Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.
This is a linkpost for https://william-r-s.github.io/implementable_informed_oversight.html
I like this suggestion of a more feasible form of steganography for NNs to figure out! But I think you'd need further advances in transparency to get useful informed oversight capabilities from (transformed or not) copies of the predictive network.