Posts

I’ve been running Claude Code heavily for the past few months — and at some point I started wondering: what exactly is it doing all day? Not out of distrust. More out of curiosity and professional habit. When you deploy any autonomous system, you want visibility into what it’s doing — what commands it ran, what files it touched, whether it made any outbound network calls. For AI agents, that visibility is almost entirely missing. ...

I had the honor of giving an invited guest lecture at Columbia University, hosted by Prof. Xiaofan (Fred) Jiang, on the topic of “Securing AI Agents.” Why AI Agent Security Matters Autonomous agents like OpenClaw have the potential to transform daily work — automating complex, multi-step tasks that previously required human judgment at every turn. But with that power comes a critical question: how do we ensure it’s safe to deploy them? What We Covered The lecture walked through the full threat landscape and defense stack for agentic AI systems: ...

Welcome to my blog. This is the first post.