[HN Gopher] Show HN: I built a tech news aggregator that works t...
       ___________________________________________________________________
        
       Show HN: I built a tech news aggregator that works the way my brain
       does
        
       An honest to god, non-algorithmic reverse chrono list of tech news
       that passes my signal-to-noise tests, updated hourly.  A
       lightweight a page design as I've been able to keep; simple, clean,
       fast. No commercial features or aspirations - this is a passion
       project, something I've been fooling around with on and off for
       decades.  There's a "Top" view too with an LLM edited front page &
       summary, and categorized views for a large number of topics - see
       the Directory. A few more buried features to explore, but the
       fundamental use case is pop in, scan, exit - fast and concise.
       Your feedback would be appreciated!
        
       Author : dreadsword
       Score  : 124 points
       Date   : 2025-10-23 17:48 UTC (5 hours ago)
        
 (HTM) web link (deadstack.net)
 (TXT) w3m dump (deadstack.net)
        
       | wmeredith wrote:
       | I've built a couple different versions of this for myself over
       | the years. I like yours! Thanks for sharing.
        
         | dreadsword wrote:
         | Cheers - thank you for the kind words!
        
       | metalliqaz wrote:
       | Really nice and clean, well done.
       | 
       | What is the purpose of having summaries for "Recent", "Incoming",
       | and "Outgoing" all at the top? Seems like all content from the
       | later two are in the first, right?
        
         | dreadsword wrote:
         | You're right --- incoming & outgoing end up being redundant on
         | the "Recent" view.
         | 
         | Where they're (more) relevant is in the "Top" view where the
         | LLM editor has picked a subset of stories to be categorized as
         | top and incoming/outgoing are the ones that didn't make the
         | cut, organized by timeliness.
         | 
         | Definitely a gap in design!
        
         | dreadsword wrote:
         | Oh I should add: incoming will show stories ~20 minutes before
         | they get picked up for "Top" inclusion, if they're going to
         | make the cut, based on how jobs are scheduled.
        
       | jarmitage wrote:
       | RSS?
        
         | dreadsword wrote:
         | In the roadmap! RSS by tag - i.e.: for
         | https://deadstack.net/tag/quantum And an RSS feed for /recent
         | are both in progress
        
       | chicagojoe wrote:
       | This is great! Are you using a news API or pulling in RSS feeds
       | yourself? Is there a list of what sources are included?
        
         | dreadsword wrote:
         | Reading RSS myself, OLD SCHOOL: Cron Jobs. PHP. Hahaha! List of
         | sources: At present, no; but if its of interest, it would not
         | be hard to add.
         | 
         | I should also add - please post any recommendations re: sources
         | to cover.
        
         | dreadsword wrote:
         | Hey - still thinking about sources here. With the data I have,
         | I could actually do an interesting analysis of news sources -
         | i.e.:
         | 
         | - how often do their stories become members of clusters? - how
         | "fast" are they to publish on a topic vs. other competitors -
         | i.e.: who "breaks" the news? - what tags (people, companies,
         | topics) does a given source stick close? Which do they shy away
         | from?
         | 
         | Thanks very much for a really interesting set of ideas to
         | explore!
        
       | fuddle wrote:
       | Cool site, an About page would be useful. It's hard to tell how
       | the site works.
        
         | dreadsword wrote:
         | Fair enough - its honestly not something I expected anyone to
         | be interested in enough such that an about page would be
         | required.
         | 
         | At a high level, it reads RSS feeds from a number of sources,
         | and uses LLMs to identify clusters of stories about the same
         | thing, group them, tag them, and designate them a "top" story
         | or not. That's it.
         | 
         | The biggest thing I've learned in all of this is that o3-mini
         | is far and away the best at following instructions (for this
         | use case). Periodically I'll cycle through the models available
         | on Groq, and always come back to o3-mini.
        
       | NetOpWibby wrote:
       | I love that your site comes with an overview instead of clicking
       | away to another site immediately. Feels snappy and looks good. I
       | can see this being my news roundup. Great work!
        
         | dreadsword wrote:
         | Cheers and thank-you!
        
       | neilellis wrote:
       | Really good, clean and to the point, love it.
        
         | dreadsword wrote:
         | Cheers - thank-you so much!
        
       | productiveminds wrote:
       | Simplistic site, looks clean and easy to navigate!
        
         | dreadsword wrote:
         | Many thanks for the kind words!
        
       | botanrice wrote:
       | This is neat! Thanks for sharing.
        
