[airstrike]

It does feels like a good use of AI (ML, really) would be to write a "disaggregator" for HN that tags submissions by category and lets users browse the bits they care about. Wish I had time to do it....

[kirubakaran]

Here it is ;)

https://histre.com/hn/

[rendaw]

Oh that's great! I wish it kept the HN style, the contrast and density is too low for me

[kirubakaran]

Thanks. I'll create a HN-like theme.

In the meantime, if you install the browser extension, you can get the tags directly in HN itself. Would that address the ui issue?

Source: https://gitlab.com/histre/hn-tags

Chrome: https://chrome.google.com/webstore/detail/hacker-news-tags/i...

Firefox: https://addons.mozilla.org/en-US/firefox/addon/hacker-news-t...

[airstrike]

Thanks for the reply! The extension seems great at first but it doesn't let me filter out tags and basically just redirects me to your domain, so it's not really how I expect an extension to behave.

[kirubakaran]

I see, thanks for the feedback. I'll improve that.

[airstrike]

That's awesome! I second the other comment re: density and contrast

[kirubakaran]

Thanks, will do. Please see my cousin comment for a potential workaround.

[DevKoala]

The HN UI is good because in 20 seconds I can assess the full top page.

If you can figure out how to add the tags while keeping down the visual bloat I would consider a switch.

[kirubakaran]

Thanks, I'll create an HN theme for that page. BTW here's more discussion about this, back when I did a "Show HN" : https://news.ycombinator.com/item?id=35904988

[miki123211]

And a TL;DR, both for the articles themselves as well as the discussions.

I don't think a TL;DR can replace most articles that appear on HN, but it can certainly tell me whether the article is interesting, much better than any headline ever could. Especially so if the TL;DR is written by a neutral AI with no interest in making me click anything, and hence no qualms about surfacing the most important information to the top.

I actually tried to do this, but it was with GPT-3.5, and I didn't exactly like how it worked. I should look at this again, I wouldn't be surprised if the code I used back then could just be ported over to 2.5 Flash and produce much better results.