←back to thread

Show HN: Doomscrolling Research Papers

(www.openpaperdigest.com)
14 points davailan | 2 comments | | HN request time: 0s | source

Hi HN,

Would love your thoughts on Open Paper Digest. It’s a mobile feed that let’s you “doomscroll” through summaries of popular papers that were published recently.

Backstory There’s a combination of factors lead me to build this:

1. Quality of content social media apps has decreased, but I still notice that it is harder than ever for me to stay away from these apps. 2. I’ve been saying for a while now that I should start reading papers to keep up with what’s going on in AI-world.

Initially, I set out to build something solely for point 2. This version was more search-focussed, and focussed on simplifying the whole text of a paper, not summarizing. Still, I wasn’t using it. After yet another 30 min doomscroll on a bus last month, point 1 came into the picture and I changed how Open Paper Digest worked. That’s what you can see today!

How it works It is checking Huggingface Trending Papers and the large research labs daily to find papers to add to the index. The PDFs gets converted to markdown using Mistral OCR, this is then given to Gemini 2.5 to create a 5 minute summary.

I notice that I am now going to the site daily, so that’s a good sign. I’m curious what you all think, and what feedback you might have.

Cheers, Arthur

1. ontouchstart ◴[] No.46161829[source]
How do you prevent AI agent to scrape your data the same way you scrape HF?

For example, I can “cache” your page as a shared link in this comment

https://www.openpaperdigest.com/paper/paperdebugger-a-plugin...

Or in a gist somewhere:

https://gist.github.com/ontouchstart/38d80cab66794014d17e193...

Then I can have a bot to scrape these pages with context as training data.

This can be out of hands for you in inference cost. Then you need VC money to sustain your website. Wish you the best luck to get there.

replies(1): >>46161861 #
2. ontouchstart ◴[] No.46161861[source]
The reason I said that is that I already have a POC to use LLM to go to a gist and do something with the date in it.

https://gist.github.com/ontouchstart/03f4c7ee853061772b479d9...