AI ALIGNMENT FORUM
AF

Pasha Kamyshev

Posts

Sorted by New

1Exploring Notions of "Utility Approximation" and testing quantilizers

8y

0

1Attempting to refine "maximization" with 3 new -izers

9y

1

1A closer look at program based UDT

9y

1

Wiki Contributions

Comments

Modal SAT: Self Cooperation

Pasha Kamyshev9y10

I am also confused. How does this do against EABot, aka C1=□(Them(Them)=D) and M = DefectBot. Is the number of boxes not well defined in this case?