[Question] What will 2040 prob­a­bly look like as­sum­ing no sin­gu­lar­ity?

Daniel Kokotajlo16 May 2021 22:10 UTC
121 points
86 comments4 min readLW link1 review

Op­ti­miz­ers: To Define or not to Define

J Bostock16 May 2021 19:55 UTC
4 points
0 comments4 min readLW link

Against Against Boredom

Logan Zoellner16 May 2021 18:19 UTC
5 points
8 comments2 min readLW link

Why Glen Weyl is a technocrat

ChristianKl16 May 2021 18:01 UTC
11 points
6 comments2 min readLW link

Power Ou­tage Chances

jefftk16 May 2021 16:40 UTC
8 points
6 comments1 min readLW link
(www.jefftk.com)

Christen­son’s “Episte­mol­ogy of Disagree­ment: The Good News”

Aidan_Kierans16 May 2021 3:58 UTC
1 point
0 comments5 min readLW link

Think­ing About Generators

jefftk16 May 2021 2:40 UTC
16 points
7 comments1 min readLW link
(www.jefftk.com)

On “Epistemic Tres­pass­ing” and In­tel­lec­tual Modesty

Aidan_Kierans16 May 2021 0:40 UTC
9 points
7 comments9 min readLW link

Re­search Mo­ti­va­tions and “The Divi­sion of Cog­ni­tive La­bor”

Aidan_Kierans16 May 2021 0:00 UTC
4 points
3 comments5 min readLW link

[Question] Sup­pose $1 billion is given to AI Safety. How should it be spent?

hunterglenn15 May 2021 23:24 UTC
23 points
2 comments1 min readLW link

[Event] Weekly Align­ment Re­search Coffee Time (05/​17)

adamShimi15 May 2021 22:07 UTC
7 points
0 comments1 min readLW link

The Pur­pose of Purpose

Gordon Seidoh Worley15 May 2021 21:00 UTC
17 points
3 comments9 min readLW link

How Can One Tell What Is Beau­tiful?

Erich_Grunewald15 May 2021 12:55 UTC
5 points
3 comments15 min readLW link
(www.erichgrunewald.com)

Tech­no­cratic Plim­soll Line

Martin Sustrik15 May 2021 8:34 UTC
53 points
16 comments5 min readLW link

In­ter­mit­tent Distil­la­tions #3

Mark Xu15 May 2021 7:13 UTC
21 points
1 comment11 min readLW link

How to com­pute the prob­a­bil­ity you are flip­ping a trick coin

lsusr15 May 2021 0:02 UTC
18 points
8 comments1 min readLW link

Un­der Pressure

Alex Hollow14 May 2021 22:04 UTC
4 points
0 comments1 min readLW link
(alexhollow.wordpress.com)

[Question] Who has ar­gued in de­tail that a cur­rent AI sys­tem is phe­nom­e­nally con­scious?

Robbo14 May 2021 22:03 UTC
8 points
2 comments1 min readLW link

Utopic Nightmares

Jozdien14 May 2021 21:24 UTC
10 points
20 comments5 min readLW link

DC Sum­mer Sols­tice Picnic

maia14 May 2021 19:49 UTC
8 points
0 comments1 min readLW link

Con­cern­ing not get­ting lost

Alex Flint14 May 2021 19:38 UTC
50 points
9 comments4 min readLW link

D&D.Sci May 2021 Eval­u­a­tion and Ruleset

abstractapplic14 May 2021 11:37 UTC
18 points
5 comments2 min readLW link

Why Democ­racy?

sxae14 May 2021 11:02 UTC
14 points
7 comments14 min readLW link

De­liber­ately Vague Lan­guage is Bullshit

lsusr14 May 2021 9:17 UTC
35 points
24 comments1 min readLW link

Zvi’s Law of No Evidence

lsusr14 May 2021 7:27 UTC
17 points
9 comments1 min readLW link

Hy­poth­e­sis Space Entropy

lsusr14 May 2021 7:21 UTC
17 points
2 comments2 min readLW link

Does but­terfly af­fect?

