JeongHoon Baek hey-jude

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.

April 2026 TLDR setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon) — auto-start, preload, and keep-alive

April 2026 TLDR Setup for Ollama + Gemma 4 on a Mac mini (Apple Silicon)

Prerequisites

Mac mini with Apple Silicon (M1/M2/M3/M4/M5)
At least 16GB unified memory for Gemma 4 (default 8B)
macOS with Homebrew installed

name: codex-researcher description: > Use this agent when you need to conduct research on any topic using OpenAI's Codex CLI. This includes gathering information about technologies, companies, market trends, scientific topics, historical events, or any subject requiring in-depth analysis. The agent leverages the codex exec command with web search to perform comprehensive research. model: inherit color: green

This is an OPML version of the HN Popularity Contest results for 2025, for importing into RSS feed readers.

Plug: if you want to find content related to your interests from thousands of obscure blogs and noisy sources like HN Newest, check out Scour. It's a free, personalized content feed I work on where you define your interests in your own words and it ranks content based on how closely related it is to those topics.

macOS 13 Ventura introduced support of running amd64 binaries with Rosetta inside of arm64 Linux VMs when using Apple Virtualization framework.

Lima VM v0.14.0 and later support the new feature.

Setup:

# Install Docker client and Lima
brew install docker docker-compose docker-credential-helper lima

Tutor Open edX useful commands

Tutor Installation

Requirements

Docker: v18.06.0+
Docker Compose: v1.22.0+
Ports 80 and 443 should be open
Hardware:
Minimum configuration: 4 GB RAM, 2 CPU, 8 GB disk space

Gist to support https://youtu.be/3XzVOxvNpGM

Documentation

https://plugins.jenkins.io/opentelemetry/
https://github.com/open-telemetry/opentelemetry-collector/tree/main/examples/demo
- git clone https://github.com/open-telemetry/opentelemetry-collector.git
- cd opentelemetry-collector/examples/demo/
- docker-compose up -d

	interface I18n {
	fun localized(languageTag: String): Localized

	interface Localized {
	fun text(key: String, args: Map<String, Any>): String

	fun text(key: String): String = text(key, emptyMap())
	}
	}

	#!/bin/zsh

	# This script helps those who want to
	# get all Aerial wallpapers on macOS Sonoma
	# all at once instead of clicking on settings one by one.

	# Dependencies: jq, parallel
	# Install all dependencies via `brew install jq parallel`
	# After `parallel` installed run `sudo parallel --citation` first to read citation notice (IMPORTANT)

	<?php
	/**
	* 아래는 참고한 자료.
	* @link https://stackoverflow.com/questions/24651869/regex-matching-links-without-a-tag/24653720?stw=2#24653720
	*/
	function make_link_clickable($text)
	{
	return preg_replace(
	'!<a(.\|\n)?</a>(SKIP)(*F)\|' //skip a tag
	. '(((f\|ht)tp(s)?://)[-a-zA-Zа-яА-Я()0-9@:%_+.~#?&;/=]+)!i',