While it could be seen as no more than a basic primer in moral philosophy, it is arguably required reading to anyone unfamiliar with the philosophical background of such concepts as Friendly AI and Coherent Extrapolated Volition.
This is a terrible primer for moral philosophy and if this counts as canon for Friendly AI debates the field is in far worse shape than I thought. It isn’t even a decent piece of writing.
This is a terrible primer for moral philosophy and if this counts as canon for Friendly AI debates the field is in far worse shape than I thought. It isn’t even a decent piece of writing.
not particularly