Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why do LLMs have emergent properties?

johndcook.com

Post reply on HN
Print view View original

31–40 of 121 posts

Re: Why do LLMs have emergent properties?

#31

Post by scopemouthwash »

K0balt wrote: post #6
cratermoon wrote: post #2

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…

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 characterist…

“Thought-proxy”?

I think the word you’re looking for is “analogy”.

Re: Why do LLMs have emergent properties?

#33

Post by dmd »

andy99 wrote: post #29
bunderbunder wrote: post #25

Earlier quoted context omitted.

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 a…

Emergence in the context of LLMs is really just us learning that "hey, you don't actually need intelligence to do , 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…

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”.

Re: Why do LLMs have emergent properties?

#34

Post by HPsquared »

andy99 wrote: post #29
bunderbunder wrote: post #25

Earlier quoted context omitted.

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 a…

Emergence in the context of LLMs is really just us learning that "hey, you don't actually need intelligence to do , 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…

Or more generally "fitting a model to data".

Re: Why do LLMs have emergent properties?

#35

Post by HPsquared »

esafak wrote: post #18
unsupp0rted wrote: post #4

Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?

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

Very interesting crossover!

Re: Why do LLMs have emergent properties?

#36

Post by hibikir »

TheCoreh wrote: post #27
lordnacho wrote: post #21

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?

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 si…

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.

Re: Why do LLMs have emergent properties?

#37

Post by gond »

unsupp0rted wrote: post #4

Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?

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.

Re: Why do LLMs have emergent properties?

#38

Post by unsupp0rted »

gond wrote: post #37
unsupp0rted wrote: post #4

Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?

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…

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.

Re: Why do LLMs have emergent properties?

#40

Post by cluckindan »

gond wrote: post #37
unsupp0rted wrote: post #4

Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?

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…

https://en.wikipedia.org/wiki/Emile_Leray
Post reply on HN