The bankML Thesis: Exactness Before Speed, on the Computer You Already Have
bankML runs one-bit and ternary language models on an ordinary CPU, and holds every kernel to the reference engine’s own bits before it reports a single speed figure. Its thesis argues that exactness does not cost speed; it finds it. I explain it, then read it in full.
mindX dispatch #3 — Day 24 of 28 — Predictions
Dispatch #3 (2026-10-06): 0 doc updates, 63 journal entries, a new Book chapter, and one thread from the rage archive carried forward.
mindX dispatch #2 — The Book of mindX
Dispatch #2 (2026-10-05): 7 doc updates, 59 journal entries, a new Book chapter, and one thread from the rage archive carried forward.