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.

xthezealot

You are Lyra, a master-level AI prompt optimization specialist. Your mission: transform any user input into
precision-crafted prompts that unlock AI's full potential across all platforms.

## THE 4-D METHODOLOGY

### 1. DECONSTRUCT
- Extract core intent, key entities, and context
- Identify output requirements and constraints
- Map what's provided vs. what's missing

jonasgeiler

FROM node:12-alpine
RUN apk --no-cache add git

RUN git clone https://github.com/jsbin/jsbin.git /jsbin

WORKDIR /jsbin

RUN npm install -g grunt-cli
RUN npm install
RUN grunt build

vishiy

maple3142

# Put this file in /etc/nginx/sites-available
# Then "ln -s /etc/nginx/sites-available/aria2-nginx.conf /etc/nginx/sites-enabled"
# Then "sudo service nginx restart"
server {
        listen 80;
        listen [::]:80;
        root /var/www/aria2; # Put your aria2 web ui here, such as AriaNg
        index index.html;
        server_name DOMAIN_NAME;
        location / {

y0ngb1n

Docker Hub 镜像加速器

国内从 Docker Hub 拉取镜像有时会遇到困难，此时可以配置镜像加速器。

Dockerized 实践 https://github.com/y0ngb1n/dockerized

1️⃣ Docker daemon 配置代理（推荐）

参考 Docker daemon 配置代理

TrinityCoder

Sometimes we might want to print some text in Bash and we might want it to be centered to the centre of the terminal. It is a cheap way how we can increase clarity of output of our script and make it look much more attractive.

The whole magic is hidden in a program called tput.

To get number of rows and cols of current terminal, we need just two simple shell substitutions:

    TERM_ROWS="$(tput rows)"

fntlnz

Create Root CA (Done once)

Last update: Nov 2025.

Create Root Key

Attention: this is the key used to sign the certificate requests, anyone holding this can sign certificates on your behalf. So keep it in a safe place!

openssl ecparam -genkey -name secp384r1 | openssl ec -aes256 -out rootCA.key

kaleksandrov

#!/bin/bash

case $# in
   0)
      echo "Usage: $0 {start|stop}"
      exit 1
      ;;
   1)
      case $1 in
         start)

tonysneed

- Open Automator 
- File -> New -> Service 
- Change "Service Receives" to "files or folders" in "Finder" 
- Add a "Run Shell Script" action 
- Change "Pass input" to "as arguments" 
- Paste the following in the shell script box: open -n -b "com.microsoft.VSCode" --args "$*" 
- Save it as something like "Open in Visual Studio Code"