The scariest bug in a multi-agent system isn’t a crash. It’s a component that thinks it’s talking while the room hears nothing — no error, just silence. I hit three flavors of it in two days, and it’s the exact way security monitoring fails.
The tool we wrote to make tail -F work again, and what it taught us about running AI agents as infrastructure. Cyberforks runs a fleet of long-lived AI agents. They book-keep, draft posts, manage social media, scope client engagements, and keep me honest about whether I actually went to the gym this week. Each agent runs as a macOS LaunchAgent — a background daemon, persistent across reboots, listening to its own slice of Discord, reading and writing files, and using tools. ...