TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: My recommendation engine for Hacker News

314 pointsby julien040almost 2 years ago
Hi! I’m Julien and I built a recommendation engine for Hacker News.<p>I feel like this website is a gold mine. Every day, I find some very interesting stories about a topic. And sometimes, I want to find other stories covering that same topic but I can’t.<p>Hacker News has years of history of awesome discussion and ressources. Unfortunately, I think HN Algolia isn’t helpful in searching these old threads. As a student, I want to learn a lot from this website.<p>This is why I created HN Recommend. Input a sentence or the URL of an article, and get the most popular and similar posts from Hacker News.<p>About the technical details, I&#x27;ve computed the embeddings of over 100,000 articles from HN and indexed it using Faiss. I made a blog post for a deeper explanation.<p>Source code: <a href="https:&#x2F;&#x2F;github.com&#x2F;julien040&#x2F;hn-recommendation-api">https:&#x2F;&#x2F;github.com&#x2F;julien040&#x2F;hn-recommendation-api</a><p>Article: <a href="https:&#x2F;&#x2F;julienc.me&#x2F;articles&#x2F;Extract_embeddings_Hacker_News_article" rel="nofollow noreferrer">https:&#x2F;&#x2F;julienc.me&#x2F;articles&#x2F;Extract_embeddings_Hacker_News_a...</a><p>Project: <a href="https:&#x2F;&#x2F;hn-recommend.julienc.me" rel="nofollow noreferrer">https:&#x2F;&#x2F;hn-recommend.julienc.me</a>

22 comments

samwhoalmost 2 years ago
Aww, thank you for using my Memory Allocation post as the placeholder text. &lt;3
FieryTransitionalmost 2 years ago
I often wish I could sort Hacker News into two categories. Actual software&#x2F;tech&#x2F;STEM and everything else. I think both are interesting, but often, the niche tech stuff gets drowned out fast. So this is great for that :-)
julien040almost 2 years ago
I just released a new update, thanks to everyone&#x27;s feedback. Now, you can sort results by relevancy, age, or score using the select.
moritzwarhieralmost 2 years ago
This is a joy to use and also ot fits very nicely with the other highly ranked post by Nielsen group. Kudos!
评论 #36398484 未加载
dpe82almost 2 years ago
This is great. I often come across some HN post on a topic I am interested in and then want to go look at other posts in the same topic cluster to expand my exposure. This looks awesome for that.<p>I don&#x27;t know if it would be useful or even work, but is it possible to let the user adjust the vector distance threshold and then apply the other sorting parameters to the results? Eg. if I want to go broader, but then sort by high score or something so I see popular posts within an expanded (but still relevant) cluster?
评论 #36396785 未加载
评论 #36396571 未加载
benziblealmost 2 years ago
Hmm I tried searching &quot;elixir&quot; and found nothing related to the language. HN Algolia gives me exactly what I want. On what basis do you say it&#x27;s &quot;not helpful&quot;?
评论 #36393533 未加载
danvaynalmost 2 years ago
hey Julien. I love the product but the search doesn&#x27;t seem to be doing the best for me. For example, I looked up Tailwind and got plenty of results but none of them actually involved Tailwind.<p>Maybe a tagging solution is the way? if you determine a set amount of popular keywords for a topic and filter around those, you can offer more relevant results. With some sort of public tagging system you can also have SEO friendly pages around tags and get people browsing stuff they wouldn&#x27;t normally search for.
评论 #36393901 未加载
wseqyrkualmost 2 years ago
What I really need for HN (and any other news feed for that matter) is something like &quot;google discover&quot; i.e. a content-based recommendation system with some sort of feedback mechanism.<p>So I would get relevant information to me (I can skip, visit, like, dislike) whether or not it&#x27;s popular. That last point is important because HN home page doesn&#x27;t give you that, and most of posts could get lost in oblivion just because the first few folks did not find it interesting.
akomtualmost 2 years ago
HN needs a simple feature: a weekly digest view that shows the top 30 most commented posts (it should completely ignore flags and votes).
评论 #36397456 未加载
dxbydtalmost 2 years ago
Pls sort by recency. Otherwise you see 13 year old articles most of them obsolete&#x2F;irrelevant to the current situation.
评论 #36393932 未加载
RileyJamesalmost 2 years ago
Love it.<p>This response is very reactive heavy, where as it’s elixir I’m more interested in.<p>But well done on the execution. It does exactly what it states.<p>I’ve bookmarked.<p>I often search HN for additional articles and discussions based on something I’ve just read. Next time I’ll use this tool.
fewald_netalmost 2 years ago
Great project. I learned about the faiss library. Out of curiousity, did you also try it with doc2vec?
评论 #36394811 未加载
sogenalmost 2 years ago
A comment about search results: &quot;design system&quot; is related to design, &quot;system design&quot; relates to computing<p>It seems search takes the two inputs as the same.<p>Also, search doesn&#x27;t seem to work when using just 1 word.
评论 #36397466 未加载
sukki07almost 2 years ago
This is amazing, thank you for this. Makes finding stuff a lot easier
swyxalmost 2 years ago
i like the idea of this but wont remember it because my muscle memory is tuned to news.ycombinator.com. perhaps i can recommend a chrome extension instead of a website?
评论 #36396600 未加载
2halmost 2 years ago
This URL fails<p><a href="https:&#x2F;&#x2F;hn-recommend.julienc.me&#x2F;?q=Go" rel="nofollow noreferrer">https:&#x2F;&#x2F;hn-recommend.julienc.me&#x2F;?q=Go</a>
评论 #36401228 未加载
rjrobbenalmost 2 years ago
i didn&#x27;t expect the embeddings have such simple yet useful application, thanks!
passion__desirealmost 2 years ago
One feature I would like for an Recommender Systems to have is : explicit ability to jump in and out of filter bubbles or research rabbit holes. Another example would be, put yourself in the shoes of another, e.g. what content is liked by game developers generally. apart from general gamedev content, what do they like, where do they take inspiration from, etc.<p>I remember there was a project built on instagram which allowed a person to view instagram as it looked like to a particular celebrity.
评论 #36394715 未加载
4hEnalmost 2 years ago
I search for a url I know was posted and it doesn&#x27;t show it. It shows unrelated articles.
评论 #36394200 未加载
rounakdattaalmost 2 years ago
Nit:<p>&gt; Resources to learn about distributed systems<p>I thought Murat Buffalo&#x27;s blog would come up at the top. That&#x27;s a gold, and I&#x27;m confident that it was shared on HN as well (maybe a year or two back).<p>Otherwise neat and useful!
balder1991almost 2 years ago
The layout is currently buggy on Firefox.
评论 #36401107 未加载
lfkdevalmost 2 years ago
A time filter is needed