What’s next for in­stru­men­tal ra­tio­nal­ity?

Andrew_CritchJul 23, 2022, 10:55 PM
63 points
7 comments1 min readLW link

Easy guide for run­ning a lo­cal Ra­tion­al­ity meetup

Nikita SokolskyJul 23, 2022, 10:52 PM
13 points
1 comment6 min readLW link

Cu­rat­ing “The Epistemic Se­quences” (list v.0.1)

Andrew_CritchJul 23, 2022, 10:17 PM
65 points
12 comments7 min readLW link

Room Opening

jefftkJul 23, 2022, 9:00 PM
8 points
3 comments4 min readLW link
(www.jefftk.com)

A Bias Against Altruism

Lone PineJul 23, 2022, 8:44 PM
58 points
30 comments2 min readLW link

What En­vi­ron­ment Prop­er­ties Select Agents For World-Model­ing?

Thane RuthenisJul 23, 2022, 7:27 PM
25 points
1 comment12 min readLW link

Which sin­gu­lar­ity schools plus the no sin­gu­lar­ity school was right?

Noosphere89Jul 23, 2022, 3:16 PM
9 points
26 comments9 min readLW link

Ba­sic Post Scarcity Q&A

lorepieriJul 23, 2022, 1:43 PM
3 points
0 comments1 min readLW link
(lorenzopieri.com)

Ro­bust­ness to Scal­ing Down: More Im­por­tant Than I Thought

adamShimiJul 23, 2022, 11:40 AM
38 points
5 comments3 min readLW link

Eat­ing Boogers

George3d6Jul 23, 2022, 11:20 AM
17 points
5 comments6 min readLW link
(www.epistem.ink)

On Akra­sia, Habits and Re­ward Maximization

AiyenJul 23, 2022, 8:34 AM
14 points
1 comment6 min readLW link

Which val­ues are sta­ble un­der on­tol­ogy shifts?

Richard_NgoJul 23, 2022, 2:40 AM
74 points
48 comments3 min readLW link
(thinkingcomplete.blogspot.com)

Try­ing out Prompt Eng­ineer­ing on TruthfulQA

Megan KinnimentJul 23, 2022, 2:04 AM
10 points
0 comments8 min readLW link

Con­nor Leahy on Dy­ing with Dig­nity, EleutherAI and Conjecture

Michaël TrazziJul 22, 2022, 6:44 PM
195 points
29 comments14 min readLW link
(theinsideview.ai)

Wy­clif’s Dust: the miss­ing chapter

David Hugh-JonesJul 22, 2022, 6:27 PM
9 points
0 comments4 min readLW link
(wyclif.substack.com)

Mak­ing DALL-E Count

DirectedEvolutionJul 22, 2022, 9:11 AM
23 points
12 comments4 min readLW link

One-day ap­plied ra­tio­nal­ity work­shop in Ber­lin Aug 29 (af­ter LWCW)

Duncan Sabien (Deactivated)Jul 22, 2022, 7:58 AM
30 points
5 comments2 min readLW link

In­ter­nal Dou­ble Crux

CFAR!DuncanJul 22, 2022, 4:34 AM
93 points
15 comments12 min readLW link

Con­di­tion­ing Gen­er­a­tive Models with Restrictions

Adam JermynJul 21, 2022, 8:33 PM
18 points
4 comments8 min readLW link

Our Ex­ist­ing Solu­tions to AGI Align­ment (semi-safe)

Michael SoareverixJul 21, 2022, 7:00 PM
12 points
1 comment3 min readLW link

Chang­ing the world through slack & hobbies

Steven ByrnesJul 21, 2022, 6:11 PM
261 points
13 comments10 min readLW link

Which per­son­al­ities do we find in­tol­er­able?

weathersystemsJul 21, 2022, 3:56 PM
10 points
3 comments6 min readLW link

YouTubeTV and Spoilers

ZviJul 21, 2022, 1:50 PM
16 points
6 comments8 min readLW link
(thezvi.wordpress.com)

Covid 7/​21/​22: Fea­tur­ing ASPR

ZviJul 21, 2022, 1:50 PM
27 points
0 comments14 min readLW link
(thezvi.wordpress.com)

[Question] How much to op­ti­mize for the short-timelines sce­nario?

SoerenMindJul 21, 2022, 10:47 AM
20 points
3 comments1 min readLW link

Is Gas Green?

