Csaba Ekart ekaktusz

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.

Effective Modern CMake

Getting Started

For a brief user-level introduction to CMake, watch C++ Weekly, Episode 78, Intro to CMake by Jason Turner. LLVM’s CMake Primer provides a good high-level introduction to the CMake syntax. Go read it now.

After that, watch Mathieu Ropert’s CppCon 2017 talk Using Modern CMake Patterns to Enforce a Good Modular Design (slides). It provides a thorough explanation of what modern CMake is and why it is so much better than “old school” CMake. The modular design ideas in this talk are based on the book [Large-Scale C++ Software Design](https://www.amazon.de/Large-Scale-Soft

Kaboo

Kaboo is played with a standard card deck. It can be played with 2 to 8 players with a single deck.

Card values

Ace = 1
2-10 = 2-10
Jack, Queen, King = 10
Red King = -1 (both of them)

Code is clean if it can be understood easily – by everyone on the team. Clean code can be read and enhanced by a developer other than its original author. With understandability comes readability, changeability, extensibility and maintainability.

General rules

Follow standard conventions.
Keep it simple stupid. Simpler is always better. Reduce complexity as much as possible.
Boy scout rule. Leave the campground cleaner than you found it.
Always find root cause. Always look for the root cause of a problem.

Design rules

NOTE: This is a question I found on StackOverflow which I’ve archived here, because the answer is so effing phenomenal.

Q: How can I make a chain of function decorators in Python?

If you are not into long explanations, see [Paolo Bergantino’s answer][2].

	theme = "gruvbox"

	[editor]
	#line-number = "relative"
	mouse = true
	auto-completion = true
	completion-timeout = 5
	completion-trigger-len = 1
	true-color = true
	bufferline = "always"

	package main

	import "core:fmt"
	import "core:math"
	import "core:math/linalg"
	import rl "vendor:raylib"

	main :: proc() {
	rl.SetConfigFlags({.VSYNC_HINT, .WINDOW_RESIZABLE, .MSAA_4X_HINT})
	rl.InitWindow(800, 600, "collision")

	#!/bin/bash

	## Bash script for setting up ROS Noetic (with Gazebo 11) development environment for PX4 on Ubuntu LTS (20.04).
	## It installs the common dependencies for all targets (including Qt Creator)
	##
	## Installs:
	## - Common dependencies libraries and tools as defined in `ubuntu_sim_common_deps.sh`
	## - ROS Noetic (including Gazebo11)
	## - MAVROS

	#include <SFML/Graphics.hpp>

	int main()
	{
	sf::RenderWindow window(sf::VideoMode(800, 600), "Parallax Example",
	sf::Style::Titlebar \| sf::Style::Close);
	window.setVerticalSyncEnabled(true);

	sf::Texture texture;
	if (!texture.loadFromFile("resources/background.jpg"))

	import tensorflow as tf

	x = tf.Variable(2, name='x', dtype=tf.float32)
	log_x = tf.log(x)
	log_x_squared = tf.square(log_x)

	optimizer = tf.train.GradientDescentOptimizer(0.5)
	train = optimizer.minimize(log_x_squared)

	init = tf.initialize_all_variables()