Skip to content

Instantly share code, notes, and snippets.

View deangiberson's full-sized avatar

Dean Giberson deangiberson

View GitHub Profile
@deangiberson
deangiberson / llm-wiki.md
Created November 7, 2026 05:07 — forked from karpathy/llm-wiki.md
llm-wiki

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.

@deangiberson
deangiberson / VSDD.md
Created July 19, 2026 05:05 — forked from dollspace-gay/VSDD.md
Verified Spec-Driven Development

Verified Spec-Driven Development (VSDD)

The Fusion: VDD × TDD × SDD for AI-Native Engineering

Overview

Verified Spec-Driven Development (VSDD) is a unified software engineering methodology that fuses three proven paradigms into a single AI-orchestrated pipeline:

  • Spec-Driven Development (SDD): Define the contract before writing a single line of implementation. Specs are the source of truth.
  • Test-Driven Development (TDD): Tests are written before code. Red → Green → Refactor. No code exists without a failing test that demanded it.
@deangiberson
deangiberson / llm-wiki.md
Created April 19, 2026 17:56 — forked from rohitg00/llm-wiki.md
LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.

@deangiberson
deangiberson / gist:1ee1430c706de07c62caac847644c7b9
Created June 15, 2016 00:25 — forked from mattm7n/gist:1405067
Monitor DHCP traffic with tcpdump
# Monitoring on interface eth0
tcpdump -i eth0 -n port 67 and port 68
@deangiberson
deangiberson / geoff-yed-tips
Created January 8, 2016 00:55 — forked from malcolmocean/geoff-yed-tips
Geoff's tips for setting up yEd
From Geoff Anders, of Leverage Research (http://www.leverageresearch.org/)
For people doing goal factoring - or for people making any sort of box-and-arrow diagram - I recommended the program yEd. It is available here: http://www.yworks.com/en/products_yed_about.html
After you install it, I highly recommend setting up the defaults in the following way:
1. Open yEd.
2. Create a new document.
3. Click the white background; a small yellow square should appear on the canvas.
4. Click the small yellow square so as to select it.

Business Models

Advertising

Models Examples
Display ads Yahoo!
Search ads Google
/**
* Circular Tooltip (SO)
* http://stackoverflow.com/q/13132864/1397351
*/
* { margin: 0; padding: 0; }
body {
overflow: hidden;
background: url(http://theearlcarlson.com/experiments/amTooltip/img/bg.jpg);
}
/* generic styles for button & circular menu */
function MonitorAssignment( F, names, valNames, E )
% MonitorAssignment( F, names, valNames, E ) - Pretty prints all the
% marginals for an assignment
%
% F contains the struct array of factors
% names contains the variable names
% valNames contains the assignment names for each variable,
% as seen in SAMIAM
% E is an N-by-2 cell array, each row being a variable/value pair.
% Variables are in the first column and values are in the second column.
@deangiberson
deangiberson / gist:4166712
Created November 29, 2012 03:52
Integrate Emacs with git grep for grepping and interactive search and replace
(defun* get-closest-pathname (&optional (file "Makefile"))
"Determine the pathname of the first instance of FILE starting from the
current directory towards root. This may not do the correct thing in presence
of links. If it does not find FILE, then it shall return the name of FILE in
the current directory, suitable for creation"
(let ((root (expand-file-name "/")))
(expand-file-name file
(loop
for d = default-directory
then (expand-file-name ".." d)