karpathy

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.

Zekfad

Quick examples

• feat: new feature
• fix(scope): bug in scope
• feat!: breaking change / feat(scope)!: rework API
• chore(deps): update dependencies

Commit types

• build: Changes that affect the build system or external dependencies (example scopes: gulp, broccoli, npm)
• ci: Changes to CI configuration files and scripts (example scopes: Travis, Circle, BrowserStack, SauceLabs)
• chore: Changes which doesn't change source code or tests e.g. changes to the build process, auxiliary tools, libraries

eenblam

Linux Networking Reading List

Currently in no particular order. Most of these are kind of ancient.

Where's all the modern documentation? So much of what I've turned up searching is other folks complaining about having few options beyond reading source code.

The OREILLY books, while dated, seem to be some of the best available. Note that these can be read with a 7-day trial. Do this! At least get through the introduction section and first chapter of each to see if it's what you're after.

https://www.netfilter.org/

stevedoyle

Git Cheatsheet

Fetching and Pulling

Task	Command
Fetch for later merging	git fetch [remote name]
Pull and merge	git pull [remote name]
Pull and rebase local changes on top (instead of merging)	git pull --rebase [remote name]
Clone only a subset of files	git init repo cd repo git remote add origin url git config core.sparsecheckout true echo "path/*" >> .git/info/sparse-checkout git pull --depth=1 origin master

stevedoyle

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

squarism

In the below keyboard shortcuts, I use the capital letters for reading clarity but this does not imply shift, if shift is needed, I will say shift. So ⌘ + D does not mean hold shift. ⌘ + Shift + D does of course.

Tabs and Windows

Function	Shortcut
New Tab	⌘ + T
Close Tab or Window	⌘ + W (same as many mac apps)
Go to Tab	⌘ + Number Key (ie: ⌘2 is 2nd tab)
Go to Split Pane by Direction	⌘ + Option + Arrow Key

tuxfight3r

Bash Shortcuts

Moving

command	description
ctrl + a	Goto BEGINNING of command line

obstschale

Octave CheatSheet

GNU Octave is a high-level interpreted language, primarily intended for numerical computations.
(via GNU Octave)

Hint: I also mad an octave docset for Dash: https://github.com/obstschale/octave-docset

Basics

MohamedAlaa

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

jboner

Latency Comparison Numbers (~2012)
----------------------------------
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        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD