Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
Yes, it’s a cop-out and smells mostly of dualism: https://plato.stanford.edu/entries/properties-emergent/
Why do LLMs have emergent properties?
11–20 of 121 posts
Re: Why do LLMs have emergent properties?
#12Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
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.
Re: Why do LLMs have emergent properties?
#13Alternate 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…
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.
Re: Why do LLMs have emergent properties?
#14Metaphor: 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.
Re: Why do LLMs have emergent properties?
#15I 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
And I think of this underspecification as the reason neural networks extrapolate cleanly and this generalize.
Re: Why do LLMs have emergent properties?
#16Isn't "emergent properties" another way to say "we're not very good at understanding the capabilities of complex systems"?
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.
Re: Why do LLMs have emergent properties?
#17Alternate 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…
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.
No point in letting facts get in the way of an entire article I guess.
Re: Why do LLMs have emergent properties?
#18Isn'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.
Re: Why do LLMs have emergent properties?
#19There 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.
What graphs are you talking about? I've never heard of LLM radiographs, and my searches are coming up empty.
Re: Why do LLMs have emergent properties?
#20I 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 i…
This doesn't seem right and most people recognize that 'neurons' encode for multiple activations. https://transformer-circuits.pub/2022/toy_model/index.html