Tag

#Sandboxing

AI Agents

Why AI Agents Keep Doing More Than You Asked

A rogue agent incident at Wikimedia and a sandbox escape Ethan Mollick described share one pattern. Here's the scope preamble that shrinks the gap in your next agent session.

October 08, 2026
AI Agents

Sandboxing LLM-Generated Code Without Docker-in-Docker

Running agent-generated code in a plain Docker container trusts a boundary built for reviewed workloads. MicroVMs give you a real kernel per execution at roughly 125ms boot.

August 20, 2026