LW/​SSC War­saw Fe­bru­ary Meetup

kaftanowiczJan 23, 2020, 7:49 PM
2 points
0 comments1 min readLW link

[Question] The­ory of Causal Models with Dy­namic Struc­ture?

johnswentworthJan 23, 2020, 7:47 PM
24 points
6 comments1 min readLW link

To­kenis­ing hu­man ver­ifi­ca­tion in or­der to de­rive in­for­ma­tion from the re­sult­ing markets

Will ClarkJan 23, 2020, 7:20 PM
3 points
4 comments3 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)

For­mu­lat­ing Re­duc­tive Agency in Causal Models

johnswentworthJan 23, 2020, 5:03 PM
33 points
0 comments2 min readLW link

Cas­sette Tape Thoughts

ElizabethJan 22, 2020, 10:50 PM
48 points
0 comments2 min readLW link
(acesounderglass.com)

Con­cerns Sur­round­ing CEV: A case for hu­man friendli­ness first

ai-crotesJan 22, 2020, 9:03 PM
1 point
19 comments1 min readLW link

(A → B) → A in Causal DAGs

johnswentworthJan 22, 2020, 6:22 PM
48 points
11 comments2 min readLW link

[AN #83]: Sam­ple-effi­cient deep learn­ing with ReMixMatch

Rohin ShahJan 22, 2020, 6:10 PM
15 points
4 comments11 min readLW link
(mailchi.mp)

[Question] Terms & liter­a­ture for pur­posely lossy communication

ozziegooenJan 22, 2020, 10:35 AM
14 points
6 comments1 min readLW link

Three signs you may be suffer­ing from im­poster syndrome

lcJan 21, 2020, 10:17 PM
9 points
7 comments2 min readLW link

Log­i­cal Rep­re­sen­ta­tion of Causal Models

johnswentworthJan 21, 2020, 8:04 PM
37 points
0 comments3 min readLW link

Disasters

jefftkJan 21, 2020, 7:20 PM
16 points
13 comments3 min readLW link
(www.jefftk.com)

Safety reg­u­la­tors: A tool for miti­gat­ing tech­nolog­i­cal risk

JustinShovelainJan 21, 2020, 1:07 PM
13 points
4 comments4 min readLW link

How Doomed are Large Or­ga­ni­za­tions?

ZviJan 21, 2020, 12:20 PM
81 points
42 comments9 min readLW link
(thezvi.wordpress.com)

Book Re­view—The Ori­gins of Un­fair­ness: So­cial Cat­e­gories and Cul­tural Evolution

Zack_M_DavisJan 21, 2020, 6:28 AM
27 points
5 comments1 min readLW link
(unremediatedgender.space)

Whipped Cream vs Fancy Butter

jefftkJan 21, 2020, 12:30 AM
−2 points
36 comments1 min readLW link
(www.jefftk.com)

In­ner al­ign­ment re­quires mak­ing as­sump­tions about hu­man values

Matthew BarnettJan 20, 2020, 6:38 PM
26 points
9 comments4 min readLW link

Work­shop on As­sured Au­tonomous Sys­tems (WAAS)

Aryeh EnglanderJan 20, 2020, 4:21 PM
2 points
0 comments1 min readLW link

Why Do You Keep Hav­ing This Prob­lem?

Davis_KingsleyJan 20, 2020, 8:33 AM
47 points
16 comments1 min readLW link

[Question] Use-cases for com­pu­ta­tions, other than run­ning them?

johnswentworthJan 19, 2020, 8:52 PM
30 points
6 comments2 min readLW link

UML VII: Meta-Learning

Rafael HarthJan 19, 2020, 6:23 PM
14 points
0 comments15 min readLW link

Ad­just­ing Out­door Reset

jefftkJan 19, 2020, 6:20 PM
1 point
0 comments1 min readLW link
(www.jefftk.com)

Madi­son SSC Meetup: Ad­ver­sar­ial Collaborations

marywangJan 19, 2020, 4:47 PM
1 point
0 comments1 min readLW link

Book re­view: Hu­man Compatible

PeterMcCluskeyJan 19, 2020, 3:32 AM
37 points
2 comments5 min readLW link
(www.bayesianinvestor.com)

Is NYC Build­ing Much Hous­ing?

jefftkJan 18, 2020, 8:50 PM
0 points
0 comments1 min readLW link
(www.jefftk.com)

The Road to Mazedom

ZviJan 18, 2020, 2:10 PM
97 points
26 comments7 min readLW link2 reviews
(thezvi.wordpress.com)

[Question] What types of com­pute/​pro­cess­ing could we dis­t­in­guish?

