there’s often no internal conflict when someone is caught up in some extreme form of the morality game
Belated reply, sorry, but I basically just think that this is false—analogous to a dictator who cites parades where people are forced to attend and cheer as evidence that his country lacks internal conflict. Instead, the internal conflict has just been rendered less legible.
In the subagents frame, I would say that the subagents have an implicit contract/agreement that any one of them can seize control, if doing so seems good for the overall agent in terms of power or social status.
Note that this is an extremely non-robust agent design! In particular, it allows subagents to gain arbitrary amounts of power simply by lying about their intentions. If you encounter an agent which considers itself to be structured like this, you should have a strong prior that it is deceiving itself about the presence of more subtle control mechanisms.
Belated reply, sorry, but I basically just think that this is false—analogous to a dictator who cites parades where people are forced to attend and cheer as evidence that his country lacks internal conflict. Instead, the internal conflict has just been rendered less legible.
Note that this is an extremely non-robust agent design! In particular, it allows subagents to gain arbitrary amounts of power simply by lying about their intentions. If you encounter an agent which considers itself to be structured like this, you should have a strong prior that it is deceiving itself about the presence of more subtle control mechanisms.