Tommy Williams wommy

The Prompt DNA of Mario Zechner

A Psychological Analysis of Human-AI Coding Interaction

How does an expert software developer actually talk to an AI coding agent? We analyzed 2,796 prompts across 626 sessions from @badlogic's publicly shared pi-mono transcripts. The answer is: like a startup founder talking to a senior dev who keeps overstepping.

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.

The Von Neumann Dark Factory

A Mental Model for Autonomous Software Manufacturing

Mapping self-replicating systems from fiction to your factory architecture.

The Source Material

~~PS2 Bios Download for PCSX2 & AetherSX2 Emulators | For All Regions~~

PS2 Bios Download (OFFICIAL) for PCSX2 & AetherSX2 Emulators

Download PS1 BIOS Files (USA, Japan, Europe, China) All Regions

--

~~scph5500.bin 26-Aug-2018 20:47 512.0K~~

Wordpress & Docker

This file will setup Wordpress, MySQL & PHPMyAdmin with a single command. Add the code below to a file called "docker-compose.yaml" and run the command

$ docker-compose up -d

# To Tear Down
$ docker-compose down --volumes

Semantic Commit Messages

See how a minor change to your commit message style can make you a better programmer.

Format: <type>(<scope>): <subject>

<scope> is optional

	# Virtual memory settings.
	# Kernel documentation: https://docs.kernel.org/admin-guide/sysctl/vm.html.
	# Arch zram: https://wiki.archlinux.org/title/zram#Optimizing_swap_on_zram.
	# Gaming tuning: https://pastebin.com/fwzW9whL.
	# PopOS tuning: https://github.com/pop-os/default-settings/pull/163.
	# MaxPerformanceWizard (MPW) https://gitlab.com/cscs/maxperfwiz/-/blob/master/maxperfwiz.

	boot.kernel.sysctl = {
	# Tunes how aggressively kernel evicts memory pages until a specific amount of free memory is left for your active working set
	## Sweet spot for gaming is 125-200, near 200 makes kswapd swap too aggressive

	#!/bin/bash

	# simple script to 'start' nvmet on TrueNAS SCALE
	#
	# to reinstall nvmetcli simply rm /usr/sbin/nvmetcli

	# debug
	#set -x

	# exit non-zero

	#!/usr/bin/env bash

	# import an MS SQL .bak backup file to an MS SQL database, then export all
	# tables to csv. run this script as `import.sh <filename>`. It expects to be
	# run in the same directory as the backup file.

	# this is only tested on my mac (OS X Catalina). I tried to stick to posix, but
	# It will probably require some tweaking for you. I hope it gives a general
	# sense of what you need to do at the very least.