Test­ing the Effi­cacy of Disagree­ment Re­s­olu­tion Tech­niques (and a Pro­posal for Test­ing Dou­ble Crux)

Ronny FernandezOct 21, 2019, 10:57 PM
35 points
2 comments15 min readLW link

Is re­quires ought

jessicataOct 28, 2019, 2:36 AM
35 points
61 comments7 min readLW link
(unstableontology.com)

Ar­ti­fact: What Went Wrong?

ZviOct 8, 2019, 12:10 PM
34 points
2 comments20 min readLW link
(thezvi.wordpress.com)

13 Causes of Bad Science (Novum Or­ganum Book 1: 69-92)

Francis BaconOct 4, 2019, 7:52 PM
33 points
1 comment30 min readLW link

AI Align­ment Writ­ing Day Roundup #2

Ben PaceOct 7, 2019, 11:36 PM
33 points
2 comments3 min readLW link

Defin­ing Myopia

abramdemskiOct 19, 2019, 9:32 PM
32 points
18 comments8 min readLW link

Bets and updating

Eigil RischelOct 7, 2019, 11:06 PM
32 points
5 comments2 min readLW link

[Question] When is pair-pro­gram­ming su­pe­rior to reg­u­lar pro­gram­ming?

ChristianKlOct 8, 2019, 11:48 AM
31 points
11 comments1 min readLW link

Im­pact mea­sure­ment and value-neu­tral­ity verification

evhubOct 15, 2019, 12:06 AM
31 points
13 comments6 min readLW link

Sets and Functions

countedblessingsOct 11, 2019, 5:06 AM
31 points
22 comments10 min readLW link

Re­place judges with Key­ne­sian beauty con­tests?

John_MaxwellOct 7, 2019, 4:00 AM
30 points
5 comments3 min readLW link

LW Team Up­dates—Oc­to­ber 2019

RubyOct 1, 2019, 11:08 PM
30 points
10 comments3 min readLW link

[Question] What’s your big idea?

Gordon Seidoh WorleyOct 18, 2019, 3:47 PM
30 points
64 comments1 min readLW link

The Pit

alkjashOct 26, 2019, 5:28 AM
30 points
7 comments8 min readLW link
(radimentary.wordpress.com)

Who lacks the qualia of con­scious­ness?

Richard_KennawayOct 5, 2019, 7:49 PM
29 points
55 comments1 min readLW link

Reflec­tions on Premium Poker Tools: Part 3 - What I’ve learned

Adam ZernerOct 11, 2019, 12:49 AM
29 points
34 comments15 min readLW link

Char­ac­ter­iz­ing Real-World Agents as a Re­search Meta-Strategy

johnswentworthOct 8, 2019, 3:32 PM
29 points
4 comments5 min readLW link

All I know is Goodhart

Stuart_ArmstrongOct 21, 2019, 12:12 PM
28 points
23 comments3 min readLW link

The Ba­co­nian Method (Novum Or­ganum Book 1: 93-107)

Francis BaconOct 10, 2019, 6:54 PM
28 points
1 comment11 min readLW link

Schematic Think­ing: heuris­tic gen­er­al­iza­tion us­ing Korzyb­ski’s method

romeostevensitOct 14, 2019, 7:29 PM
28 points
7 comments3 min readLW link

Theater Tick­ets, Sleep­ing Pills, and the Idiosyn­crasies of Del­e­gated Risk Management

DavidmanheimOct 30, 2019, 10:33 AM
27 points
7 comments3 min readLW link

Planned Power Outages

jefftkOct 12, 2019, 2:10 PM
27 points
18 comments1 min readLW link
(www.jefftk.com)

Book Re­view: The AI Does Not Hate You

PeterMcCluskeyOct 28, 2019, 5:45 PM
27 points
0 comments5 min readLW link
(www.bayesianinvestor.com)

Why “Referer”?

jefftkOct 23, 2019, 1:40 PM
27 points
0 comments2 min readLW link
(www.jefftk.com)

Ex­am­ples of Categories

countedblessingsOct 10, 2019, 1:25 AM
27 points
2 comments5 min readLW link

[Question] What fund­ing sources ex­ist for tech­ni­cal AI safety re­search?

