From Panel to Protocol
Eight compounds. Six months. Twenty-one weekly injections distributed across six active days. The locked-in elite biohacker protocol — fully instrumented, fully reversible, fully documented.
Two Models, One Branch
Two models on one branch. Claude writes the code and ships the PR; Codex reviews with fresh eyes. No agent framework, no MCP plumbing — just one CLI call from inside the editor. The simplest agent orchestration that actually works.
Bushidō
They called it 'the way of the warrior.' Most translations stop there. The code is older, stranger, and more useful than the name suggests.
Día del Niño: cuando los hijos piden disciplina
Ayer fue 25 de abril. En Colombia se celebra el Día del Niño el último sábado de abril. Para Miranda (11) y Maxi (9), una pregunta sencilla: — ¿Qué quieren hacer? Podemos ir a alguna playa de lujo en el Caribe, planear un paseo, lo que ustedes elijan. La respuesta me
Indie Hacking, Different Game
Indie hacking is back. Different game now. The old playbook still works — small surface-area products, charge from day one, kill fast, ship rough — but the math underneath has fundamentally changed. Build cost collapsed. Judgment cost stayed the same. The economics inverted. What used to take three months of nights and
El guerrero inmóvil: Sun Tzu, Marco Aurelio y la economía silenciosa del poder
Un ensayo sobre la asimetría entre el atacante que se dispersa y el defensor que se aquieta — leído a través de Sun Tzu, Fabio Máximo, los estoicos romanos y la teoría moderna de los juegos de desgaste.
GPT-5.5: The Frontier Just Split in Two
OpenAI shipped GPT-5.5 today — first ground-up retrain since GPT-4.5, double the token price, state-of-the-art on agentic benchmarks. Opus 4.7 still wins precision coding. What the numbers say, what practitioners are reporting, and how to pair it with Claude Code.
Panel Says Go. Time to Push.
26 of 27 markers back. Liver pristine. Insulin sensitive. GH axis running hot. The panel gave clearance. Now the harder question: how hard to push — and where's the line before pro-bodybuilder damage?
The Mythos Ritual
Anthropic built an AI that finds zero-days in every major OS. Day one of the announcement, a Discord room guessed its URL and walked in. The fear marketing writes itself. That's the point.
OpenAI's New Image Model Thinks Before It Draws
gpt-image-2 shipped yesterday. Native reasoning. 8 coherent images per request. Legible text at 2K. And somewhere in a dashboard, Nano Banana 2 just lost its Arena top spot by 242 points.
Baseline Drawn: One Clean Night, Blood on the Table
The prep week ran. One clean night rewrote my Oura numbers. Nine tubes of blood later, the baseline is locked. Results land in three waves over the next two weeks.
The Field That Schedules Your World
A hundred-hour descent into constraint programming. CP-SAT, a Kotlin DSL, MiniZinc, benchmarks against three engines, and a full nurse-scheduling application. Why the quietest branch of AI still runs the world.