Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Why are LLMs general learners?

intuitiveai.substack.com

Post reply on HN
Print view View original

31–40 of 64 posts

Re: Why are LLMs general learners?

#31

Post by famouswaffles »

SkyPuncher wrote: post #29
famouswaffles wrote: post #28

Earlier quoted context omitted.

>That is do it correctly, every time, for any size number. Then no human is good at arithmetic.

I suspect most people on this forum can do arithmetic for any "reasonable" size number. It might take weeks to complete, but most people on this forum can calculate large numbers by hand.

Post moving. "Reasonable" is just an arbitrary line. Especially since most if not all would make some mistake somewhere along the line.

You can greatly increase GPT's arithmetic capabilities tackling it like a problem to solve "on paper" in context. And this was done on 3.5 not 4. https://arxiv.org/abs/2211.09066

Re: Why are LLMs general learners?

#32

Post by aidenn0 »

doctor_eval wrote: post #25
iliane5 wrote: post #5

Earlier quoted context omitted.

> LLMs are not particularly good at arithmetic, counting syllables, or recognizing haikus I suspect most of this is due to tokenization making it difficult to generalize these concepts. There are some weird edge cases though, for example GPT-4 will almost always be able to add two 40 digits number but it is also almost always wrong when adding a 40 digit and 35 digit number.

Could it also be that syllables are intrinsically mechanical? They are strongly related to how our mouths work. While it may be possible to extract syllables from written text - following the consonants and vowels - I'm not sure that many humans could easily count syllables without using their mouths.

Many humans are also often really bad at doing speech related things when writing.

I've known many native English speakers who write things like "an healthy" (because they learned to write "an" before words starting with "h") and write poems that don't rhyme because the words end with the same letters (e.g. "most" and "cost").

Re: Why are LLMs general learners?

#33

Post by 8note »

dgreensp wrote: post #4

LLMs are not particularly good at arithmetic, counting syllables, or recognizing haikus, though, because (contrary to the thesis of the article) they don’t magically acquire whatever ability would “simplify” predicting the next token. I don’t feel like the points made here align with any insight about the workings of LLMs. The fact that, as a human, I “wouldn’t know where to start” when asked to add two numbers witho…

I'm surprised they're bad at predicting haikus.

I assume because there's little documentation about how many syllables every word has on the internet?

Re: Why are LLMs general learners?

#34

Post by galaxyLogic »

dgreensp wrote: post #27
pgspaintbrush wrote: post #16

Earlier quoted context omitted.

Author here. First off, thank you for reading and for your thoughts. I provided examples that I thought would be intuitive for humans to help folks understand that an understanding of the underlying phenomena is useful for next token prediction (I've added this as a note). Could you share what part of the article came across as suggesting that LLMs "magically" acquire whatever ability helps them to predict? I'd like…

Thanks for responding to my comment. I'm not an expert in the field, but, there are lots of previous algorithms for predicting the next token in a series (Markov chains, autocomplete). None of them felt so much pressure to make an accurate prediction that they had no alternative but to teach themselves arithmetic! It seems what is different about LLMs (as far as the post goes) is that we can anthropomorphize them. Mo…

> what problems an LLM can solve is a function of what it can model.

Well said. The model that LLM has is very simple: If text X precedes current conversation then the most likely continuation of discussion is, according to the model held by LLM, Y. Right?

So the point is LLM does not create models. It has only a single model based on probabilities of text-sequences, created by its programmers. So it can (mostly?) only solve the problem of what would be a good textual response to an earlier text. It can do it well but most difficult problems don't fall into that category of "having a great chat".

Re: Why are LLMs general learners?

#35

Post by 8note »

SkyPuncher wrote: post #29
famouswaffles wrote: post #28

Earlier quoted context omitted.

>That is do it correctly, every time, for any size number. Then no human is good at arithmetic.

I suspect most people on this forum can do arithmetic for any "reasonable" size number. It might take weeks to complete, but most people on this forum can calculate large numbers by hand.

If its going to take weeks, most people will get it wrong. That's a lot of calculations to never get wrong and never misinterpret some prior note you left

Re: Why are LLMs general learners?

#36

Post by Paul-Craft »

im3w1l wrote: post #3
Paul-Craft wrote: post #2

This seems like just another way of saying that when you train an LLM on a text, its weights incorporate the tokens in that text, which is nothing really profound. I think the real magic here comes from the fact that LLMs are a specialized sort of neural network, and that neural networks are universal approximators [0]. In other words, LLMs are general learners because they are neural networks. This is also not parti…

A lot of universal approximators are piss poor at general learning. It's taken a lot of hard work and clever people to get LLM's to where they are. It's not as simple as neural network and done.

