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.

jboner

Latency Comparison Numbers (~2012 except when noted)
----------------------------------
L1 cache reference                           0.5 ns
Branch mispredict                            5   ns
L2 cache reference                           7   ns                      14x L1 cache
Mutex lock/unlock                           25   ns
Main memory reference                      100   ns                      20x L2 cache, 200x L1 cache
Compress 1K bytes with Zippy             3,000   ns        3 us
Send 1K bytes over 1 Gbps network       10,000   ns       10 us
Read 4K randomly from SSD*             150,000   ns      150 us          ~1GB/sec SSD

bcherny

Notes on Martin Kleppmann's excellent Designing Data-Intensive Applications.

Chapter 1: Reliable, Scalable, and Maintainable Applications

• Data Systems
  • Dimensions to consider when thinking about data systems: access patterns, performance characteristics, implementations.
  • Modern data systems often blur the lines between databases, caches, streams, etc.
• Reliability
  • Systems should perform the expected function at a given level of performance, and be tolerant to faults and user mistakes
• Fault: One component of a system deviating from its spec. Prefer tolerating faults over preventing them (except for things like security issues). Faults stem from hardware failures, software failures, and human error (in a study, config errors caused most outages).

bruxx-6243

🐞 Atelier de débogage JavaScript — Task Manager

Niveau : Débutant → Intermédiaire Langage : JavaScript Format : 5 exercices progressifs Thème : Identifier, comprendre et corriger les erreurs dans le code d'un gestionnaire de tâches

---

📌 Présentation

MotherSphere

NIKKE PC launcher compromise (November 2026)

한국어 번역 (Korean translation): nikke-pc-launcher-compromise_ko.md

Caution

From 2026-09-27, four official JavaScript files on Level Infinite's CDN contained attacker code. The NIKKE PC launcher loads these files. From Oct 23 at the latest, opening the launcher could install a remote-control agent: while the launcher was open, the attacker could run any command on your machine, read any file and take screenshots.

Update, 2026-11-03 22:40 GMT: three of the files were replaced on Nov 3 at 17:04, 17:13 and 17:21 GMT. The fourth, FeedList.feb647c9.js, was cleaned at the origin on Oct 28, but two CDN servers still delivered the modified copy at 22:26 GMT. The attacker's server no longer answered at 18:31 GMT. None of this undoes anything on machines that were already infected, and the old files may still be in your launcher's cache. **Do not open the NIKKE PC launcher until Level Infinite confirms the fix,

miketartar

import json

import sqlite3

import os

DB_PATH = "C:/ProgramData/Cold Turkey/data-app.db"

def activate():

NathanSebhastian

{
  "maxEffortLevel": "medium",
  "permissions": { "defaultMode": "acceptEdits" },
  "env": {
    "ANTHROPIC_BASE_URL": "http://localhost:20128",
    "ANTHROPIC_AUTH_TOKEN": "YOUR OMNIROUTE API KEY",
    "ANTHROPIC_API_KEY": "",
    "ANTHROPIC_MODEL": "YOUR OMNIROUTE COMBO",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "YOUR OMNIROUTE COMBO",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "YOUR OMNIROUTE COMBO",

LuviKunG

// Copyright by Thanut Panichyotai (@LuviKunG)
// CC BY-SA 4.0
// https://creativecommons.org/licenses/by-sa/4.0/

#include "Widgets/RichTextBlockInputActionDecorator.h"

#include "EnhancedInputSubsystems.h"
#include "InputMappingContext.h"
#include "Fonts/FontMeasure.h"
#include "Kismet/GameplayStatics.h"

isdaviddong

<!DOCTYPE html>
<html>
<head>
    <title></title>
	<meta charset="utf-8" />
    <script src="Scripts/jquery-1.9.1.min.js"></script>
    <link href="Content/bootstrap.min.css" rel="stylesheet" />
    <script src="Scripts/isRockFx.js"></script>
    <script>
        $(function () {

k16shikano

name	japanese-tech-writing
description	日本語の技術文書・書籍原稿の文章規範。段落と論証の構成（パラグラフライティング）、論証の厳密さ（ツッコミどころの除去）、読み手の負荷の管理、視点と語り、演出の抑制、LLM っぽい空句の禁止、翻訳調の比喩と擬人化の禁止（「運ぶ」「効く」「開かれた問い」など）、冗長の排除を定める。日本語で技術書の章、草稿、記事、解説文を書くとき、または推敲・リライトするときに使用する。
license	Unlicense（https://gist.github.com/k16shikano/67625f2a7d96e3bbdfae8d571a936063）

日本語技術文書の文章規範

日本語で技術的な原稿（書籍の章、記事、解説文）を書く・推敲するときは、以下の規範に従う。