RSS

RyanCarey

Karma: 1,628

Re­ward Hack­ing from a Causal Perspective

Jul 21, 2023, 6:27 PM
29 points
6 comments7 min readLW link

In­cen­tives from a causal perspective

Jul 10, 2023, 5:16 PM
27 points
0 comments6 min readLW link

Causal­ity: A Brief Introduction

Jun 20, 2023, 3:01 PM
49 points
18 comments6 min readLW link

In­tro­duc­tion to Towards Causal Foun­da­tions of Safe AGI

Jun 12, 2023, 5:55 PM
67 points
6 comments4 min readLW link

Sur­vey re AIS/​LTism office in NYC

RyanCareyJun 20, 2022, 7:21 PM
7 points
0 comments1 min readLW link

[Question] Mechanism de­sign /​ queue­ing the­ory for gov­ern­ment to sell visas

RyanCareyFeb 19, 2022, 12:33 PM
5 points
11 comments1 min readLW link

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

RyanCareySep 28, 2021, 11:03 AM
8 points
13 comments1 min readLW link

RyanCarey’s Shortform

RyanCareyJan 24, 2021, 11:32 AM
6 points
6 comments1 min readLW link

New pa­per: The In­cen­tives that Shape Behaviour

RyanCareyJan 23, 2020, 7:07 PM
23 points
5 comments1 min readLW link
(arxiv.org)

[Question] What are some good ex­am­ples of in­cor­rigi­bil­ity?

RyanCareyApr 28, 2019, 12:22 AM
23 points
17 comments1 min readLW link

When to use quantilization

RyanCareyFeb 5, 2019, 5:17 PM
65 points
5 comments4 min readLW link

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

RyanCareyOct 21, 2018, 12:03 PM
23 points
1 comment6 min readLW link

USA v Pro­gres­sive 1979 excerpt

RyanCareyNov 27, 2017, 5:32 PM
22 points
2 comments2 min readLW link

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

RyanCareyJul 18, 2017, 6:30 AM
4 points
1 comment1 min readLW link
(www.biorxiv.org)

Equil­ibria in ad­ver­sar­ial su­per­vised learning

RyanCareyMay 3, 2017, 8:14 AM
5 points
1 comment3 min readLW link

Call for Spe­cial Is­sue on Su­per­in­tel­li­gence—Informatica

RyanCareyMay 3, 2017, 5:08 AM
5 points
0 comments1 min readLW link
(www.informatica.si)

On­line Learn­ing 3: Ad­ver­sar­ial ban­dit learn­ing with catastrophes

RyanCareyNov 14, 2016, 10:58 PM
3 points
0 comments10 min readLW link

On­line Learn­ing 2: Ban­dit learn­ing with catastrophes

RyanCareyOct 29, 2016, 4:53 PM
0 points
5 comments4 min readLW link

On­line Learn­ing 1: Bias-de­tect­ing on­line learners

RyanCareyOct 29, 2016, 4:45 PM
6 points
7 comments3 min readLW link

Im­prov­ing long-run civil­i­sa­tional robustness

RyanCareyMay 10, 2016, 11:15 AM
14 points
43 comments3 min readLW link