stevedomin

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.

stevedomin

Latency numbers every programmer should know

L1 cache reference ......................... 0.5 ns
Branch mispredict ............................ 5 ns                     on recent CPU
L2 cache reference ........................... 7 ns                     14x L1 cache
Mutex lock/unlock ........................... 25 ns
Main memory reference ...................... 100 ns                     20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy ............. 3,000 ns  =   3 µs
Send 2K bytes over 1 Gbps network ....... 20,000 ns  =  20 µs
SSD random read ........................ 150,000 ns  = 150 µs

Read 1 MB sequentially from memory ..... 250,000 ns = 250 µs 4X memory

stevedomin

From: Chris DeSalvo <chris.desalvo@voxer.com>
Subject: Why we can't process Emoji anymore
Date: Thu, 12 Jan 2012 18:49:20 -0800
Message-Id: <AE459007-DF2E-4E41-B7A4-FA5C2A83025F@voxer.com>

--Apple-Mail=_6DEAA046-886A-4A03-8508-6FD077D18F8B
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
	charset=utf-8

stevedomin

#!/usr/bin/env bash

set -o errtrace
set -o errexit


facter_version=$1
puppet_version=$2
target_volume=$3

stevedomin

Latency Comparison Numbers
--------------------------
L1 cache reference                            0.5 ns
Branch mispredict                             5   ns
L2 cache reference                            7   ns             14x L1 cache
Mutex lock/unlock                            25   ns
Main memory reference                       100   ns             20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy              3,000   ns
Send 1K bytes over 1 Gbps network        10,000   ns    0.01 ms
Read 4K randomly from SSD*              150,000   ns    0.15 ms