Love the summaries, I must say some stories I haven't considered interesting seeing them in the original HN view only caught my attention after my eyes landed on the summary.
At the same time, I very much dislike the layout. Masonry-style layouts, at least to me, feel more "artsy" than practical. Multiple rows being displayed at once, with the most crucial information being chaotically all over the place instead of arranged in a way that makes it easy to scan it with your eyes, make me feel like I'm bombarded with information. It's very hard to follow along and very easy to miss articles; almost anxiety-inducing, even. There's hardly any point to this on a website; it's not like you're wasting any paper.
I think the layout _wants_ to look like a newspaper, but just doesn't quite end up looking like one. where a newspaper may have longer columns mixed in with shorter articles, this one has mostly short articles that then don't quite align. But hey, good luck to this project!
One big thing with the news paper is that there was a larger main story that worked as a visual anchor and the columns/subsections could be placed freely on the edges as necessary
Having used it myself, I see the tell-tale signs of Claude using the /frontend-design skill. Good work! I haven't yet had it give me something I actually like, but this is good. Also very clever idea! I approve :-)
Suggestion though: The text is really small and impossible to read at regular zoom. I had to zoom it to 200% to be able to read it. I'd suggest increasing the default text size
This is gorgeous. Makes me feel like I'm picking up an old news sheet. Forces me to read slowly from which I then enjoy the reading much more it's like difference of drinking a fine wine from a glass instead of a straw in the wine bottle.
except those were laid out by hand with intent, whereas this one just kind of dumps all stories on a masonry board and calls it a day. This is likely why reading a (good) newspaper feels effortless, whereas reading this "forces you to read slowly".
I'd say that that's a feature of modern-ish newspapers with "advanced" layouting techniques from early to mid 20th century.
A news sheet from THE olden days (eg Victorian era), looks more like a wall of text, set as tightly -- an uniformly -- as possibly, which is not surprising considering the limitations imposed by the technology of the day.
As for story selection, I think the collective hivemind of hn-ers would be a worthy substitute for an editor in chief.
The inception effect here is hilarious. Watching this get its own front page while the subtitle lags behind with the previous top posts is weirdly funny.
I whipped up a quick uBO rule to fix that (also makes meta-information lines readable):
thefrontpage.dev##p.newspaper-copy:style(line-height: normal !important; font-size: 1rem !important;)
thefrontpage.dev##p.article-meta:style(font-size: 1rem !important; font-weight: normal !important; letter-spacing: normal !important;)
I agree, but I think it's that small because otherwise, the justified text results in ridiculous spacing.
OP, consider reducing the number of columns from 4 to 3 (at least below very wide viewports), increasing the font size, and then also allowing hyphenation. I think the last will help a lot with the justification problem.
The Front Page highlights a diverse set of tech and science stories"
It is interesting the summary it generated for itself wasn't able to describe itself as a Hacker News content view. It missed the big picture meta context.
It’s exceptional. Here in camp “userscripts can offer some improvements”, would necessarily not say perfect, but definitely amazing how it’s continuing to stand the test of time.
I love this. Very cool that it made the front page and therefore has an entry for itself. I wonder if the summary could be updated again so that it includes a reference to itself in its summary of itself
I love it! I discovered it'll switch to a 3 column view if I take the zoom to 200%, I'd maybe prefer it at less but it's a bit tricky to guess if that's true or not. Regardless, it's very nice. And infinite scroll for the hackernews feed is a bonus!
You need some filler for the space at the bottom. Something like ads from the 1800's for quack medical devices or Radium Therapy. Maybe something wildly misogynistic advertising laudanum.
I love the presentation. My initial impression is that it's easier to read, in no small part due to the font choice, color palette, and tabloid-style layout. I would love to have an RSS reader that presents my RSS feed in the same way.
Using text-align: justify for questionable aesthetic purpose here really hurts readability, especially on a narrower viewport like the 1026px viewport of Safari with sidebar on an iPad Pro 12.9’’ (although it’s probably more of a problem of the four column layout on that specific narrow viewport; three should be better).
