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.

gbiellem

$reg = @{
    Path = 'Registry::HKEY_CURRENT_USER\Software\Microsoft\Windows\CurrentVersion\Policies\Attachments'
    Name = 'SaveZoneInformation'
    PropertyType = 'DWORD'
    Value = 1
}

if (-not (Test-Path -Path $reg.Path)) {
    New-Item $reg.Path
}

gbiellem

; CouchDB Configuration Settings

; Custom settings should be made in this file. They will override settings
; in default.ini, but unlike changes made to default.ini, this file won't be
; overwritten on server upgrade.

[couchdb]
;max_document_size = 4294967296 ; bytes
;os_process_timeout = 5000
uuid = a4380b3563aa5c628fa98c5ccc4e160b

mendozao

Get ClamAV running on Mac OS X (using Homebrew)

The easiest way to get the ClamAV package is using Homebrew

$ brew install clamav

Before trying to start the clamd daemon, you'll need a copy of the ClamAV databases.

Inside /your/location/to/brew/etc/clamav, you'll see 2 files:

rondy

FWIW: I (@rondy) am not the creator of the content shared here, which is an excerpt from Edmond Lau's book. I simply copied and pasted it from another location and saved it as a personal note, before it gained popularity on news.ycombinator.com. Unfortunately, I cannot recall the exact origin of the original source, nor was I able to find the author's name, so I am can't provide the appropriate credits.

---

Effective Engineer - Notes

• By Edmond Lau
• Highly Recommended 👍
• http://www.theeffectiveengineer.com/

What's an Effective Engineer?

QuantumGhost

@startuml
' uncomment the line below if you're using computer with a retina display
' skinparam dpi 300
!define Table(name,desc) class name as "desc" << (T,#FFAAAA) >>
' we use bold for primary key
' green color for unique
' and underscore for not_null
!define primary_key(x) <b>x</b>
!define unique(x) <color:green>x</color>
!define not_null(x) <u>x</u>

btroncone

Comprehensive Introduction to @ngrx/store

By: @BTroncone

Also check out my lesson @ngrx/store in 10 minutes on egghead.io!

Update: Non-middleware examples have been updated to ngrx/store v2. More coming soon!

Table of Contents