* It filters out things that are clearly not AI related (like the one titled ' Mind-altering drugs played key role in rise of Andean civilization ') - or maybe it's just slow to update (that post was 3 hours ago)
* No ability to go to the next page
* Order is often different than on HN, even account for the missing posts. It's mostly the same, but not quite, which always throws me for a loop to see if something else is missing.
otherayden 4 days ago [-]
Thank you for sharing my site :)
gonzalohm 4 days ago [-]
Do you know if there is a way of pointing any of the hackernews phone apps to your site instead of the official one?
otherayden 4 days ago [-]
I don't personally use those apps so I'm not sure, but if they're open source I'm confident you could easily update them to work with my site. In case it's useful, here's the source code https://github.com/leiDnedyA/hn-without-ai
toomuchtodo 4 days ago [-]
Huh, perhaps there is a project to be done to consume the HN firehose and serve it AT Proto style from the firehose. HN mobile clients can then pick the feed they want. AI? No AI? Politics? No politics? Frameworks? No frameworks? Choose your own HN post feed adventure. Read replica esq consumption, writes (comments, posts, votes) go to the primary data store (HN).
postalcoder 3 days ago [-]
You can do a lot of this stuff w/ the feed builder on hcker.news.
xvinci 4 days ago [-]
It does not have a license so it cannot be used though.
Thank you for basically only filtering and not changing the style. :)
WarcrimeActual 3 days ago [-]
Help me out here. Is AI something prevalent on HN now? I check the site a lot but just browse headlines and visit some sites.
buggy6257 3 days ago [-]
At the bottom of the linked site, it says "79 of 179 submissions survived the filter" so if only ~44% survived I'd say that counts as "prevalent" yeah.
WarcrimeActual 10 hours ago [-]
I guess I more meant what is it filtering. Anything talking about AI, or just things created by it? And it created by AI is the filter, how are they discovering that?
Instead of filtering keywords this ranks the content using Pangram. But it's also pretty effective at filtering content about AI. Turns out that a lot of LLM tooling projects have LLM written project descriptions/blog posts.
It's amazing to see how many of the "AI hurts my brain" posts are apparently written by an LLM.
OPs solution does more than keyword filtering. But its still about filtering out "content about ai" not filtering out "ai written content".
adrianwaj 3 days ago [-]
Great point. I think the key is differentiating between "prompt generated" content vs "AI as a Topic" content and then being able to toggle them at will.
I am not averse to prompt-generated content, but it should be marked and quoted as such, just like any other reference. If it's not, it's like the author is double-cheating.
In fact there are no shortage of comments here on HN, especially open-ended questions that could've been plugged into a bot for an answer. Avoiding LLMs altogether is foolhardy. It's a matter of balance, and being able to write a good prompt is a skill - no mental atrophy there. Content derived from non-English sources using English-based LLMs is also an interesting area. [1]
It's possible to obtain AIaaT from https://aibriefs.news/ and then prune it elsewhere if need be. But the best aggregators like that may be machine-generated with a lot of human moderation. I wonder if that is 100% machine generated.
Nice! I was considering doing this but the Pangram API is very expensive. Then I considered training my own model and I fortunately stopped at the edge of that rabbit hole.
nilsherzig 4 days ago [-]
Yea very expensive (hence me siphoning another page haha).
Im trying to get something cheaper to work, Pangram has some nice docs on how to build something like their service https://github.com/pangramlabs/EditLens, they even have training data online.
The harm a missclassification carries is much lower for a hn post than a masters thesis, so we might be fine with a worse model.
postalcoder 4 days ago [-]
Yeah agree, Pangram puts out interesting material. I recently came across their v4 technical report and they shared a lot more than I would have expected them to.
But see, here I am back at the edge of the rabbit hole, and you're trying to pull me in. I refuse!
