john/tractatus
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat: Add recent paper references to home-ai.html

Browse source 
- 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 <noreply@anthropic.com>
This commit is contained in:
TheFlow 2026-02-09 19:54:32 +13:00
parent 90376f9089
commit 70bdb0ed33
1 changed files with 12 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
public/home-ai.html
View file

@ -294,6 +294,12 @@
<strong>Honest caveat:</strong> Layer A (inherent governance via training) is designed but not yet empirically validated &mdash; 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.
</p>
</div>
<div class="bg-white rounded-lg shadow-sm p-5 border border-gray-200 mt-4">
<p class="text-gray-700 text-sm">
<strong>Related research:</strong> The <a href="/docs-viewer.html?slug=taonga-centred-steering-governance-polycentric-authority-for-sovereign-small-language-models" class="text-blue-600 hover:underline">Taonga-Centred Steering Governance</a> paper (Feb 2026) extends this dual-layer architecture with polycentric authority &mdash; replacing platform hierarchy with co-equal steering authorities drawn from te ao M&#257;ori concepts of rangatiratanga and kaitiakitanga.
</p>
</div>
</section>
<!-- Philosophical Foundations -->
@ -568,6 +574,12 @@
</div>
</div>
</div>
<div class="bg-white rounded-lg shadow-sm p-5 border border-gray-200 mt-4">
<p class="text-gray-700 text-sm">
<strong>Related research:</strong> The <a href="/docs-viewer.html?slug=steering-vectors-mechanical-bias-sovereign-ai" class="text-blue-600 hover:underline">Steering Vectors and Mechanical Bias</a> 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 &mdash; a technique that modifies model activations without retraining.
</p>
</div>
</section>
<!-- What's Live Today -->