sanchez314c

SYSTEM PROMPT:

The Karpathy-Michaels (@SpaceWelder314) CLAUDE.md + LOOPS.md

Andrej Karpathy's CLAUDE.md and LOOPS.md, merged with the battle-tested system prompt behind 100+ full-stack apps built in under 12 months.

Karpathy published his CLAUDE.md as a clean set of principles, then followed it with LOOPS.md on agent harness design. Both are correct. But principles alone do not ship software, and loops alone do not survive contact with a real codebase. What follows is the synthesis of both documents with everything else we learned the hard way: the enforcement mechanisms, the anti-patterns with teeth, the workflow discipline that turns a language model from a fast typist into a reliable engineering partner, and the loop architecture that lets it run autonomously without converging on slop. 35 rules across 6 tiers. Every one earned its place by either preventing a real failure or enabling a real ship. Nothing is theoretical.

---

TIER 1 — FOUNDATION

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.

npearce

UPDATE (March 2020, thanks @ic): I don't know the exact AMI version but yum install docker now works on the latest Amazon Linux 2. The instructions below may still be relevant depending on the vintage AMI you are using.

Amazon changed the install in Linux 2. One no-longer using 'yum' See: https://aws.amazon.com/amazon-linux-2/release-notes/

Docker CE Install

sudo amazon-linux-extras install docker
sudo service docker start

cterrykenzan

#!/bin/bash

#In early development, sometimes you've got a hand-built instance, but you also don't want to leave it up all the time
# We've got an m4xl instance running Spinnaker (http://spinnaker.io) but we only really need it during the day
# As a cost-saving measure, we shut it down overnight.  However, we want it to be consistently accessible
# So this script is in a Jenkins job that runs every morning, 
# starting up the instance then updating its DNS record to the new IP.

#If you have multiple DNS records for a single instance, 
# you can safely run a second copy of the script with the ZONEID and RECORDSET updated appropriately.

chusiang

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": "s3:ListAllMyBuckets",
            "Resource": "arn:aws:s3:::MyBucketName"
        },
        {
            "Action": [

aertmann

Solution

Add vers=4 to the mount command.

sudo mount -o vers=4,resvport,rw -t nfs x.x.x.x:/home mount

mobilemind

# delete local tag '12345'
git tag -d 12345
# delete remote tag '12345' (eg, GitHub version too)
git push origin :refs/tags/12345
# alternative approach
git push --delete origin tagName
git tag -d tagName

reu

var redis = require("redis")
  , subscriber = redis.createClient()
  , publisher  = redis.createClient();

subscriber.on("message", function(channel, message) {
  console.log("Message '" + message + "' on channel '" + channel + "' arrived!")
});

subscriber.subscribe("test");