JonathanFly's favorites

1.		Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed (can.ac)
		819 points by kachapopopow 3 days ago \| 294 comments
2.		Moltbook (moltbook.com)
		1652 points by teej 17 days ago \| 5 comments
3.		TimeCapsuleLLM: LLM trained only on data from 1800-1875 (github.com/haykgrigo3)
		737 points by admp 34 days ago \| 314 comments
4.		I'm making a game engine based on dynamic signed distance fields (SDFs) [video] (youtube.com)
		451 points by imagiro 38 days ago \| 78 comments
5.		How to code Claude Code in 200 lines of code (mihaileric.com)
		816 points by nutellalover 38 days ago \| 240 comments
6.		Welcome to Gas Town (steve-yegge.medium.com)
		354 points by gmays 45 days ago \| 224 comments
7.		Two kinds of vibe coding (davidbau.com)
		137 points by jxmorris12 59 days ago \| 106 comments
8.		Prompt caching for cheaper LLM tokens (ngrok.com)
		306 points by samwho 61 days ago \| 72 comments
9.		History LLMs: Models trained exclusively on pre-1913 texts (github.com/dgoettlich)
		897 points by iamwil 59 days ago \| 421 comments
10.		Neural audio codecs: how to get audio into LLMs (kyutai.org)
		428 points by karimf 3 months ago \| 119 comments
11.		Why do LLMs freak out over the seahorse emoji? (vgel.me)
		734 points by nyxt 4 months ago \| 416 comments
12.		Show HN: A little notebook for learning linear algebra with Python (little-book-of.github.io)
		190 points by tamnd 4 months ago \| 46 comments
13.		Qwen3-Omni: Native Omni AI model for text, image and video (github.com/qwenlm)
		571 points by meetpateltech 4 months ago \| 143 comments
14.		Almost anything you give sustained attention to will begin to loop on itself (henrikkarlsson.xyz)
		773 points by jger15 5 months ago \| 223 comments
15.		VibeVoice: A Frontier Open-Source Text-to-Speech Model (microsoft.github.io)
		448 points by lastdong 5 months ago \| 170 comments
16.		The decline of high-tech manufacturing in the United States (waldrn.com)
		124 points by giuliomagnifico 6 months ago \| 192 comments
17.		FFmpeg 8.0 adds Whisper support (ffmpeg.org)
		1033 points by rilawa 6 months ago \| 325 comments
18.		Training language models to be warm and empathetic makes them less reliable (arxiv.org)
		358 points by Cynddl 6 months ago \| 375 comments
19.		Diffusion language models are super data learners (jinjieni.notion.site)
		218 points by babelfish 6 months ago \| 16 comments
20.		Open music foundation models for full-song generation (map-yue.github.io)
		121 points by selvan 6 months ago \| 74 comments
21.		Show HN: KVoiceWalk – Voice cloning for Kokoro TTS using random walk algorithms (github.com/robviren)
		13 points by robviren 9 months ago
22.		The unreasonable effectiveness of an LLM agent loop with tool use (sketch.dev)
		447 points by crawshaw 9 months ago \| 320 comments
23.		[dupe] Embeddings are underrated (2024) (technicalwriting.dev)
		484 points by jxmorris12 9 months ago \| 150 comments
24.		ACE-Step: A step towards music generation foundation model (github.com/ace-step)
		109 points by wertyk 9 months ago \| 52 comments
25.		Dummy's Guide to Modern LLM Sampling (rentry.co)
		228 points by nkko 9 months ago \| 37 comments
26.		Llasa: Llama-Based Speech Synthesis (llasatts.github.io)
		168 points by CalmStorm 9 months ago \| 22 comments
27.		Ask HN: Share your AI prompt that stumps every model
		440 points by owendarko 9 months ago \| 633 comments
28.		DeepMind releases Lyria 2 music generation model (deepmind.google)
		300 points by velcrobeg 9 months ago \| 426 comments
29.		Show HN: Dia, an open-weights TTS model for generating realistic dialogue (github.com/nari-labs)
		652 points by toebee 10 months ago \| 190 comments
30.		Packing Input Frame Context in Next-Frame Prediction Models for Video Generation (lllyasviel.github.io)
		270 points by GaggiX 10 months ago \| 27 comments
		More