Some references to lesswrong, and value alignment there.
David Abel has provided a fairly nice summary set of notes: https://cs.brown.edu/people/dabel/blog/posts/misc/aaai_2018.pdf
Some references to lesswrong, and value alignment there.
David Abel has provided a fairly nice summary set of notes: https://cs.brown.edu/people/dabel/blog/posts/misc/aaai_2018.pdf