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.

raullenchai

## Workflow Orchestration

### 1. Plan Mode Default

* Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
* If something goes sideways, STOP and re-plan immediately – don't keep pushing
* Use plan mode for verification steps, not just building
* Write detailed specs upfront to reduce ambiguity

### 2. Subagent Strategy

jeffdonthemic

This simple controller (without CRUD and FLS) ...

public with sharing class AccountController {

    @AuraEnabled
    public static List<Account> findAll() {
        return [SELECT id, name, Location__Latitude__s, Location__Longitude__s
            FROM Account
            WHERE Location__Latitude__s != NULL AND Location__Longitude__s != NULL
            LIMIT 50];