Surely, a Power will be slightly more complicated than a human being.
Surely, because of the complexity/robustness necessary a Power will need
nonalgorithmic control. If yes, then the whole concept of "hardwired
behaviour" is meaningless. Imagine you could control a human: if a threat
is detected you could disrupt his motorics, so that he is frozen
immobile. But how does one detect a threat? There are zillion
possiblities how a human being might kill another one with dire violence,
and even more of them how it could be done with cunning. To catch them
all, the filter must become arbitrarily complicated, nay, even sentient.
Clearly, such a filter should become unreliable?
ciao,
'gene