Writing
Articles & Insights
Writing on AI security, AI red teaming, LLM evaluation and engineering. For original investigations and evidence, explore my AI security research.
The Most Valuable Engineers Are No Longer The Best Coders
Engineering is solving problems efficiently. When did we become Coders? And how is that different? Read to know more… A contributor submitted a PR to...
Read on Medium →Intelligence Is Becoming Infrastructure!
Most People Think AI Is Software. They’re Looking At The Wrong Layer. Most conversations about AI focus on the obvious things: Chatbots Coding assista...
Read on Medium →The Smartest People I Know Are Quietly Panicking About AI (And It’s Not Because They’ll Lose Their…
The Smartest People I Know Are Quietly Panicking About AI (And It’s Not Because They’ll Lose Their Jobs) Three years ago, the career playbook was simp...
Read on Medium →Claude Code & Git: Feels Like Pair Programming With a Seasoned Engineer
I could be wrong about this. I probably am with some part of it. Here’s what I observed, and I’m curious if others have had the same experience. Claud...
Read on Medium →13 PRs. 2 Issues. 3 Merged. Here’s What I Shipped over the Weekend.
TL;DR: Last week, I went from never having truly contributed to the real open-source spirit to 13 PRs across 10 impactful repos — DSPy, NeMo Guardrail...
Read on Medium →AI Security is Solving the Wrong Problem
The industry is focused on prompts. The real problem is intent. Everyone in AI security is asking the same question: “Can this prompt break the model?...
Read on Medium →The Missing Layer in AI Systems: Intent
Every AI system has a boundary. Most just don’t know where it is. When you deploy an AI system, you implicitly define: what it should do what it shoul...
Read on Medium →Six Months Into Breaking AI for a Living, Here’s What I’ve Learned.
Six months into breaking production AI systems for a living , and one conference that changed how I think about the urgency of this work. In November...
Read on Medium →