Align­ment be­ing im­pos­si­ble might be bet­ter than it be­ing re­ally difficult

Martín Soto25 Jul 2022 23:57 UTC
13 points
2 comments2 min readLW link

[Question] How op­ti­mistic should we be about AI figur­ing out how to in­ter­pret it­self?

oh5432125 Jul 2022 22:09 UTC
3 points
1 comment1 min readLW link

Pro­tec­tion­ism in One Coun­try: How In­dus­trial Policy Worked in Canada

Davis Kedrosky25 Jul 2022 22:08 UTC
5 points
0 comments16 min readLW link
(daviskedrosky.substack.com)

Mis­takes as agency

pchvykov25 Jul 2022 16:17 UTC
12 points
8 comments4 min readLW link

My Bit­coin Th­e­sis @2022 - Part 1

aysajan25 Jul 2022 15:49 UTC
6 points
6 comments13 min readLW link

The Reader’s Guide to Op­ti­mal Mone­tary Policy

Ege Erdil25 Jul 2022 15:10 UTC
56 points
10 comments14 min readLW link

AGI Safety Needs Peo­ple With All Skil­lsets!

Severin T. Seehrich25 Jul 2022 13:32 UTC
28 points
0 comments2 min readLW link

[Question] Is there any ev­i­dence that hand­wash­ing does any­thing to pre­vent COVID?

mukashi25 Jul 2022 7:34 UTC
4 points
3 comments1 min readLW link

Open­ing Ses­sion Tips & Advice

CFAR!Duncan25 Jul 2022 3:57 UTC
81 points
3 comments14 min readLW link1 review

How much should we worry about mesa-op­ti­miza­tion challenges?

sudo25 Jul 2022 3:56 UTC
4 points
13 comments2 min readLW link

[Question] Does agent foun­da­tions cover all fu­ture ML sys­tems?

Jonas Hallgren25 Jul 2022 1:17 UTC
2 points
0 comments1 min readLW link

Unify­ing Bar­gain­ing No­tions (1/​2)

Diffractor25 Jul 2022 0:28 UTC
204 points
41 comments16 min readLW link

Re­ward is not the op­ti­miza­tion target

TurnTrout25 Jul 2022 0:03 UTC
348 points
123 comments10 min readLW link3 reviews

Brain­storm of things that could force an AI team to burn their lead

So8res24 Jul 2022 23:58 UTC
134 points
8 comments13 min readLW link

Find­ing Skele­tons on Rashomon Ridge

24 Jul 2022 22:31 UTC
30 points
2 comments7 min readLW link

Gather­ing In­for­ma­tion you won’t use di­rectly is of­ten useful

Johannes C. Mayer24 Jul 2022 21:21 UTC
6 points
1 comment1 min readLW link

[Question] Im­pact of ” ‘Let’s think step by step’ is all you need”?

yrimon24 Jul 2022 20:59 UTC
20 points
2 comments1 min readLW link

The Most Im­por­tant Cen­tury: The Animation

24 Jul 2022 20:58 UTC
46 points
2 comments20 min readLW link
(youtu.be)

Hiring Pro­gram­mers in Academia

jefftk24 Jul 2022 20:20 UTC
36 points
19 comments2 min readLW link
(www.jefftk.com)

Less Wrong Bu­dapest July 30th Meetup

Richard Horvath24 Jul 2022 19:07 UTC
2 points
0 comments1 min readLW link

Re­la­tion­ship be­tween sub­jec­tive ex­pe­rience and in­tel­li­gence?

Q Home24 Jul 2022 9:10 UTC
5 points
4 comments9 min readLW link

Dou­ble Crux

CFAR!Duncan24 Jul 2022 6:34 UTC
56 points
9 comments11 min readLW link

Ex­am­ple Meetup Description

Julius24 Jul 2022 5:38 UTC
6 points
0 comments2 min readLW link

Eaves­drop­ping on Aliens: A Data De­cod­ing Challenge

anonymousaisafety24 Jul 2022 4:35 UTC
44 points
9 comments4 min readLW link

In­for­ma­tion the­o­retic model anal­y­sis may not lend much in­sight, but we may have been do­ing them wrong!

