RyanCarey(Ryan Carey)

[Question] Prob­lems with us­ing ap­proval vot­ing to elect to a multi-in­di­vi­d­ual body?

RyanCarey’s Shortform

New pa­per: The In­cen­tives that Shape Behaviour

[Question] What are some good ex­am­ples of in­cor­rigi­bil­ity?

When to use quantilization

Ad­dress­ing three prob­lems with coun­ter­fac­tual cor­rigi­bil­ity: bad bets, defend­ing against back­stops, and over­con­fi­dence.

USA v Pro­gres­sive 1979 excerpt

A com­bined anal­y­sis of ge­net­i­cally cor­re­lated traits iden­ti­fies 107 loci as­so­ci­ated with in­tel­li­gence | bioRxiv

Equil­ibria in ad­ver­sar­ial su­per­vised learning

Call for Spe­cial Is­sue on Su­per­in­tel­li­gence—Informatica

On­line Learn­ing 3: Ad­ver­sar­ial ban­dit learn­ing with catastrophes

On­line Learn­ing 2: Ban­dit learn­ing with catastrophes

On­line Learn­ing 1: Bias-de­tect­ing on­line learners

Im­prov­ing long-run civil­i­sa­tional robustness

Re­duc­ing Catas­trophic Risks, A Prac­ti­cal Introduction

The Effec­tive Altru­ism Handbook

One week left for CSER re­searcher applications

SETI-re­lated: fast ra­dio bursts

GCRI: Up­dated Strat­egy and AMA on EA Fo­rum next Tuesday

Cer­tifi­cates of Im­pact [Paul Chris­ti­ano; Link]