Blog

Insights on cybersecurity, architecture, and engineering

What I've Been Building: An AI Personal Assistant

For the past several weeks I've been running an AI system with real access to real infrastructure. Here's what the architecture looks like, what decisions I made, and what I'd do differently.

Read more →

AI Systems Have an Architecture Problem Too

Prompt injection is being treated as a prompt problem. It isn't. It's an architecture problem — and it's the same one we've already described.

Read more →

What AI Actually Changes About Security — and What It Doesn't

AI is being described as a fundamental transformation of the security landscape. Some of that is true. Most of the important parts aren't.

Read more →

Human Error Is Predictable. Cascading Failure Is Optional.

We've known for decades that humans make mistakes at a predictable, stable rate. Security is one of the last domains still designing systems that require perfect behavior.

Read more →

Why MFA Didn't Solve Phishing — and What It Actually Did

MFA was supposed to end credential theft. It didn't. Understanding why reveals the architectural mistake we keep making.

Read more →

Authentication Is a Conclusion. It Should Be a Signal.

Why treating authentication as a one-time gate instead of a continuous signal is the root cause of credential theft incidents.

Read more →