Otherwise you've ended up with a brief snapshot, and not the top posts of the day.
It also seems odd to have a "summary of 16/03" produced while that day has barely begun in the US timezone, so looking retrospectively at the previous day would make this better.
I think the concept is great, I'd love something like this even more broadly, sort of a daily "customizable" newspaper. The issue I see is that it's a bit... bland? Obviously you're doing this with AI and there's no other way to do it, but one of the main reasons why something like HN has stayed relevant for this long is its variety: front page stories often have remarkable diversity, not only in topics and content, but also in tone and writing style. I feel a digest like this one flattens everything more than I'd like.
> Obviously you're doing this with AI and there's no other way to do it
What do you mean "no other way to do it"? Traditionally these sort of things been curated, by humans who read and make judgements, how is that not another way to do it? Probably would solve the whole "bit... bland?" problem to, given the right curator.
I agree that this is likely to flatten out the depth of comments I come here for. It's also hard to get a brief that is tailored to the subset of posts you might actually be interested in.
The approach I tried was to rely mainly on what comments I've upvoted, have the AI look at those comments and gather context from the article/link and the parent comment chain, then give me a "here's what you learned yesterday" brief.
I had plans to add some memory to mention related things from recent weeks. Relying mainly on being able to visually code all this with n8n, and never quite got it working.
I've been thinking about this for a while too. Probably what I will do is create embeddings of the frontpage results and then let users pick 3-5 topics that they would like to see. Then summarize the top 10 for those topics.
Something I've been tinkering on for the last few weeks is absent.dev[1], was working towards getting the guts to share this on HN but there's a few things I want to polish first. This is the MVP, but it will essentially be moving towards what you're suggesting, much more customisable news aggregation and more importantly, where you consume it. Feed agnostic, channel agnostic, in the form(s) you want (longform, shortform, summary, tl;dr etc). You can check the clustering logic on the digest[2].
Not a perfect solution but I wonder if asking the LLM to preserve style when summarizing works well. I will have to try that. Because they do indeed otherwise default to bland slop style.
I can't see the page at the moment (getting the No digest yet).
I made a thing[0] that splits stories by day without mixing old popular with new stories. That helped cut down my HN visits to a few times per day. [I had originally made it to list all stories on one page and load story links at stops in a subway/metro commute.]
What I'm finding now is that there's too much noise at the top and what I really want to see are the stories not upvoted by mainstream/populist interests--if anyone knows a solution to that, please share.
Edit: I was hosting this on Vercel free tier, and since this post made it to the front page, I've hit Vercel's quota limit. I will work on getting around this.
? This has been done before, plus apps like Harmonic support Best by X hrs. Do people love re-inventing the wheel before googling "drive car from A to B"?
46 comments
I then went to "past" and nothing from yesterday.
I then realised this site is based off the current front-page.
So I forced the "past" page to be today, and it's the third result: https://news.ycombinator.com/front?day=2026-03-16
But it's not on my actual front-page.
So this must have been done at a very brief window when this story was top, which even hnrankings didn't capture: https://hnrankings.info/47393619/
I think this would be better if powered by https://news.ycombinator.com/front , which is relatively stable after a day.
Otherwise you've ended up with a brief snapshot, and not the top posts of the day.
It also seems odd to have a "summary of 16/03" produced while that day has barely begun in the US timezone, so looking retrospectively at the previous day would make this better.
Will look into tightening this up
> Obviously you're doing this with AI and there's no other way to do it
What do you mean "no other way to do it"? Traditionally these sort of things been curated, by humans who read and make judgements, how is that not another way to do it? Probably would solve the whole "bit... bland?" problem to, given the right curator.
The approach I tried was to rely mainly on what comments I've upvoted, have the AI look at those comments and gather context from the article/link and the parent comment chain, then give me a "here's what you learned yesterday" brief.
I had plans to add some memory to mention related things from recent weeks. Relying mainly on being able to visually code all this with n8n, and never quite got it working.
1. https://absent.dev/ 2. https://absent.dev/episode/ABS-0014/clusters
> Hackerbrief
> No digest yet. Trigger
GET /api/cron/digest.> GET https://hackerbrief.vercel.app/api/cron/digest
> 401 Unauthorized
hmm
Would it be possible to:
- do "horizontal" swiping gesture to go to next/previous summarized article? Kind of like instagram stories
- keep the link to original article as I scroll through the summary so I can quickly navigate to full article if the summary is interesting?
http://www.daemonology.net/hn-daily/
I made a thing[0] that splits stories by day without mixing old popular with new stories. That helped cut down my HN visits to a few times per day. [I had originally made it to list all stories on one page and load story links at stops in a subway/metro commute.]
What I'm finding now is that there's too much noise at the top and what I really want to see are the stories not upvoted by mainstream/populist interests--if anyone knows a solution to that, please share.
[0] https://hackerer.news/
Active:
https://news.ycombinator.com/active
Highlights:
https://news.ycombinator.com/highlights
https://hnarcade.com
This was for the bigfoot story: https://www.msn.com/en-us/news/us/a-new-bigfoot-documentary-...
I wonder why.