I build software, follow questions, and write about what I find. Systems, AI, design, and the occasional loose thread.
A time converted to another pool should come back to where it started. I fit three course maps on one shared scale and tested them on swimmers who raced both pools within a month.
Read the essay: What Eight Million Swims Say About the WallSameness comes from two places: training narrows what a model will produce, and a review loop narrows what survives. I've built something against both and don't yet know if either holds.
Most of the new advice on running coding agents validates an older idea: constraints do the work. At multi-agent scale, the constraint that matters most is who holds which decision rights.
I stopped prompting coding agents and started designing the loops that prompt them. The loops nest, tight inside medium inside long, each with its own primitives and share of human involvement.
Everyone wants to be the source of truth; almost nobody builds the conditions that let truth survive. From the Delphic Oracle to Grokipedia, the failure is structural, whatever the intent.
Terence McKenna said time would end on December 21, 2012. The year felt ordinary. From here it looks like the year most of the present was planted, and I don't trust that feeling.
AI can already clean-room rebuild commercial software. The useful question is how fast each kind of moat decays, and which ones regenerate faster than they erode.
Software engineering compensation was built on scarcity, not just difficulty. That scarcity is eroding. The people who survive are either unusually broad or unusually deep.
bristanback.com/ · Bri Stanback
