There is an example linked to on the homepage of this submission but here it is:

https://asxiv.org/pdf/1706.03762

Possibly. I had to kind of be very specific to get the model to link to the pages in a specific format my frontend can parse and then interact with the pdf viewer[1]. It seems very full featured so it may have a way to highlight portions of the page, but my experience with PDFs leads me to believe it would be tricky.

1. https://mozilla.github.io/pdf.js/

That seems like a social network? This is just a tool to have an AI model answer questions without needing to do anything other than replace the domain.

I've had better results running it with the Gemini 2.5 Pro model but it's much more expensive. The website is using the very cheap 2.5 flash lite model.

You can run it yourself using the better model to see if you get better results as well:

https://github.com/montanaflynn/asxiv

Very cool! I chose gemini for two reasons; the first being it supported pdf input and the second the flash lite model being very cheap so I could comfortably make it public and free.

Thank you, that's probably correct. I think the gemini api might turn the pages into images and use those. Sending the original tex source was something I thought of but not all papers have those submitted.

As for markdown / latex output that could be done, especially for equations! I'll have to look into the best way to render that.

I hadn't, but at a glance it seems more of a community that an AI tool?

Thank you! If you have any suggestions feel free to let me know.

Shameless plug but I made a similar tool called asXiv[1] which allows you to "ask" arXiv.org papers questions.

It also recommends questions on initial load that can help understand or explore the paper, here's a demo[2] from the popular Attention Is All You Need paper.

The code is all opensource[3], it uses the google 2.5 flash lite model to keep costs down (it's completely free atm), but that can be changed via env var if you run it locally.

1. https://asxiv.org

2. https://asxiv.org/pdf/1706.03762

3. https://github.com/montanaflynn/asxiv

That looks interesting! I put your Show HN (https://news.ycombinator.com/item?id=45212535) in the second-chance pool (https://news.ycombinator.com/pool, explained at https://news.ycombinator.com/item?id=26998308), so it will get a random placement on HN's front page.

This looks great. Just fyi this is also possible via alphaxiv's assistant. Navigate to a paper, click tools -> assistant.

[0] https://www.alphaxiv.org/abs/1706.03762

Seems legit, I'll have to try later. Just curious, why didn't you make this a commercial SaaS?

maybe because every LLM provider has an "attach file" feature so you can attach a paper and then ask questions about it?

what's the value add of the wrapper that this person wrote at all?

I built it because it was tiresome to save the pdf, open a new window, add it and give a prompt.

Simply replacing the domain arxiv.org with asxiv.org does all that for me now.

Also it links to pages in it's answers and scrolls the pdf to it on click, allowing to view the pdf side by side with the chat.

Right. I do this all the time with Gemini. Add a pdf or a link and ask it whatever I want. It will even turn it into a podcast with two people discussing the entire paper that I can listen to on the tram to work.

whoa this is fantastic. wish I had known about this earlier! just made a similar product for reading arXiv / epub / pdfs called Ruminate (www.tryruminate.com), would love to hear what you think

How is that different than generic RAG though? Genuinely curious

Any chance you could open source it so we can add more languages and run it locally?

Open sourced it: https://github.com/ronv/skanas.lv PRs are welcome!

ctrl+u