teleo-codex/domains/ai-alignment/multi-layer-ensemble-probes-outperform-single-layer-by-29-78-percent.md

**Source:** Theseus synthetic analysis
The 29-78% AUROC improvement is a clean-data accuracy result. Nordby et al. did not test adversarial robustness. Under white-box adversarial conditions (open-weights models), multi-layer ensembles are *predicted* to provide no structural protection against SCAV-generalization attacks. This improvement applies only to non-adversarial monitoring contexts.