Martin Czygan miku

I'm well aware of how old the version of Bash is that ships with MacOS and Apple's public deprecation plans. That said, I don't like having to fiddle with this in VS Code and every other tool that tries to be clever. This will kill the message everywhere for processes of this user. Don't bother screwing around with $HOME .bashrc .profiile .bash_profile BS. Or do, but realize the local config specific to the user won't suffice for VS Code et al. You can also use Brew to do this, which will use the most recent version of Bash, but I have a love-hate relationship with Brew and prefer to use this approach instead. Caveat Emptor: This works for me, but use at your own risk.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

title

AI Agents - A Comprehensive Database of The Best AI Agents

AI Agents: A Comprehensive Database of The Best AI Agents

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

	#!/bin/sh

	COOKIE_DB="${2:-$HOME/.config/google-chrome/Default/Cookies}"

	sqlite3 -separator ' ' "$COOKIE_DB" \
	"select name,value from cookies WHERE host_key=\"$1\"" \|
	awk 'BEGIN{ ORS=";" } { print $1 "=" $2 }'

	<!DOCTYPE html>
	<html lang="en">
	<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no">
	<title>Frontier Foundry — RTS</title>
	<link rel="preconnect" href="https://fonts.googleapis.com">
	<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
	<link href="https://fonts.googleapis.com/css2?family=Orbitron:wght@500;700;900&family=Rajdhani:wght@400;500;600;700&display=swap" rel="stylesheet">
	<style>

	# th30z@u1310:[Desktop]$ psql -h localhost -p 55432
	# Password:
	# psql (9.1.10, server 0.0.0)
	# WARNING: psql version 9.1, server version 0.0.
	# Some psql features might not work.
	# Type "help" for help.
	#
	# th30z=> select foo;
	# a \| b
	# ---+---

	#!/bin/bash
	set -eu -o pipefail

	token="${GITHUB_TOKEN:?Set GITHUB_TOKEN before running this script}"

	clone_or_pull() {
	local page="$1"
	local tmpfile
	tmpfile=$(mktemp)
	trap "rm -f '$tmpfile'" RETURN

	#EXTM3U
	#EXTINF:-1,ARD
	https://daserste-live.ard-mcdn.de/daserste/live/hls/de/master.m3u8
	#EXTINF:-1,ARD ONE
	https://mcdn-one.ard.de/ardone/hls/master.m3u8
	#EXTINF:-1,ARD Alpha
	https://mcdn.br.de/br/fs/ard_alpha/hls/de/master.m3u8
	#EXTINF:-1,ARD Tagesschau
	https://tagesschau.akamaized.net/hls/live/2020115/tagesschau/tagesschau_1/master.m3u8
	#EXTINF:-1,ZDF

	""" To use: install Ollama, clone OpenVoice, run this script in the OpenVoice directory
	brew install portaudio
	brew install git-lfs
	git lfs install

	git clone https://github.com/myshell-ai/OpenVoice
	cd OpenVoice
	git clone https://huggingface.co/myshell-ai/OpenVoice
	cp -r OpenVoice/* .