Discover gists

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.

FP(y)LLL & G6K Lab

Add English (US, alt. intl.)

It's because the cedilla module isn't loaded by default when the locale is set to en, so you have to change the configuration files for gtk to add them:

Edit configuration files:

sudo vim /usr/lib/x86_64-linux-gnu/gtk-3.0/3.0.0/immodules.cache

sudo vim /usr/lib/x86_64-linux-gnu/gtk-2.0/2.10.0/immodules.cache

58 bytes of CSS to look great nearly everywhere

When making this website, i wanted a simple, reasonable way to make it look good on most displays. Not counting any minimization techniques, the following 58 bytes worked well for me:

main {
  max-width: 38rem;
  padding: 2rem;
  margin: auto;
}

NanoClaw — Personal Claude Assistant

A self-hosted, compounding-memory AI assistant running on a Raspberry Pi.

What Is This?

NanoClaw is a personal AI assistant built on Anthropic's Claude that runs entirely on a Raspberry Pi. It connects to messaging channels (WhatsApp, Telegram, Slack, Discord), processes voice and images, schedules recurring tasks, and — unlike a standard chatbot — accumulates knowledge over time through a structured memory system.

エンジニア向け研修

CARTA HOLDINGS（旧VOYAGE GROUP）
- 技術広報が新卒研修<Open AIハッカソン>をスパイしてみた - (2023/04/11)
- @t_wadaに学ぶテスト駆動開発【CARTA 23新卒研修】 - (2023/04/19)
- 【新卒研修】監修者@t_wadaと読む！プログラマが知るべき97のこと読書会 - (2024/04/09)
Classi
- 当たり前にリリースしていく ~ 新卒研修編 - (2021/05/20)
- リモートワークのための質問力向上研修を実施しました - (2021/12/07)
- Classi 2025年新卒エンジニア研修「そーだい塾」を開催しました - (2025/06/18)
CyberZ

	using System;
	using System.Collections.Generic;
	using System.Linq;
	using System.Runtime.CompilerServices;
	using System.Net;
	using System.Reflection;
	using System.Runtime.InteropServices;
	namespace Test
	{
	// CCOB IS THE GOAT

	#!/bin/bash

	# Update GTK cache to include support for the cedilla module in English
	GTK3_CACHE_FILE="/usr/lib/x86_64-linux-gnu/gtk-3.0/3.0.0/immodules.cache"
	if [ -f "$GTK3_CACHE_FILE" ]; then
	sudo sed -i 's/\("cedilla" "Cedilla" "gtk30" \)/\1en:/' "$GTK3_CACHE_FILE"
	fi

	GTK2_CACHE_FILE="/usr/lib/x86_64-linux-gnu/gtk-2.0/2.10.0/immodules.cache"
	if [ -f "$GTK2_CACHE_FILE" ]; then