         | dreadsword wrote:
         | Cheers and thank you!
        
       | tamimio wrote:
       | If you can get rid of the cookies message that would be great, as
       | I will place the site as an app in my phone and that message is
       | annoying to have when I open it.
        
         | dreadsword wrote:
         | You should only see that message once when you first show up,
         | and as annoying as it is, there's a compliance element to it.
         | Let me know if its persisting for you after accepting!
        
       | _menelaus wrote:
       | This is pretty cool man. How do you cluster the articles into
       | stories? It looks like you did a good job of it.
        
         | dreadsword wrote:
         | Thanks so much for the kind words - its 100% o3-mini for
         | clustering. I have zero editorial input as to what constitutes
         | a cluster, what's "top" news, etc.
         | 
         | The one subtlety is setting up the LLM to understand whether a
         | new story belongs in an existing cluster, or with > 1
         | neighbors, constitutes a new cluster. The challenge there is
         | scoping the clustering window (hours of stories for
         | consideration) and topic breadth to avoid creating Katamari-
         | super-clusters that just end up with every story associated to
         | them.
         | 
         | At this point I seem to have found a sweet spot re: the hours
         | window, the frequency of processing, and the design of the
         | prompt such that its working consistently.
         | 
         | Very few false positives in terms of spurious clusters being
         | created, or potential clusters being missed.
        
       | embit wrote:
       | I have done similar style for tech news. Aggravating based on
       | Tags. That way I can read tech news on micro topics.
       | https://embit.ca/ Your feedback is appreciated.
        
         | dreadsword wrote:
         | Looking good - keep at it! Use it yourself every day, and
         | iterate it continuously.
        
       | amatecha wrote:
       | This is probably a dumb question, but.. what does "incoming" and
       | "outgoing" mean?
        
         | dreadsword wrote:
         | Oh man, don't ask - not a dumb question at all. I'll reshare
         | what I put in another comment that answers it, but bottom line
         | is they're a design gap in the context of /recent.
         | 
         | You're right --- incoming & outgoing end up being redundant on
         | the "Recent" view. Where they're (more) relevant is in the
         | "Top" view where the LLM editor has picked a subset of stories
         | to be categorized as top and incoming/outgoing are the ones
         | that didn't make the cut, organized by timeliness.
         | 
         | Definitely a gap in design!
        
           | thekevan wrote:
           | I assumed it meant stories that trended highly and were now
           | fading in popularity (outgoing) and stories that are trending
           | but trending quickly and may be on a fast ascent.
           | 
           | Sort of a combo of "in case you missed it" and "the next new
           | big stories".
        
           | amatecha wrote:
           | Oh, sure, but I literally just don't understand what their
           | meaning is >_>
        
       | al_borland wrote:
       | I like it. It kind of reminds me of the old Fever RSS reader,
       | which would group together similar articles from different
       | sources, and use that to rank how hot a story was.
        
         | dreadsword wrote:
         | Not familiar with fever, but there is something similar buried
         | at the heart of mine - the LLM clusters stories, and they get
         | promoted to public when they reach a threshold of unique
         | sources.
         | 
         | That threshold is a function of day of the week - on weekends
         | when the news cycle is quiet, it lowers the bar --- tuesday to
         | thursday its at its most restrictive.
        
       | lateforwork wrote:
       | Love it, but the body font (garamond) is not easy on the eyes.
       | Garamond is one of my favorite fonts in print and at not-too-
       | small sizes. On the screen it doesn't look good because where the
       | characters get thin it gets too thin (or as font experts call it,
       | too much contrast).
        
         | dreadsword wrote:
         | Noted, thank you! I haven't put a tonne into readability, other
         | than some basics - I prefer a serif'd font, and I made sure the
         | background was easier on the eyes than #FFFFFF haha
        
       | jiwidi wrote:
       | Pretty cool! How do you do to build these "stories" based on
       | news?
        
         | dreadsword wrote:
         | Cheers and thank you! I'll reshare an earlier comment that I
         | think answers your question - let me know:
         | 
         | Thanks so much for the kind words - its 100% o3-mini for
         | clustering. I have zero editorial input as to what constitutes
         | a cluster, what's "top" news, etc.
         | 
         | The one subtlety is setting up the LLM to understand whether a
         | new story belongs in an existing cluster, or with > 1
         | neighbors, constitutes a new cluster. The challenge there is
         | scoping the clustering window (hours of stories for
         | consideration) and topic breadth to avoid creating Katamari-
         | super-clusters that just end up with every story associated to
         | them.
         | 
         | At this point I seem to have found a sweet spot re: the hours
         | window, the frequency of processing, and the design of the
         | prompt such that its working consistently.
         | 
         | Very few false positives in terms of spurious clusters being
         | created, or potential clusters being missed.
        
