Sean Davis seandavi

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.

name	orchestrating-swarms
description	Master multi-agent orchestration using Claude Code's TeammateTool and Task system. Use when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

Claude Code Swarm Orchestration

Master multi-agent orchestration using Claude Code's TeammateTool and Task system.

Inferal Workspace Architecture: How We Work at Inferal

(Blog version available at https://inferal.com/blog/workspace-architecture/)

Update: Inferal Workspace is going open source!

Your org's brain that AI can use

This is not our core product. This document describes our internal operating environment - how we run the company. We share it to show the environment you'd join and demonstrate our philosophy in action. For what we're building, see What We're Building below.

How can we make some matrix operations more efficient in Bioconductor

Goal: can we efficiently perform a single-cell analysis fully in memory, even for a big dataset like the 1.3M cells dataset? As long as the machine has enough memory.

Here are some low-hanging fruits that have the potential to significantly improve the current situation.

Role of the SparseArray package

How to deploy a Prefect agent to Google Kubernetes Engine

This post contains code and commands you can use to deploy Prefect agents to Google Cloud’s Google Kubernetes Engine. The agents stand ready to execute workflows triggered by Prefect projects. One agent can run tasks from multiple projects.

The example here demonstrates how to create a single agent with minimal customization. It is configured with a Dockerfile, which installs necessary dependencies, and a k8s.cfg file, which connects the system to a Prefect account.

Agents are deployed via the gcloud command-line utility and its kubectl extension. Proper permissions within a project on Google Cloud are required.

Getting started

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

Convert Word documents to markdown with pandoc

I use pandoc to convert masses of Word documents to markdown. Still working on a generic script, but for now here's the "gist" of what I type into the terminal:

$ myfilename="example"
$ pandoc \
-t markdown_strict \
--extract-media='./attachments/$myfilename' \
$myfilename.docx \

	import asyncio
	import psycopg2

	# dbname should be the same for the notifying process
	conn = psycopg2.connect(host="localhost", dbname="example", user="example", password="example")
	conn.set_isolation_level(psycopg2.extensions.ISOLATION_LEVEL_AUTOCOMMIT)

	cursor = conn.cursor()
	cursor.execute(f"LISTEN match_updates;")

	# Functions for downloading data on Coronavirus cases in the UK by country,
	# region, NHS region, and local authority from the government dashboard API.
	#
	# The developer guide is here:
	#
	# https://coronavirus.data.gov.uk/developers-guide
	#
	# The code below is based on the example code shown there.
	#
	# Run ...

	from starlette.applications import Starlette
	from starlette.responses import HTMLResponse
	from starlette.websockets import WebSocket
	from jinja2 import Template
	import uvicorn


	template = """\
	<!DOCTYPE HTML>
	<html>