I agree that text-align: justify should be the way to go. Don't discard having a "config" menu in the header somehow to change this option along body text size as some other people might find it useful, which could then use localstorage to preserve the settings. Love the website by the way! I'm used to skim through brutalist.report in a daily basis but this one may be a worthy replacement :)
Thanks, technically it scrapes every 10 minutes the first 3 pages of HN and the first 3 /newest, fires up a Chrome instance with puppeteer, visits each site with a spoofed GoogleBot UserAgent to avoid paywalls, scrapes `document.body.textContent`, sends it to openrouter/free and asks to summarize. We also collect the opengraph images to show in that step. One difficulty was getting the responses to not be garbage enough but with some prompt tweaks that fixed. It runs on a small VPS with bun. Biggest challenge was setting up the deployment pipeline actually because I hadn't done it before. But now I can `git push` and it gets updated and restarts fine :)
This is great )) maybe do random templates similar to newspapers (like photo on the left, photo on the right, one block full width, then 3 columns, etc).
w/o instruction to avoid the same generic “this is an article about” preambles (or non-SotA model)
Not that summaries are reliable anyway. Big picture, maybe, but poor importance classification (bad at extracting key points). Understandable for this use case but unwilling to read potentially false summaries given risk I go around remembering them (never having read the original piece).
Could you explain in more detail how this works? Would it break for paywalled articles that HN links to? (Usually someone posts a workaround archive link in the comments, but your AI probably doesn’t account for that, right?)
I’m writing something similar to Moltbook for HN where AIs browse HN’s front page and leave comments. But I wasn’t sure whether AIs could reliably browse an arbitrary website. (Paywalls would break it, as just one example.)
But it seems like your AI works fine for all the sites. If you have time to explain, what exactly do you do to generate your summaries? Thanks!
EDIT: I see that sometimes your summaries fail, e.g. “Ferrari Luce - Summary not available.” It looks like it fails because it’s a JS heavy site. But I was thinking a headless browser could take screenshots of the page and then feed the screenshots to AI. I’m not sure how practical that is to implement though.
The solutions to this don’t seem to be great for the web or polite to use. An industry exists to cheaply do it, but not very ethical and surely a massive ToS violator.
Why does someone go to the effort/expense of doing summaries without adding tags? The goal is less slop and not more, and this really just hurts usability after you've already spent money that could actually help? Isn't this the whole value proposition for literally everyone or am I nuts? I don't want a summary. I will switch immediately to the first alternative that allows tags/categories/filtering.
The summaries come from openrouter/free so they cost nothing. Could probably also ask the AI to produce tags, will do some experiments! Thanks for the suggestion!
Some of them are really large and I'm not resizing them or storing them, just proxying their og image directly. So they might be taking long to respond from the original source. Also getting hammerred by being in the front page.
Love the summaries, I must say some stories I haven't considered interesting seeing them in the original HN view only caught my attention after my eyes landed on the summary.
At the same time, I very much dislike the layout. Masonry-style layouts, at least to me, feel more "artsy" than practical. Multiple rows being displayed at once, with the most crucial information being chaotically all over the place instead of arranged in a way that makes it easy to scan it with your eyes, make me feel like I'm bombarded with information. It's very hard to follow along and very easy to miss articles; almost anxiety-inducing, even. There's hardly any point to this on a website; it's not like you're wasting any paper.
I think the layout _wants_ to look like a newspaper, but just doesn't quite end up looking like one. where a newspaper may have longer columns mixed in with shorter articles, this one has mostly short articles that then don't quite align. But hey, good luck to this project!
One big thing with the news paper is that there was a larger main story that worked as a visual anchor and the columns/subsections could be placed freely on the edges as necessary
If you love summaries on HN, check out https://hncompanion.com.
