcome of well-understood X's in a well-
           | understood jar.
        
             | gond wrote:
             | Ah. Not semantics, that is cybernetics and systems theory.
             | 
             | As in your example: If a bunch of x in a jar leads to the
             | jar tipping over, it is not emergent. That's just cause and
             | effect. Problem to start with is that the jar containing x
             | is not even a system in the first place, emergence as a
             | concept is not applicable here.
             | 
             | There may be a misunderstanding on your side of the term
             | emergence. Emergence does not equal non-understanding or
             | some spooky-hooky force coming from the unknown. We
             | understand the functions of the elements of a car quite
             | well. The emergent behaviour of a car was intentionally
             | brought about by massive engineering.
             | 
             | Reductionism does not lead to an explaining-away of
             | emergence.
        
           | cluckindan wrote:
           | https://en.wikipedia.org/wiki/Emile_Leray
        
             | tinix wrote:
             | haha cool!
             | 
             | turned the car into a motorcycle.
             | 
             | here's an article with a photo for anyone who's interested:
             | https://archive.is/y96xb
        
         | jfengel wrote:
         | It's more specific than that. Most complex systems just produce
         | noise. A few complex systems produce behavior that we perceive
         | as simple. This is surprising, and gets the name "emergent".
        
       | Michelangelo11 wrote:
       | How could they not?
       | 
       | Emergent properties are unavoidable for any complex system and
       | probably exponentially scale with complexity or something (I'm
       | sure there's an entire literature about this somewhere).
       | 
       | One good instance are spandrels in evolutionary biology. The
       | wikipedia article is a good explanation of the subject:
       | https://en.m.wikipedia.org/wiki/Spandrel_(biology)
        
       | OtherShrezzing wrote:
       | It feels like this can be tracked with addition. Humans expect
       | "can do addition" is a binary skill, because humans either can or
       | cannot add.
       | 
       | LLMs approximate addition. For a long time they would produce hot
       | garbage. Then after a lot of training, they could sum 2 digit
       | numbers correctly.
       | 
       | At this point we'd say "they can do addition", and the property
       | has emerged. They have passed a binary skill threshold.
        
         | skydhash wrote:
         | Or you could cobble up a small electronic circuit or a
         | mechanical apparatus and have something that can add numbers.
        
       | me3meme wrote:
       | Metaphor: finding a path from a initial point to a destination in
       | a graph. As the number of parameters increases one can expect the
       | LLM to be able to remember how to go from one place to another
       | and in the end it should be able to find a long path. This can be
       | an emergent property since with less parameters the LLM could not
       | be able to find the correct path. Now one has to find what kind
       | of problems this metaphor is a good model of.
        
       | andy99 wrote:
       | I didn't follow entirely on a fast read, but this confused me
       | especially:                 The parameter count of an LLM defines
       | a certain bit budget. This bit budget must be spread across many,
       | many tasks
       | 
       | I'm pretty sure that LLMs, like all big neural networks, are
       | massively under-specified, as in there are way more parameters
       | than data to fit (understanding the training data set is bigger
       | than the size of the model, but the point is the same loss can be
       | achieved with many different combinations of parameters).
       | 
       | And I think of this underspecification as the reason neural
       | networks extrapolate cleanly and this generalize.
        
         | vonneumannstan wrote:
         | This doesn't seem right and most people recognize that
         | 'neurons' encode for multiple activations. https://transformer-
         | circuits.pub/2022/toy_model/index.html
        
       | lordnacho wrote:
       | What seems a bit miraculous to me is, how did the researchers who
       | put us on this path come to suspect that you could just throw
       | more data and more parameters at the problem? If the emergent
       | behavior doesn't appear for moderate sized models, how do you
       | convince management to let you build a huge model?
        
         | educasean wrote:
         | You might appreciate this article:
         | https://www.quantamagazine.org/when-chatgpt-broke-an-entire-...
        
         | TheCoreh wrote:
         | This is perhaps why it took us this long to get to LLMs, the
         | underlying math and ideas were (mostly) there, and even if the
         | Transformer as an architecture wasn't ready yet, it wouldn't
         | surprise me if throwing sufficient data/compute at a worse
         | architecture wouldn't also produce comparable emergent behavior
         | 
         | There needed to be someone willing to try going big at an
         | organization with sufficient idle compute/data just sitting
         | there, not a surprise it first happened at Google.
        
