Blog
Thoughts on software, tools, and building things that work.
-
LLMs Are Practically ADHD
ADHD and large language models share the same structural failure modes — context loss, confabulation, drift without governance. The solutions for one transfer directly to the other.
-
Your Reminders Don't Work Because They're Too Predictable
Traditional reminder apps fail ADHD brains because predictability breeds dismissal. I built a Telegram bot with fuzzy scheduling, natural language parsing, and a nag mode that won't shut up until you respond.
-
Your AI Builds the Code. Who Reviews It?
If the same AI agent that writes your code also reviews it, you have someone grading their own homework. I built an adversarial code review agent to fix that.
-
Auto-Compaction Is Costing You Sessions
Claude Code auto-compacts at ~83% context usage. You lose the chance to control what's preserved. I built a script that warns you before it happens.
-
What Is Pass@1?
Pass@1 isn't 'AI writes code fast.' It's a development methodology where governance documents are thorough enough that the AI generates correct implementations on the first attempt. Speed is a byproduct. Governance is the product.