Indirect normativity is an approach to the AI alignment problem that attempts to specify AI values indirectly, such as by reference to what a rational agent would value under idealized conditions, rather than via direct specification.
Further reading
Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press, ch. 13.
Christiano, Paul (2012) A formalization of indirect normativity, Ordinary Ideas, April 21.
Yudkowsky, Eliezer (2013) Five theses, two lemmas, and a couple of strategic implications, Machine Intelligence Research Institute’s Blog, May 5.