           | jiwidi wrote:
           | Very interesting, how do you do that? Do you limit yourself
           | what you feed or via custom instructions? I had a similar
           | case so would love how you are doing the prompting here.
           | 
           | In my case we went with embeddings and clustering to find
           | close papers to each other because llm were allucinating.
        
       | p-s-v wrote:
       | cool, how did you create it? whats the architecture like ?
        
         | dreadsword wrote:
         | Thanks very much! Architecture - is truly recidivistic - LAMP,
         | cron jobs, o3-mini, bootstrap. It works, its fast because its
         | not complicated, and b/c I'm doing things like updating hourly
         | vs. real time.
        
       | jhack wrote:
       | I'm REALLY liking this, way more than I thought I would. Great
       | job! What's your stack if you don't mind my asking?
        
         | dreadsword wrote:
         | Awesome - glad you're enjoying it and thank you for the kind
         | words!
         | 
         | My "Stack" ---- LAMP + o3-mini for editorial tasks + Bootstrap
         | for responsive front end. That is to say: Its old school, and
         | painfully functional. But, light & fast.
        
       | taftster wrote:
       | I'm not sure, something about the "Recent Stories Summary"
       | section (first view) is hard to read. The spacing is wrong. And
       | the blue font. Someone mentioned Garamond too.
       | 
       | It's creating a "wall of text" effect to me and I'm not able to
       | quickly skim and allow my eye to catch the bits that are
       | interesting to me.
       | 
       | As a comparison, the HN homepage is very accessible to me for
       | skimming and finding things to click into (like this entry).
       | 
       | UI is often quite subjective, understood. But I can't really
       | "scan" the first view fast enough. It's all blending together and
       | causes extra processing on my mind.
        
         | dreadsword wrote:
         | I hear you - there's something to be done there. My initial
         | thought was to stay as close to convention as I could (links
         | are blue!), but as the RECENT list gets long, its definitely
         | gets less scannable.
         | 
         | Thank you for the feedback!
        
           | taftster wrote:
           | I hear you about "links are blue" ... except when you are a
           | link aggregator.
           | 
           | The links are blue design from early HTML was meant to
           | highlight links in the context of a paragraph of prose, not a
           | list of link items. "Blue" means something special about the
           | text in the context of the text around it.
           | 
           | In this case, the blue font is distracting because the links
           | _are_ the content. You don 't need the blue to help your
           | links "stand out". Because the links are normal text, using a
           | normal palette would be appropriate.
           | 
           | I don't mind some subtle clues that these are links.
           | Underlines, slight grey text. Or even a subtle hover effect.
           | Two cents.
        
         | dreadsword wrote:
         | How about now? Story titles are still clickable links, but are
         | black. Made the story count a link as well, and kept it blue as
         | a visual cue.
        
           | taftster wrote:
           | Better, to be honest. Keep refining of course. But this is
           | definitely more readable.
           | 
           | I admit that straight black is not quite the right answer
           | either. A slightly toned down dark grey would be nice. And
           | again, subjectively, I like how HN has a row of non-link
           | smaller (lighter shaded) text under each listing, which I
           | think plays nice for the white space between each item.
        
             | bcrl wrote:
             | Personally, I far prefer black over grey. Grey is really
             | hard to read across a variety of lighting conditions and
             | devices. The older you get, the more important contrast
             | becomes.
        
               | taftster wrote:
               | Fair and good point. Sharp black bothers me, so just
               | adding in a little hue is nice for my eyes. But that's
               | me, of course.
               | 
               | Noting also that this text is #000000 black, per the CSS.
               | Maybe the background color helps soften it a little? Like
               | contrast white/black is hard on the eyes, but HN is not?
        
           | felideon wrote:
           | Some additional feedback:
           | 
           | There's no reason for both the story count and the story
           | summary to be clickable. It's confusing because:
           | 
           | (a) It's not clear what the number in parentheses even means
           | (until you click and infer)
           | 
           | (b) Separate links makes you think they lead to different
           | pages
           | 
           | Also, echoing another comment, it's not really clear what
           | "incoming" and "outgoing" stories mean. Maybe "new" vs.
           | "stale"?
        
