Recent
Latest posts and articles.
love your llm, don't abuse your llm
CI/CD has been solved. Not perfectly, but well enough. You push code, tests run, artifacts build, things deploy. The pipeline is boring and that’s the point. Boring infrastructure ships product. …
Agents versus agents
There’s a naming collision at the center of the AI conversation right now. Everyone is building “agents.” No one agrees on what that means.
So let me make a distinction the industry …
fortran's wager
Pascal built the Pascaline in 1642 — one of the first mechanical calculators. Gears, dials, carry mechanisms. He spent years trying to offload arithmetic from human minds into metal. A programming …
Dawkins's Biggest Mistake: Giving Genes a Mind
Richard Dawkins is one of the clearest scientific communicators alive. The Selfish Gene (1976) is a genuine landmark — it took the gene-centric view of evolution and made it unforgettable. That is the …
Tradpute
Most of what we’re calling “AI” at the product layer is just traditional computing in a trenchcoat.
I’ve been using a word for this: tradpute. Traditional computing. CPUs, …
The Hard Part Isn't the Tool
I set up OpenClaw in forty minutes. Gateway running, Discord connected, models hooked up, skills installed. It worked first try. Good docs, clean implementation, zero drama.
Then I opened SOUL.md — …
slashface
Slashface, V3R. Joshua Tree. Probably 2014 or so.
This is a highball. You fall, you break something. No rope, no pad that matters at that height. Just you and the rock and the decision to keep going. …
dogs are analog AI
super mega giga ultra productive
multi-tabling
Riley Brown said something that caught my attention:
“AI Agent Workflows in 2026 will look like Online Poker in 2010. During the online poker boom, really good players started multi-tabling — …