AlexMennen(Alex Mennen)

Pri­soner’s Dilemma (with visi­ble source code) Tournament

Pri­soner’s dilemma tour­na­ment results

When wish­ful think­ing works

A com­ment on the IDA-AlphaGoZero metaphor; ca­pa­bil­ities ver­sus alignment

Against the Lin­ear Utility Hy­poth­e­sis and the Lev­er­age Penalty

Harsanyi’s So­cial Ag­gre­ga­tion The­o­rem and what it means for CEV

Log­i­cal un­cer­tainty and Math­e­mat­i­cal uncertainty

Fic­tion: Let­ter from the End

Why bet Kelly?

Aver­age prob­a­bil­ities, not log odds

What is cal­ibra­tion?

VNM agents and lot­ter­ies in­volv­ing an in­finite num­ber of pos­si­ble outcomes

A util­ity-max­i­miz­ing vari­ent of AIXI

Safely and use­fully spec­tat­ing on AIs op­ti­miz­ing over toy worlds

Ex­is­ten­tial risk from AI with­out an in­tel­li­gence explosion

In­ter­per­sonal and in­trap­er­sonal util­ity comparisons

Event [Berkeley]: Align­ment Col­lab­o­ra­tor Speed-Meeting

Com­pu­ta­tional effi­ciency rea­sons not to model VNM-ra­tio­nal prefer­ence re­la­tions with util­ity functions

More on the Lin­ear Utility Hy­poth­e­sis and the Lev­er­age Prior

Su­per­in­tel­li­gence via whole brain emulation