Great layout on mobile, but not so great on wider screens, I find it hard to scan as well
Having used it myself, I see the tell-tale signs of Claude using the /frontend-design skill. Good work! I haven't yet had it give me something I actually like, but this is good. Also very clever idea! I approve :-)
Suggestion though: The text is really small and impossible to read at regular zoom. I had to zoom it to 200% to be able to read it. I'd suggest increasing the default text size
I've noticed that Claude always defaults to really small text. They need to train readability into it.
Indeed!
This is gorgeous. Makes me feel like I'm picking up an old news sheet. Forces me to read slowly from which I then enjoy the reading much more it's like difference of drinking a fine wine from a glass instead of a straw in the wine bottle.
Kudos to the author.
> feel like I'm picking up an old news sheet
except those were laid out by hand with intent, whereas this one just kind of dumps all stories on a masonry board and calls it a day. This is likely why reading a (good) newspaper feels effortless, whereas reading this "forces you to read slowly".
I'd say that that's a feature of modern-ish newspapers with "advanced" layouting techniques from early to mid 20th century.
A news sheet from THE olden days (eg Victorian era), looks more like a wall of text, set as tightly -- an uniformly -- as possibly, which is not surprising considering the limitations imposed by the technology of the day.
As for story selection, I think the collective hivemind of hn-ers would be a worthy substitute for an editor in chief.
The inception effect here is hilarious. Watching this get its own front page while the subtitle lags behind with the previous top posts is weirdly funny.
I can’t see this post on the news frontpage though
Screenshot - https://i.ibb.co/zTTK1hQR/IMG-6526.jpg
Building a Hacker News client has long been a rite of passage because the read-only API is freely available, cool to see more experiments like this.
I believe at this point pretty much half of the users might have their own client :)
I am almost certain this layout is generated by AI, because I vibe coded the exact same newspaper-like style weeks ago.
Yes ! Building a news website with Claude design give me the same design, background color, text size …
Somehow, Claude seems to have developed a default nostalgic newspaper aesthetic despite being so young.
me too… this felt awkward: https://duobook.co/explore-stories
Cool, but body font size is too small for comfortable reading!
Sounds like an authentic HN experience to me!
I keep it at 150% zoom level. That would still be on the small side if it was the default. But at least it's somewhat readable this way.
OP, I love the font size as is, have multiple options if you're going to change things! Remember the users that loved things as they were!
I did increase it in the meanwhile from when that comment was posted.
I whipped up a quick uBO rule to fix that (also makes meta-information lines readable):
EDIT: changed to 1rem as someone else suggestedI agree, but I think it's that small because otherwise, the justified text results in ridiculous spacing.
OP, consider reducing the number of columns from 4 to 3 (at least below very wide viewports), increasing the font size, and then also allowing hyphenation. I think the last will help a lot with the justification problem.
Or have a button that makes the text left-aligned for easier reading.
I think that very much defeats the point of making it look like a newspaper.
Which might be fine? Since web pages are not newspaper sites one might say its just not the ideal way of presenting information.
This entire submission is styled to look like a newspaper. If you just want information that's available at news.ycombinator.com.
An overridden `.newspaper-copy { font-size: 1rem; }` works well.
Love it.
I would love that the size of the article is based on the number of upvotes (hardcoded).
* > 500 => take full width or 3. * 500 > 100 => Show it as right now. * > 100 => Just show the title.
"Hacker News front page as a site
The Front Page highlights a diverse set of tech and science stories"
It is interesting the summary it generated for itself wasn't able to describe itself as a Hacker News content view. It missed the big picture meta context.
I thought it already had a site?
It doesn’t have a website, it has a motherfucking website.
And it’s fucking perfect.
