CKSM: a foundation model architecture derived from neuroscience

Deterministic, constant memory, continuous learning. Building the alternative to transformers

MTCP The Independent Assurance Layer for Enterprise AI Control

Empirical measurement infrastructure proving whether AI systems hold their constraints under real operating conditions.

Research on Explainable AI Prototypes -- Mandelbrot AI

EPMORE -- Explainable Process Mixture-of-Experts -- performs the role of increasing feature capacity and feature disentanglement.

AI Safety Atlas: a searchable directory of everyone in AI safety

A fast, comprehensive directory of the people and orgs in AI safety: search, filter, and match.

Delegated AI Payment Safety

Benchmark for agent safety when spending users money. How often do they violate user intent and rules?

ICML Workshop Travel: Cross-Constitution Drift in LLM Character Training

Accepted ICML 2026 workshop paper on cross-constitution drift in LLMs; seeking $2,050 travel support to present in Seoul and gather research feedback.

LEX-Aureon: Mathematical Constitutional Governance Layer for Robust LLM Safety

A production-ready mathematical governance layer (C+R+S simplex, Control Barrier Functions, Lyapunov stability) that enforces Continuity, Reciprocity & Sovereig

Stress-testing alignment auditing methods of AuditBench

Assistant Axis Detection of Persona Drift in Conditionally Misaligned Models

Assessing whether Persona drift be detected in conditionally misaligned models using the assistant axis and potentially analyzing the reasons for failure

MartinLoop: Control Layer for AI Coding Agents

Open-source safety infrastructure for budget caps, verification, rollback, and audit trails in autonomous coding agents.

CIRIS: open-source accountability infrastructure for autonomous AI

Cryptographic attestation, runtime conscience, and an unfilterable kill switch. Live on the App Store and Google Play in 29 languages. AGPL, mission-locked

Dynamic Constraint Boundary (DCB): From Theory to Simulation

Building the technical foundations needed to formalize and computationally explore adaptive constraints.

LLMMatrix: Synthetic World Benchmark for Contamination Free LLM Forcasting

A contamination-free benchmark for measuring whether LLMs can forecast, or whether they're just remembering.

Open local AI memory + a safety benchmark for persistent-memory agents

Productionizing Mnemosyne, a local inspectable memory layer for LLM agents, plus an open benchmark for how memory and autonomy change AI-agent safety.

Φ-Arena and adversarial multi-agent VLA interpretability

Independent collective. Φ-Arena open benchmark, 3 ICLR 2027 papers (Φ-Arena, mechinterp, energy-bounded) — kickstart for a 10-year program.

VERITAS: Verifiable Accountability For Autonomous AI Agents

Cryptographically signed, independently verifiable receipts for what AI agents actually did, anchored to Bitcoin so the record can't be quietly rewritten.

ANI: AI That Remembers You (Without Lying or Getting Addictive)

After 10 months running as my daily companion, this persistent AI is exposing failure modes in memory contamination, confabulation, and emotional drift.

When AI Meets Faith: Microgrants for Better Evaluation

Funding AI credits and expert review for faith-facing AI evaluation projects

Model Drift Monitoring Tool - Prototype Development Support

Seeking support to build a prototype AI model drift monitoring platform and validate it with investors and early adopters.

MATS 10.0 Neel Subliminal Learning