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.

rain-1

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

chshersh

-- To run: 
--    cabal repl -b pretty-simple
--
-- Colorizing and pretty-printing ghci output
-- requires: pretty-simple
:set -interactive-print=Text.Pretty.Simple.pPrint

-- green bold lambdas and multiline mode
:set prompt      "\ESC[1;32mλ: \ESC[m"
:set prompt-cont "\ESC[1;32mλ| \ESC[m"

madsbuch

{-# LANGUAGE GADTs                #-} -- Soft dependent types
{-# LANGUAGE PolyKinds            #-} -- Allow general specification of Refl
{-# LANGUAGE RankNTypes           #-} -- Explicit quantification and inline type context
{-# LANGUAGE DataKinds            #-} -- Lift data constructors to Kind level
{-# LANGUAGE TypeFamilies         #-} -- Equational reasoning about types
{-# LANGUAGE TypeOperators        #-} -- Allow types such as :~:

-- Starting the interactive shell:
-- 
-- ghci -XDataKinds -XTypeOperators -Wall -Werror Script.hs

bishboria

These links no longer work. Springer have pulled the free plug.

Graduate texts in mathematics

duplicates = multiple editions

A Classical Introduction to Modern Number Theory, Kenneth Ireland Michael Rosen

A Classical Introduction to Modern Number Theory, Kenneth Ireland Michael Rosen

leroux

Haskell Resources

• Learning Haskell
• Learn You a Haskell for Great Good
  • Learn You A Haskell Exercises
• Real World Haskell
• FPComplete's School of Haskell
• Haskell Wikibook
• Write Yourself a Scheme in 48 Hours
• Parallel and Concurrent Programming in Haskell

MohamedAlaa

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

IcyMidnight

DELIMITER |

CREATE FUNCTION uuid_from_bin(b BINARY(16))
RETURNS CHAR(36) DETERMINISTIC
BEGIN
  DECLARE hex CHAR(32);
  SET hex = HEX(b);
  RETURN CONCAT(LEFT(hex, 8), '-', MID(hex, 9,4), '-', MID(hex, 13,4), '-', MID(hex, 17,4), '-', RIGHT(hex, 12));
END
|

ghoseb

#Newbie programmer
def factorial(x):
    if x == 0:
        return 1
    else:
        return x * factorial(x - 1)
print factorial(6)


#First year programmer, studied Pascal