marcel mpoisot

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.

Automatic build versions from git in Xcode (and other goodies)

Installation procedure for pre-build actions to automatically populate Xcode Info.plist with dynamic data.

1. Xcode Scheme pre-action

Edit Xcode Scheme and add a pre-action script. Copy the contents of preaction.sh into the pre-action script box.

What forces layout / reflow

All of the below properties or methods, when requested/called in JavaScript, will trigger the browser to synchronously calculate the style and layout*. This is also called reflow or layout thrashing, and is common performance bottleneck.

Generally, all APIs that synchronously provide layout metrics will trigger forced reflow / layout. Read on for additional cases and details.

Element APIs

Getting box metrics

elem.offsetLeft, elem.offsetTop, elem.offsetWidth, elem.offsetHeight, elem.offsetParent

	class FilterVisualizer():
	def __init__(self, size=56, upscaling_steps=12, upscaling_factor=1.2):
	self.size, self.upscaling_steps, self.upscaling_factor = size, upscaling_steps, upscaling_factor
	self.model = vgg16(pre=True).cuda().eval()
	set_trainable(self.model, False)

	def visualize(self, layer, filter, lr=0.1, opt_steps=20, blur=None):
	sz = self.size
	img = np.uint8(np.random.uniform(150, 180, (sz, sz, 3)))/255 # generate random image
	activations = SaveFeatures(list(self.model.children())[layer]) # register hook

	#!/usr/bin/env node

	var GCC_PREPROCESSOR_DEFINITIONS = '"$(inherited) DISABLE_PUSH_NOTIFICATIONS=1"';

	var fs = require("fs");
	var path = require("path");
	var xcode = require('xcode');
	var projectRoot = process.argv[2];

	function getProjectName(protoPath) {

	#!/usr/bin/env node

	var IOS_DEPLOYMENT_TARGET = '7.0';

	var fs = require("fs"),
	path = require("path"),
	shell = require("shelljs"),
	xcode = require('xcode'),
	projectRoot = process.argv[2];

	#########################
	# .gitignore file for Xcode4 and Xcode5 Source projects
	#
	# Apple bugs, waiting for Apple to fix/respond:
	#
	# 15564624 - what does the xccheckout file in Xcode5 do? Where's the documentation?
	#
	# Version 2.6
	# For latest version, see: http://stackoverflow.com/questions/49478/git-ignore-file-for-xcode-projects
	#

	<!doctype html>

	<!-- http://taylor.fausak.me/2015/01/27/ios-8-web-apps/ -->

	<html>
	<head>
	<title>iOS 8 web app</title>

	<!-- CONFIGURATION -->