ChristianKlJul 21, 2022, 10:30 AM
19 points
19 comments1 min readLW link

Why are poli­ti­ci­ans po­larized?

ErnestScribblerJul 21, 2022, 8:17 AM
15 points
24 comments7 min readLW link

[AN #173] Re­cent lan­guage model re­sults from DeepMind

Rohin ShahJul 21, 2022, 2:30 AM
37 points
9 comments8 min readLW link
(mailchi.mp)

Don’t take the or­ga­ni­za­tional chart literally

lcJul 21, 2022, 12:56 AM
54 points
21 comments4 min readLW link

Per­sonal fore­cast­ing ret­ro­spec­tive: 2020-2022

eliflandJul 21, 2022, 12:07 AM
35 points
3 comments8 min readLW link
(www.foxy-scout.com)

Defin­ing Op­ti­miza­tion in a Deeper Way Part 3

J BostockJul 20, 2022, 10:06 PM
8 points
0 comments2 min readLW link

Cog­ni­tive Risks of Ado­les­cent Binge Drinking

Jul 20, 2022, 9:10 PM
70 points
12 comments10 min readLW link
(acesounderglass.com)

Why AGI Timeline Re­search/​Dis­course Might Be Overrated

Noosphere89Jul 20, 2022, 8:26 PM
5 points
0 comments1 min readLW link
(forum.effectivealtruism.org)

En­light­en­ment Values in a Vuln­er­a­ble World

Maxwell TabarrokJul 20, 2022, 7:52 PM
15 points
6 comments31 min readLW link
(maximumprogress.substack.com)

Coun­ter­ing ar­gu­ments against work­ing on AI safety

Rauno ArikeJul 20, 2022, 6:23 PM
7 points
2 comments7 min readLW link

A Short In­tro to Humans

Ben AmitayJul 20, 2022, 3:28 PM
1 point
1 comment7 min readLW link

How to Diver­sify Con­cep­tual Align­ment: the Model Be­hind Refine

adamShimiJul 20, 2022, 10:44 AM
87 points
11 comments8 min readLW link

[Question] What are the sim­plest ques­tions in ap­plied ra­tio­nal­ity where you don’t know the an­swer to?

ChristianKlJul 20, 2022, 9:53 AM
26 points
11 comments1 min readLW link

AI Safety Cheat­sheet /​ Quick Reference

Zohar JacksonJul 20, 2022, 9:39 AM
3 points
0 comments1 min readLW link
(github.com)

Get­ting Un­stuck on Counterfactuals

Chris_LeongJul 20, 2022, 5:31 AM
7 points
1 comment2 min readLW link

Pit­falls with Proofs

scasperJul 19, 2022, 10:21 PM
19 points
21 comments8 min readLW link

A daily rou­tine I do for my AI safety re­search work

scasperJul 19, 2022, 9:58 PM
21 points
7 comments1 min readLW link

Progress links and tweets, 2022-07-19

jasoncrawfordJul 19, 2022, 8:50 PM
11 points
1 comment1 min readLW link
(rootsofprogress.org)

Ap­pli­ca­tions are open for CFAR work­shops in Prague this fall!

John SteidleyJul 19, 2022, 6:29 PM
64 points
3 comments2 min readLW link

Sex­ual Abuse at­ti­tudes might be infohazardous

Pseudonymous OtterJul 19, 2022, 6:06 PM
256 points
72 comments1 min readLW link

Spend­ing Up­date 2022

jefftkJul 19, 2022, 2:10 PM
28 points
0 comments3 min readLW link
(www.jefftk.com)

Abram Dem­ski’s ELK thoughts and pro­posal—distillation

Rubi J. HudsonJul 19, 2022, 6:57 AM
19 points
8 comments16 min readLW link

Bounded com­plex­ity of solv­ing ELK and its implications

Rubi J. HudsonJul 19, 2022, 6:56 AM
11 points
4 comments18 min readLW link

Help ARC eval­u­ate ca­pa­bil­ities of cur­rent lan­guage mod­els (still need peo­ple)

Beth BarnesJul 19, 2022, 4:55 AM
95 points
6 comments2 min readLW link

A Cri­tique of AI Align­ment Pessimism

ExCephJul 19, 2022, 2:28 AM
9 points
1 comment9 min readLW link