Show HN: Hacker News, without AI
Posted by postalcoder 1 day ago
Comments
Comment by dorkrawk 1 day ago
Comment by postalcoder 1 day ago
Comment by ant6n 23 hours ago
Comment by snarf21 1 day ago
Comment by layer8 1 day ago
Comment by Night_Thastus 19 hours ago
* 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.
Comment by otherayden 1 day ago
Comment by gonzalohm 1 day ago
Comment by otherayden 1 day ago
Comment by xvinci 23 hours ago
Comment by otherayden 19 hours ago
Comment by toomuchtodo 23 hours ago
Comment by postalcoder 19 hours ago
Comment by layer8 1 day ago
Comment by WarcrimeActual 22 hours ago
Comment by buggy6257 20 hours ago
Comment by kakwa_ 3 hours ago
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.
Comment by nilsherzig 23 hours ago
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.
Comment by nilsherzig 23 hours ago
OPs solution does more than keyword filtering. But its still about filtering out "content about ai" not filtering out "ai written content".
Comment by adrianwaj 15 hours ago
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"
Comment by postalcoder 23 hours ago
Comment by nilsherzig 23 hours ago
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.
Comment by postalcoder 23 hours ago
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.
Comment by nilsherzig 22 hours ago
Comment by postalcoder 22 hours ago
Comment by account42 1 day ago
Comment by busymom0 1 day ago
9 out of 30 posts have been removed.
Steps:
Install uBlock Origin Lite. Then create a custom filter:
news.ycombinator.com##tr.athing:has(a:has-text(/\b(?:A\.?I\.?|A\.?G\.?I\.?|LLMs?|GPTs?|TPU|NPU|RAG|MoE|RLHF|xAI)\b|Anthropic|agent|super-?intelligence|Blackwell|Cerebras|ChatGPT|Claude|Cohere|Command\s*R|Context\s*window|Copilot|Cursor|DALL-E|deep\s*learning|DeepSeek|ElevenLabs|Fine-tun(?:e|ing)|Flux|Gemini|GenAI|Generative|Gemma|Grok|Groq|H100|Hallucination|harness(?:es)?|Hugging\s*Face|LangChain|Llama|LlamaIndex|Midjourney|Mistral|Ollama|OpenAI|OpenRouter|Perplexity|prompt|Qwen|Runway\s*(?:AI|ML)|Gen-[1-4](?:\.5)?|Sora|Synthetic\s*data|token|vibecod|vLLM|Whisper/i)):xpath(. | following-sibling::tr[1])
Any improvements to above filter are welcome.Comment by amelius 1 day ago
Comment by bronlund 1 day ago
Comment by armchairhacker 23 hours ago
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
Comment by loldidntwork 1 day ago
Comment by postalcoder 1 day ago
Comment by TouchGrass 1 day ago
Checking the connection Checking the proxy and the firewall ERR_CONNECTION_RESET
Comment by postalcoder 1 day ago
Comment by Gualdrapo 1 day ago
Comment by sajithdilshan 19 hours ago
Comment by postalcoder 19 hours ago
Comment by d3Xt3r 18 hours ago
Comment by postalcoder 18 hours ago
Comment by chilipepperhott 1 day ago
Comment by postalcoder 1 day ago
Comment by vanschelven 1 day ago
Comment by tcfhgj 23 hours ago
Comment by postalcoder 23 hours ago
Comment by nilsherzig 23 hours ago
Comment by nilsherzig 22 hours ago
Comment by dr_kiszonka 22 hours ago
Comment by jessetemp 1 day ago
Comment by datakan 1 day ago
Comment by gdulli 1 day ago
Comment by basch 1 day ago
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
Comment by postalcoder 1 day ago
Comment by basch 22 hours ago
Comment by postalcoder 22 hours ago
Comment by osquar 7 hours ago
Comment by Tepix 1 day ago
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."
Comment by ranger_danger 23 hours ago
Comment by dsiegel2275 19 hours ago
Comment by sejje 1 day ago
Comment by thisisauserid 23 hours ago
Comment by postalcoder 1 day ago
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
RSS feed here: https://hcker.news/feeds/atom?period=day&ai=excludeHN 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.
Comment by vova_hn2 19 hours ago
Comment by bananaflag 1 day ago
Comment by postalcoder 1 day ago
Comment by NeedNewForums 23 hours ago
Comment by niyonx 1 day ago
Comment by grandwizardmarv 23 hours ago
Comment by 1vuio0pswjnm7 19 hours ago
https://hcker.news/feeds/atom?period=day&ai=exclude
https://hcker.news/feeds/json?period=week&ai=exclude
More info about parameters
Comment by jrm4 1 day ago
Comment by NeedNewForums 23 hours ago
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!
Comment by ragall 18 hours ago
Comment by postalcoder 18 hours ago
Comment by ragall 16 hours ago
Perhaps it's Cloudflare that's doing the blocking.
Comment by postalcoder 12 hours ago
Comment by mpalmer 23 hours ago
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.
Comment by postalcoder 23 hours ago
Comment by verdverm 23 hours ago
I suppose it depends on what point of view we answer from. It is very hacker-newsery to make something like this
Comment by ares623 18 hours ago
Comment by visarga 1 day ago
Edit: ah yes, sure it exists
Comment by postalcoder 1 day ago
Comment by flashu 23 hours ago
Comment by nonsensical_ 1 day ago
Comment by sochowski 23 hours ago
Comment by narrator 18 hours ago
Comment by postalcoder 18 hours ago
Comment by ChrisArchitect 23 hours ago
Stick to sharing your thing in the current thread today:
Ask HN: Can we please limit the AI news flood?
Comment by RIMR 1 day ago
Comment by vladsiu 9 hours ago
Comment by throwaway613746 1 day ago