106 points postalcoder 2 hours ago 62 comments
loldidntwork 2 hours ago | parent
postalcoder 2 hours ago | parent
TouchGrass 2 hours ago | parent
Checking the connection Checking the proxy and the firewall ERR_CONNECTION_RESET
postalcoder 2 hours ago | parent
Gualdrapo 1 hour ago | parent
niyonx 1 hour ago | parent
chilipepperhott 1 hour ago | parent
basch 1 hour ago | parent
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
postalcoder 1 hour ago | parent
dorkrawk 1 hour ago | parent
snarf21 1 hour ago | parent
postalcoder 1 hour ago | parent
ant6n 12 minutes ago | parent
postalcoder 1 hour ago | parent
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.
RIMR 1 hour ago | parent
account42 1 hour ago | parent
amelius 1 hour ago | parent
busymom0 1 hour ago | parent
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.layer8 1 hour ago | parent
otherayden 1 hour ago | parent
layer8 1 hour ago | parent
gonzalohm 1 hour ago | parent
otherayden 1 hour ago | parent
toomuchtodo 1 hour ago | parent
xvinci 22 minutes ago | parent
visarga 1 hour ago | parent
Edit: ah yes, sure it exists
postalcoder 1 hour ago | parent
jrm4 1 hour ago | parent
NeedNewForums 50 minutes ago | parent
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!
jessetemp 1 hour ago | parent
datakan 1 hour ago | parent
gdulli 1 hour ago | parent
sejje 1 hour ago | parent
bronlund 1 hour ago | parent
armchairhacker 57 minutes ago | parent
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
Tepix 1 hour ago | parent
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 21 minutes ago | parent
nonsensical_ 1 hour ago | parent
ChrisArchitect 56 minutes ago | parent
Stick to sharing your thing in the current thread today:
Ask HN: Can we please limit the AI news flood?
tcfhgj 48 minutes ago | parent
postalcoder 7 minutes ago | parent
nilsherzig 47 minutes ago | parent
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.
nilsherzig 42 minutes ago | parent
OPs solution does more than keyword filtering. But its still about filtering out "content about ai" not filtering out "ai written content".
postalcoder 35 minutes ago | parent
nilsherzig 27 minutes ago | parent
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 13 minutes ago | parent
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 5 minutes ago | parent
verdverm 46 minutes ago | parent
I suppose it depends on what point of view we answer from. It is very hacker-newsery to make something like this
mpalmer 41 minutes ago | parent
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 32 minutes ago | parent
sochowski 36 minutes ago | parent
grandwizardmarv 35 minutes ago | parent
flashu 32 minutes ago | parent
thisisauserid 26 minutes ago | parent