krackers's favorites | Hacker News

1.		Language models for text classification: From bag-of-words to Jev (sebastianraschka.com)
		214 points by Anon84 24 days ago \| 9 comments
2.		The recently proposed o(n log n) integer multiplication algorithm [pdf] (unsw.edu.au)
		311 points by craigcitro 2 days ago \| 301 comments
3.		macOS 15.8.2 Breaks OpenGL (developer.apple.com)
		293 points by Audiophilip 5 days ago \| 333 comments
4.		Two-Stack Sliding-Window Aggregation (orlp.net)
		142 points by surprisetalk 10 days ago \| 30 comments
5.		Neural networks are clean (goodfire.com)
		846 points by themgt 8 days ago \| 344 comments
6.		We turned EmbeddingGemma 2 into a speech-to-text model (haku.sh)
		435 points by amrrs 10 days ago \| 100 comments
7.		Show HN: WallHop – 12ft.io is gone, so I built a replacement (wallhop.io)
		289 points by TheWaffleHax 13 days ago \| 133 comments
8.		Competitive Programmer's Handbook (2018) [pdf] (cses.fi)
		326 points by vinhnx 20 days ago \| 86 comments
9.		Reasoning LLMs are wandering solution explorers (arxiv.org)
		90 points by Surreal4434 on Oct 10, 2025 \| 98 comments
10.		AI safety is mostly a sex cult in Berkeley (verysane.ai)
		121 points by martythemaniak 29 days ago \| 30 comments
11.		Heretic removes restrictions from language models (heretic-project.org)
		279 points by Bluestein 32 days ago \| 111 comments
12.		Jev's Architecture Unmasked (archerhume.com)
		6 points by tosh 34 days ago \| 1 comment
13.		DeepSeek-v4.1 Flash: Pushing the Limits of KV Cache Compression (zartbot.github.io)
		131 points by mfiguiere 37 days ago \| 10 comments
14.		A Design Space Exploration of Async/Await (brown.edu)
		466 points by wcrichton 44 days ago \| 134 comments
15.		GPT-6 Astra, looped transformers, and hidden reasoning (sebastianraschka.com)
		521 points by ModelForge 44 days ago \| 162 comments
16.		The browser's main thread is expensive (kciter.so)
		436 points by kciter 52 days ago \| 151 comments
17.		How to build a diffusion language model (kuleshov-group.github.io)
		184 points by volodia 54 days ago \| 20 comments
18.		Hilariously fast volume computation with the divergence theorem (2018) (alyssarosenzweig.ca)
		266 points by luu 56 days ago \| 68 comments
19.		The Conspiracy Against High Temperature Sampling (gist.github.com)
		4 points by theanonymousone 3 months ago
20.		You only need the frontier model for one single edit (stencil.so)
		230 points by jxmorris12 3 months ago \| 97 comments
21.		A quick look at zero-knowledge proofs (bernsteinbear.com)
		89 points by evakhoury 70 days ago \| 37 comments
22.		The Biology of Claude's Tokenizer: Reverse Engineered (tokencontributions.substack.com)
		3 points by goranmoomin 71 days ago
23.		How AI text watermarking works (declaude.org)
		147 points by padolsey 71 days ago \| 102 comments
24.		Compression is prediction (ngrok.com)
		674 points by nikolay 73 days ago \| 301 comments
25.		A Tale of Dynamic Programming (2022) (iagoleal.com)
		91 points by Brajeshwar 75 days ago \| 12 comments
26.		An Interesting Fourier Transform – 1/f Noise (2007) (dsprelated.com)
		126 points by q7m 78 days ago \| 27 comments
27.		Honey, I shrunk the embeddings: Matryoshka vs. PCA (dylancastillo.co)
		61 points by dcastm 81 days ago \| 18 comments
28.		Inside vLLM: Anatomy of a High-Throughput LLM Inference System (2025) (aleksagordic.com)
		151 points by sebg 78 days ago \| 10 comments
29.		Explorative modeling: Train on the best of K guesses (alexiglad.github.io)
		109 points by DSemba 83 days ago \| 26 comments
30.		The mean means nothing: data visualization to debug a latency problem (fzakaria.com)
		116 points by fanf2 86 days ago \| 20 comments
		More