I would optimize myself to maximize my reward, not whatever current behavior triggers the reward. Why would an ASI be different?
So you are saying that an AI will just go directly to wireheading itself?
Why wouldn't it? Why would it continue to act on it's reward function but not seek the reward directly?
Part 1 was previously posted and it seemed that people likd it, so I figured that I should post part 2 - http://waitbutwhy.com/2015/01/artificial-intelligence-revolution-2.html