Earlier quoted context omitted.
There are adults who can't count as well as ChatGPT.
Ok, but how does that change the argument?
Inability to count does not prove inability to reason.
It's not just statistics: GPT-4 does reason
91–100 of 101 posts
Re: It's not just statistics: GPT-4 does reason
#92Earlier quoted context omitted.
So, I just tried this. I pasted 60 letter A's into GTP4 and asked it to count, it got it wrong, but I repeatedly said "count again" and nothing else, so as to not give it any hints. Here's GTP4's guesses along the way as I repeatedly said "count again". 69, 50, 100, 70, 68, 60, 60, 60, 60 (GTP gathered its own guesses into this list for me BTW) It seems if GTP is given "attention" enough, it can do the counting. But…
Aside: I've become so overexposed to the acronym "GPT" from months of completely breathless hype that I'm taken aback whenever I see it consistently misspelled as e.g. GTP. Feels like the equivalent of seeing someone inexplicably write about "chainblock technology."
I've been corrected.
Re: It's not just statistics: GPT-4 does reason
#93Earlier quoted context omitted.
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 cour…
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 o…
> they cannot do causal graph analysis
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.
Re: It's not just statistics: GPT-4 does reason
#94Earlier quoted context omitted.
Ok, but how does that change the argument?
Inability to count does not prove inability to reason.
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?
Re: It's not just statistics: GPT-4 does reason
#95Earlier quoted context omitted.
Inability to count does not prove inability to reason.
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.
Re: It's not just statistics: GPT-4 does reason
#96Earlier quoted context omitted.
Again, I think the disagreement is not whether it has learned to approximate a sorting algorithm, but whether that qualifies as reasoning and, if it does, in what sense.
I won't take a hard stance on what counts as "reasoning", which I picked in the title for lack of a better summarizing word; I am open to alternatives. So if you think that making abstractions and implementing a sorting algorithm does not count as reasoning, I will not disagree with that position. Where I am going to take a hard stance is on what does a stochastic parrot cannot do. And a stochastic parrot, defined as…
Given that so often the people claiming GPT4 is a stochastic parrot don't understand what stochastic parrots are, it can be said that they are the stochastic parrots themselves.
Re: It's not just statistics: GPT-4 does reason
#97Earlier quoted context omitted.
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…
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.
Re: It's not just statistics: GPT-4 does reason
#98Earlier quoted context omitted.
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…
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 it…
> It's not counting, it's just outputting something that is likely to sound right.
What does this mean? How can it possibly come up with the number 4 in a way that doesn’t involve counting?
Re: It's not just statistics: GPT-4 does reason
#99Earlier quoted context omitted.
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 it…
> It's not counting, it's just outputting something that is likely to sound right. What does this mean? How can it possibly come up with the number 4 in a way that doesn’t involve 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? 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'.
Re: It's not just statistics: GPT-4 does reason
#100Earlier quoted context omitted.
> It's not counting, it's just outputting something that is likely to sound right. What does this mean? How can it possibly come up with the number 4 in a way that doesn’t involve 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? 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: ban…
> 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.