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

ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

github.com

Post reply on HN
Print view View original

21–30 of 105 posts

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#21

Post by mtlmtlmtlmtl »

krageon wrote: post #18
elashri wrote: post #11

Earlier quoted context omitted.

I don't think it is seroud. Abstract are usually tends to be a short summary. In many cases it is a short paragraph. I was skimming on arxiv before I opened HN now and saw a couple of abstracts that are 4-5 sentences. Are ChatGPT going to write a one sentence summary or will the summary of the summary be comparable or longer?

Abstracts can also be close to a full page long. While this doesn't have to be bad, it's usually more information you're looking for (especially if you were only going to read the abstract anyway).

I can skim several full pages in the time it takes just to send off the abstract and get the response back...

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#22

Post by visarga »

aflag wrote: post #19
herbst wrote: post #16

Ive used ChatGPT to make short factual videos for YouTube and honestly it's a bit worrying with supposed 'facts' I would not suggest anyone to use ChatGPT outputs for actual knowledge at this point.

You can use it for that, but you have to test its claims. It's specially helpful with questions that would take a lot of research to find the answer, but which are easier to test. That could be a good thing overall. If people get used to always testing everything anyone tells them, people will be a lot better informed.

I think LLM checking is going to be the most important research direction this year. Generative models are worthless without verification. It relates to deciding truth and dealing with fake information, synthetic text and spam. Google hasn't been able to solve it in the last decade, but some people have an idea:

> "Discovering Latent Knowledge in Language Models Without Supervision" Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can't detect. We propose circumventing this issue by directly finding latent knowledge inside the internal activations of a language model in a purely unsupervised way.

https://arxiv.org/abs/2212.03827

In other words the model already tries to predict the truth because it is useful in next token prediction, but we need to find a way to detect the 'truth alignment' in its activations.

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#23

Post by alexanderdavide »

voxelghost wrote: post #13
meghan_rain wrote: post #10

What if the paper is longer than what fits in a prompt?

You can ask chatGPT about arxiv.org papers if you have the doi and the full title if the paper is from 2021 or earlier

This renders the extension pretty useless for older papers, doesn't it? There doesn't seem to be a fallback to prompt older papers in a whole because it exceeds the prompt limit.

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#24

Post by alexanderdavide »

I'm wondering about two things related to development of customer-facing programs that use paid APIs in the background:

Are you using your own API key and pay for the usage? How can you justify operation of programs that produce high costs but no income? Isn't the API publicly exposed to the client-side and possible subject of theft and abuse?

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#25

Post by m4lvin »

alexanderdavide wrote: post #24

I'm wondering about two things related to development of customer-facing programs that use paid APIs in the background: Are you using your own API key and pay for the usage? How can you justify operation of programs that produce high costs but no income? Isn't the API publicly exposed to the client-side and possible subject of theft and abuse?

The extension here does not include an API key. You either need to log in using an account or provide your own API key in its settings.

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#26

Post by Abecid »

alexanderdavide wrote: post #24

I'm wondering about two things related to development of customer-facing programs that use paid APIs in the background: Are you using your own API key and pay for the usage? How can you justify operation of programs that produce high costs but no income? Isn't the API publicly exposed to the client-side and possible subject of theft and abuse?

It asks the user to sign in to chat.openai.com

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#27

Post by visarga »

mtlmtlmtlmtl wrote: post #21
krageon wrote: post #18

Earlier quoted context omitted.

Abstracts can also be close to a full page long. While this doesn't have to be bad, it's usually more information you're looking for (especially if you were only going to read the abstract anyway).

I can skim several full pages in the time it takes just to send off the abstract and get the response back...

then batch summarise your paper feed every morning

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#29

Post by blackbear_ »

goldemerald wrote: post #5

The example here is a bit worrying for the peer review process. I am not looking forward to my "peers" reviewing my paper by putting it through LLMs and blindly copy pasting the output. I can already imagine emailing the Area Chair and saying "While reviewer 2 is detailed, the questions show a severe lack of basic understanding. We believe the contents are AI generated." Then again, perhaps LLMs could simply be incor…

I've seen so many s*ht reviews already. Perhaps, just perhaps, a LLM would make better ones.

Re: ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT

#30

Post by voxelghost »

alexanderdavide wrote: post #23
voxelghost wrote: post #13

Earlier quoted context omitted.

You can ask chatGPT about arxiv.org papers if you have the doi and the full title if the paper is from 2021 or earlier

This renders the extension pretty useless for older papers, doesn't it? There doesn't seem to be a fallback to prompt older papers in a whole because it exceeds the prompt limit.

Well yes in a way, the extension settings include the prompt they're using, so you can formulate your own prompt along the same lines.

I think the extension is only useful for someone who spends a lot of time doing research on arxiv.org, (and if the quality of the summary is good enough, the jury's still out on that one)

Post reply on HN