Explainpaper

Productivity

research paper reading aid

SHOW HN2022

223points
38comments
#241of 2,570 in 2022
Top 10%of 2022 by points

How HN took it

DebatedReal support and real criticism

13 positive, 5 neutral or asking, 5 mixed, 8 critical, out of 31 comments about the project. Thread score +0.19.

Execution: 2 for, 4 againstIdea: 4 for, 0 againstDesign: 0 for, 3 againstPricing: 2 for, 0 againstPrivacy: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Explanations work impressively well for non-math-heavy papers

    From 4 comments
    • Thanks for building this. Me and my team have been driving it for the last few days, and it is a pleasure to use. Those law documents - that is probably us :) Can you comment a…
      somberi on HN
    • It's amazing how well it works. E.g. to test context I asked it "what is EtF"? There is no such acronym in the paper, but they mention English-to-French and that was the answer.…
      comboy on HN
    • As mentioned in the comments in this thread, it certainly seems useful for non-math-heavy papers. I tried it on a data-structures paper I've been reading: Tree-Independent…
      pncnmnp on HN
    • This was actually very useful! At least on the single paper I had saved for some later time when I would have time to drill down into the unfamiliar syntax (i.e. probably…
      stareatgoats on HN
  • Useful for reading and understanding papers

    From 2 comments
    • This was actually very useful! At least on the single paper I had saved for some later time when I would have time to drill down into the unfamiliar syntax (i.e. probably…
      stareatgoats on HN
    • This is fantastic. Congratulations to the authors! I would pay for a more polished version of the service. This service is precious!
      peperunas on HN

Objections

  • Misleading or wrong explanations, especially with math notation

    From 4 comments
    • This is an interesting idea, and I'm interested to see investigation in this area. However, for my sample size of 1 (my paper,…
      CJefferson on HN
    • As mentioned in the comments in this thread, it certainly seems useful for non-math-heavy papers. I tried it on a data-structures paper I've been reading: Tree-Independent…
      pncnmnp on HN
    • This is genuinely neat. I may need to start playing with GPT. I am clearly missing on a lot of fun. Original fragment: <<The dominant sequence transduction models are based on…
      A4ET8a8uTh0 on HN
    • >Yes, the paper says that the Transformer model is superior because it is more parallelizable and requires less time to train. "Superior because it is X" is not the same as…
      Jiro on HN
  • Does not work on mobile or iPad

    From 3 comments
    • Site unusable due to content misaligned with page, not working for me on Safari on iPhone. Looks cool though will try looking from Desktop…
      nelsondev on HN
    • This looks great !! A few nitpicks: - does not work at all on mobile, even with the browser's "desktop mode" (i guess it has to do with the highlighting hook) - a landing page…
      return_to_monke on HN
    • can confirm this, doesn't work on iPad
      _throwawayaway on HN
  • Poor contrast for extended reading

    From 1 comment
    • Congrats!!. Great work. One small request. The contrast of background and text is not great for extended reading sessions (imho). It would be nice if you could let the user…
      namaesan on HN

Requests

  • Better handling of math notation

    From 2 comments
    • Looks neat. I was hoping it would magically translate some of the math notation into plain English but I think it kind of just ignored it. Would love to see this. Minor feedback:…
      petargyurov on HN
    • We're actively working on math notation! Tough problem but lots of people have asked. And we'll push an update soon with better loading :)
      aman_jha on HN
  • Mobile-friendly view

    From 1 comment
    • yeah sorry! we're shipping a functional mobile view soon
      aman_jha on HN
  • User-level fine-tuning options

    From 1 comment
    • Thanks for building this. Me and my team have been driving it for the last few days, and it is a pleasure to use. Those law documents - that is probably us :) Can you comment a…
      somberi on HN
  • Landing page explaining the product

    From 1 comment
    • This looks great !! A few nitpicks: - does not work at all on mobile, even with the browser's "desktop mode" (i guess it has to do with the highlighting hook) - a landing page…
      return_to_monke on HN

Questions

  • How expensive is it to run and how is it priced

    From 2 comments
    • Can you explain more about what you mean by feeding context from the paper into the prompt? Also, how expensive is this to run? I’d love to build some fun projects on GPT-3, but…
      ryanwaggoner on HN
    • That's a real nice idea. I especially like how it is aware of the context of a selection. Looking at the network requests, it seems pricey to run though, as it appears to use a…
      sva_ on HN
  • How the context from the paper is fed into the GPT-3 prompt

    From 2 comments
    • It's amazing how well it works. E.g. to test context I asked it "what is EtF"? There is no such acronym in the paper, but they mention English-to-French and that was the answer.…
      comboy on HN
    • Can you explain more about what you mean by feeding context from the paper into the prompt? Also, how expensive is this to run? I’d love to build some fun projects on GPT-3, but…
      ryanwaggoner on HN
  • How long the service will stay free

    From 1 comment
    • This was actually very useful! At least on the single paper I had saved for some later time when I would have time to drill down into the unfamiliar syntax (i.e. probably…
      stareatgoats on HN

Alternatives named

  • Browser extensions for highlighting and explaining text

    From 1 comment
    • I'd love to know this also, my wishlist is to have this feature as browser extension, so that I have highlight something on random articles or hn comments to find out what…
      andycjw on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/33410408)