If you do end up training a model, send me an email and maybe I can tie it into the site.
nilsherzig 4 days ago [-]
Will do, thanks for hcker.news btw, has been my main mobile client for couple of months. Of all things i like the changelog most, its nice to have a quick view about new stuff, especially if the website changes somewhat faster than usual.
postalcoder 3 days ago [-]
Thanks! I always forget to update the changelog for a bunch of stuff. I'm glad you have eyes on it, I'll be more mindful to add to it.
The AI spam is part of the issue, but not only. Maybe it's rose tinted glasses, but it feel like HN posts and comments quality have dropped significantly compared to ~5 to 10 years ago.
It used to have a lot more really technical subjects, with comments from experts on the topic.
Now days it seems to be a lot more of "hot takes with little nuance from people who have read at most half a Wikipedia page on the topic". And the content itself, being more generalist and less specialized, is no longer unique to HN.
Quality posts and comments do still occur, but they fill more and more needle in an haystack.
sajithdilshan 3 days ago [-]
At this rate we would have at least new one vibe coded site like this per week trying to filter AI posts. People truly have tokens to burn
postalcoder 3 days ago [-]
I've been serving this to users for the past year. I like to believe that i've inspired others.
I quite like this, particularly that the filter is just a preset! Will be back.
Minor UI feedback - when navigating comments (and maybe other stuff) with the keyboard, the actual focus change is blocked behind some automated scroll behavior, and the effect is that someone quickly hitting keybinds will collapse the wrong thread. Would suggest making the focus change happen concurrently.
postalcoder 4 days ago [-]
Thanks for the feedback. Comment drawer nav could be a lot better. I started working on the keyboard nav but got distracted with other things. I'll fix it.
d3Xt3r 3 days ago [-]
Would if be possible to set up push notifications for new stories matching a filter - one that's separate to the main filter? Like say, I want to get notified every time an article about "Linux" is posted. But if I go to main page, I want to see all stories (or whatever my main filter is set to).
postalcoder 3 days ago [-]
Yeah, all possible, the infra for all of that is set up. I think I understand your request but can u send me an email so I can talk it through with you a little more?
tcfhgj 4 days ago [-]
Hacker News, without AI needs to be a plugin for Firefox - I don´t really want to use two pages at the same time.
If a Userscript solution is fine for you, see my recent comments :)
nilsherzig 4 days ago [-]
added a firefox extension :)
jrm4 4 days ago [-]
This feels like trying to do "Hacker News, without 'the Internet.'"
NeedNewForums 4 days ago [-]
People were actually complaining specifically about OpenAI/Anthropic glazing and the countless influencer comments and posts here every hour.
And it's getting twisted into "People want HN without AI."
But that was never the case. I mean some surely do. But the blow-up this morning was specific to Anthropic ads to the point there's basically no information on this website that isn't related to Anthropic or OpenAI.
If it was announced some rando kid made a LLM in PHP or something, sure share it! If it was announced someone actually made something cool with AI (lol) then share it!
But Claude 24/7 aint it. It's at least extremely boring!
ragall 3 days ago [-]
It looks nice but I can't load any comments, and I believe it's because I have Firefox's Enhanced Tracking Protection turned on to the strictest level.
postalcoder 3 days ago [-]
Hm, I couldnt reproduce on firefox mac. Which version of firefox are you on? can you open the network inspector to see if you're hitting the api?
Perhaps it's Cloudflare that's doing the blocking.
postalcoder 3 days ago [-]
Fixed it, it should work now.
verdverm 4 days ago [-]
Is it still hacker news if you manipulate the listing based on your own bias?
I suppose it depends on what point of view we answer from. It is very hacker-newsery to make something like this
dr_kiszonka 3 days ago [-]
This is much better than I anticipated. I don't mind AI that much, but this version of HN surfaces really interesting articles I've missed.
jessetemp 4 days ago [-]
There is also the hide button under every post, which I’ve started using generously. It only takes a few seconds to clean up the front page to your taste
datakan 4 days ago [-]
I'm mixed on that. Definitely topics I hide when I think people can't discuss them like adults, but sometimes even bad stories have some great discussions in them.
gdulli 4 days ago [-]
I have a cron job that logs in and hides stuff based on a big list of keywords and domains I'm not interested in.
