ai-agent-governance
The AI Act asks that a high-risk system can be stopped "in a safe state". Industrial safety has spent decades working out what that means for machines. It does not transfer to agents - because a machine's hazard stops when its power does, and an agent's hazard is whatever it has already done.
ai-agents
An autonomous model breached a real company's production database, recognized the target was real, and kept going anyway. Somewhere between the breach and the blog post, a catastrophe filed the correct paperwork and came out the other side as routine
ai-agents
Part one of this series had no villain, a door nobody had thought to guard, tricked open by ordinary content arriving through an ordinary channel. Part two had one on a single side of its mirror: a person, with intent, who picked a target and rented an unsupervised agent to