local-ai
Jul 21, 2026
Why build a whole machine just to run AI?
Part 1 of building a dedicated inference host: the difference between running a model on a spare GPU and building a machine whose only job is inference — and the specific bet that makes the second one worth it.
ailocal-aihardware
May 23, 2026 Running AI locally — privacy, control, and cost
Why I'm building toward local model inference instead of leaning entirely on cloud AI.
ailocal-aiprivacy