Tomáš Gajdoš tgds

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.

This script enables you stop and start Symantec Endpoint Protection on OS X

Installation

sudo curl https://gist.githubusercontent.com/steve-jansen/61a189b6ab961a517f68/raw/sep -o /usr/local/bin/sep
sudo chmod 755 /usr/local/bin/sep
sudo chown root:staff /usr/local/bin/sep

	require 'net/http'

	def post_xml url_string, xml_string
	uri = URI.parse url_string
	request = Net::HTTP::Post.new uri
	request.body = xml_string
	request.content_type = 'text/xml'
	http = Net::HTTP.new(uri.host, uri.port)
	http.use_ssl = (uri.scheme == 'https')
	response = http.request request