       | tiaremnt wrote:
       | I just configured my own rss website to only find this awesome
       | solution. I'm crying right now if only it found you earlier I
       | would have saved me so much time. Also do you have the code
       | publicly available so that I can customize for my own needs?
        
       | MiiMe19 wrote:
       | This is exactly the stuff that I think LLMs are best at. We have
       | created the world's coolest string manipulator and this is
       | exactly the kind of things I think LLMs are best suited for.
       | Awesome job!
        
         | dreadsword wrote:
         | Cheers and thanks for the kind words! And yes - LLMs (at least
         | o3-mini) do a great job as my editorial team - the site is 100%
         | automated.
        
       | sweenzor wrote:
       | Very cool. Having an immutable record "time machine" you can use
       | to re-find something you remember reading is very humane. I'd
       | love to see this for world news, politics, etc.
        
         | dreadsword wrote:
         | Ah cool! it is built to be extensible, and I'll give you a
         | preview of another vertical here: https://northfeed.ca/
         | 
         | And - did you actually see the time machine at the bottom of
         | the right hand column? Or - was that just a wish list item of
         | yours?
        
       | hackncheese wrote:
       | Combines the strength of AI at summarizing text and easy access
       | to the actual information sources for verification, well done
       | well done!
        
         | dreadsword wrote:
         | Cheers and thank you very much --- yes, LLMs are very well
         | suited to editorial tasks!
        
       | clueless wrote:
       | looks very similar to https://particle.news how would you
       | distinguish your approach (other than the tech focus)?
        
         | dreadsword wrote:
         | Cool - particle looks great - I really like how visual it is.
         | 
         | Distinguishing characteristics - personally I get value from
         | the unambiguous timeline (no editorializing in /recent), and
         | (as nice as the visual is) the non-visual, super simplistic
         | presentation & the curated sources (...which I value b/c I
         | curated them myself haha).
         | 
         | So bottom line is that DS will appeal to a certain kind of
         | obsessive compulsive news consumer and synthesizer that wants
         | the right balance of signal to noise ands a streamlined
         | presentation that doesn't slow them down. I count myself among
         | that group!
        
       | wccrawford wrote:
       | Wow. That's amazing! I've bookmarked it because I think it's one
       | of the best news sites I've seen now.
        
         | dreadsword wrote:
         | Well thank you so much for the very kind words, and don't
         | hesitate to reach out with any feedback!
        
       | Biologist123 wrote:
       | Great idea! May I ask what the information source is?
        
         | dreadsword wrote:
         | Individual feeds from ~100 sites!
        
       | nathanwallace wrote:
       | A similar site I've enjoyed for >15 years (!!) is
       | https://techmeme.com/
       | 
       | I also use it's sister aggregator site for political news every
       | day - https://www.memeorandum.com/
        
         | dreadsword wrote:
         | Yes - Techmeme is definitely the archetype and a great product,
         | and I have spent lots of time there over the years as well!
        
       | swader999 wrote:
       | Maybe I'm the only one but I would love a feed that never showed
       | me items again that I've already scrolled past without engaging
       | in the first time.
        
         | stevage wrote:
         | Me too. That's the number one thing I always wish for with
         | every feed. And if I reach the end of the feed, that's fine.
        
           | taftster wrote:
           | Right, I'm so tired of "infinite scroll". There's a
           | mental/emotional reward for actually reaching The End of
           | something.
        
             | dasil003 wrote:
             | I wonder how much this is a factor of the widespread mental
             | health malaise that is often attributed to tech these days?
             | Certainly plenty of factors to go around, but consider the
             | connotation of "scrolling" and how common it is a default
             | replacement to boredom in modern life and suddenly it seems
             | quite insidious.
        
         | facundo_olano wrote:
         | I built that feature (auto mark as read by scrolling) into my
         | feed reader if you're up to self host and curate your sources
         | 
         | https://github.com/facundoolano/feedi
         | 
         | I did try to build a public facing news aggregator with a
         | similar ux but I couldn't pull it off purely based on client
         | side state (and I didn't want to do user management)
        
       | econ wrote:
       | Clicking "more" for a few extra words feels wrong.
        
         | dreadsword wrote:
         | Where are you seeing that?
        
       | stevage wrote:
       | I would love this but with more blogs and less product
       | announcements.
        
         | dreadsword wrote:
         | I hear you - today was heavier on product announcements than
         | normal I feel. And re: blogs - for sure: send me suggestions
         | and I'll add them...!
        
       ___________________________________________________________________
       (page generated 2025-10-23 23:01 UTC)