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

## The Claim (current version)


## Challenging Evidence

**Source:** Theseus synthetic analysis (2026-04-22)

While multi-layer ensembles improve clean-data accuracy substantially, this synthetic analysis suggests they provide no structural protection against white-box adversarial attacks (open-weights models) and uncertain protection in black-box settings (depends on untested rotation pattern universality). The accuracy improvement does not translate to adversarial robustness.