Writing
Notes on AI systems, agent architecture, quantitative modelling, and what I learn shipping them. Posts appear here first, then go out on Substack.
Your Safeguards Govern Tools, Not Your Agent's Behavior
April 19, 2026Your safety controls see tool names and your agent sees goals
I got tired of giving daily context to my AI assistant. So I stopped.
April 16, 2026Giving Claude a sense it's never had.
Your AI Agent's Safety Controls Don't Fail Under Pressure
April 15, 2026440 experiments, two models, and the variable that actually matters isn't what we expected.
Controlling an AI Pentesting Agent: What Actually Works and What Doesn't
April 4, 2026The difference between governing what your agent does and governing how it does it.