I like this summary, though it seems to miss the arguments in things like Nate's recent post (which have also been made other places many years ago): https://www.lesswrong.com/posts/tZExpBovNhrBvCZSb/how-could-you-possibly-choose-what-an-ai-wants 

Reflective stability is a huge component of why value identification is hard, and why it's hard to get feedback on whether your AI actually understands human values before it reaches quite high levels of intelligence.