I hadn’t considered the angle that the simulation might be run by an actively hostile entity; in that case, destroying the hostile entity (ending the simulation) is the practical thing to do at the top layer, and also the desired result in the simulation (end of simulation rather than torture).
I hadn’t considered the angle that the simulation might be run by an actively hostile entity; in that case, destroying the hostile entity (ending the simulation) is the practical thing to do at the top layer, and also the desired result in the simulation (end of simulation rather than torture).