Shane O'Grady shaneog

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.

Shakespeare Sonnet++ Postmortem (incident #465)

Date

2015-10-21

Authors

jennifer
martym

Product management process with Trello

A Trello board is a software equivalent of a physical wall with columns of sticky notes. In Trello terminology, the wall is called a "board." The columns are called "lists." The sticky notes in columns are called "cards."

No two products are the same, so flexibility in the product management process is important. Trello responds well to changing the structure of the process "on the fly."

Docker Container Name

A one paragraph description about the container.

Getting Started

These instructions will cover usage information and for the docker container

Prerequisities

Contributing

When contributing to this repository, please first discuss the change you wish to make via issue, email, or any other method with the owners of this repository before making a change.

Please note we have a code of conduct, please follow it in all your interactions with the project.

Pull Request Process

Ensure any install or build dependencies are removed before the end of the layer when doing a

Project Title

One Paragraph of project description goes here

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

	aws_ecr_curl() {
	login_cmd=$(aws ecr get-login)
	username=$(echo "$login_cmd" \| cut -d " " -f 4)
	password=$(echo "$login_cmd" \| cut -d " " -f 6)
	endpoint=$(echo "$login_cmd" \| cut -d " " -f 9)

	args=("$@")
	args_length=${#args[@]}
	args_last=${args[$args_length-1]}
	unset 'args[${args_length}-1]'

	apiVersion: v1
	kind: Service
	metadata:
	name: nginx-ingress
	spec:
	loadBalancerIP: xxxxxxx
	type: LoadBalancer
	ports:
	# - port: 80
	# name: http

	#!/usr/bin/python
	# encoding: utf-8

	# Based off the script from https://gist.github.com/Paaskehare/3949299
	# @author: Ash Ramesh (27/10/2016)

	import cookielib
	import urllib
	import urllib2
	import re

	#!/bin/bash -e

	# Wrapper for the toggle_alfred_theme.py script at
	# https://gist.github.com/deanishe/ce442c3a768adedc9c39
	# (where this script also comes from)
	#
	# The purpose of this wrapper is to enable you to update the Python script
	# without having to edit the script to change the settings each time. You keep
	# them in here instead, and this script should hopefully prove dumb enough
	# to require little updating...