Latest Posts

With AI, I can work on four or five projects at once. The limit is no longer what I can build. It's my own brain, and how much of what I do I actually mean.

Running Mac Virtual Display and ALVR on an Apple Vision Pro at the same time made ALVR stutter. The fix: put the router on a non-DFS 80 MHz block with its primary channel on AWDL's social channel (44 in the UK), so the Apple devices stop hopping between the router's channel and AWDL's.

I use the same coding agents in two opposite ways: fast and furious, where I barely read the code and have made 10,000+ commits in the last 12 months, vs. slow and careful, where every decision is mine. Neither is right. The real decision is where to set the quality bar for each project, right now, and when to move it.

I got a good deal on a Codex plan and wanted to try its models inside Claude Code. A local proxy and six small fish functions later, `claude-astra` starts Claude Code on GPT-6-Astra. Here's how it's wired, how the agents built it, and what's still missing.

The main agent, secondary and worker setup I pieced together by hand is now built into tmux-agents. One command starts the chain, a script starts one for every project after a reboot, and /resume brings back the conversations.

Move fast with AI, and add proper engineering when real usage shows you need it. For tmux-agents, that meant letting each agent's name double as its id, until it couldn't, and then adding real ids and guard rails so the agents and I don't repeat the mistake.

Built-in sub-agents hand you a summary and the work behind it is gone. tmux-agents gives every delegated task its own Claude or Codex session in a tmux pane instead, so you can watch it, step in, and pick its conversation up later.

With up to ten agents working on one project, the Claude agent I talked to was also juggling replies, merges and servers, and I kept waiting for my turn. The fix was one more pane: a main agent whose only job is to talk to me, while the old one became a coordinator.

Claude, Codex and their sub-agents each got their own git worktree, and my disk quietly filled up with copies of an 8GB game project. The fix was a small script that makes agents borrow worktrees from a shared pool instead of creating new ones.

Moving a resume pipeline onto Maestri, teaching it to enforce its own two-page limit, and trying local dictation apps all removed the same thing: the mechanical tax between having an idea and acting on it.