Dennis Staiger davosian

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.

Bruno API Collection Generator

Scan any codebase and generate a complete, executable Bruno API collection using AI. Works with ChatGPT, Claude, Gemini, or any local model. Copy the full prompt below, paste it into any AI model along with your source files, and get organized .bru files back.

What it does: Finds every HTTP call in your project (fetch, axios, GraphQL), extracts methods, URLs, headers, bodies, and generates a fully organized Bruno collection with environments, authentication, and documentation. Ready to drop into your repo and start testing.

How to use: Scroll down, copy everything inside the code block, paste it into the AI along with your source code.

You will need ssh access to your USG. I suggest running sudo su so you're the root user throughout

Installation

Download tailscale and put the files in /config/. Find the latest stable or unstable version for your USG's processor.

curl https://pkgs.tailscale.com/stable/tailscale_1.36.1_mips64.tgz | tar xvz -C /tmp
mv /tmp/tailscale_1.36.1_mips64 /config/tailscale

You will need ssh access to your USG. I suggest running sudo su so you're the root user throughout

Installation

Download tailscale and put the files in /config/. Find the latest stable or unstable version for your USG's processor.

curl https://pkgs.tailscale.com/stable/tailscale_1.36.1_mips64.tgz | tar xvz -C /tmp
mv /tmp/tailscale_1.36.1_mips64 /config/tailscale

Security Advisories / Bulletins / vendors Responses linked to Log4Shell (CVE-2021-44228)

Errors, typos, something to say ?

If you want to add a link, comment or send it to me
Feel free to report any mistake directly below in the comment or in DM on Twitter @SwitHak

Other great resources

Royce Williams list sorted by vendors responses Royce List
Very detailed list NCSC-NL
The list maintained by U.S. Cybersecurity and Infrastructure Security Agency: CISA List

Vagrant and VMWare Tech Preview 21H1 on Apple M1 Pro

UPDATE November 20, 2022: VMWare Fusion 13

VMWare Fusion 13 is now released. Read Vagrant and VMWare Fusion 13 Player on Apple M1 Pro for the latest.

Summary

This document summarizes notes taken while to make the VMWare Tech preview work on Apple M1 Pro, it originated

	# This is minimal demonstration on how to obtain text metadata and album art from Sendspin and display it using LVGL on an ESP32-S3 Box 3.
	# The track title is displayed below the cover art will scroll if too long for the screen.
	# Touching the screen pops up controls for 5 seconds where you can pause/resume and go to the previous/next track
	# Swiping left or right will go to a different page. It should show a picture of the artist (but there are some bugs on the MA side, so this doesn't work consistently)
	# The main page displays the track progress in m:ss format on the lower left and the track duration on the right in m:ss format.
	---
	substitutions:
	name: esp32-s3-box-3
	friendly_name: ESP32 S3 Box 3 Sendspin
	font_glyphsets: "GF_Latin_Core"

	alias: Add unique to-do
	mode: single
	icon: mdi:clipboard-list
	sequence:
	- service: todo.get_items
	target:
	entity_id: "{{ list }}"
	data:
	status: needs_action
	response_variable: mylistneedsaction

	sourceServer=https://...
	sourceRepo=
	sourceUser=
	sourcePassword=
	targetRepositoryUrl=https://maven.pkg.github.com/[owner]/[repository]
	targetRepositoryId=

	filters=() # Grab only the packages specificed in the filter or leave the variable blank to grab everything
	logfile=$sourceRepo-backup.log
	outputFile=$sourceRepo-artifacts.txt

	import io
	import pathlib

	import pycdlib

	ubuntu = pathlib.Path('ubuntu-22.04.1-live-server-amd64.iso')
	new_iso_path = pathlib.Path('ubuntu-22.04.1-live-server-amd64-auto.iso')

	iso = pycdlib.PyCdlib()
	iso.open(ubuntu)