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.

nup002

Setting Up a Physics and Electronics R&D Lab

A practitioner's guide based on experience setting up and operating sensor development and characterisation labs at CERN, LBNL, DESY, and the University of Bergen.

Author: Magne Lauritzen

Contact: magne.lauritzen@summacogni.com

The majority of this guide applies to any lab doing experimental physics, electronics development, or instrumentation work. Sensor-specific sections are clearly marked.

karpathy

"""
The most atomic way to train and run inference for 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

cablej

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

• NEVER use meta-phrases (e.g., "let me help you", "I can see that").
• NEVER summarize unless explicitly requested.
• NEVER provide unsolicited advice.
• NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
• ALWAYS be specific, detailed, and accurate.

AncientJames

#!/usr/bin/env python
import time
import sys
import getpass

from rgbmatrix import RGBMatrix, RGBMatrixOptions
import cv2 as cv

options = RGBMatrixOptions()
options.hardware_mapping = 'regular'

awni

Setup

On every machine in the cluster install openmpi and mlx-lm:

conda install conda-forge::openmpi
pip install -U mlx-lm

Next download the pipeline parallel run script. Download it to the same path on every machine:

ctlllll

import tiktoken
import langdetect
T = tiktoken.get_encoding("o200k_base")

length_dict = {}

for i in range(T.n_vocab):
    try:
        length_dict[i] = len(T.decode([i]))
    except:

karlhillx

macOS Big Sur 11.0 Setup: Homebrew + Apache + PHP + MariaDB

This document helps get your macOS development environment up and running with the latest versions of Homebrew, Apache, PHP, and MariaDB.

g2hollow

import pya

class AreaCalculator(pya.QDialog):
  """
  This class implements a dialog for calculating area of shapes
  in a layout. The calculator adds up shapes in the currently
  selected cell and below.
  """

  def button_clicked(self, checked):

iambibhas

Here is a list of scopes to use in Sublime Text 2 snippets - 

ActionScript: source.actionscript.2
AppleScript: source.applescript
ASP: source.asp
Batch FIle: source.dosbatch
C#: source.cs
C++: source.c++
Clojure: source.clojure
CoffeeScript: source.coffee