Derives closed-form output-space gaps for gradient-based unlearning in linear regression, extended to nonlinear models, and proposes leverage diagnostics for auditing forget sets.
A conceptual essay proposing hospital-style containment for AI: gradient routing to wall off dangerous capabilities, provenance-based data labels, and an immune-system analogy for defending against prompt injection and contamination.
A methodology essay arguing alignment researchers should test ideas on MNIST first, illustrated with gradient routing, unlearning robustness via distillation, and subliminal learning results.