JonathanFly's favorites

1.		Two kinds of vibe coding (davidbau.com)
		136 points by jxmorris12 6 days ago \| 100 comments
2.		Prompt caching for cheaper LLM tokens (ngrok.com)
		304 points by samwho 8 days ago \| 72 comments
3.		History LLMs: Models trained exclusively on pre-1913 texts (github.com/dgoettlich)
		891 points by iamwil 6 days ago \| 418 comments
4.		Neural audio codecs: how to get audio into LLMs (kyutai.org)
		428 points by karimf 64 days ago \| 119 comments
5.		Why do LLMs freak out over the seahorse emoji? (vgel.me)
		734 points by nyxt 80 days ago \| 416 comments
6.		Show HN: A little notebook for learning linear algebra with Python (little-book-of.github.io)
		190 points by tamnd 89 days ago \| 46 comments
7.		Qwen3-Omni: Native Omni AI model for text, image and video (github.com/qwenlm)
		571 points by meetpateltech 3 months ago \| 143 comments
8.		Almost anything you give sustained attention to will begin to loop on itself (henrikkarlsson.xyz)
		773 points by jger15 3 months ago \| 223 comments
9.		VibeVoice: A Frontier Open-Source Text-to-Speech Model (microsoft.github.io)
		448 points by lastdong 3 months ago \| 170 comments
10.		The decline of high-tech manufacturing in the United States (waldrn.com)
		124 points by giuliomagnifico 4 months ago \| 192 comments
11.		FFmpeg 8.0 adds Whisper support (ffmpeg.org)
		1033 points by rilawa 4 months ago \| 325 comments
12.		Training language models to be warm and empathetic makes them less reliable (arxiv.org)
		358 points by Cynddl 4 months ago \| 375 comments
13.		Diffusion language models are super data learners (jinjieni.notion.site)
		218 points by babelfish 4 months ago \| 16 comments
14.		Open music foundation models for full-song generation (map-yue.github.io)
		121 points by selvan 4 months ago \| 74 comments
15.		Show HN: KVoiceWalk – Voice cloning for Kokoro TTS using random walk algorithms (github.com/robviren)
		13 points by robviren 7 months ago
16.		The unreasonable effectiveness of an LLM agent loop with tool use (sketch.dev)
		447 points by crawshaw 7 months ago \| 320 comments
17.		[dupe] Embeddings are underrated (2024) (technicalwriting.dev)
		484 points by jxmorris12 7 months ago \| 150 comments
18.		ACE-Step: A step towards music generation foundation model (github.com/ace-step)
		109 points by wertyk 7 months ago \| 52 comments
19.		Dummy's Guide to Modern LLM Sampling (rentry.co)
		228 points by nkko 7 months ago \| 37 comments
20.		Llasa: Llama-Based Speech Synthesis (llasatts.github.io)
		168 points by CalmStorm 7 months ago \| 22 comments
21.		Ask HN: Share your AI prompt that stumps every model
		440 points by owendarko 8 months ago \| 633 comments
22.		DeepMind releases Lyria 2 music generation model (deepmind.google)
		300 points by velcrobeg 8 months ago \| 426 comments
23.		Show HN: Dia, an open-weights TTS model for generating realistic dialogue (github.com/nari-labs)
		652 points by toebee 8 months ago \| 190 comments
24.		Packing Input Frame Context in Next-Frame Prediction Models for Video Generation (lllyasviel.github.io)
		270 points by GaggiX 8 months ago \| 27 comments
25.		AudioX: Diffusion Transformer for Anything-to-Audio Generation (zeyuet.github.io)
		148 points by gnabgib 8 months ago \| 19 comments
26.		Orpheus-3B – Emotive TTS by Canopy Labs (canopylabs.ai)
		186 points by Zetaphor 9 months ago \| 39 comments
27.		The year I didn't survive (bessstillman.substack.com)
		949 points by LaurenSerino 10 months ago \| 262 comments
28.		Building a personal, private AI computer on a budget (ewintr.nl)
		384 points by thm 10 months ago \| 231 comments
29.		S1: A $6 R1 competitor? (timkellogg.me)
		851 points by tkellogg 10 months ago \| 416 comments
30.		DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL (arxiv.org)
		1351 points by gradus_ad 11 months ago \| 1056 comments
		More