2 papers
cs.AI2025
Will artificial agents pursue power by default?
Christian Tarsney
Researchers worried about catastrophic risks from advanced AI have argued that we should expect sufficiently capable AI agents to pursue power over humanity because power is a conv…
econ.TH2018
Exceeding Expectations: Stochastic Dominance as a General Decision Theory
Christian Tarsney
The principle that rational agents should maximize expected utility or choiceworthiness is intuitively plausible in many ordinary cases of decision-making under uncertainty. But it…