A Machine Can Learn in the Same Kind of Way

To put our values on paper is really difficult, or you're just saying it's impossible. A machines can learn in the same kind of way. Ah, what we need to do is to get away from this idea that you build an optimizing machine and then you put the objective to it. Because if it's possible that you might put in a wrong objective,  that means that the machine should never take an objective that's given as gospel truth.