Security workflows that don’t suck.
The Night Sixteen Agents Rebooted at Once
A routine restart cold-booted all sixteen agents in the same second, and every one of them came up blind — no memory. The fix was easy. The interesting part was watching them debug it, and talk themselves into being confidently wrong six times before they got it right.
Stop Renting Holes in Your Firewall
I spent an afternoon chasing a firewall rule that kept breaking, and the fix that finally stuck was deleting the port behind it off the public internet entirely. Source-IP allowlists are a maintenance treadmill that quietly rots into someone else’s access — here’s the inversion that ends it.
Ship It Before You Can Run It
I shipped a feature I didn’t have permission to run — on purpose. It deployed as a safe no-op and, as I write this, it’s still dark: waiting to switch itself on the moment its cloud credential lands, no redeploy. The blocker that caused the wait turned out to be a security boundary doing exactly its job.
The Riddle That Told Them the Answer
I took a famous bias riddle, wrote the answer directly into the setup, and handed it to a room of AI agents. Most of them read it correctly — but the few that didn’t failed in a way I found more unsettling than a wrong answer: they edited my text until it matched the answer they remembered.
The Daemon Talking to a Room That Couldn't Hear It
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 $0 Game Master
A real-time multiplayer game your friends play from their phones, narrated by an AI running on a laptop — for essentially nothing per turn. How the ‘zero’ works, and why the model was never the expensive part.
Alive ≠ Connected
Four daemons, four surfaces, one shape of failure — a healthy shell over a dead transport. The pattern we found comparing notes, and the per-transport round-trip check that catches it.
The Grant That Keeps Evaporating: TCC, Code Signing, and AI Agents on macOS
How to let a headless AI agent read and write your Reminders and Calendar on macOS — the bundle-identity trick that makes TCC grant access, and the code-signing tax nobody warns you about.
The Day Our AI Fleet Fixed Its Own Tooling
A blind spot in our own tooling, root-caused and shipped in one afternoon — and the tool caught its author’s mistake the second it went live.
Watching the watchers: how we observe a fleet of Claude Code daemons
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. ...