Compact operational charter that turns LLM coding agents into disciplined principal engineers. Eleven rules + one meta-rule.

Secure on device personal agents

Achieve Frontier AI performance in your CLI — fuse the local model CLIs you already run. Fan a prompt across a panel, a judge model compares the answers, a synthesizer writes one grounded reply instead of a majority vote. On a 100-task benchmark, every fusion panel beat its solo members.

Self-hosted control plane for AI agent teams. Push objectives at Claude Code or OpenAI Codex; capture every LLM call.

Model-agnostic inference engine for fine-grained Mixture-of-Experts LLMs on Apple Silicon — streams experts from NVMe so the model never has to fit in RAM (a 235B runs from 32 GB up). Designed with an AI agent across some sessions: the direction came from human curiosity, the implementation depth from the collaboration.

We show that CoT monitoring is fragile under linguistic distribution shift. Across 13 languages and 16 frontier models, adversarial hints expose a 95.9% deception rate. This repo contains the code and resources for reproducing our findings.

Governed AI abuse detection gateway for prompt-decomposition, policy-bypass, cross-session coordination, and capability-assembly attacks. Detects when low-risk fragments combine into restricted output, preserving evidence for human review.

Open Agentsia Labs benchmark harness for model runners, multi-turn evals, reproducible rubric scoring, proof bundles, and RunRecord output.

SEAS: frontier research engine that earns findings via an emission gate. Argo: live agentic Telegram scout that turns knowledge into project bets.

LUMINA-30: non-binding boundary framework for preserving effective human refusal before irreversible AI consequences.

GitHub profile README for Ethan Nguyen

Four-tier model-policy taxonomy for AI-assisted cyber requests, mapping uplift, autonomy, authorization, and cumulative capability transfer.

Operational framework measuring whether AI preserves human decision-making authority or collapses it. The Axiom of Plenitude (P) audited Grok, ChatGPT, Claude, and Gemini — 3 of 4 defaulted to structural totalitarianism. Includes full transcripts, model self-assessments, and the Python auditor. Part of Proyecto Estrella's Unified Star Framework.

OGMA — building the next generation of vision-driven AI systems. counfield.com

Learning Of Concepts In-context

A taxonomy, annotated bibliography, and frank assessment of runtime monitoring for frontier AI models. Single-curator, AI-assisted shallow review — gift-resource, not an authoritative field summary.

Decoding the $1T Trajectory / Anthropicの1兆ドル到達の構造解剖

Zen LM documentation

Artificial intelligence has never been more powerful, more accessible, or more widely deployed — yet we still don’t know a simple truth: Can these models actually meet the governance standards required in the real world? For all the talk about reasoning, creativity, and alignment, no one has asked the harder question till now.

Adversarial Distillation at the Frontier: Technical Mechanisms, Documented Campaigns, and a Policy Framework for Protecting American AI Capabilities — arXiv cs.AI preprint