Tomas Ruzicka LeZuse

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.

This script is designed to be used within BrowersStack as a "quick" way to get the WebVitals reporting on INP for mobile devices

It uses the web-vitals library and provides a slimmed down version of the official web-vitals chrome extension

Usage

Brew Bundle Brewfile Tips

Copyright & License

Unless otherwise noted (either in this file or in a file's copyright section) the contents of this gist are Copyright ©️2020 by Christopher Allen, and are shared under spdx:Creative Commons Attribution Share Alike 4.0 International (CC-BY-SA-4.) open-source license.

Sponsor

If you more tips and advice like these, you can become a monthly patron on my GitHub Sponsor Page for as little as $5 a month; and your contributions will be multipled, as GitHub is matching the first $5,000! This gist is all about Homebrew, so if you like it you can support it by donating to them or becoming one of their Github Sponsors.

`Option` vs non-`Option`

	`Option<T>`	non-`Option` (`T \| undefined`)
accessing property	`userOption.map(user => user.age)`	`userNullish?.age`
calling a method	`userOption.map(user => user.fn())`	`userNullish?.fn()`
providing fallback	`ageOption.getOrElse(0)`	`ageNullish ?? 0`
filter	`ageOption.filter(checkIsOddNumber)`	`ageNull

This gist will no longer be updated as the changelog will be on the official website.

Sublime Text/Merge Official Discord chat server: https://discord.gg/D43Pecu
Sublime Text/Merge 中文 Telegram 交流群組： https://t.me/sublime_tw

Converted via https://domchristie.github.io/turndown

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	#!/usr/bin/env bash
	set -euo pipefail

	bold() { printf "\033[1m%s\033[0m\n" "$*"; }
	info() { printf "• %s\n" "$*"; }
	warn() { printf "\033[33m! %s\033[0m\n" "$*"; }
	err() { printf "\033[31m✗ %s\033[0m\n" "$*" >&2; }
	ok() { printf "\033[32m✓ %s\033[0m\n" "$*"; }

	require_macos() {

	---
	description: >
	Git Commit Assistant rule to enforce clean,
	structured, and traceable commit workflows. This rule should be applied
	whenever a developer attempts to stage or commit changes. It ensures that:
	- Commits are grouped logically and use conventional commit messages tied to Jira tickets.
	- Feature branches are created from `development` with proper naming conventions.
	- No direct work is allowed on `master`.
	- Sensitive or excluded files (e.g., .env, secrets) are never accidentally committed.
	This rule improves collaboration, auditability, and consistency across the codebase,

	(function () {
	Error;
	console.log('aca')
	function e(t, n, o) {
	const r = o();
	return t > 0 ? r.catch((r) => new Promise((e, t) => setTimeout(e, n)).then((r) => e(t - 1, n, o))) : r;
	}
	var t;
	!(function (e) {
	function t() {

	View: Pods(<namespace>)[number of pods listed]

	NAME pod name
	READY number of pods in ready state / number of pods to be in ready state
	RESTARTS number of times the pod has been restarted so far
	STATUS state of the pod life cycle, such as Running \| ... \| Completed
	CPU current CPU usage, unit is milli-vCPU
	MEM current main memory usage, unit is MiB
	%CPU/R current CPU usage as a percentage of what has been requested by the pod
	%MEM/R current main memory usage as a percentage of what has been requested by the pod