(A longer text-based version of this post is also available on MIRI's blog here, and the bibliography for the whole sequence can be found here)
Insofar as the AI Alignment Forum is part of the Best-of-2018 Review, this post deserves to be included. It's the friendliest explanation to MIRI's research agenda (as of 2018) that currently exists.
(A longer text-based version of this post is also available on MIRI's blog here, and the bibliography for the whole sequence can be found here)