HackerNews News Recommender

Productivity

news recommendation browser extension

SHOW HN2012

97points
36comments
#225of 1,677 in 2012
Top 14%of 2012 by points

How HN took it

CuriousMostly questions and neutral comments

1 positive, 8 neutral or asking, 0 mixed, 4 critical, out of 13 comments about the project. Thread score -0.17.

Execution: 0 for, 4 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

  • Idea is interesting and the maker's approach is useful

    From 1 comment
    • Sweet, this is awesome. I'll give you some feedback in a week or two after I give it a spin!
      deepkut on HN

Objections

  • Recommendations did not appear for several users

    From 3 comments
    • Doesn't seem to be doing anything for me. Installed it, clicked on a ton of links from hacker news, clicked on "more" a few times, and don't see anything recommended. The…
      meraku on HN
    • Same here. Even after resetting the data, and clicking more again, nothing.
      phreeza on HN
    • Doesn't seem to be working for me unfortunately, doesn't show any highlighted links. I think I've trained it properly.
      timtamboy63 on HN
  • Training requires clicking the more link, which users do not do normally

    From 1 comment
    • Do I have to do it every time I need to train it? I never click "more" in regular usage, I read one page and close it.
      StavrosK on HN
  • Trained state does not persist between visits

    From 1 comment
    • Does the data not persist between visits? I used this yesterday and it highlighted some posts, but today I got on HN and nothing is getting highlighted.
      james33 on HN

Requests

  • Open source the code

    From 1 comment
  • Train on link opens or use a link's content rather than only its title

    From 2 comments
    • Without seeing the source it's hard to ask relevant technical questions, but why not train every time a link is opened?
      polyfractal on HN
    • You might want to take a look at my implementation. I use the content of the linked sites via viewtext.org. This is probably more reliable.
      rogerbraun on HN
  • Allow telling the classifier when a suggestion is wrong

    From 1 comment
    • Click the "more" link how often? Is there a way to tell it that I don't agree with one of its suggestions?
      lachyg on HN

Questions

  • Does it count opened links or only upvoted links as liked?

    From 1 comment
    • Will look into it in detail shortly, but would it make more sense to treat the links I upvote as the ones I "liked" rather than the ones I open? Or, is this how it already works?
      karterk on HN
  • Is it working and how to know it is trained?

    From 1 comment
    • How do I know if it's working? I've activated it, clicked a ton of links that interest me and I'm not seeing anything.
      lachyg on HN

Alternatives named

  • Another HN recommender written in Ruby posted days earlier

    From 2 comments
    • Wasn't there another one of these that worked the same exact way posted a few days ago? http://news.ycombinator.com/item?id=3616763
      apgwoz on HN
    • DAYS ago, I remember the other hacker showed his program about HN recommendation written in Ruby.
      Alind 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/3637132)