CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Mon, 29 Dec 2025 12:52:53 GMT access-control-allow-origin: * etag: W/"695279a5-4821" expires: Tue, 30 Dec 2025 02:18:24 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 20C0:2BC55:97823D:AA35C1:69533418 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 02:08:24 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210095-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767060504.499886,VS0,VE208 vary: Accept-Encoding x-fastly-request-id: 12a62987ff6020c214e058ac6d020d33005e3775 content-length: 4761 Christopher Altman · Research Lead · NASA-trained Commercial Astronaut · Quantum ML · Alignment

Christopher Altman

AI Alignment · Automated Falsification · Quantum ML · Space Telemetry Anomaly Detection · Superconducting Qubits

NASA-trained Commercial Astronaut · Research Lead (Quantum + AI)

Stress-testing alignment claims with quantum-inspired testbeds

This research program builds falsification frameworks for AI alignment claims, with particular focus on local recoverability assumptions in neural network editing. We combine quantum machine learning methods with classical testbeds to probe function–representation decoupling, continuation interests, and the reliability of geometric proxies in model repair.

Current work spans quantum kernel methods for satellite anomaly detection, binarized quantum neural networks, Hamiltonian dynamics for data augmentation, and superconducting qubit simulation—each project packaged as a reproducible evaluation harness with diagnostic plots, baselines, and reviewable artifacts designed to test specific technical claims under controlled conditions.

Transmon anharmonicity vs EJ/EC ratio (log-scale)

Collaborations

This live codebase reflects active research collaborations and coauthored work across AI alignment, quantum machine learning, and superconducting circuits. Repositories are maintained as reproducible artifacts; credit for specific contributions appears in papers, commit history, and project documentation.