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.

knowsuchagency

Comparison: Agent Browser Protocol vs Vercel agent-browser

Two browser automation solutions purpose-built for AI agents, both born in January 2026, taking radically different architectural approaches.

Overview

	Agent Browser Protocol (ABP)	Vercel agent-browser
Repo	theredsix/agent-browser-protocol	vercel-labs/agent-browser
Approach	Chromium fork with engine-level integration	Rust CLI wrapping a Playwright/Node.js daemon

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

hongsw

flowchart TD
    %% 중심 노드
    OSS[오픈소스 소프트웨어 교육 경로] 
    
    %% 서브그래프 레벨 정의
    subgraph 레벨1[레벨 1 - 핵심 기반 기술]
        direction TB
        TERMINAL[터미널 기본]
        SHELL[쉘 스크립트]

hongsw

flowchart TB
    subgraph "자연어 처리 전통적 접근법 (1950s~1980s)"
        RULE["규칙 기반 시스템<br>- 문법 규칙 수동 정의<br>- 전문가 지식 기반<br>- 확장성 한계"]
        SYM["기호주의 접근법<br>- 형식 언어 및 문법<br>- 논리 기반 추론<br>- 애매성 처리 어려움"]
        PARSE["구문 분석 트리<br>- 문장 구조 표현<br>- 계층적 분석<br>- 의미 파악 제한"]
    end

    subgraph "수학적 기반"
        subgraph "선형대수학 (Linear Algebra)"

hongsw

#!/bin/bash

# Create backup filename with current date and time
BACKUP_FILE=~/.zshrc.backup.$(date +%Y%m%d%H%M%S)

# Backup original file
cp ~/.zshrc "$BACKUP_FILE"
echo "Existing .zshrc file has been backed up to $BACKUP_FILE"

# Remove existing ASDF-related settings and create new file

willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

hongsw

void main() {
	var hello = 'Hello, 🌍!';
	print(hello.toUpperCase());  // Output: "HELLO, 🌍!"

  hello = 'Hello, 🌍!';
	print(hello.toLowerCase());  // Output: "hello, 🌍!"

  hello = '  Hello, 🌍!  ';
	print(hello.trim());  // Output: "Hello, 🌍!"

hongsw

import 'package:flutter/material.dart';

void main() {
  runApp(MyApp());
}

class MyApp extends StatefulWidget {
  @override
  State<MyApp> createState() => _MyAppState();

hongsw

import 'package:flutter/material.dart';

void main() {
  runApp(MyApp());
}

class MyApp extends StatefulWidget {
  @override
  State<MyApp> createState() => _MyAppState();