BitCook bit-cook

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.

打开论坛，按下F12，运行以上代码。

Setup:

Add this code to your ~/.bash_aliases file.

function gdrive_download () {
  CONFIRM=$(wget --quiet --save-cookies /tmp/cookies.txt --keep-session-cookies --no-check-certificate "https://docs.google.com/uc?export=download&id=$1" -O- | sed -rn 's/.*confirm=([0-9A-Za-z_]+).*/\1\n/p')
  wget --load-cookies /tmp/cookies.txt "https://docs.google.com/uc?export=download&confirm=$CONFIRM&id=$1" -O $2
  rm -rf /tmp/cookies.txt
}

Keybase proof

I hereby claim:

I am zhiiker on github.
I am zhiiker (https://keybase.io/zhiiker) on keybase.
I have a public key ASDn98stR7K5nnpSLTtIoMFuNKQwXpXu85B2u25mrhXWIgo

To claim this, I am signing this object:

	"""
	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

	class LinearRegression {
	w: Mat;
	constructor() { }

	//x: M-by-N matrix. M data with N dimensions. Each row is an N-dim vector
	//y: M-by-1 matrix
	fit(x_: Mat, y_: Mat) : LinearRegression{
	let y = y_;
	if (y_.rows != 1 && y_.cols == 1) {y = y_.T();} //check the dimension of y
	var x = x_.resize(x_.rows, x_.cols + 1, 1); //expan x_ with one more column with 1

	-- 只扫原生WS,不要太恐慌.

	local stdnse = require "stdnse"
	local http = require "http"

	categories = { "default", "discovery", "safe" }

	portrule = function(host, port)
	return true
	end

	import requests
	import json
	import base64
	import sqlite3
	import zlib
	import time
	from datetime import datetime
	from gql import gql, Client
	from gql.transport.requests import RequestsHTTPTransport

	#include<cstdio>
	#include<cstring>
	#include<cstdlib>
	#include<windows.h>
	#include<conio.h>
	#include<ctime>
	using namespace std;
	clock_t t1,t2;
	int ti;
	POINT pt;

	@echo off
	>nul 2>&1 "%SYSTEMROOT%\system32\cacls.exe" "%SYSTEMROOT%\system32\config\system"
	if '%errorlevel%' NEQ '0' (
	goto UACPrompt
	) else ( goto gotAdmin )
	:UACPrompt
	echo Set UAC = CreateObject^("Shell.Application"^) > "%temp%\getadmin.vbs"
	echo UAC.ShellExecute "%~s0", "", "", "runas", 1 >> "%temp%\getadmin.vbs"
	"%temp%\getadmin.vbs"
	exit /B