[wruza]

You can prove that LLMs can reason by simply giving it a novel problem where no data exists and having it solve that problem

They scan a hyperdimensional problem space whose facetness and capacity a single human is unable to comprehend. But there potentially exist a slice that corresponds to a problem that is novel to a human. LLMs are completely alien to us both in capabilities and technicalities, so talking about whether they can reason makes as much sense as if you replaced “LLMs” with “rainforests” or “antarctica”.

[ninetyninenine]

Reasoning is an abstract term. It doesn’t need to be similar to human reasoning. It just needs to be able to arrive at the answer through a process.

Clearly we used the term reasoning for many varied techniques. The term doesn’t narrow to specifically one form of “human” like reasoning only.

[wruza]

Oh, that is true. "It" doesn't have to do human reasoning, at all.

But we have to at least define "reasoning" for the given manifestation of "it". Otherwise it's just birdspeak. Because reasoning is "the action of thinking about something in a logical, sensible way", which has to happen somewhere if not finger-pointable, then at least somehow scannable or otherwise introspectable. Otherwise it's yet another omnidude in the sky who made it all so that you cannot see him, but there will be hints if you believe.

Anyway, we have to talk something specific, not handwavy. Even if you prove that they CAN reason for some definition of it, both the proof and the definition must have some predictive/scientific power, otherwise they are as useless as nil thought about it.

For example, if you prove that the reasoning is somehow embedded as a spatial in-network set of dimensions rather than in-time, wouldn't that be literally equivalent to "it just knows the patterns"? What would that term substitution actually achieve?

[ninetyninenine]

Well no. If you create a machine that produces output indistinguishable from the output of things we "know" can "reason" aka "humans". Then I would call that reasoning.

If the output has a low probability of occuring by random chance then it must be reason.

>For example, if you prove that the reasoning is somehow embedded as a spatial in-network set of dimensions rather than in-time, wouldn't that be literally equivalent to "it just knows the patterns"? What would that term substitution actually achieve?

I mean, this is a method many humans use to reason themselves.

[wruza]

A side effect of this is that a zip.exe that unzips a zip into a book that contains text indistiguishable from the output of a human must reason too.

From what I can see, you’re only massaging semantics. That is uninteresting.

[ninetyninenine]

No. I clearly said it must output novel things that aren’t part of the input.

In your example the book is the training data or aka the input.

[wruza]

Agreed, that was a wrong example.