Blog
Notes from the network.
Engineering posts, capacity reports, pricing notes. We publish here when we have something to say — one a month at most, no apologies.
May 15, 2026
7 min
What $0.02 per million embeddings actually costs to run
Unit economics of running embedding inference on idle consumer Apple Silicon.
Read →
May 14, 2026
8 min
How we sign and audit every task
The trust model behind running customer code on someone else's Mac.
Read →
May 13, 2026
6 min
Why we run on idle Macs, not data centers
The economics of consumer Apple Silicon are weird in a useful way.
Read →