Mostly self-taught developer. I’ve pushed two live projects so far (below). I love trying to improve my software and workflows, and documenting it when I’m able to do interesting things. Currently obsessed with AI systems, been an infosec nerd forever.
yeswekanban · live
yeswekanban helps people learn whatever skill or reach whatever goal through AI-powered, project-based learning. It also lets families run those projects as internship-style paid work. It started as a way for my dad to give me work, and grew into a product to help get this kind of learning into the hands of more people like myself.
Kinetik Break · playable
Kinetik Break started as a physics sandbox I made to test myself. Everything in the game, from enemies to projectiles, is a physics object you can grab and use with the character’s tools. It’s an early build, and I’ve got plans to add more characters, levels, enemies, and real art.
Writing
Original research and engineering writing from building yeswekanban.
Eight blind, controlled experiments on whether an AI agent's persona is load-bearing — and the discovery that a checklist can make it worse.
How a platform that puts minors, real money, and AI in one place keeps all three safe — from the big picture down to the mechanisms.
How I catch the bugs correctness reviews and security reviews each miss on their own. Two AI reviewers, strict scope, one judge.
Why the machinery around a capable AI model should be the most boring part of the system — the shared bet under four systems I built, and the one that failed.
Why a capable AI agent drifts into a mediocre generalist over a long session, and the deliberately simple system I use to summon a sharp identity back on demand.
What we built, exactly how it broke, and where the next person should start.
Contact
The best way to reach me is email. I read everything.