[fluffster]

>Most of his articles on it seem to be very tl;dr.

This is a good start: http://www.singinst.org/upload/artificial-intelligence-risk....

These videos are good intros to EY's work too:

http://video.google.co.uk/videoplay?docid=611451877200179691...

http://video.google.co.uk/videoplay?docid=-82119137046281951...

[Eliezer]

Yup, linked paper above is the canonical intro at this point.