           | hibikir wrote:
           | But we got here step by step, as other interesting use cases
           | came up by using somewhat less compute. Image recognition,
           | early forms of image generation, AlphaGo, AlphaZero for
           | chess. All earlier forms of deep neural networks that are
           | much more reasonable than training a top of the line LLM
           | today, but seemed expensive at the time. And ultimately a lot
           | of this also comes from the hardware advancements and the
           | math advancements. If you took classes neural networks in the
           | 1990s, you'd notice that they mostly talked about 1 or 2
           | hidden layers, and not all that much focus on the math to
           | train large networks, precisely because of how daunting the
           | compute costs were for anything that wasn't a toy. But then
           | came video card hardware, and improvements to use it to do
           | gradient descent, making going past silly 3 layer networks
           | somewhat reasonable.
           | 
           | Every bet makes perfect sense after you consider how
           | promising the previous one looked, and how much cheaper the
           | compute was getting. Imagine being tasked to train an LLM in
           | 1995: All the architectural knowledge we have today and a
           | state-level mandate would not have gotten all that far. Just
           | the amount of fast memory that we put to bear wouldn't have
           | been viable until relatively recently.
        
         | prats226 wrote:
         | I don't think model sizes increased suddenly, there might not
         | be emergent properties for certain tasks at smaller scales but
         | there was improvement at slower rate for sure. Competition to
         | improve that metric albeit at lower pace led to slow increase
         | in model sizes and by chance led to emergence the way its
         | defined in paper?
        
         | Al-Khwarizmi wrote:
         | While GPT-2 didn't show emergent abilities, it did show
         | improved accuracy on various tasks with respect to GPT-1. At
         | that point, it was clear that scaling made sense.
         | 
         | In other words, no one expected GPT-3 to suddenly start solving
         | tasks without training as it did, but it was expected to be
         | useful as an incremental improvement to what GPT-2 did. At the
         | time, GPT-2 was seeing practical use, mainly in text generation
         | from some initial words - at that point the big scare was about
         | massive generation of fake news - and also as a model that one
         | could fine-tune for specific tasks. It made sense to train a
         | larger model that would do all that better. The rest is
         | history.
        
       | waynecochran wrote:
       | Since gradient descent converges on a local minima, would we
       | expect different emergent properties with different
       | initialization of the weights?
        
         | jebarker wrote:
         | Not significantly, as I understand it. There's certainly
         | variation in LLM abilities with different initializations but
         | the volume and content of the data is a far bigger determinant
         | of what an LLM will learn.
        
           | waynecochran wrote:
           | So there is an "attractor" that different initializations end
           | up converging on?
        
             | andy99 wrote:
             | Different initialization converge to different places, e.g
             | https://arxiv.org/abs/1912.02757
             | 
             | For LLMs (as with other models), many local optima appear
             | to support roughly the same behavior. This is the idea of
             | the problem being under-specified ie many more equations
             | than unknowns so there are many ways to get the same
             | result.
        
       | juancn wrote:
       | I always wondered if the specific dimensionality of the layers
       | and tensors has a specific effect on the model.
       | 
       | It's hard to explain, but higher dimensional spaces have weird
       | topological properties, not all behave the same way and some
       | things are perfectly doable in one set of dimensions while for
       | others it just plain doesn't work (e.g. applying surgery on to
       | turn a shape into another).
        
         | etrautmann wrote:
         | How is topology specifically related to emergent capabilities
         | in AI?
        
       | scopemouthwash wrote:
       | The authors haven't demonstrated emergence of LLMs. If I write a
       | piece of code and it does what I programmed it to do that's not
       | emergence. LLMs aren't doing anything unexpected yet. I think
       | that's the smell test because emergence is still subjective.
        
         | IshKebab wrote:
         | They weren't trying to demonstrate it. They were explaining why
         | it might not be surprising.
        
       | teekert wrote:
       | Perhaps we should ask: Why do humans pick arbitrary points on a
       | continuum beyond which things are labeled "emergent"?
        
       | nthingtohide wrote:
       | What do you think about this analogy?
       | 
       | A simple process produces a Mandelbrot set. A simple process
       | (loss minimization through gradient descent) produces LLMs. So
       | what plays the role of 2D-plane or dense point grid in the case
       | of LLMs? It is the embeddings, (or ordered combinations of
       | embeddings ) which are generated after pre-training. In case of a
       | 2D plan, the closeness between two points is determined by our
       | numerical representation schema. But in case of embeddings, we
       | learn the 2D-grid of words (playing the role of points) by
       | looking at how the words are getting used in corpus
       | 
       | The following is a quote from Yuri Manin, an eminent
       | Mathematician.
       | 
       | https://www.youtube.com/watch?v=BNzZt0QHj9U Of the properties of
       | mathematics, as a language, the most peculiar one is that by
       | playing formal games with an input mathematical text, one can get
       | an output text which seemingly carries new knowledge. The basic
       | examples are furnished by scientific or technological
       | calculations: general laws plus initial conditions produce
       | predictions, often only after time-consuming and computer-aided
       | work. One can say that the input contains an implicit knowledge
       | which is thereby made explicit.
       | 
       | I have a related idea which I picked up from somewhere which
       | mirrors the above observation.
       | 
       | When we see beautiful fractals generated by simple equations and
       | iterative processes, we give importance to only the equations,
       | not to the cartesian grid on which that process operates.
        
