2026-10-04 · latest
We assumed AI would do the thinking for us. Instead, it acts as a ruthless mirror. By stripping away the buffer of human intuition and social grace, your ability to direct an agent becomes a mathematically pure reflection of your ability to think.
agents · leadership · philosophy · orchestration
2026-09-30
When to delegate coding work from a scarce premium model to cheaper ones — and when not to. A multi-file benchmark where hierarchical orchestration matched solo pass rate, burned similar premium tokens, and was ~2.8× slower.
agents · orchestration · llm · benchmarks · workflows
2026-07-14
A Scarthgap image line with custom meta-parhelion, staged WIC artifacts, and an OS-vs-app release split. Build and final-WIC hardware checks are documented. End-to-end flight app smoke is still deferred.
linux · yocto · embedded · raspberry-pi · operations · systemd · rocketry
2026-04-08
The full technical account of building a distributed local voice assistant: system split, speech pipeline, PostgreSQL memory, and what a formal benchmark campaign measured.
llm · voice · docker · postgres · self-hosting · thesis · benchmarks