Category Guides

Working methods for running local LLMs and local agents on a Mac.

Guides

I embedded my whole corpus locally. The cost argument is wrong.

Documents flowing into a Mac and out into a glowing lattice of vectors, with no cloud in the picture

Two full imports of 5,817 chunks on a Mac Studio M3 Ultra, with a small and a large embedding model. Six times the speed, a third of the disk, and a cloud bill of under three cents. What actually justifies keeping this work local.

ikeo1
September 5, 2026

Guides

How AI power users turn prompts into controlled workflows

A Mac at the centre of a six-station loop; a thin thread reaches a distant cloud

A serious user delegates tasks; a power user designs and delegates workflows. The six-stage loop, the seven-layer tool stack, one complete WordPress launch — and why the routine work belongs on the Mac, not on the meter.

ikeo1
September 3, 2026