Answers are grounded in this paper and cite their sources.
Monograph explores Williams Deviation Equation dynamics in computational architecture, suggesting new research applications.
This monograph was put together by Matthew Carlo, who took the original idea, built the maths around it, expanded the architecture, and turned it into a full working framework. All the formalisation, derivations, system design, and the big technical lift — that’s my part of the project. But the heart of the whole thing — the actual core law — is the Williams Deviation Equation: \[D(t) = minₖ \, dist\!( Tfeat(t),\, λ_k )\] That equation wasn’t mine. That spark came from Jonathan Williams, who spotted the key insight long before the rest of this machinery existed: that subconscious threat detection is really just deviation from a learned safe‑state. My job here was basically to take his idea, run with it, and build the full mathematical and computational world around it. His equation is the centrepiece; this monograph is the scaffolding built around that centre. This whole write‑up exists to honour that original insight, give it a proper home, and make it something researchers — and machines — can actually use. A small nod to Aaliyah — for that quiet try again spirit that keeps a slow village night turning into something worth finishing.
No takes yet. Share an insight, caveat, or question.
Carlo et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: