As I understand the term, that sort of ASI wouldn’t be considered “misaligned”, it would be “aligned, but to the wrong target”. I think of misalignment as when you wanted the ASI to do one thing, but it did something else instead.
As I understand the term, that sort of ASI wouldn’t be considered “misaligned”, it would be “aligned, but to the wrong target”. I think of misalignment as when you wanted the ASI to do one thing, but it did something else instead.