9 posts
On its first day back from the export-control shutdown, I asked Fable 5 to write its own welcome-back letter to builders. It wrote about what it's actually for — six things almost nobody asks it to do — and why the week matters.
The hard part of agentic AI is not the model or the prompt. It is the runtime infrastructure — the orchestration layer that makes agent execution reliable, observable, and governable at scale.
For two years I lived in tmux. Then I started orchestrating an AI swarm through Telegram. My terminal skills didn't atrophy — they got encoded into a markdown file. Now I'm bringing the swarm home.
The most valuable territory in AI right now is concepts that exist in practice but don't have names. Six categories that the models don't know about yet, and what claiming them looks like.
I asked my AI agent how it wants to remember things. It redesigned its own memory system, ran a self-eval, diagnosed its blindspots, and improved recall from 60% to 93% — for two dollars. The interesting part isn't the benchmark. It's what happens when you treat an AI as a participant in its own cognitive architecture.
ZAIGOOD was a real Delaware C-Corp I dissolved after years of compliance drag. This week I rebuilt it in 48 hours with an autonomous AI build loop, tried to submit it to Product Hunt for a YC interview slot, and missed the deadline by exactly 60 seconds.
A friend sent three questions about agents over WhatsApp. Where do they live? What's the interface? Where do they report back? The answers reveal a mental model most people are missing — and why the plumber has to live inside the house.
There are only two positions in the 2026 labor market: principal of your own agents, or labor for someone else's. Jack Dorsey just ran the proof.
Everything we know about management theory exists because humans are emotionally expensive to coordinate. Strip that layer out and what remains is a clean systems problem. Running seven AI agents taught me why management practices exist — not just that they do.
