← Back to context

Comment by simonw

7 days ago

I built you this: https://tools.simonwillison.net/hacker-news-filtered

It shows you the Hacker News page with ai and llm stories filtered out.

You can change the exclusion terms and save your changes in localStorage.

o3 knocked it out for me in a couple of minutes: https://chatgpt.com/share/68766f42-1ec8-8006-8187-406ef452e0...

Initial prompt was:

  Build a web tool that displays the Hacker
  News homepage (fetched from the Algolia API)
  but filters out specific search terms,
  default to "llm, ai" in a box at the top but
  the user can change that list, it is stored
  in localstorage. Don't use React.

Then four follow-ups:

  Rename to "Hacker News, filtered" and add a
  clear label that shows that the terms will
  be excluded

  Turn the username into a link to
  https://news.ycombinator.com/user?id=xxx -
  include the comment count, which is in the
  num_comments key

  The text "392 comments" should be the link,
  do not have a separate thread link

  Add a tooltip to "1 day ago" that shows the
  full value from created_at

120 comments

simonw

Reply
yencabulator  1 day ago

That exclusion filter seems to be just a very dumb substring test? Try filtering out "a" and almost everything disappears. That means filtering out "ai" filters out "I used my brain not a computer".

simonw  7 days ago

I updated it to fetch 200 stories instead of 30, so even after filtering you still get hopefully 140+ things to read.

https://github.com/simonw/tools/commit/ccde4586a1d95ce9f5615...

rottc0dd  7 days ago

Top story: Kiro: new agentic IDE

simpaticoder  7 days ago

An interesting example of both LLMs' strengths and weaknesses. It is strong because you wrote a useful tool in a few minutes. It is weak because this tool is strongly coupled to the problem: filtering HN. It's an example of the more general problem of people wanting to control what they see. This has existed at least since the classic usenet "killfiles", but is an area that, I believe, has been ripe for a comprehensive local solution for some time.

OTOH, narrow solutions validate the broader solution, especially if there are a lot of them. Although in that case you invite a ton of "momentum" issues with ingrained user bases (and heated advocacy), hopelessly incompatible data models and/or UX models, and so on. It's an interesting world (in the Chinese curse sense) where such tools can be trivially created. It's not clear to me that fitness selection will work to clean up the landscape once it's made.

  • azath92  7 days ago

    Not sure what a local solution would look like when what you see is on websites, maybe a browser extension? we just made a similar reskin as a website, and it works great, but is ultimately another site you have to go to. Its another narrow solution with some variation (we do use AI to do the ranking rather than keyword filtering), but im interested in the form factors that might give maximal control to a user.

  • aorloff  7 days ago

    It is strong because you believed it created something of value. Did it work ? Maybe. But regardless of whether it worked, you still believed in the value, and that is the "power" of AIs right now, that humans believe that they create value.

NotPractical  7 days ago

Probably would work better as a userscript, so you don't have to rely on a random personal website never going down just to use HN. I don't have a ChatGPT account but I am curious as to if it could do that automatically too.

  • aleksituk  7 days ago

    Interesting idea, we could consider that as an alternative implementation to https://www.hackernews.coffee/. While we are planning on making it open-source, a userscript would be even more robust as a solution, although would need a personal API key to one of the services.

michaelcampbell  4 days ago

This is interesting, but I found it amusing that you used:

"I built..." and "o3 knocked it out in a couple minutes...", not ironically, talking about a tool to keep us from having to be inundated with AI/LLM stuff.

CL_ergo  7 days ago

There's a special kind of irony to use AI to help out the people who hate AI.

It's not hypocrisy or anything negative like that, but I do find it amusing for some reason.

pxc  7 days ago

This is neat, but with the given filters you autoselected (just the phrases "llm" and "ai"), of the 14 stories I see when I visit the page, 4 of them (more than 25%!) are still stories about AI. (At least one of them can't be identified by this kind of filtering because it doesn't use any AI-related words in its headline, arguably maybe two.)

  • azath92  7 days ago

    people have said it elsewhere, but I think you might have to fight fire with fire if you want semantic filtering.

  • IanCal  7 days ago

    > of the 14 stories I see when I visit the page, 4 of them (more than 25%!)

    Llm maths? ;)

    • juped  7 days ago

      25% of 14 is 3.5. 4 is more than 3.5. Ask grock if you still don't get it.

bodash  7 days ago

I also built https://lessnews.dev (HN filtered by webdev links)

One decision I had to make was whether the site should update in real time or be curated only. Eventually, I chose the latter because my personal goal is not to read every new link, but to read a few and understand them well.

heavyset_go  7 days ago

Almost certain you can use the HN Algolia to do the same thing by excluding terms

  • simonw  7 days ago

    I had to switch away from Algolia - the problem is they only model "show items on the homepage" using a tag that's automatically applied to exactly 30 items, which means any filtering knocks that down to eg 15.

