M. Y. Zuo comments on Parametrically retargetable decision-makers tend to seek power

[M. Y. Zuo]

Thanks for sharing. Though can you explain this phrasing in the abstract?:

Eventually, retargetable training procedures may train real-world agents which seek power over humans.

As I understand, agents inherently have some non-zero possibility of seeking power over humans, other agents, etc., by definition.