I am working on creating chapter-wise notes of Nick Bostrom's Superintelligence, to highlight what I consider to be the most salient points and make the information more accessible for people with limited time on their hands. My hope is that this will make AI safety accessible to a wider range of people.
I feel I should note that the book is well-researched and provides citations accordingly, which I have neglected to include in my notes for the sake of ease and time. I would encourage you to check out the full book if you enjoy reading the notes and want a deeper contextualization of the concepts discussed.
Check out my notes from Chapter 1 of the book here!