Charles Cai charles-cai

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 10K Stars ⭐️, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

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.

Update firmware WD Black SN770 firmware on Arch Linux

Been having problems with my new SN770 drive, and decided to check if I can firmware update it on Linux. WD only provides a Windows tool, Western Digital Dashboard to download and install firmwares, but, it's possible to find the firmware and install it using Linux tooling as well.

1. Check that `nvme-cli` is installed:

❱ sudo pacman -S nvme-cli

Building a Wireless Bluetooth USB-C Keyboard with ESP32-S3 Mini

Creating a wireless Bluetooth USB-C keyboard using an ESP32-S3 Mini involves connecting a USB-C keyboard to an ESP32-S3 via a USB Host Shield. This project allows you to transform a wired keyboard into a wireless one, leveraging Bluetooth communication. Below is a detailed guide on how to set up and program this system.

Components Needed

ESP32-S3 Mini
USB Host Shield or USB Host Adapter (e.g., USB Host Shield for Arduino or a USB Host Module)
USB-C Keyboard
USB-C to USB-A Adapter (if necessary)

Ollama GPU Selector: Customize GPU Usage for Ollama

If you want to run Ollama on a specific GPU or multiple GPUs, this tutorial is for you. By default, Ollama utilizes all available GPUs, but sometimes you may want to dedicate a specific GPU or a subset of your GPUs for Ollama's use. The idea for this guide originated from the following issue: Run Ollama on dedicated GPU.

Steps:

Create a script let's call it ollama_gpu_selector.sh:
```
nano ollama_gpu_selector.sh
```

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	import pandas as pd
	import requests
	import configparser
	import psycopg2

	# raw_data = requests.get("https://storage.googleapis.com/generall-shared-data/startups_demo.json")

	# with open("raw_files/raw_data.json", "w") as f:
	# f.write(raw_data.text)

	# 2023-11-27 MIT LICENSE

	Here's the open source version of my ChatGPT game MonkeyIslandAmsterdam.com.

	It's an unofficial image+text-based adventure game edition of Monkey Island in Amsterdam, my home town.

	Please use it however you want. It'd be nice to see more ChatGPT-based games appear from this. If you get inspired by it, please link back to my X https://x.com/levelsio or this Gist so more people can do the same!

	Send me your ChatGPT text adventure game on X, I'd love to try it!