Show HN: CLI to order groceries via reverse-engineered REWE API (Haskell)(github.com)

183 points by wazHFsRy 7 months ago | 78 comments

Show HN: An experimental pattern-first DAW that supports MCP(github.com)

71 points by androsynth89 13 days ago | 30 comments

GitHub repository for blokkily, an experimental pattern-first digital audio workstation with Model Context Protocol (MCP) support.

Boot a Virtual iPhone via Apple's Virtualization.framework(github.com)

402 points by hentrep 1 month ago | 108 comments

GitHub repository for vphone-cli, a tool to boot a virtual iPhone using Apple's Virtualization.framework on macOS.

Codes – typed application outcomes for Kotlin and Java(github.com)

10 points by aalsanie 2 months ago | 3 comments

Show HN: Omacosy – Omarchy-style tiling desktop for macOS, no SIP(github.com)

33 points by paulsp 2 months ago | 25 comments

Show HN: Claudoro, Pomodoro timer embedded in the Claude Code statusline(github.com)

39 points by emson 3 months ago | 28 comments

Run Kimi K3 using 29 GB of RAM at 0.50 tok/s(github.com)

318 points by marcobambini 2 months ago | 152 comments

GitHub repository for waste, a dependency-free embeddable C inference engine that runs the 2.78-trillion-parameter Kimi K3 model by streaming weights from NVMe.

Run Llama 13B with a 6GB graphics card(gist.github.com)

564 points by rain1 3 years ago | 233 comments

A GitHub Gist with instructions for running Meta's Llama 13B model on a 6GB GPU using llama.cpp's CUDA/cuBLAS layer offloading.

Lima: A nice way to run Linux VMs on Mac(jvns.ca)

469 points by jseliger 3 years ago | 137 comments

Julia Evans blog post recommending Lima as a simpler alternative to Vagrant for running Linux virtual machines on a Mac.

2025: The Year in LLMs(simonwillison.net)

823 points by simonw 9 months ago | 451 comments

Simon Willison's annual blog post reviewing major LLM trends of 2025, including reasoning models, coding agents, Chinese open weight models, and Gemini.

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

How to speed up the Rust compiler in September 2026(nnethercote.github.io)

266 points by trickypr 25 days ago | 157 comments

Nicholas Nethercote's blog post reporting Rust compiler performance improvements from late July to late September 2026, including a 4.57% mean wall-time reduction.