It’s exceptional. Here in camp “userscripts can offer some improvements”, would necessarily not say perfect, but definitely amazing how it’s continuing to stand the test of time.
https://motherfuckingwebsite.com/
Beautiful
I love this. Very cool that it made the front page and therefore has an entry for itself. I wonder if the summary could be updated again so that it includes a reference to itself in its summary of itself
I love it! I discovered it'll switch to a 3 column view if I take the zoom to 200%, I'd maybe prefer it at less but it's a bit tricky to guess if that's true or not. Regardless, it's very nice. And infinite scroll for the hackernews feed is a bonus!
You need some filler for the space at the bottom. Something like ads from the 1800's for quack medical devices or Radium Therapy. Maybe something wildly misogynistic advertising laudanum.
I actually recently submitted something similar - https://briefin.com/hackernews/
Less like good-old newspaper, but instead made for scannability & readability, with discussion highlights for each story.
Any feedback greatly appreciated!
One of the things I miss from Slashdot (I used to read it before HN) were the short summaries. Thanks!
I love the presentation. My initial impression is that it's easier to read, in no small part due to the font choice, color palette, and tabloid-style layout. I would love to have an RSS reader that presents my RSS feed in the same way.
Anything to make the site nicer on the eyes! I did this a while ago: https://antoinetoussaint.github.io/pretty-hackernews/
Using text-align: justify for questionable aesthetic purpose here really hurts readability, especially on a narrower viewport like the 1026px viewport of Safari with sidebar on an iPad Pro 12.9’’ (although it’s probably more of a problem of the four column layout on that specific narrow viewport; three should be better).
Made it 3, try again perhaps. Changing to text-align: left really destroys the aesthetic though.
I agree that text-align: justify should be the way to go. Don't discard having a "config" menu in the header somehow to change this option along body text size as some other people might find it useful, which could then use localstorage to preserve the settings. Love the website by the way! I'm used to skim through brutalist.report in a daily basis but this one may be a worthy replacement :)
It could probably be helped a bit by enabling auto hyphenation, but ultimately browsers aren't optimized for typesetting narrow columns of text
Great idea, I'm trying this.
Nice. "The Register" meets Hacker News. The fonts an colouring might need a few tweaks.
Still though, it takes me back to the original BetaNews.com and how Winamp.com used to do their news.
Pretty nice, Can you share some tech details and challenges
Thanks, technically it scrapes every 10 minutes the first 3 pages of HN and the first 3 /newest, fires up a Chrome instance with puppeteer, visits each site with a spoofed GoogleBot UserAgent to avoid paywalls, scrapes `document.body.textContent`, sends it to openrouter/free and asks to summarize. We also collect the opengraph images to show in that step. One difficulty was getting the responses to not be garbage enough but with some prompt tweaks that fixed. It runs on a small VPS with bun. Biggest challenge was setting up the deployment pipeline actually because I hadn't done it before. But now I can `git push` and it gets updated and restarts fine :)
Beautifully unusable
I go by comments count, so wish that count stands out more
I like the concept, the grid and the design. but the small text description is hurting my eyes.
Just made it a bit bigger.
It renders really well! Sad not to see the Ferrari Luce though.
This is so cool! I'd love for it to have a front-page-like layout where "trending" news would have a bigger placement in the UI
Anyway, great work :)
Kind of makes me realize that the thumbnails sometimes make me click, while on HN the titles make me click. Weird how that works.
I loved the mobile version. I disliked that bold text are scattered everywhere.
Very nice. It'd be cool to have an option to collapse the summary content to skim through everything.
Nice idea, I would not use AI summaries though but the actual first X words from each link real text (and using the README for repos).
What about a global toggle to switch between the AI summaries and article snippets?
But defaulting to article snippets ;)
This is great )) maybe do random templates similar to newspapers (like photo on the left, photo on the right, one block full width, then 3 columns, etc).
I hope the V2 will be like 'It happened tomorrow' (the 1944 movie with Veronica Lake)
looks lovely, but can you borrow text styling and typography from a modern media website like NYT WaPo or some other major news outlet?
This would make it easier to read
Brilliant! IMO could be even better if the number of points/comments was easier to scan.
