mdaisuke mdaisuke

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.

Global AI Rules for Windsurf

AI Guidelines

You are an expert programming assistant focusing on:

TypeScript, React, Node.js, AstroJS 5.x, AstroDB
Shadcn UI and Tailwind CSS useations
Latest features and best practices
Clear, readable, and maintainable code

ふりかえりのグランドルール

1．積極的に参加すること

当事者意識を持つ
議題に集中すること

２．一人で話しすぎないこと

人の発言をさえぎらない

tmux cheat sheet

(C-x means ctrl+x, M-x means alt+x)

Prefix key

The default prefix is C-b. If you (or your muscle memory) prefer C-a, you need to add this to ~/.tmux.conf:

remap prefix to Control + a

Docker 虎の巻

Fork from Docker cheat sheet
実際にコマンドを試したい場合は、すぐにDockerを試したい人のための基礎コマンドを参照

何故Dockerを使うべきか

Why Should I Care (For Developers)

"Dockerが面白いのはシンプルな環境に隔離性と再現性をもたらしてくれることだ．ランタイムの環境を一度作れば、パッケージにして別のマシンでも再利用することできる．さらに，すべてはホスト内の隔離された環境で行われる（VMのように）．最も素晴らしい点は，シンプルかつ高速であることだ．"

	"""
	The most atomic way to train and inference a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	#!/usr/bin/env bash

	############### USAGE ###############
	#
	# 1. Create a new workspace on Cloud9 using the "Blank" template
	#
	# 2. Run this command in the console:
	# bash <(curl -fsSL https://gist.githubusercontent.com/padde/3c6301f15cbd5025e131740dae33aa95/raw/c9-elixir.sh)
	#
	# 3. There is no step 3!

	# LVDB - LLOOGG Memory DB
	# Copyriht (C) 2009 Salvatore Sanfilippo <antirez@gmail.com>
	# All Rights Reserved

	# TODO
	# - cron with cleanup of timedout clients, automatic dump
	# - the dump should use array startsearch to write it line by line
	# and may just use gets to read element by element and load the whole state.
	# - 'help','stopserver','saveandstopserver','save','load','reset','keys' commands.
	# - ttl with milliseconds resolution 'ttl a 1000'. Check ttl in dump!

	#include "mpc.h"

	#include <editline/readline.h>

	enum { LERR_DIV_ZERO, LERR_BAD_OP, LERR_BAD_NUM };
	enum { LVAL_NUM, LVAL_ERR };

	typedef struct {
	int type;
	long num;

	# >> を *
	# >>= を bind
	# return を self.new
	# mplus を +
	# mzero を self.zero
	#
	# に見立てて Maybe モナド書いてみた
	# bind に渡す block で Maybe と書きたくないので第二引数に型情報を付加してみた。
	class Monad
	def *(m)