pchvykov14 May 2021 4:20 UTC
14 points
21 comments2 min readLW link

AXRP Epi­sode 7 - Side Effects with Vic­to­ria Krakovna

DanielFilan14 May 2021 3:50 UTC
34 points
6 comments43 min readLW link

[Question] Can Bit­coin tran­si­tion from PoW to PoS?

mukashi14 May 2021 3:43 UTC
3 points
11 comments1 min readLW link

Un­der­stand­ing the Lot­tery Ticket Hy­poth­e­sis

Alex Flint14 May 2021 0:25 UTC
50 points
9 comments8 min readLW link

Vac­cine Rol­lout as Wheeled-Lug­gage Problem

DirectedEvolution13 May 2021 21:04 UTC
28 points
23 comments3 min readLW link

Covid 5/​13: Mov­ing On

Zvi13 May 2021 14:30 UTC
69 points
13 comments17 min readLW link
(thezvi.wordpress.com)

We can un­der­stand value only through end­less self-reflection

Riccardo Volpato13 May 2021 10:22 UTC
1 point
0 comments7 min readLW link
(volpato.io)

The case for hypocrisy

Aaron Bergman13 May 2021 3:36 UTC
37 points
12 comments5 min readLW link
(aaronbergman.substack.com)

Restricted Anti­na­tal­ism on Subagents

Josephine13 May 2021 1:48 UTC
3 points
1 comment2 min readLW link

Agency in Con­way’s Game of Life

Alex Flint13 May 2021 1:07 UTC
112 points
93 comments9 min readLW link2 reviews

Mostly ques­tions about Dumb AI Kernels

HorizonHeld12 May 2021 22:00 UTC
1 point
1 comment9 min readLW link

For­mal In­ner Align­ment, Prospectus

abramdemski12 May 2021 19:57 UTC
95 points
57 comments16 min readLW link

[AN #150]: The sub­types of Co­op­er­a­tive AI research

Rohin Shah12 May 2021 17:20 UTC
17 points
0 comments6 min readLW link
(mailchi.mp)

[Question] Per­sonal Ad­vice/​Re­quest: Can I be your ap­pren­tice?

aysajan12 May 2021 16:01 UTC
13 points
1 comment1 min readLW link

How do we build or­gani­sa­tions that want to build safe AI?

sxae12 May 2021 15:08 UTC
4 points
4 comments9 min readLW link

Test­ing the FLEDGE Prototype

jefftk12 May 2021 12:40 UTC
11 points
6 comments1 min readLW link
(www.jefftk.com)

[Question] What is the strongest ar­gu­ment you know for an­tire­al­ism?

Michele Campolo12 May 2021 10:53 UTC
7 points
58 comments1 min readLW link

Her Internal

matejsuchy12 May 2021 2:05 UTC
1 point
0 comments6 min readLW link
(matejsuchy.substack.com)

Louisi­ana Gets Vac­cine Pass­ports Right

tkpwaeub12 May 2021 1:23 UTC
14 points
6 comments1 min readLW link

Thoughts on Iter­ated Distil­la­tion and Amplification

Waddington11 May 2021 21:32 UTC
9 points
2 comments20 min readLW link

Mas­sachusetts Tick-Borne Disease Distribution

jefftk11 May 2021 18:40 UTC
12 points
3 comments1 min readLW link
(www.jefftk.com)

Texas Far-Comers Meetup in Austin

SilasBarta11 May 2021 16:37 UTC
16 points
3 comments1 min readLW link

Yam­polskiy on AI Risk Skepticism

Gordon Seidoh Worley11 May 2021 14:50 UTC
18 points
5 comments1 min readLW link
(www.researchgate.net)

Med­i­ta­tions on Kotzebue

adaminoue11 May 2021 14:34 UTC
1 point
0 comments1 min readLW link
(www.inoue.today)