muggermuch's favorites

1.		Show HN: Tiny-vLLM – high performance LLM inference engine in C++ and CUDA (github.com/jmaczan)
		204 points by yu3zhou4 6 days ago \| 18 comments
2.		SQLite is all you need for durable workflows (obeli.sk)
		716 points by tomasol 6 days ago \| 386 comments
3.		Show HN: Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks (github.com/antoinezambelli)
		687 points by zambelli 17 days ago \| 252 comments
4.		RTX 5090 and M4 MacBook Air: Can It Game? (scottjg.com)
		699 points by allenleee 22 days ago \| 180 comments
5.		Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model (github.com/cactus-compute)
		776 points by HenryNdubuaku 23 days ago \| 211 comments
6.		Training an LLM in Swift, Part 1: Taking matrix mult from Gflop/s to Tflop/s (cocoawithlove.com)
		263 points by zdw 26 days ago \| 13 comments
7.		High Performance Git (gitperf.com)
		268 points by gnabgib 38 days ago \| 81 comments
8.		Archive of BYTE magazine, starting with issue #1 in 1975 (archive.org)
		602 points by DamnInteresting 49 days ago \| 153 comments
9.		Migrating from DigitalOcean to Hetzner (isayeter.com)
		893 points by yusufusta 48 days ago \| 430 comments
10.		I run multiple $10K MRR companies on a $20/month tech stack (stevehanov.ca)
		980 points by tradertef 54 days ago \| 517 comments
11.		Show HN: Marimo pair – Reactive Python notebooks as environments for agents (github.com/marimo-team)
		140 points by manzt 58 days ago \| 35 comments
12.		Universal Claude.md – cut Claude output tokens (github.com/drona23)
		471 points by killme2008 66 days ago \| 162 comments
13.		Show HN: Duplicate 3 layers in a 24B LLM, logical deduction .22→.76. No training (github.com/alainnothere)
		265 points by xlayn 78 days ago \| 80 comments
14.		Show HN: Soros – AI for geopolitical macro investing (asksoros.com)
		26 points by muggermuch 79 days ago \| 10 comments
15.		Show HN: How I topped the HuggingFace open LLM leaderboard on two gaming GPUs (dnhkng.github.io)
		495 points by dnhkng 87 days ago \| 126 comments
16.		NanoGPT Slowrun: Language Modeling with Limited Data, Infinite Compute (qlabs.sh)
		185 points by sdpmas 3 months ago \| 35 comments
17.		Inside the M4 Apple Neural Engine, Part 1: Reverse Engineering (maderix.substack.com)
		376 points by zdw 3 months ago \| 117 comments
18.		Show HN: Govbase – Follow a bill from source text to news bias to social posts (govbase.com)
		219 points by foxfoxx 3 months ago \| 89 comments
19.		What I learned while trying to build a production-ready nearest neighbor system (github.com/thatipamula-jashwanth)
		23 points by Jashwanth01 3 months ago \| 14 comments
20.		LCM: Lossless Context Management [pdf] (voltropy.com)
		81 points by ClintEhrlich 3 months ago \| 31 comments
21.		Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
		169 points by Haakam21 4 months ago \| 169 comments
22.		How to code Claude Code in 200 lines of code (mihaileric.com)
		816 points by nutellalover 4 months ago \| 239 comments
23.		Children and Helical Time (moultano.wordpress.com)
		201 points by moultano 5 months ago \| 125 comments
24.		Build a Deep Learning Library (quarto.pub)
		134 points by butanyways 5 months ago \| 15 comments
25.		I canceled my book deal (austinhenley.com)
		614 points by azhenley 5 months ago \| 363 comments
26.		Scaffolding to Superhuman: How Curriculum Learning Solved 2048 and Tetris (kywch.github.io)
		150 points by a1k0n 5 months ago \| 33 comments
27.		Readings in Database Systems (5th Edition) (2015) (redbook.io)
		152 points by teleforce 5 months ago \| 19 comments
28.		Project ideas to appreciate the art of programming (codecrafters.io)
		224 points by vitaelabitur 5 months ago \| 79 comments
29.		A2UI: A Protocol for Agent-Driven Interfaces (a2ui.org)
		164 points by makeramen 5 months ago \| 75 comments
30.		Show HN: AlgoDrill – Interactive drills to stop forgetting LeetCode patterns (algodrill.io)
		178 points by henwfan 5 months ago \| 108 comments
		More