Progress and preservation in IDA
Overview This post arose out of my attempts to understand IDA and ways it could fail. It might help you do the same and could provide useful vocabulary for discussing desiderata for IDA. We want IDA to satisfy progress---decomposition should make answering questions easier---and preservation---semantics should be retained across transformations....
Dec 8, 201911
This post in which I use a probe to remove sleeper agent behavior in a toy model may also be of interest: https://www.col-ex.org/posts/sleeper-agent/