There are substantial works already showing reasoning capabilities in GPT-4, which show that these models do reason extremely well - near human performance for many causal reasoning tasks. (1)
Additionally, there is a mathematical proof that these systems align with dynamic programming, and therefore can do algorithmic reasoning. (2,3)
is GPT4 a graph neural network? also, isn't it training time and data dependent how big (how many tokens) a problem it can tackle?
so it's great that it can reason better than humans on small-medium probems already well trained for, but so far Transformers are not reasoning (not doing causal graph analysis, or not even doing zero order logic), they are eerily well writing text that has the right keywords. and of course it's very powerful and probably will be useful for many applications.
They are GNNs with attention as the message passing function and additional concatenated positional embeddings. As for reasoning, these are not quite 'problems well-trained for', in the sense that they're not in the training data. But they are likely problems that have some abstract algorithmic similarity, which is the point.
I'm not quite sure what you mean that they cannot do causal graph analysis, since that was one of many different tasks provided in the various different types of reasoning studies in the paper I mentioned. In fact it may have been the best performing task. Perhaps try checking the paper again - it's quite a lot of experiments and text, so it's understandable to not ingest all of it quickly.
In addition, if you're interested in seeing further evidence of algorithmic reasoning capabilities occurring in transformers, Hattie Zhou has a good paper on that as well. https://arxiv.org/pdf/2211.09066.pdf
The story is really not shaping up to be 'stochastic parrots' if any real deep analysis is performed. The only way that I see someone could have such a conclusion is if they are not an expert in the field, and simply glance at the mechanics for a few seconds and try to ham handedly describe the system (hence the phrase: "it just predicts next token"). Of course, this is a bit harsh, and I don't mean to suggest that these systems are somehow performing similar brain-like reasoning mechanisms (whatever that may mean) etc, but stating that they cannot reason (when there is literature on the subject) because 'its just statistics' is definitely not accurate.
I mean the ANN in the inference stage when run does not draw up a nice graph, doesn't calculate weights, doesn't write down pretty little Bayesian formulas, it does whatever is encoder in the matrices-innerproduct-context.
And it's accurate in a lot of cases (because there's sufficient abstract similarity in the training data), and that's what I meant by "of course it'll likely be useful in many cases".
At least this is my current "understanding", I haven't had time to dig into the papers unfortunately. Thanks for the further recommendation!
What seems very much missing is characterizing the reasoning that is going on. Its limitations, functional dependencies, etc.
I never said that it does. I was pointing out a logical flaw in that person's argument. Also, why are the creators of GPT-4 authorities on what does or doesn't count as reasoning?
It’s suspect until it’s demonstrated. Once someone has demonstrated it, counterexamples are meaningless.
I claim I can juggle. I pick up three tennis balls and juggle them. You hand me three basketballs. I try and fail. My original claim, that I can juggle, still stands.
I disagree -- that would disprove your claim, as your claim was too broad. Same if they handed you chainsaws or elephants, or seventy-two tennis balls.
The more correct claim is you can juggle [some small number of items with particular properties].
Normal English implies that you can do something, not everything. It’s an any versus all distinction, and all is totally unreasonable except for the most formal circumstances.
“Can you ride a bike?”
“Yeah.”
“Prove it. Here I have the world’s smallest bicycle.” <- this person is not worth your time and attention.
It can't even count reliably. And this is a computer, not a human. That is one of the simplest things a computer should be able to do. It can't count because it doesn't know what counting is, not because it's unreliable in the way a human would be when counting. You cannot reason if you do not understand the concepts you are working with. The result is not the measure of success here, because it is good at mimicking, but when it fails at such a basic computing task, you can reasonably conclude it has no idea what it's doing.
A child may not be able to count, because they don't yet understand the concept, but may be able to reason at a more basic level, yes. But GPT has ingested most of the books in the world and the entire internet. So if it hasn't learned to count, or what counting is by now, what is going to change? A child can learn the concept, GPT cannot. It doesn't understand concepts at all, it only seems like it does because the output is so close to what beings that do understand concepts generate themselves, and it's mimicking that.
It can't count because it doesn't know what counting is. Otherwise it would be able to count like a computer can. After ingesting all the literature in the world, why can't it count yet?
It can, just not very well. Often the issue is people have it count letters and words but those aren’t the abstractions or deals with. It would be like if I told you to pick up the ball primarily reflecting 450nm light and called you colorblind if you couldn’t do it.
GPT is built on a computer. It is not a computer itself. I am made of cells, but I am not able to perform mitosis.
It’s also very capable of offloading counting tasks, since computers are so good at that. Just suggest it format things in code and evaluate it.
Here’s an example of it counting. I’m pretty confident it’s never seen this exact problem before.
How many fruits are in this list? banana, hammer, wrench, watermelon, screwdriver, pineapple, peach
There are 4 fruits in the list you provided: banana, watermelon, pineapple, and peach. The other items are tools, not fruits.
It's not counting, it's just outputting something that is likely to sound right. The reason it can't count is that it doesn't know that it should run a counting algorithm when you ask it to count, or what a counting algorithm is. There is no reason why an AI should not be able to run an algorithm. Coming up with appropriate algorithms and running them is one definition of AIs. This is not an AI. It is an algorithm itself but it cannot create or run algorithms, though it can output things that look like them. The "algorithms" it outputs are not even wrong, correctness and truth is orthogonal to it's output and without that you don't have real intelligence.
How does it come up with comprehensible sentences that make logical sense about everyday things without understanding what these things are in the real world or even understanding what logic is? I don't have a stack trace for you, but if you want to hang on "the proof's in the pudding" and say the output is evidence for what it's doing, here's Chat GPT's output to your question:
There are two fruits in this list: banana and watermelon.
So what is the difference between GPT 4 and Chat GPT? Is GPT 4 all of a sudden running a counting algorithm over the appropriate words in the sentence because it understands that's what it needs to do to get the correct answer? Can anyone explain how you would get from whatever Chat GPT is doing to that by the changes to GPT 4? And more to the point, how does Chat GPT get to the answer 2 without counting? Apparently somehow, because if it can't even count to 4, I'm not sure how you could call whatever it's doing 'counting'.
> How does it come up with comprehensible sentences that make logical sense about everyday things without understanding what these things are in the real world or even understanding what logic is?
This is begging the question.
> Can anyone explain how you would get from whatever Chat GPT is doing to that by the changes to GPT 4?
I don't know. I can't explain how a 2-year-old can't count but an 8-year-old can, either. 3.5 generally can't count[0]. 4 generally can.
You've really sidestepped the question. I suggest you seriously consider it. What's the difference between something that looks like it's counting versus actually counting when it comes to data it's never seen before?
Thanks for discussing this with me.
[0] Add "Solve this like George Polya" to any problem and it will do a better job. When I do that, it's able to get to 4.
> I can juggle at all; I can juggle at least some things
and the basketball case is only a counterexample to the much stronger claim
> I can juggle anything
But the argument about AIs reasoning has little to do with such examples, because juggling is about the ability to complete the task alone. When it comes to reasoning there are questions about authenticity that don't have analogs I'm determine whether a person can juggle.
What would “not alone” mean? Do you think someone is passing it the answers? Of course it was trained, but that’s like cheating on a test by reading the material so you can keep a cheat sheet in your brain.
