It is still laughably easy to foil SotA AI with adversarial attacks. Why? Because such systems lack embodiment. But dropping deep learners into robots and calling the result Embodied AI misses the mark: Embodiment is about more than just having a body; it is about change. Consider how much the world changes from the perspective of a human as she grows from one cell into 36x10^12 of them. Grappling with such massive internal change makes grappling with external change, like learning to read or drive, easy by comparison. Thus, to realize safe AI, we must similarly create autonomous technologies whose internal physical changes pretrain them to handle external change, like new tasks or adversarial attacks. I will demonstrate some soft and biological robots capable of this “morphological pre-training” and point out several paths via which the CVPR community can join us in creating such a future.