johnswentworthOct 1, 2019, 3:30 PM
27 points
5 comments1 min readLW link

Strong stances

KatjaGraceOct 15, 2019, 12:40 AM
27 points
9 comments9 min readLW link
(meteuphoric.com)

Long Term Fu­ture Fund ap­pli­ca­tion is clos­ing this Fri­day (Oc­to­ber 11th)

habrykaOct 10, 2019, 12:44 AM
26 points
0 comments1 min readLW link
(docs.google.com)

AI Align­ment Open Thread Oc­to­ber 2019

habrykaOct 4, 2019, 1:28 AM
26 points
58 comments1 min readLW link

On Col­lu­sion—Vi­talik Buterin

Matt GoldenbergOct 9, 2019, 2:45 PM
24 points
3 comments1 min readLW link
(hackernoon.com)

Al­gorithms of De­cep­tion!

Zack_M_DavisOct 19, 2019, 6:04 PM
24 points
7 comments5 min readLW link

Look­ing for re­mote writ­ing part­ners (for AI al­ign­ment re­search)

rmoehnOct 1, 2019, 2:16 AM
23 points
4 comments2 min readLW link

[Question] What’s go­ing on with “prov­abil­ity”?

Sunny from QADOct 13, 2019, 3:59 AM
23 points
22 comments1 min readLW link

Polyamory is Ra­tional(ist)

Jacob FalkovichOct 18, 2019, 4:48 PM
23 points
2 comments1 min readLW link
(putanumonit.com)

De­liber­a­tion as a method to find the “ac­tual prefer­ences” of humans

riceissaOct 22, 2019, 9:23 AM
23 points
5 comments10 min readLW link

The prob­lem/​solu­tion ma­trix: Calcu­lat­ing the prob­a­bil­ity of AI safety “on the back of an en­velope”

John_MaxwellOct 20, 2019, 8:03 AM
22 points
4 comments2 min readLW link

Rea­sons for Hope & Ob­jec­tion Preemp­tion (Novum Or­ganum Book 1: 108-130)

Francis BaconOct 18, 2019, 2:32 AM
22 points
1 comment24 min readLW link

For­mal Me­taethics and Me­tase­man­tics for AI Alignment

June KuOct 8, 2019, 5:37 AM
22 points
6 comments5 min readLW link

Septem­ber 2019 gw­ern.net newsletter

gwernOct 4, 2019, 4:44 PM
21 points
0 commentsLW link
(www.gwern.net)

Reflec­tions on Premium Poker Tools: Part 4 - Smaller things that I’ve learned

Adam ZernerOct 11, 2019, 1:26 AM
21 points
8 comments6 min readLW link

[Link] Tools for thought (Ma­tuschak & Niel­sen)

ioannesOct 4, 2019, 12:42 AM
21 points
7 comments2 min readLW link

Why Ranked Choice Vot­ing Isn’t Great

jefftkOct 19, 2019, 11:10 AM
21 points
28 comments3 min readLW link
(www.jefftk.com)

Ideal Num­ber of Parents

jefftkOct 4, 2019, 8:00 PM
20 points
4 comments3 min readLW link
(www.jefftk.com)

The best of the www, in my opinion

aiiixiiiOct 17, 2019, 3:14 PM
20 points
4 comments1 min readLW link

Full toy model for prefer­ence learning

Stuart_ArmstrongOct 16, 2019, 11:06 AM
20 points
2 comments12 min readLW link

Con­scious Pro­pri­o­cep­tion.

leggiOct 4, 2019, 4:33 AM
20 points
8 comments7 min readLW link

Jacy Reese (born Jacy An­this)?

jefftkOct 26, 2019, 9:00 PM
20 points
8 comments3 min readLW link
(www.jefftk.com)

The Miss­ing Piece

Martin SustrikOct 27, 2019, 5:50 AM
19 points
6 comments3 min readLW link
(250bpm.com)

The Dual­ist Pre­dict-O-Matic ($100 prize)

John_MaxwellOct 17, 2019, 6:45 AM
19 points
35 comments5 min readLW link

[Link] Book Re­view: ‘The AI Does Not Hate You’ by Tom Chivers (Scott Aaron­son)

eigenOct 7, 2019, 6:16 PM
19 points
0 comments1 min readLW link