[anonymoushn]

It's about the immutability of the network at runtime. But I really don't think this is a big deal. General-purpose computers are immutable after they are manufactured, but can exhibit a variety of useful behaviors when supplied with different data. Human intelligence also doesn't rely on designing and manufacturing revised layouts for the nervous system (within a single human's lifetime, for use by that single human) to adapt to different settings. Is the level of mutability used by humans substantially more expressive than the limits of in-context learning? what about the limits of more unusual in-context learning techniques that are register-like, or that perform steps of gradient descent during inference? I don't know of a good argument that all of these techniques used in ML are fundamentally not expressive enough.

[mgraczyk]

LLMs, considered as a function of input and output, are not immutable at runtime. They create tokens that change the function when it is called again. That breaks most theoretical arguments

[anonymoushn]

Sure. Another view is that an LLM is an immutable function from document-prefixes to next-token distributions.

[mgraczyk]

But that view is wrong, the model outputs multiple tokens.

The right alternative view is that it's an immutable function from prefixes to a distribution over all possible sequences of tokens less than (context_len - prefix_len).

There are no mutable functions that cannot be viewed as immutable in a similar way. Human brains are an immutable function from input sense-data to the combination (brain adaptation, output actions). Here "brain adaptation" doing a lot of work, but so would be "1e18 output tokens". There is much more information contained within the latter