Thinking about AI boxing - note that it is Harry who represents humanity, his core values and goals were not changed that much by the Vow, they were just formalized.
It is LV that has goals that are mostly what we'd agree about (`ensure the continuous existence of the world'), but he has very different values and no moral constraints. In short, dealing with him is like dealing with an Unfriendly AI or an Alien mind (like Sorting Hat).
So this is more like a clash between Unfriendly (or better, Indifferent) and a Friendly AI, where the goals are more or less compatible, but in addition the FAI keeps human values. And the UFAI got there first and is more powerful.
The rational way if your goals are compatible is to cooperate - however, Harry's values almost ensure that he will defect given the chance. And LV knows it, so the rational action for him is to defect (=kill) as well.
Unfriendly (or better, Indifferent)
Same thing.
‘The AI does not hate you, nor does it love you, but you are made out of atoms which it can use for something else.’
This is a new thread to discuss Eliezer Yudkowsky’s Harry Potter and the Methods of Rationality and anything related to it. This thread is intended for discussing chapter 113.
There is a site dedicated to the story at hpmor.com, which is now the place to go to find the authors notes and all sorts of other goodies. AdeleneDawner has kept an archive of Author’s Notes. (This goes up to the notes for chapter 76, and is now not updating. The authors notes from chapter 77 onwards are on hpmor.com.)
IMPORTANT -- From the end of chapter 113: