Comment by famouswaffles | Hacker News Reader

Comment by famouswaffles | Hacker News Reader

The idea that it needs so is looking more and more questionable. Don't get me wrong, i'd love to see some multimodal LLMs. In fact, i think research should move in that direction...However "needing" is a strong word. The text only GPT-4 has a solid understanding of space. Very, very impressive. It was only trained on text. The vast improvement on arithmetic is also very impressive.

(People learn language and concepts through sentences, and in most cases semantic understanding can be built up just fine this way. It doesn't work quite the same way for math. When you look at some numbers and are asked even basic arithmetic , 467383 + 374748. Or say are these numbers primes or factors?. With a glance, you have no idea what the sum of those numbers would be or if the numbers are primes or factors because the numbers themselves don't have much semantic content. In order to understand whether they are those things or not actually requires to stop and perform some specific analysis on them learned through internalizing sets of rules that were acquired through a specialized learning process.)

all of this is to say that arithmetic, math is not highly encoded in language at all.

and still the vast improvement. It's starting to seem like multimodality will get things going faster rather than any real specific necessity.

also, i think that if we want say vision/image modality to have positive transfer with NLP then we need to move past the image to text objective task. It's not good enough. The task itself is too lossy and the datasets are garbage. That's why practically every Visual Language model flunks stuff like graphs, receipts, UIs etc. Nobody is describing those things t the level necessary

what i can see from gpt-4 vision is pretty crazy though. if it's implicit multimodality and not something like say MM-React, then we need to figure out what they did. By far the most robust display of computer vision i've seen.

I think what kosmos is doing (sequence to sequence for Language and images ) has potential.

Chris Espinosa just posted this example of GPT-4 attempting (and failing miserably) to explain how a square has the same area as a circle that circumscribes it:

https://mastodon.social/@Cdespinosa/110092792044177610

Do you think GPT-4 knows what it’s own limits of understanding are? Most people have a sense of what they know and don’t know. I suspect GPT-4 has no concept of either.

Most people don't have a great sense of what they do or don't know.

That's been my overwhelming experience interacting with people on the internet.

As for GPT-4, It does to some extent. Calibration tests show a vast improvement in this area but certainly less than an equivalent human expert.

GPT-4 is actually multimodal. It can't be publicly prompted with images yet, but that's planned.

I think that multimodal training will also solve the data shortage problem. There are hundreds of times more bytes in video and audio than there are in text, so we'll likely be able to scale pre-training for quite a while before needing to go fully embodied on Transformers.

They trained a text only model first and then made it multimodal. The experiments I was referring to (spatial understanding) were done with the text only model.

> GPT-4 is actually multimodal

The released version. Microsoft's paper was talking about an early internal text-only version.

> There are hundreds of times more bytes in video and audio than there are in text

But the information density is similarly hundreds to thousand times less.

I'm not actually sure that's true. There is a lot of detail in the world represented in audio and video, and presumably large transformers could learn from the textures and shadows and articulated movements and the physical modeling of how sounds are made, etc.

> has a solid understanding of space

How so? Is it simply better at predicting the answer to spatial questions based on being a more powerful autocomplete than predecessors? How is this proven?

In science results matter much more than vague and ill defined assertions.

A system reasons and understands when it demonstrates understanding and reasoning. That's how you asses reasoning in anything/anybody. Evaluation.

If you want to tell me there's a special distinction between what an LLMs outputs and "true reasoning TM" then cool but when you can't show me what that distinction is, how to test for it, the qualitative or quantitative differences then I'm going to throw your argument away because it's not a valid one. It's just an arbitrary line drawn on sand.

A distinction that can't be tested for is not a distinction.

The point is as far as I know it hasn't been properly tested for. No one has come up with a comprehensive framework of tests to evaluate spacial reasoning using entirely sentences that aren't isomorphic to training data.

Try asking chatgpt to solve a non-well-known programming exercise. It will fail miserably and insist on rehashing the same wrong solution when told that it was wrong.

A real person might give up, but would not claim that an obviously wrong answer was in fact the answer.

In the Microsoft sparks paper they ask it to "draw a unicorn in TikZ". It does well. Then they remove the horn and ask it to put the horn on the unicorn and it gets that to.

To the understanding of space, while it certainly has gaps, I've had GPT4 do basic graph layout by giving it (simple) Graphviz graphs in and asking it to generate draw.io xml out and telling it to avoid overlapping nodes and edges.

>all of this is to say that arithmetic, math is not highly encoded in language at all.

How did you learn arithmetic then, if not by being shown numbers and equations, and having math rules and concepts explained to you through language?

I didn't say it's not there. or that you couldn't communicate the ideas of math/arithmetic with language.

You can get GPT-3 (yes 3) to have 98.5% accuracy on addition arithmetic (even very large numbers) by..simply describing the algorithm of addition to performed on 2 numbers. https://arxiv.org/abs/2211.09066

The basic idea i'm communicating is that not everything that can be extracted from self supervisory token prediction can be extracted with the same ease. and it is very easy to see why math is one the higher difficulty things.

It is extremely easy comparatively to infere "happy" from the sentence - John is smiling therefore he is ----. all the information you need to make that inference is packed tightly in the preceding words. it is not the same for arithmetic at all.

Isn't a 98.5% accuracy quite low for a computer adding numbers?

It's quite huge for an LLM AI not taught specifically to add numbers.

This is not a specialized adding algorithm - it's a general purpose one.

And probably better than most humans :-)

But it was taught specifically to add numbers. Unless my understanding of it's training corpus is way out of line.

Reply on news.ycombinator.com