news.ycombinator.com

Ask HN: How do you keep up with HN these days?

simonebrunozzi · 68 points · 121 comments · 15 hours ago

In the last 2-3 years, mostly because of AI, keeping up with interesting articles on HN has become harder and harder. How do you deal with it? Besides the simple solution of simply ignoring interesting stuff more and more.

Comments

5 preview comments · loading full thread
codingdave10 hours ago

Think about what problem HN solves in your life. To achieve that solution, is it required that you "keep up"? Or does HN serve its purpose in your life when you casually browse some stories once in a while? I suspect that when you think about those questions, you'll realize that it really doesn't matter if you keep up or not. If something comes to this industry that is big enough to impact your actual life, you'll hear about it regardless of how often you read HN. Odds are, there is no problem you need to deal with. HN is here when you have time for it, but your life is there all the time. Focus on the right one.

romaniitedomum14 hours ago

Same way as always. Open the page, glance down it to see if there's anything that interests me, hit hide on the domains that I never want to see anything from. Lather, rinse, repeat. But I'm guessing you have more of a FOMO (Fear Of Missing Out) kind of problem, which admittedly I don't have. However, you could look at something using RSS, maybe in combination with an agent told to find and show articles based on some heuristics. Personally, I'm OK with missing something. If it's good, I figure it'll surface somewhere else and impinge on my notice sooner or later.

pllbnk10 hours ago

I have vibe-coded a HN RSS feed reader and plugged an LLM into it to learn my preferences. So far it's been in the training mode over the past week and half but it's been getting better at predicting and I hope eventually to have it filter news according to my interests. It's been tracking all the news I have opened and trying to build my taste profile. If my experiment doesn't work out, given that it's a naive training without any special methods, I will try to come up with more advanced approaches for the next iterations. Took about an evening to build it to my liking, so not going to share it unless I am happy with the result. Here's the screenshot for inspiration: https://imgur.com/a/TszTHQb

xrd8 hours ago

I built a Firefox extension that allows me to track comments. https://plzat.me When I see an interesting topic, I will read through the comments. If I see a good comment, I add it to plzat.me (it adds a little @ symbol next to the comment actions). That "subscribes" to that comment, so I get an email update if anyone replies to it. And, then I have a little dashboard which collects all the comments I've subscribed to by the topic. I review those topics and can cycle through the comments to remind myself about interesting things. plzat.me is basically a bookmarking tool, but with email updates of the threads, and a customized dashboard which makes it easier to review recent bookmarks. Firefox extensions work on mobile so I use this from my phone and desktop and the subscriptions are synced. It uses pocketbase as the backend.

m4tthumphrey13 hours ago

This is a very apt right now. The amount of AI posts is... boring to say the least. I've always used the comments to upvotes ratio to workout if an article is worth reading. If the comments are higher than the upvotes, it's poor. Vice versa it's worth looking into. I skip all AI posts.