AI Alignment · Automated Falsification · Quantum ML · Space Telemetry Anomaly Detection · Superconducting Qubits
NASA-trained Commercial Astronaut · Research Lead (Quantum + AI)
Our research program develops rigorous 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 fundamental questions about 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 designed to rigorously test specific technical claims under controlled conditions.
This codebase reflects active 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.
Research claims are anchored in publishable units: falsifiable hypotheses, experimental protocols, and measurable outcomes.
Projects are structured so collaborators can reproduce, extend, or refute results with minimal friction.
The emphasis is disciplined iteration: refine the claim, tighten the test, and keep the artifact honest.
Collaboration inquiries: x@christopheraltman.com