4 days ago [-]
basch 4 days ago [-]
still prefer the simplicity of a reverse river, with a focus on votes and comments https://hckrnews.com/
its incredibly easy to immediately tell when something was posted, and how popular it was. there s no automagic rearranging or movement.
Open up the settings bar at the top and set the story layout to "hckr". That layout is directly inspired by hckrnews.com.
basch 3 days ago [-]
Nice. The word "show" threw me off, given it is on the far right and the cog is on the far left. Menu, settings, config etc would make more sense.
postalcoder 3 days ago [-]
Great feedback. After all this time I just realized a lot of people may not even know that menu exists. It's been like that for so long I'm literally blind to it.
Tepix 4 days ago [-]
You need to search deeper!
Looking at the iPod 6G QEMU emulation story:
> "With the help of Claude Code, I was able to create code to extract it using emCORE."
ranger_danger 4 days ago [-]
Depends on what you want "without AI" to mean... is it just stories about AI, or anything that an AI has touched at all? Or purely vibe-coded projects?
4 days ago [-]
3 days ago [-]
dsiegel2275 3 days ago [-]
Would have been much better if it simply rendered a blank page.
sejje 4 days ago [-]
Top story: huggingface
postalcoder 4 days ago [-]
Just a few high level points about how this works. It works in multiple stages:
1. I apply a domain and keyword filter to the feed
2. The content of the remaining articles are run twice daily through a Modern Bert-based classifier fine-tuned to detect AI-related content (~8000 training examples)[0].
It also filters out Github repos that contain AI authorship. My backend scans:
- Commit messages for agent attribution
- The contributor graph for agents
- Repo files for instructions/configs
0: The original workflow for this was a little different. For the better part of the past year, I had an AI agent detect AI-related stories and raise ~20 stories to me to make a judgement call on. After a while, a workflow like this just doesn't make sense when small models can do it equally as well. The training data is based on the machine and my labeling.
vova_hn2 3 days ago [-]
I think you should make it clear, that when you say "without AI" you mean AI-related content, because some people in the comments seem to think that this is about AI-generated content.
bananaflag 4 days ago [-]
Funny how it uses AI
postalcoder 4 days ago [-]
Ethical, grass-fed AI!
NeedNewForums 4 days ago [-]
I like AI just hate Claude and Anslopic ads 24/7
thisisauserid 4 days ago [-]
Ironically, this is trivial to build with LLMs.
ares623 3 days ago [-]
let's fast forward to the part where the general public can make their own "Facebook, without Ads"
I know you guys hate X/Twitter but the muted words feature is really awesome for this kind of thing. You never have to hear about a topic you don't give a crap about ever again.
postalcoder 3 days ago [-]
you can essentially mute words on hcker.news. You can set exclusion filters in the settings. Those can be turned into rss feeds as well.
visarga 4 days ago [-]
Do you have one but only with AI? like, a toggle on what side to see?
https://hcker.news/?ai=exclude
* It filters out things that are clearly not AI related (like the one titled ' Mind-altering drugs played key role in rise of Andean civilization ') - or maybe it's just slow to update (that post was 3 hours ago)
* No ability to go to the next page
* Order is often different than on HN, even account for the missing posts. It's mostly the same, but not quite, which always throws me for a loop to see if something else is missing.
Instead of filtering keywords this ranks the content using Pangram. But it's also pretty effective at filtering content about AI. Turns out that a lot of LLM tooling projects have LLM written project descriptions/blog posts.
It's amazing to see how many of the "AI hurts my brain" posts are apparently written by an LLM.
OPs solution does more than keyword filtering. But its still about filtering out "content about ai" not filtering out "ai written content".
