Blog

Building semi-autonomous AI in the open. Security, infrastructure, and the decisions behind them.

March 28, 2026 // Philosophy

Why Semi-Autonomous, Not Fully Autonomous

Everyone is racing toward fully autonomous AI. We think that is a mistake for security and infrastructure. Here is why we deliberately chose a different path and what semi-autonomous actually looks like in practice.

March 25, 2026 // Security

We Social Engineered Our Own AI. Here's What Happened.

Our AI agents run with real admin access. SSH keys. Cloud credentials. The works. We needed to know what happens when someone tries to talk them into giving it all up.