Stop Picking Models. Start Building Harnesses.

Stop Picking Models. Start Building Harnesses.

Most companies are playing a game they don’t understand the rules to. They’re standing in a room full of competitors, all of them staring at the same two doors. One door says OpenAI. The other says Anthropic. They believe the strategic decision is which door to walk through. They believe this so deeply that they’re paying enormous premiums for inference that’s past the point of diminishing returns, and getting nothing their competitors aren’t also getting.

[Read more]

The Incidents Are the Training Data

A factory floor made of circuit traces and error budget gauges, with incident timelines running like conveyor belts through an AI flywheel. Ink and amber on parchment, controlled delirium.

There is a structural transformation happening in software operations. The output of production is increasingly training data, training data produces automation, and automation runs production. Site Reliability Engineering is one place this shift becomes visible in concrete terms. Not because SRE has the most data, but because SRE already solved a piece of the governance problem this new model depends on.

[Read more]

The Org Chart in a Box

Multiple hands reaching toward a shared blueprint from different directions, each holding a different tool (wrench, magnifying glass, shield, pen), rendered in gonzo ink illustration style on warm parchment

The Product Manager wanted to ship an MVP. Three phases. Skip the reproducible build. Skip the caching subsystem. Skip the Mermaid diagrams. Ship fast, iterate later.

The Debugger said that path would destroy maintainer trust.

“Non-Deterministic Bug Blindness,” the Debugger said. “Skip the reproduction baseline and the ‘fails on main’ gate? The agent writes a fix, runs the test, it passes, but it was passing BEFORE the fix too because the test is tautological. The trust curve is steep to climb and vertical to fall off.”

[Read more]