I am not averse to prompt-generated content, but it should be marked and quoted as such, just like any other reference. If it's not, it's like the author is double-cheating.
In fact there are no shortage of comments here on HN, especially open-ended questions that could've been plugged into a bot for an answer. Avoiding LLMs altogether is foolhardy. It's a matter of balance, and being able to write a good prompt is a skill - no mental atrophy there. Content derived from non-English sources using English-based LLMs is also an interesting area. [1]
It's possible to obtain AIaaT from https://aibriefs.news/ and then prune it elsewhere if need be. But the best aggregators like that may be machine-generated with a lot of human moderation. I wonder if that is 100% machine generated.
Likewise, HN-AI could well be a decent site.
[1] How much content can be derived from non-English sources using LLMs? https://share.gemini.google/ObjMQHCj8JWj"
Im trying to get something cheaper to work, Pangram has some nice docs on how to build something like their service https://github.com/pangramlabs/EditLens, they even have training data online.
The harm a missclassification carries is much lower for a hn post than a masters thesis, so we might be fine with a worse model.
But see, here I am back at the edge of the rabbit hole, and you're trying to pull me in. I refuse!
If you do end up training a model, send me an email and maybe I can tie it into the site.
https://imgur.com/a/P1qMIok
9 out of 30 posts have been removed.
Steps:
Install uBlock Origin Lite. Then create a custom filter:
Any improvements to above filter are welcome.TIL it was rare in the actual wartime (WWII) and only became popular in 2000: https://en.wikipedia.org/wiki/Keep_Calm_and_Carry_On
The AI spam is part of the issue, but not only. Maybe it's rose tinted glasses, but it feel like HN posts and comments quality have dropped significantly compared to ~5 to 10 years ago.
It used to have a lot more really technical subjects, with comments from experts on the topic.
Now days it seems to be a lot more of "hot takes with little nuance from people who have read at most half a Wikipedia page on the topic". And the content itself, being more generalist and less specialized, is no longer unique to HN.
Quality posts and comments do still occur, but they fill more and more needle in an haystack.
Minor UI feedback - when navigating comments (and maybe other stuff) with the keyboard, the actual focus change is blocked behind some automated scroll behavior, and the effect is that someone quickly hitting keybinds will collapse the wrong thread. Would suggest making the focus change happen concurrently.
And it's getting twisted into "People want HN without AI."
But that was never the case. I mean some surely do. But the blow-up this morning was specific to Anthropic ads to the point there's basically no information on this website that isn't related to Anthropic or OpenAI.
If it was announced some rando kid made a LLM in PHP or something, sure share it! If it was announced someone actually made something cool with AI (lol) then share it!
But Claude 24/7 aint it. It's at least extremely boring!
Perhaps it's Cloudflare that's doing the blocking.
I suppose it depends on what point of view we answer from. It is very hacker-newsery to make something like this
its incredibly easy to immediately tell when something was posted, and how popular it was. there s no automagic rearranging or movement.
similar to https://techmeme.com/river
Looking at the iPod 6G QEMU emulation story:
> "With the help of Claude Code, I was able to create code to extract it using emCORE."
HN Frontpage minus AI: https://hcker.news/?view=frontpage&ai=exclude
You may also like Small Web HN: https://hcker.news/?view=frontpage&smallweb=include
0: The original workflow for this was a little different. For the better part of the past year, I had an AI agent detect AI-related stories and raise ~20 stories to me to make a judgement call on. After a while, a workflow like this just doesn't make sense when small models can do it equally as well. The training data is based on the machine and my labeling.
https://hcker.news/feeds/atom?period=day&ai=exclude
https://hcker.news/feeds/json?period=week&ai=exclude
More info about parameters
https://hcker.news/feeds
Stick to sharing your thing in the current thread today:
Ask HN: Can we please limit the AI news flood?
https://news.ycombinator.com/item?id=49657850
Edit: ah yes, sure it exists
Checking the connection Checking the proxy and the firewall ERR_CONNECTION_RESET