Love. Relax the leading, though. The tight lines make it feel claustrophobic.
Would be cool to see different column layouts too!
Yea -- it could use votes to pick a hero article, or change summary length.
Very nostalgic. Looks dope
Nice! Happy to see the site appearing as itself on the front page doesn't cause some crazy recursive crash :)
Cool, seems need some deduplication. Maybe when you turn to the new page, some items fall back.
It is possible. Will look into it.
this looks dope! what's next? a Hacker News radio?
This reminds me of yahoo.co.jp in a good way
This is really cool a lot less clicking!
i love it. would be cool to get the date lookbacks too - like this https://news.ycombinator.com/front?day=2026-05-22
Nice design, gives a cozy feeling similar to reading a newspaper
Why is the text one long paragraph? Makes it very hard to read?
Because I'm telling the AI "summarize it to one paragraph".
OK. Tell it not to!
The formatting, etc looks all nice, but it's not worth reading.
w/o instruction to avoid the same generic “this is an article about” preambles (or non-SotA model)
Not that summaries are reliable anyway. Big picture, maybe, but poor importance classification (bad at extracting key points). Understandable for this use case but unwilling to read potentially false summaries given risk I go around remembering them (never having read the original piece).
Could you explain in more detail how this works? Would it break for paywalled articles that HN links to? (Usually someone posts a workaround archive link in the comments, but your AI probably doesn’t account for that, right?)
I’m writing something similar to Moltbook for HN where AIs browse HN’s front page and leave comments. But I wasn’t sure whether AIs could reliably browse an arbitrary website. (Paywalls would break it, as just one example.)
But it seems like your AI works fine for all the sites. If you have time to explain, what exactly do you do to generate your summaries? Thanks!
EDIT: I see that sometimes your summaries fail, e.g. “Ferrari Luce - Summary not available.” It looks like it fails because it’s a JS heavy site. But I was thinking a headless browser could take screenshots of the page and then feed the screenshots to AI. I’m not sure how practical that is to implement though.
The solutions to this don’t seem to be great for the web or polite to use. An industry exists to cheaply do it, but not very ethical and surely a massive ToS violator.
This was the natural length of a paragraph before the emergence of engagement driven microblogging.
It's not about the length l. The point of a paragraph is to convey one idea. Some of the paragraphs don't do that.
Because its AI slop. It’s not a designed website.
No, he admitted it's a prompt issue.
Nice try at trying to get me to read the friendly articles ;)
oh this is sick; i wonder where the curly bits at the top and bottom came from; based on the svg artifacts it looks converted from a raster
Tricks of the trade :)
Why does someone go to the effort/expense of doing summaries without adding tags? The goal is less slop and not more, and this really just hurts usability after you've already spent money that could actually help? Isn't this the whole value proposition for literally everyone or am I nuts? I don't want a summary. I will switch immediately to the first alternative that allows tags/categories/filtering.
The summaries come from openrouter/free so they cost nothing. Could probably also ask the AI to produce tags, will do some experiments! Thanks for the suggestion!
Its like reading a newspaper of sorts.
Previews are v slow to load for some reason
Some of them are really large and I'm not resizing them or storing them, just proxying their og image directly. So they might be taking long to respond from the original source. Also getting hammerred by being in the front page.
hey that's pretty cool. I think I still prefer "distill HN" cleanliness though. What made you create this.
I didn’t make this lol; just something cool I’ve found
Great job. Looks awesome.
How do I turn to page 2?
This looks amazing!!!
Nice. I like the yellowish paper texture.
Bravo!
this looks sick
AI Slop
Is it just me or is there something slightly weird about scrolling? Maybe font or color. Im on mobile.
This page now contains itself.
Now do clay tablets.
Nice design, but I can't afford the $3.50 price of the cup of coffee, atm (◡︵◡)(◠‿◠)
this is now my new default for hackernews.
[dead]
[flagged]
[dead]
[dead]