MoritzGJan 18, 2020, 10:04 AM
2 points
9 comments1 min readLW link

[Question] Poli­ti­cal Roko’s basilisk

Abhimanyu Pallavi SudhirJan 18, 2020, 9:34 AM
10 points
10 comments1 min readLW link

Risk and un­cer­tainty: A false di­chotomy?

MichaelAJan 18, 2020, 3:09 AM
6 points
9 comments20 min readLW link

Re­mote AI al­ign­ment writ­ing group seek­ing new members

rmoehnJan 18, 2020, 2:10 AM
11 points
0 comments1 min readLW link

“How quickly can you get this done?” (es­ti­mat­ing work­load)

kerspoonJan 18, 2020, 12:10 AM
15 points
9 comments4 min readLW link

Study­ing Early Stage Science: Re­search Pro­gram Introduction

habrykaJan 17, 2020, 10:12 PM
32 points
1 comment15 min readLW link
(medium.com)

Fid­dle Effects Tech

jefftkJan 17, 2020, 5:00 PM
2 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] How does a Liv­ing Be­ing solve the prob­lem of Sub­sys­tem Align­ment?

Alan GivréJan 17, 2020, 9:32 AM
3 points
7 comments1 min readLW link

Can we always as­sign, and make sense of, sub­jec­tive prob­a­bil­ities?

MichaelAJan 17, 2020, 3:05 AM
11 points
15 comments13 min readLW link

Against Ra­tion­al­iza­tion II: Se­quence Recap

dspeyerJan 16, 2020, 10:51 PM
6 points
2 comments1 min readLW link

Us­ing Ex­pert Disagreement

dspeyerJan 16, 2020, 10:42 PM
13 points
1 comment5 min readLW link

Bay Sols­tice 2019 Retrospective

mingyuanJan 16, 2020, 5:15 PM
75 points
36 comments15 min readLW link

Real­ity-Re­veal­ing and Real­ity-Mask­ing Puzzles

AnnaSalamonJan 16, 2020, 4:15 PM
264 points
57 comments13 min readLW link1 review

How to Es­cape From Im­moral Mazes

ZviJan 16, 2020, 1:10 PM
79 points
21 comments19 min readLW link1 review
(thezvi.wordpress.com)

Test­ing for Rationalization

dspeyerJan 16, 2020, 8:12 AM
19 points
0 comments2 min readLW link

[Question] How use­ful do you think par­ti­ci­pat­ing to the Hu­man Micro­biome Pro­ject would be?

Mati_RoyJan 15, 2020, 11:51 PM
4 points
0 comments1 min readLW link

The Align­ment-Com­pe­tence Trade-Off, Part 1: Coal­i­tion Size and Sig­nal­ing Costs

GentzelJan 15, 2020, 11:10 PM
30 points
4 comments3 min readLW link
(theconsequentialist.wordpress.com)

In Defense of the Arms Races… that End Arms Races

GentzelJan 15, 2020, 9:30 PM
38 points
9 comments3 min readLW link
(theconsequentialist.wordpress.com)

Fire Alarm for AGI

user134723Jan 15, 2020, 8:41 PM
1 point
0 comments1 min readLW link
(blog.acolyer.org)

Go F*** Someone

Jacob FalkovichJan 15, 2020, 6:39 PM
19 points
23 comments8 min readLW link

[AN #82]: How OpenAI Five dis­tributed their train­ing computation

Rohin ShahJan 15, 2020, 6:20 PM
19 points
0 comments8 min readLW link
(mailchi.mp)

ACDT: a hack-y acausal de­ci­sion theory

Stuart_ArmstrongJan 15, 2020, 5:22 PM
50 points
16 comments7 min readLW link

Nashville Jan­uary 2020 SSC Meetup

friedelcraftinessJan 15, 2020, 5:02 PM
1 point
0 comments1 min readLW link