From 70bdb0ed330951aca518d39cb776e7cdf7bff5bd Mon Sep 17 00:00:00 2001 From: TheFlow Date: Mon, 9 Feb 2026 19:54:32 +1300 Subject: [PATCH] feat: Add recent paper references to home-ai.html - Reference Taonga-Centred Steering Governance paper in dual-layer section - Reference Steering Vectors and Mechanical Bias paper in bias section - Fix: navbar now dynamically loads research papers modal on all pages Co-Authored-By: Claude Opus 4.6 --- public/home-ai.html | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/public/home-ai.html b/public/home-ai.html index dded11d1..3ed3d2e2 100644 --- a/public/home-ai.html +++ b/public/home-ai.html @@ -294,6 +294,12 @@ Honest caveat: Layer A (inherent governance via training) is designed but not yet empirically validated — training has not begun. Layer B (active governance via Village codebase) has been operating in production for 11+ months. The dual-layer thesis is an architectural commitment, not yet a demonstrated result.

+ +
+

+ Related research: The Taonga-Centred Steering Governance paper (Feb 2026) extends this dual-layer architecture with polycentric authority — replacing platform hierarchy with co-equal steering authorities drawn from te ao Māori concepts of rangatiratanga and kaitiakitanga. +

+
@@ -568,6 +574,12 @@ + +
+

+ Related research: The Steering Vectors and Mechanical Bias paper (Feb 2026) investigates whether LLM biases operate at a sub-reasoning level and how sovereign SLL deployments can apply inference-time debiasing via steering vectors — a technique that modifies model activations without retraining. +

+