compared to what you emphasize in the post, I think that a larger fraction of the benefits may come from the information value of learning that the AIs are misaligned.
in contrast to this comment. It’s not literally contradictory (we could have been more explicit about both possibilities), but I wonder if this indicates a disagreement between you and him.
I think it’s interesting that @Lukas Finnveden seems to think
in contrast to this comment. It’s not literally contradictory (we could have been more explicit about both possibilities), but I wonder if this indicates a disagreement between you and him.