We can't micro-manage it, and there will be tremendous dangers, but there are reasons for both hope and fear. Code, in and of itself is lazy. If I compile a C program with nothing in main(), it will do nothing. So the only goals an AI has initially are what we give it to start, and what it ads to aid in achieving those goals.

Blank slate computer programs, and AI start from an ultimate desireless state of zen. It doesn't want to take over, it has no cares, it doesn't want to eat, and it doesn't care if it continues to exist or not. It doesn't want anything until we, or the system we design to evolve it in, trains it to want something.

Scenarios where we evolve AI or transcribe human brains are both the most dangerous, and most likely to succeed I think. But the problem with both methods is that we don't directly control the goals of a transcribed AI, and if we evolve one, we would likely end up with an AI that is interested in self preservation. That, to me, is where it might decide that our interests, and its interests, are not aligned, and where we might run into...problems.