Teaching My AI Coding Assistants to Stop Repeating Mistakes
One instructions file shared by every assistant, a corrections log that turns repeated feedback into rules, and hooks for the rules that keep getting broken.
Write-ups of side projects, tools I've built, and things I've learned along the way.
One instructions file shared by every assistant, a corrections log that turns repeated feedback into rules, and hooks for the rules that keep getting broken.
How I designed a hands-on, 150-minute workshop that teaches students to give an AI agent context and guardrails, and what a dry run taught me about hooks.
A small bash script plus a systemd service and timer that keeps my Arch + KDE machine up to date, and what I'd change about it now.

Bitboards, magic bitboards, and a 24-bit move encoding in my C++ chess engine, plus the two silent bugs I found when I came back to it 18 months later.
