Split the Shot
Same testosterone, same weekly dose — just twice a week instead of once. You lose nothing. You trade one extra needle a week for a flatter curve.
The Agent Without a Face
There are two ways to use a coding agent: sit in its terminal, or take its face off and drive the engine from your own code. If you're building anything around agents, the second mode is the whole game — and it's full of traps nobody warns you about.
Amnesia as a Feature
Ralph is a five-line bash loop that forgets everything every iteration — and the amnesia is the whole point. It's also wrapped in more hype than almost anything in AI. Here's what's real, what isn't, and why Anthropic's official plugin gets it backwards.
Stop Babysitting the Babysitter
I built a gate that wouldn't let Claude fake “done.” It worked — and then I spent a month babysitting the gate. The native trio that replaces the whole rig was shipping the entire time, and the hard part was never the loop.
Off the Leash
/loop dies the moment you close your laptop, and I argued that leash was a safety feature. /schedule cuts it: your code keeps shipping on Anthropic's cloud while your machine sleeps — and the thing that made the loop safe is gone.
The Loop on a Leash
/loop re-runs a prompt on a timer, inside your session — Boris Cherny babysits his own PRs with it. The catch: it's the same conversation, so a forgotten loop can quietly run up a serious bill.
Define the Finish Line
Claude Code's /goal works across turns until a condition holds — judged by a second, blind model. The catch: it forces you to learn the one skill most engineers are bad at, naming a finish line a machine can actually check.
The Dashboard on Your Forehead
Your oily skin isn't a cosmetic problem. On TRT plus GH peptides, that shine is the cheapest, fastest readout that your androgen and growth-hormone axis just came online — and most people blot it away without ever reading it.
You Can't Authorize Autonomy
Autonomy isn't a permission you grant an agent — it's a property of the environment you engineer. A worked example: the two-layer verifier I own, the self-driving loop around it, the lessons from weeks of running it, and exactly how to run your own.
Multiplayer AI: What Claude Tag Actually Changes
Anthropic just put @Claude inside your Slack channels — one shared, persistent, agentic teammate per channel, billed to the org and learning the company over time. The genuinely new part isn't that Claude can read Slack. It's that AI just went multiplayer.
Better Than Ever: Seven Protocol Changes That Compounded
Seven changes over the last few weeks — carbs back, heavier iron, 4x creatine, daily cardio, double Retatrutide, fixed sleep, and real socializing again. Each helped on its own. Stacked, they compounded into a system that runs better than it ever has.
Ultracode Is Session-Only, and That Breaks Your settings.json
I wanted ultracode as my Claude Code default. I reached for "effortLevel": "ultracode" in settings.json — it silently did nothing. Here's what ultracode actually is, the only three ways to turn it on, and the config that actually sticks.