martin chan siutin

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.

Make Ubuntu packages 90% faster by rebuilding them

TL;DR

You can take the same source code package that Ubuntu uses to build jq, compile it again, and realize 90% better performance.

Setting

I use jq for processing GeoJSON files and other open data offered in JSON format. Today I am working with a 500MB GeoJSON file that contains the Alameda County Assessor's parcel map. I want to run a query that prints the city for every parcel worth more than a threshold amount. The program is

FAQ on the xz-utils backdoor (CVE-2024-3094)

This is a living document. Everything in this document is made in good faith of being accurate, but like I just said; we don't yet know everything about what's going on.

Update: I've disabled comments as of 2025-01-26 to avoid everyone having notifications for something a year on if someone wants to suggest a correction. Folks are free to email to suggest corrections still, of course.

Background

GOAL : Debian 11 minimal server, size 700 MB

TOOL :

Linux : Debian 11 at /dev/sda, Target at /dev/sdb
Application : debootstrap, parted
User : root

Installing the NVIDIA driver, CUDA and cuDNN on Linux (Ubuntu 20.04)

This is a companion piece to my instructions on building TensorFlow from source. In particular, the aim is to install the following pieces of software

NVIDIA graphics card driver (v450.57)
CUDA (v11.0.2)
cuDNN (v8.0.2.39)

on an Ubuntu Linux system, in particular Ubuntu 20.04.

32-bit ELF binary

how to assemble and link:

nasm -f elf32 -o <filename>.o <filename>.asm
ld -m elf_i386 -o <filename> <filename>.o

template code (hello world):

section .text
global _start

Swift Concurrency Manifesto

Author: Chris Lattner

Chinese Translation by Jason Yu

Multiple MySQL Versions for Development

Options included below:

Using Docker docker-compose
Using Homebrew brew

Using Docker (recommended)

This gist was originally created for Homebrew before the rise of Docker, yet it may be best to avoid installing mysql via brew any longer. Instead consider adding a barebones docker-compose.yml for each project and run docker-compose up to start each project's mysql service.

	import cv2
	import time

	CONFIDENCE_THRESHOLD = 0.2
	NMS_THRESHOLD = 0.4
	COLORS = [(0, 255, 255), (255, 255, 0), (0, 255, 0), (255, 0, 0)]

	class_names = []
	with open("classes.txt", "r") as f:
	class_names = [cname.strip() for cname in f.readlines()]

	# Python 2/3 compatibility
	from __future__ import print_function

	import numpy as np
	import imutils
	import cv2
	import sys


	# Global vars: