Funny story. Just today I read the dissertation of a Rutgers philosophy PhD student (Rutgers is the #2 philosophy department worldwide according to the standard ranking ) on strategies for action in the face of normative uncertainty. It explores at great length the idea of instrumentally valuable strategies that boost our ability to attain a wide range of goals, and in particular the goals that we would seek under various idealizations.
Its introduction cites three inspirations leading to the work: John Stuart Mill’s “On Liberty,” John Rawls’ “Theory of Justice,” and Eliezer Yudkowsky’s “Creating Friendly AI” (2001), discussed at greater length than the others.
EDIT: Because of the OP, I should note that I do favor SIAI publishing in mainstream venues.
That’s quite interesting. It should be noted though that (according to google scholar at least) both his chapters in Bostrom’s volume have eclipsed the Introduction to Bayes, even though they are much, much more recent. I expect the effect to be compounded with time.
Funny story. Just today I read the dissertation of a Rutgers philosophy PhD student (Rutgers is the #2 philosophy department worldwide according to the standard ranking ) on strategies for action in the face of normative uncertainty. It explores at great length the idea of instrumentally valuable strategies that boost our ability to attain a wide range of goals, and in particular the goals that we would seek under various idealizations.
Its introduction cites three inspirations leading to the work: John Stuart Mill’s “On Liberty,” John Rawls’ “Theory of Justice,” and Eliezer Yudkowsky’s “Creating Friendly AI” (2001), discussed at greater length than the others.
EDIT: Because of the OP, I should note that I do favor SIAI publishing in mainstream venues.
Also, these recent papers refer to or quotes Eliezer’s Bayes tutorial several times, as do many others.
That’s quite interesting. It should be noted though that (according to google scholar at least) both his chapters in Bostrom’s volume have eclipsed the Introduction to Bayes, even though they are much, much more recent. I expect the effect to be compounded with time.