    I switched to using the older firebase API which can return up to 500 item IDs from the current (paginated) homepage - then I fetch and filter details of the first 200.

    https://github.com/simonw/tools/commit/ccde4586a1d95ce9f5615...

jtbaker  7 days ago

feature request for OP: sort by "LLM Agentic AI" embedding cosine distance desc

schmookeeg  7 days ago

AI solving the too-much-AI complaint is heart-warming. We're at the point where we will start demanding organic and free-range software, not this sweatshop LLM one-shot vibery.

Love it. :D

duncangh  7 days ago

simon how do you get so much done? It’s incredible. Would love to see the day in the life TikTok :P

Bukhmanizer  7 days ago

I think there is a fundamental disconnect in this response. What the user is asking for is for a procedural and cultural change. What you’ve come up with is a technical solution that kind of mimics a cultural change.

I don’t think it’s wrong, but I also don’t think we can really “AI generate” our way into better communities.

  • op00to  7 days ago

    Simonw’s response is the right response. You should not bend the community to your will simply because you do not like the majority of the posts. Obviously many people do like those posts, as evidenced by them making the front page. Instead, find ways to avoid the topics you do not desire to read without forcing your will on people who are happy with the current state.

    Let me stop folks early, don’t make comparisons to politics or any bullshit like that. We’re talking only about hacker news here.

rjh29  7 days ago

[flagged]

  • simonw  7 days ago

    In a thread devoted to filtering out AI, I gave them a way of filtering out AI.

    (The fact that I wrote it using AI doesn't really matter, but I personally found it amusing so I included the prompts.)

    • dttze  7 days ago

      > The fact that I wrote it using AI doesn't really matter

      Given that it is a poorly implemented solution that doesn't really do what the OP asked, yes it is.

fouronnes3  7 days ago

Great example of the power of vibe coding. The first item is literally "Kiro: A new agentic IDE".

  • raincole  7 days ago

    There is literally an input box to put terms you want to exclude...

    The prompt asks for "filters out specific search terms", not "intelligently filter out any AI-related keywords." So yes, a good example of the power of vibe coding: the LLM built a tool according to the prompt.

  • firesteelrain  7 days ago

    I like this because things can stay permanently filtered. Just not across devices. But that wasn't one of the original requirements.

  • aorloff  7 days ago

    Also a great example of how software can be perfectly to spec and also completely broken.

  • savolai  7 days ago

    llm, ai, cuda, agent, gpt.

    Wish it returned more unfiltered items tho.

    • bee_rider  7 days ago

      Isn’t knocking out CUDA going to take out a significant chunk of GPGPU stuff with it? I can see wanting to avoid AI stuff, for sure, but I can’t imagine not wanting to hear anything about the high-bandwidth half of your computer…

      1 reply →

voxl  7 days ago

[flagged]

  • simonw  7 days ago

    Not at all. I think you misunderstood the point I was making here.

    I think the idea of splitting Hacker News into AI and not AI is honestly a little absurd.

    If you don't want to engage with LLM and AI content on Hacker News, don't engage with it! Scroll right on past. Don't click it.

    If you're not going to do that, then since we are hackers here and we solve things by building tools, building a tool that filters out the stuff you don't want to see is trivial. So trivial I could get o3 to solve it for me in literally minutes.

    (This is a pointed knock at the "AI isn't even useful crowd", just in case any of them are still holding out.)

    There's a solid meta-joke here too, which is that filtering on keywords is a bad way to solve this problem. The better way to solve this profile... is to use AI!

    So yeah, I'm not embarrassed at all. I think my joke and meta joke were pretty great.

  • ukprogrammer  5 days ago

    It solves the problem in a simpler and faster way than OP requested. OP does not wish to see AI content, this tool solves it. Simple.

    Your statement is factually incorrect. Have you no embarrassment?

pton_xd  7 days ago

[flagged]

  • gamerDude  7 days ago

    Now that's impressive. I've worked with and managed many humans and almost never do I get want I want back in one prompt.

    Even ones with detailed specs and the human agreed to them don't come back exactly as written.

th0ma5  7 days ago

Perhaps you should add a privacy policy or just release the source rather than assume people will trust your site. Why do you do these demos if you aren't upfront about all the things the LLMs didn't do?