[devmor]

That's not going to help you understand the subject material better. It's just going to assemble a facsimile of the lowest common denominator of other people on the internet talking about it. If anything, it will hurt your understanding and give you a false sense of knowledge.

[ben_w]

Given how well chatGPT can explain code, I'm reasonably confident it can do much better than the lowest common denominator of people on the internet talking about any given expert document.

May well still give a false sense of knowledge, but that's a very common problem for all of us.

[devmor]

An LLM can reasonably explain code because code is both a closed, finite set of instructions and heavily explained in the training data that contains a vast number of learning materials.

A novel scientific paper is much, much different than code.

[ben_w]

> A novel scientific paper is much, much different than code.

Sure, just not in a way that matters.

Human language is a "closed, finite set" of symbols (to the same extent as code, at least), all of which are heavily explained in the training data that contains a vast number of learning materials.

Science is about the novel things; but when the things are so novel the research has to invent new words to discuss these things, those new words come with explanations of what they mean.

[xcv123]

It is clear that you haven't tried this with GPT-4

You have an obsolete understanding of this technology and are putting yourself at a disadvantage.

[devmor]

It is clear that you do not understand how an LLM works if you believe it can explain a novel scientific paper to you with any reasonable degree of accuracy.

[jiggawatts]

I’ve had paper authors confirm that the GPT 4 version is correct and more readable than their own writing.

[devmor]

What papers, and were they on subjects that are widely explained already across the internet?

[xcv123]

It doesn't look up or use existing explanations of papers like some kind of internet or database search. You have a fundamental misunderstanding of how it all works.

[devmor]

The fact that you don’t know that GPT was primarily trained on public crawler data and feel inclined to make authoritative comments on it, refuting people who do understand how an LLM works is exactly what I mean by “false sense of knowledge”.

[xcv123]

You don't know how it works. The fact that it is a "novel" scientific paper is completely irrelevant. Try it on a new paper just released today, that is definitely not in the training set.