[FeepingCreature]

> No model of the regularities of text will ever produce a language-user.

No but it will produce language-users, incidentally. Language-users are an irreducible aspect of the underlying regularity in language. Now I'm not saying that "GPT will wake up" purely from language tasks, that GPT will become a language user by being a system that picks up regularities. But for GPT to contain systems like language users, to instantiate language-users, which it has to (on some level) in order to successfully predict the next frame, is already enough to be threatening.

I know that using examples from fiction is annoying, but - purely as a rhetorical aid - consider the Enterprise computer (in Elementary, Dear Data) as GPT, and the Moriarty hologram as an embedded agent. The Enterprise computer is not conscious, but as a very powerful pattern predictor it can instantiate conscious agents "by accident", purely by completing a pattern it has learnt. It doesn't want to threaten the Enterprise, it doesn't want to not threaten the Enterprise, because it doesn't have any intentional stance. Instead, it was asked "A character that can challenge Data is ¬" and completed the sentence, as is its function.

[mjburgess]

How does the computer answer "Do you like what i'm wearing today?" ?

Well, if we say the computer is, in fact, not participating in the world with us -- it is merely predicting "the next word", then it cannot.

I am not asking for any answer to this question. I want to know what it (like a friend) actually thinks about what i'm wearing.

To do this, it would need to be a competent language user; not a word annoucer. It would, in otherwords, need to know what the language was about -- and need to be able to make a judgement of taste based on its prior experiences, etc.

I dont think our ability to misattribute a capacity of languge to things (eg., to bugs bunny) is salient -- we are fools, easily fooled. Bugs bunny doesnt exist.

In this case, the star trek computer, insofar as it actually answers the questions its asked -- is routinely depicted as being actually present in the world with us. That the show might claim "no it isnt!", or we otherwise hold this premise whilst observing that it is, is just foolishness. Bugs bunny likewise, is depicted with the premise that bugs is within his own world; this likewise, is irrelevant.

[FeepingCreature]

Well, GPT is not the sort of thing that can have a "you." But it has seen dialogues that have a "you" in it, and it knows how a "you" tends to answer. For instance, depending on context, it may be operating under a different model for the "you" agent - the sort of person who likes a red dress, or the sort of person who likes suspenders. If we assume a multimodal GPT, it's going to draw on its pattern recognition from movies and its context window for what it's previously said as "you" or what you've prompted it as in order to guess what the agent it's pattern completing for "you" would think of your dress.

In effect, I'm saying that just because GPT is not a word-user, that doesn't mean that its model of "you" - the layered system of patterns that generates its prediction for words that come after "I think your dress looks" - isn't a word-user. The "you" model, effectively, takes in sensory input, processes it, and produces output. Because the language model has learnt to complete sentences using agents as predictive patterns - because agents compress language - the you pattern acts agentic, despite the fact that the language model itself is not "committed" to this agent and will, if you reset its context window, readily switch to pattern predicting another agent.

GPT is not an agent, but GPT can predict an agent, and this is equivalent to containing it.

[mjburgess]

I dont think it is equivalent. If you assume it has the same modal properties, sure -- let's say that's plausible.

Ie., if GPT said on the occasion it was asked Q, an answer A, in a possible world W, such that this answer A was the "relevant and reasonable" answer in W -- then GPT is "doing something interesting".

Eg., if I am wearing red shoes (World W1) and it says "i like your red shoes" in W1, then that's for-sure really interesting.

My issue is that it isnt doing this; GPT is completely insensitive to what world its in and just generates an average A in reply to a world-insensitive Q.

If you take a langauge-user, eg. me, and enumerate my behaviour in all possible worlds you will get somehting like what GPT is aiming to capture. Ie., what i would say, if asked Q, in world-1, wolrd-2, world-infinity.

My capacity to answer the question in "relevant and reasonable" ways across a gegnuine infinity of possible worlds comes from actual capacities i have to obvserve, imagination, explore, question, intereact, etc. It doesnt come from being an implementation of the (Q, A, W) pattern -- which is an infintity on top of an infinity.

No model which seeks to directly implement (Q, A, W) can ever have the same properties of an actual agent. That model would be physically impossible to store. So GPT does not "contain" an agent in the sense that QAW patterns actually occur as they should.

And no route through modelling those patterns will ever produce the "agency pattern". You actually need to start with the capacities of agents themselves to generate these in the relevant situations, which is not a matter of a compressed representation of QAW possibilities -- its the very ability to imagine them peicemeal (investigate, explore, etc .)

[FeepingCreature]

I mean, how would you discover that you're in world W? If you ask "what do you think about my red shoes?" and I say "I think your red shoes are pretty", then you will say this is just me completing the pattern. But if I have no idea what shoes you're wearing, then even I, surely agreed to be an agent, could not compliment your clothing. So I'm not sure how this distinction works.

