x

AI ALIGNMENT FORUM
AF

Pasha Kamyshev

Ω4300

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

agilecaveman — AI Alignment Forum

No wikitag contributions to display.

1Exploring Notions of "Utility Approximation" and testing quantilizers

10y

0

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

10y

1

1A closer look at program based UDT

10y

1

Modal SAT: Self Cooperation

agilecaveman10y10

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?