Just because these factors apply even without adversarial pressure, does not mean they stop being relevant in the presence of adversarial pressure. I’m not assuming away deception here, I’m saying that these factors are still potentially-limiting problems when one is dealing with potentially-deceptive advisors, and therefore experiments should leave room for them.
Just because these factors apply even without adversarial pressure, does not mean they stop being relevant in the presence of adversarial pressure. I’m not assuming away deception here, I’m saying that these factors are still potentially-limiting problems when one is dealing with potentially-deceptive advisors, and therefore experiments should leave room for them.