Show HN: Hacker News with AI stories filtered out

Posted by postalcoder 5 hours ago

Hi folks,

I've noticed that a lot of people here seem exhausted by the amount of AI news on the front page. I shared hcker.news here a year ago and it has since gained a ton of filtering features, including a dedicated AI filter, so I figured I should tell more people about it.

The filter works in three passes:

  1. Known AI-related keywords and domains are filtered automatically.
  2. An agent reviews the remaining articles and removes those it identifies as AI-related.
  3. I make the call on uncertain cases.

You can also exclude GitHub repos posted to HN that show signs of AI authorship. The filter checks:

  - Commit messages for agent attribution
  - Contributors for known coding agents
  - Repository files for agent instructions and configs

No filter will be perfect, but this is as good as it gets. lmk what you think. Cheers.

Comments

Comment by k310 2 hours ago

I don't normally read the front page, more /newest

Any chance of implementing that?

Your site works with my Firefox auto-pager, which is really nice for archiving posts for later search.

Comment by postalcoder 1 hour ago

Hmm, right now I only process a subset of all submissions to keep things lean, so this is the closest that the site can do to /newest right now: https://hcker.news/?filter=top200&ai=exclude

Feel free to email me.

Comment by k310 20 minutes ago

No problem, and thanks. I understand the size of the problem, and why the above link is "most upvoted"

By archiving all, I can easily filter titles as text, if I really wanted to do so, but it's not all that important for me. grep -v works!

Again, thanks for the effort.

Comment by coldpie 4 hours ago

I also built a browser extension to do this client-side. It just auto-clicks the Hide links for any story with an AI-related term. Source & Firefox add-on link here: https://github.com/ColdPie1/enough-ai-on-hn

Comment by postalcoder 4 hours ago

There are a lot of ways of tackling this, but the only way to truly filter everything out is to update the list constantly.

My filter currently has 146 keyword filters and 101 domain filters. Even with those, I've had to filter almost 400 exact urls on top of that in the past two weeks!

Comment by coldpie 4 hours ago

Definitely a lot of approaches. I like that mine is dead simple & runs in the browser; but an advantage to a deeper inspection like yours is it will catch those endless AI thinkpieces that don't obviously stick an AI term in the title. Pros & cons!