Garrett Baker24 Jul 2022 0:42 UTC
7 points
0 comments10 min readLW link

What’s next for in­stru­men­tal ra­tio­nal­ity?

Andrew_Critch23 Jul 2022 22:55 UTC
63 points
7 comments1 min readLW link

Easy guide for run­ning a lo­cal Ra­tion­al­ity meetup

Nikita Sokolsky23 Jul 2022 22:52 UTC
13 points
1 comment6 min readLW link

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

Andrew_Critch23 Jul 2022 22:17 UTC
65 points
12 comments7 min readLW link

Room Opening

jefftk23 Jul 2022 21:00 UTC
8 points
3 comments4 min readLW link
(www.jefftk.com)

A Bias Against Altruism

Lone Pine23 Jul 2022 20:44 UTC
58 points
30 comments2 min readLW link

What En­vi­ron­ment Prop­er­ties Select Agents For World-Model­ing?

Thane Ruthenis23 Jul 2022 19:27 UTC
24 points
1 comment12 min readLW link

Which sin­gu­lar­ity schools plus the no sin­gu­lar­ity school was right?

Noosphere8923 Jul 2022 15:16 UTC
9 points
26 comments9 min readLW link

Ba­sic Post Scarcity Q&A

lorepieri23 Jul 2022 13:43 UTC
3 points
0 comments1 min readLW link
(lorenzopieri.com)

Ro­bust­ness to Scal­ing Down: More Im­por­tant Than I Thought

adamShimi23 Jul 2022 11:40 UTC
37 points
5 comments3 min readLW link

Eat­ing Boogers

George3d623 Jul 2022 11:20 UTC
17 points
5 comments6 min readLW link
(www.epistem.ink)

On Akra­sia, Habits and Re­ward Maximization

Aiyen23 Jul 2022 8:34 UTC
13 points
1 comment6 min readLW link

Which val­ues are sta­ble un­der on­tol­ogy shifts?

Richard_Ngo23 Jul 2022 2:40 UTC
73 points
48 comments3 min readLW link
(thinkingcomplete.blogspot.com)

Try­ing out Prompt Eng­ineer­ing on TruthfulQA

Megan Kinniment23 Jul 2022 2:04 UTC
10 points
0 comments8 min readLW link

Con­nor Leahy on Dy­ing with Dig­nity, EleutherAI and Conjecture

Michaël Trazzi22 Jul 2022 18:44 UTC
194 points
29 comments14 min readLW link
(theinsideview.ai)

Wy­clif’s Dust: the miss­ing chapter

David Hugh-Jones22 Jul 2022 18:27 UTC
9 points
0 comments4 min readLW link
(wyclif.substack.com)

Mak­ing DALL-E Count

DirectedEvolution22 Jul 2022 9:11 UTC
23 points
12 comments4 min readLW link

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

[DEACTIVATED] Duncan Sabien22 Jul 2022 7:58 UTC
30 points
5 comments2 min readLW link

In­ter­nal Dou­ble Crux

CFAR!Duncan22 Jul 2022 4:34 UTC
88 points
15 comments12 min readLW link

Con­di­tion­ing Gen­er­a­tive Models with Restrictions

Adam Jermyn21 Jul 2022 20:33 UTC
18 points
4 comments8 min readLW link

Our Ex­ist­ing Solu­tions to AGI Align­ment (semi-safe)

Michael Soareverix21 Jul 2022 19:00 UTC
12 points
1 comment3 min readLW link

Chang­ing the world through slack & hobbies

Steven Byrnes21 Jul 2022 18:11 UTC
258 points
13 comments10 min readLW link

Which per­son­al­ities do we find in­tol­er­able?

weathersystems21 Jul 2022 15:56 UTC
10 points
3 comments6 min readLW link

YouTubeTV and Spoilers

Zvi21 Jul 2022 13:50 UTC
16 points
6 comments8 min readLW link
(thezvi.wordpress.com)

Covid 7/​21/​22: Fea­tur­ing ASPR

Zvi21 Jul 2022 13:50 UTC
27 points
0 comments14 min readLW link
(thezvi.wordpress.com)

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

SoerenMind21 Jul 2022 10:47 UTC
20 points
3 comments1 min readLW link