       | RigelKentaurus wrote:
       | I'm not a techie, so perhaps someone can help me understand this:
       | AFAIK, no theoretical computer scientist predicted emergence in
       | AI models. Doesn't that suggest that the field of theoretical
       | computer science (or theoretical AI, if you will) is suspect?
       | It's like Lord Kelvin saying that heavier-than-air flying
       | machines are impossible a decade before the Wright brothers'
       | first flight.
        
         | waynecochran wrote:
         | https://hai.stanford.edu/news/ais-ostensible-emergent-abilit...
        
         | xboxnolifes wrote:
         | Has emergent behavior ever been predicted prior to it being
         | observed in other theoretical fields?
        
           | tinix wrote:
           | emergent behavior is common in all large systems.
           | 
           | it doesn't seem that surprising to me.
        
         | lutusp wrote:
         | > Doesn't that suggest that the field of theoretical computer
         | science (or theoretical AI, if you will) is suspect?
         | 
         | Consider the story of Charles Darwin, who knew evolution
         | existed, but who was so afraid of public criticism that he
         | delayed publishing his findings so long that he nearly lost his
         | priority to Wallace.
         | 
         | For contrast, consider the story of Alfred Wegener, who
         | aggressively promoted his idea of (what was later called) plate
         | tectonics, but who was roundly criticized for his radical idea.
         | By the time plate tectonics was tested and proven, Wegener was
         | long gone.
         | 
         | These examples suggest that, in science, it's not the claims
         | you make, it's the claims you prove with evidence.
        
         | chasd00 wrote:
         | I'm not even clear on the AI def of "emergent behavior". The AI
         | crowd mixes in terms and concepts from biology to describe
         | things that are dramatically more simple. For example, using
         | "neuron" to really mean a formula calculation or function.
         | Neurons are a lot more than that and not even understood
         | completely to begin with however developers use the term as if
         | they have neurons implemented in software.
         | 
         | Maybe it's a variation of the "assume a frictionless spherical
         | horse" problem but it's very confusing.
        
       | interstice wrote:
       | The bag of heuristics thing is interesting to me, is it not
       | conceivable that a NN of a certain size trained only on math
       | problems would be able to wire up what amounts to a calculator?
       | And if so, could that form part of a wider network, or is I/O
       | from completely different modalities not really possible in this
       | way?
        
       | anon373839 wrote:
       | I remain skeptical of emergent properties in LLMs in the way that
       | people have used that term. There was a belief 3-4 years ago that
       | if you just make the models big enough, they magically acquire
       | intelligence. But since then, we've seen that the models are
       | actually still pretty limited by the training data: like other ML
       | models, they interpolate well between the data they've been
       | trained on, but they don't generalize well beyond it. Also, we
       | have seen models that are 50-100x smaller now exhibit the same
       | "emergent" capabilities that were once thought to require
       | hundreds of billions of parameters. I personally think the
       | emergent properties really belong to the data instead.
        
         | andy99 wrote:
         | Yes, deep learning models only interpolate, and essentially
         | represent an effective way of storing data labeling effort.
         | Doesn't mean they're not useful, just not what tech adjacent
         | promoters want people to think.
        
           | john-h-k wrote:
           | > Yes, deep learning models only interpolate
           | 
           | What do you mean by this? I don't think the understanding of
           | LLMs is sufficient to make this claim
        
             | andy99 wrote:
             | An LLM is a classifier, there is lots of research into how
             | deep learning classifiers work, that I haven't seen
             | contradicted when applied to LLMs.
        
         | gond wrote:
         | Interesting. Is there a quantitative threshold to emergence
         | anyone could point at with these smaller models? Tracing the
         | thoughts of a large language model is probably the only way to
         | be sure, or is it?
        
       | gyomu wrote:
       | The reasoning in the article is interesting, but this struck me
       | as a weird example to choose:
       | 
       | > "The real question is how can we predict when a new LLM will
       | achieve some new capability X. For example, X = "Write a short
       | story that resonates with the social mood of the present time and
       | is a runaway hit"
       | 
       | Framing a capability as something that is objectively measurable
       | ("able to perform math on the 12th grade level", "able to write a
       | coherent, novel text without spelling/grammar mistakes") makes
       | sense within the context of what the author is trying to
       | demonstrate.
       | 
       | But the social proof aspect ("is a runaway hit") feels orthogonal
       | to it? Things can be runaway hits for social factors
       | independently of the capability they actually represent.
        
       | samirillian wrote:
       | *Do
        
       ___________________________________________________________________
       (page generated 2025-05-08 23:00 UTC)