Show HN: Hacker News, without AI
hcker.news
hcker.news
* 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.
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])
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.
I suppose it depends on what point of view we answer from. It is very hacker-newsery to make something like this
Perhaps it's Cloudflare that's doing the blocking.
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."
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].
- Commit messages for agent attribution
- The contributor graph for agents
- Repo files for instructions/configs
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
Stick to sharing your thing in the current thread today:
Ask HN: Can we please limit the AI news flood?
Edit: ah yes, sure it exists