Bounding eval awareness of ~human-level AI across the safe-to-dangerous shift

In our last post, we argued that measuring evaluation awareness is fundamentally challenging because of the safe-to-dangerous distributional shift: we cannot directly measure the evaluation awareness of a model without deploying it, but we cannot safely deploy it until we know it is not scheming. We expect sufficiently superhuman AI will be eval aware, but this post outlines a tentative solution for bounding the awareness of a ~human-expert-level[1] AI across this safe-to-dangerous shift:Instead...