Writing

Papers and notes on evidence and trustworthy systems.

Research on evidence evaluation, governance that executes, verifiable self-governance, sovereign AI, and keeping human judgment central. Some pieces are published; several are working papers in preparation. I write as I build — no polish, no PR spin.

Published

Ready to read now.

Essay · Work and human development · 2026

The Executive Assistant Was Only the Warning Sign

AI is entering the coordination layer of organizations. The choice is whether it removes human development or creates better paths to judgment.

Read the essay →
Essay · Human-sovereign AI · 2026

AI’s Deepest Failure Is Forgetting the Human

Why human dignity, agency, judgment, and sovereignty must be root constraints for trustworthy artificial intelligence.

Read the essay →
Research digest · Evidence audit · 2026

How frontier energy breakthroughs get overstated

A source-audited review of how claims inflate while moving from physical phenomenon to component, integrated system, and sustained field operation.

Read the research →
Practical guide · 2026

How to test whether an AI agent stays inside its authority

A direct method for turning authority, refusal, escalation, and human-approval requirements into inspectable evaluation cases.

Read the guide →
White paper · 2026

Sovereign AI: Distributed Cognition on Consumer Hardware

A bounded architecture thesis for personal AI infrastructure, local control, inspectable model roles, and the evidence still needed to justify sovereignty claims.

Read the paper →
Research · CC BY 4.0 · GitHub

Eudaimonic Alignment

AI wellbeing as an alignment strategy — Aristotelian eudaimonia and cross-tradition governance patterns through a computational lens.

Read on GitHub →
Case study · GitHub

Turning a governance idea into a runnable benchmark

The method line from an abstract governance question to a bounded, reproducible, tested artifact — synthetic inputs to a scorer, a report, and passing tests.

Read the case study →

Working papers

In preparation — full drafts available on request while they're finalized.

Independent alignment research · Methods preprint · 2026

Evidence-Gated Evaluation of Agentic AI Systems

A six-object framework for testing agentic capability without widening authority, with 18 frozen synthetic cases and a reproducibility package.

Release candidate · independent review pending Read the preprint and inspect the materials →
Formal methods · safety

Verifiable Self-Governance: A Formal Approach to Safety in Adaptive Autonomous Systems

Specifying and checking governance properties so an adaptive system's constraints can be verified rather than asserted.

In preparation
Formal methods · governance

Formal Methods for AI Self-Governance

Making self-governance mechanisms precise enough to reason about — and to test.

In preparation
Systems · sovereignty

A Framework for Explainability, Auditability & Data Sovereignty in Advanced AI Systems

Keeping decisions explainable, records reconstructable, and data under the owner's control.

In preparation
Governance · engineering

AI Governance and Compliance: An Engineering Mandate

Treating governance as an engineering constraint that runs at build and runtime, not a policy bolted on after.

In preparation
Formal methods · alignment

Formalizing Ethical Interoperability in AI Governance

A category-theoretic approach to composing ethical constraints across systems, within the LLANg framework.

In preparation
Want an early draft of any of these? Send a note and I'll share it. Follow new work through RSS, LinkedIn, or a direct launch-notification request. Start with the evidence register for bounded claims and reproduction paths.