Many fear that future artificial agents will resist shutdown. I present an idea – the POST-Agents Proposal – for ensuring that doesn’t happen. I propose that we train agents to satisfy Preferences Only Between Same-Length Trajectories(POST). I then prove that POST – together with other conditions – implies Neutrality+: the agent maximizes expected utility, ignoring the probability distribution over trajectorylengths. I argue that Neutrality+ keeps agents shutdownable and allows them...