> It doesnt come from being an implementation of the (Q, A, W) pattern

Well, isn't this just a (Q, A, W, H) pattern though? You have a hidden state that you draw upon in order to map Qs onto As, in addition to the worldstate that exists outside you. But inasmuch as this hidden state shows itself in your answers, then GPT has to model it in order to efficiently compress your pattern of behavior. And inasmuch as it doesn't ever show itself in your answers, or only very rarely, it's hard to see how it can be vital to implementing agency.

And, of course, teaching GPT this multi-step approach to problem solving is just prompting it to use a "hidden" state, by creating a situation in which the normally hidden state is directly visualized. So the next step would be to allow GPT to actually generate a separate window of reasoning steps that are not directly compared against the context window being learnt, so it can think even when not prompted to. I'm not sure how to train that though.

[mjburgess]

Sure, GPT has to model H -- that's a way of putting it. However think of how the algorithm producing GPT works (and thereby how GPT models QAWH) -- it produces a set of weights which interpolate between the training data --- even if we give it QAWH as training data, implementing the same QAWH patterns would require more storage capacity than is physically possible.

I think there's a genuine ontological (practical, empirical, also) difference between how a system scales with these "inputs". In otherwords if a machine is a `A = m(Q | World, Hidden)`, and a person is a `A = p(Q | World, Hidden)` then their complexity properties *matter*.

We know that the algorithm which produces `m` does so with exponential complexity; and we know that the algorithm producing `p` doesnt. In otherwords, for a person to answer `A` in the relevant ways, does not require exponential space/time. We know that NNs are already exponential scaling in their parameters in their even fairly radically stupid solutions (ie., ones which are grossly insensitive even to W).

So whilst `m` and `p` are equivalent if all we want is an accurate mapping of `Q`-space to `A`-space, they arent equivalent in their complexity properties. This inequivalence makes `m` physically impossible, but i also think, just not intelligent.

As in, it was intelligent to write the textbook; after its written, the HDD space which stores it isnt "intelligent". Intelligence is that capacity which enables low-complexity systems to do "high-complexity" stuff. In other words, that we can map-out QAWH with physically-possible, indeed, ordinary capacities -- our-doing-that is intelligence.

I think this is a radically empirical question, rather than a merely philosophical one. No algorithm which relies on interpolation of training data will have the right properties; it just wont, as a matter of fact, answer questions correclty.

You cannot encode the whole QAWH-space in parameters. Interpolation, as a strategy, is exponential-scaling; and cannot therefore cover even a tiny fraction of the space.

Ie., if I ask "what did you think of will smith hitting christopher walken?" it is unlikely to reply, "I think you mean Chris Rock" firstly; and then if will does hit walken, to reply, "I think Walken deserved it!".

Interpolation, as a strategy, cannot deal with the infinities that counter-factuals require. We are genuinely able to perform well in an infinite number of worlds. We do that by not modelling QA pairs, at all; nor even the W-infinity.

Rather, we implement "taste, imagination, curiosity" etc. and are able to simulate (and much else) everything we need. We arent an interpolation through relevant hisotry, we are a machine direclty responsible to the local environment in ways that show a genuine deep understanding of the world and abiliyt to similate it.

This ability enables `p` to have a lower complexity than `m`, and thereby be actually intelligent.

As an empirical matter, i think you just can't build a system which actually succeeds in answering the-right-way. It isnt intelligent; but likewise, it also just doesnt work.

[FeepingCreature]

The notion that GPT "interpolates between the training data" is a widespread misconception. There is no evidence that that's what's going on. GPT seems to be capable of generalizing, in ways that let it mix features of training samples at least, and even generalize to situations that it has never seen.

It seems to me your entire argument derives from this. If GPT is not exponential, then the m/p distinction falls apart. And GPT has way too much world-knowledge, IMO, to be storing things in such a costly fashion.

Neural networks learn features, not samples. Layered networks learn features of features (of features of features...). Intelligence works because for many practical tasks, the feature recursion depth of reality is limited. For instance, we can count sheep by throwing pebbles in a bucket for every sheep that enters the pasture, because the concept of items generalizes both sheep and pebbles, and the algorithm ensures that sheep and pebbles move as one. So to come up with this idea, you only need to have enough layers to recognize sheep as items, pebbles as items, those two conceptual assignments as similar, and to notice that when two things are described by similar conceptual assignments in the counting domain, you can use a manual process that represents a count in one domain to validate the other domain. Now I don't think this is actually what our brain is literally doing when we work out this algorithm, it probably involves more visual imagination and looking at systems coevolve in our worldmodel to convince us that the algorithm works. But I also don't think that working this out on purely conceptual grounds needs all that many levels of abstraction/Transformer layers of feature meta-recognition. And once you have that, you get it.