Correction: hard work, clever people, and massive increases in computational power. I'm sure all three matter quite a lot here.

I'm not saying that if your goal is to come up with a usable general learning algorithm that it is just "as simple as neural network and done." What I'm saying is the converse: that the general learning capabilities of LLMs are most likely explained by the fact that, well, they are general learners, via the universal approximation theorem.

Your other comment, I think, suggests why we're just now starting to see more general learning capabilities out of neural networks, when the theory says that a single hidden layer is enough: with a single hidden layer, you really need to get all the weights pretty close to "right" to see general learning/universal approximator behavior. When you have more than one hidden layer, then some of your weights can be wrong, as long as the errors are corrected in later layers.

Now, I'm not an AI researcher or even anyone who works anywhere near this area, but I did take a course or two in grad school, and this seems at least intuitively plausible to me. If there are researchers in the field reading this, I'd definitely like to hear their takes, because I'm totally open to being completely wrong here. I'd rather be one of the lucky 10,000 than just have this half-baked idea that seems right. :-)

Re: Why are LLMs general learners?

#37

Post by butyEah »

Paul-Craft wrote: post #36
im3w1l wrote: post #3

Earlier quoted context omitted.

A lot of universal approximators are piss poor at general learning. It's taken a lot of hard work and clever people to get LLM's to where they are. It's not as simple as neural network and done.

Correction: hard work, clever people, and massive increases in computational power. I'm sure all three matter quite a lot here. I'm not saying that if your goal is to come up with a usable general learning algorithm that it is just "as simple as neural network and done." What I'm saying is the converse: that the general learning capabilities of LLMs are most likely explained by the fact that, well, they are general l…

Hardware matters most. No matter how clever there’s no storing such large parameter sets on an Intel 286 with 4MB RAM.

No matter how clever the programmer there’s no encoding GPT4 with that. It was the hardware constraints that required programmers to be clever to begin with. These days it’s much more “copy paste the math directly because our data set is so robust and our hardware and networks so performant clever low level hacks don’t matter.”

Especially at big tech where they’ve used their own AI to guide them; the ability to just ask an ML system to simplify math has existed for a few years now, we’ve all seen how clever outputs were set aside for safe linear hacking.

Truly clever work is occurring in more traditional sciences like chemistry and biology these days.

Re: Why are LLMs general learners?

#38

Post by tarvaina »

Paul-Craft wrote: post #2

This seems like just another way of saying that when you train an LLM on a text, its weights incorporate the tokens in that text, which is nothing really profound. I think the real magic here comes from the fact that LLMs are a specialized sort of neural network, and that neural networks are universal approximators [0]. In other words, LLMs are general learners because they are neural networks. This is also not parti…

The ingredients you need for training a useful machine learning model are expressivity, learnability, and generalization. Many methods are universal approximators but that only takes care of the first ingredient. Arguably the reason neural networks are so successful is that they can offer a good balance between the three.

Before transformers we built different neural network architectures for each domain. These architectures offered better inductive biases for their respective domains and thus traded off some of the expressivity for better learnability and generalization.

Nowadays the best architectures seem to be merging towards transformers. They appear to offer more generally useful inductive biases and thus a better trade-off between the three ingredients than the earlier architectures.

Re: Why are LLMs general learners?

#39

Post by HALtheWise »

I don't see enough discussion of the fact that LLMs are actually trained with two losses: text prediction and a regularization loss of some sort that effectively encourages the network to use "simple" internal structure. That means the training process isn't only trying to predict the next token, it's specifically trying to find the simplest explanation that predicts the next token.

Given that the history of science is mostly driven by trying to find the simplest explanation for observed phenomenon, thinking about regularization makes it much less surprising that LLMs end up learning how the world "actually works".

Re: Why are LLMs general learners?

#40

Post by ChatGTP »

im3w1l wrote: post #24
Retric wrote: post #10

Earlier quoted context omitted.

Current LLM’s are also piss poor general learners, they are however really good at learning specific things which people value highly.

Some 15 years ago, textbooks taught that multi level perceptrons (fully connected feed forward network) with one hidden layer were sufficient because they were universal approximators. That thought kinda held back the field for a long time. Going against that dogma was so revolutionary that new paradigm was given its own name: deep learning. Just because you can find some gotcha counterexample LLM's struggle with doe…

What's the destination, we've come along way, and where do you think we're going?
Post reply on HN