Why will AI be dan­ger­ous?

LegionnaireFeb 4, 2022, 11:41 PM
40 points
13 comments1 min readLW link

Anti-Parfit’s Hitchhiker

k64Feb 4, 2022, 11:37 PM
2 points
3 comments1 min readLW link

[Question] Is it ra­tio­nal to mod­ify one’s util­ity func­tion?

k64Feb 4, 2022, 11:37 PM
6 points
11 comments1 min readLW link

[Question] Blog ded­i­cated to re­build­ing tech­nol­ogy from civ col­lapse?

Casey_Feb 4, 2022, 11:28 PM
4 points
4 comments1 min readLW link

Align­ment ver­sus AI Alignment

Alex FlintFeb 4, 2022, 10:59 PM
88 points
15 comments22 min readLW link

A Quick Look At 20% Time

ElizabethFeb 4, 2022, 10:10 PM
86 points
8 comments4 min readLW link
(acesounderglass.com)

What is a “philos­o­phy of progress?”

jasoncrawfordFeb 4, 2022, 10:02 PM
10 points
0 comments2 min readLW link
(rootsofprogress.org)

Convoy

ZviFeb 4, 2022, 9:40 PM
28 points
18 comments9 min readLW link
(thezvi.wordpress.com)

[Question] Can you prove that 0 = 1?

purplelightFeb 4, 2022, 9:31 PM
−10 points
4 comments1 min readLW link

Ex­pec­ta­tions In­fluence Real­ity (and AI)

purplelightFeb 4, 2022, 9:31 PM
0 points
3 comments7 min readLW link

AI Wri­teup Part 1

SNlFeb 4, 2022, 9:16 PM
8 points
1 comment18 min readLW link

[Question] Do mesa-op­ti­miza­tion prob­lems cor­re­late with low-slack?

sudoFeb 4, 2022, 9:11 PM
1 point
1 comment1 min readLW link

Im­pact­ful Fore­cast­ing Prize for fore­cast write­ups on cu­rated Me­tac­u­lus questions

Feb 4, 2022, 8:06 PM
41 points
0 comments4 min readLW link

[un­ti­tled post]

superads91Feb 4, 2022, 7:03 PM
14 points
17 comments1 min readLW link

Money-gen­er­at­ing en­vi­ron­ments vs. wealth-build­ing en­vi­ron­ments (or “my thoughts on the stock mar­ket”)

Nicole DiekerFeb 4, 2022, 5:37 PM
7 points
9 comments7 min readLW link

[Question] Trans­fer­ring cre­dence with­out trans­fer­ring ev­i­dence?

KaarelFeb 4, 2022, 8:11 AM
11 points
6 comments3 min readLW link

Positly covid sur­vey 2: con­trol­led pro­duc­tivity data

KatjaGraceFeb 4, 2022, 7:30 AM
15 points
1 comment4 min readLW link
(worldspiritsockpuppet.com)

Play­ing With a Talk Box

jefftkFeb 4, 2022, 2:50 AM
9 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] How can I see a daily count of all words I type?

Alex_AltairFeb 4, 2022, 2:05 AM
8 points
4 comments1 min readLW link

Covid 2/​3/​22: Loos­en­ing Bounds

ZviFeb 3, 2022, 11:00 PM
53 points
4 comments16 min readLW link
(thezvi.wordpress.com)

Fore­cast­ing Newslet­ter: Jan­uary 2022

NunoSempereFeb 3, 2022, 7:22 PM
17 points
0 comments6 min readLW link

The Ur­gency of Nor­mal: An Ex­er­cise in Bounded Distrust

ZviFeb 3, 2022, 6:10 PM
46 points
3 comments11 min readLW link
(thezvi.wordpress.com)

QNR prospects are im­por­tant for AI al­ign­ment research

Eric DrexlerFeb 3, 2022, 3:20 PM
94 points
12 comments11 min readLW link1 review

On Bounded Distrust

ZviFeb 3, 2022, 2:50 PM
137 points
19 comments56 min readLW link1 review
(thezvi.wordpress.com)

Why Do I Think I Have Values?

J BostockFeb 3, 2022, 1:35 PM
22 points
9 comments2 min readLW link

Try­ing harder works, sometimes

Kaveh-SedghiFeb 3, 2022, 5:04 AM
6 points
1 comment2 min readLW link

Ob­served pat­terns around ma­jor tech­nolog­i­cal advancements

Richard Korzekwa Feb 3, 2022, 12:30 AM
44 points
15 comments11 min readLW link
(aiimpacts.org)

Con­tra In­finite Ethics, Utility Functions

kyleherndonFeb 2, 2022, 10:32 PM
6 points
9 comments1 min readLW link

Jan­uary 2022 Time Tracking

jefftkFeb 2, 2022, 10:00 PM
17 points
5 comments2 min readLW link
(www.jefftk.com)

OpenAI Solves (Some) For­mal Math Olympiad Problems

Michaël TrazziFeb 2, 2022, 9:49 PM
78 points
27 comments2 min readLW link

[Question] Is asymp­tomatic trans­mis­sion less com­mon af­ter vac­ci­na­tion?

Brendan LongFeb 2, 2022, 8:53 PM
8 points
1 comment1 min readLW link

Thoughts on AGI safety from the top

jylin04Feb 2, 2022, 8:06 PM
36 points
3 comments32 min readLW link

[Question] Good books about over­com­ing co­or­di­na­tion prob­lems?

Sean AubinFeb 2, 2022, 7:09 PM
22 points
14 comments1 min readLW link

Fe­bru­ary 2022 Open Thread

RaemonFeb 2, 2022, 6:38 PM
17 points
54 comments1 min readLW link

Vot­ing Re­sults for the 2020 Review

RaemonFeb 2, 2022, 6:37 PM
108 points
17 comments59 min readLW link

[Question] How would you go about test­ing a poli­ti­cal the­ory like Ne­ofeu­dal­ism?

FinalFormal2Feb 2, 2022, 5:09 PM
3 points
6 comments1 min readLW link

An Ex­per­i­ment in Habit Chang­ing − 5 Week Retrospective

WillaFeb 2, 2022, 5:00 PM
33 points
9 comments9 min readLW link

Com­pet­i­tive pro­gram­ming with AlphaCode

AlgonFeb 2, 2022, 4:49 PM
58 points
36 comments15 min readLW link
(deepmind.com)

[In­tro to brain-like-AGI safety] 2. “Learn­ing from scratch” in the brain

Steven ByrnesFeb 2, 2022, 1:22 PM
60 points
12 comments25 min readLW link

[Question] Are there al­ter­na­tive routes to var­i­o­late COVID in­stead of the res­pi­ra­tory tract?

df fdFeb 2, 2022, 10:45 AM
3 points
3 comments1 min readLW link

[Question] Help me un­der­stand the ra­tio­nale of the NIH to not recom­mend Flu­vox­am­ine for COVID treat­ment.

df fdFeb 2, 2022, 10:23 AM
17 points
1 comment1 min readLW link

Au­topi­lot Ethics And The Illu­sory Self

George3d6Feb 2, 2022, 10:11 AM
9 points
5 comments3 min readLW link
(www.epistem.ink)

Im­pos­si­bil­ity re­sults for un­bounded utilities

paulfchristianoFeb 2, 2022, 3:52 AM
167 points
109 comments8 min readLW link1 review

So­lar Snow Redi­rec­tor?

jefftkFeb 2, 2022, 2:20 AM
12 points
3 comments1 min readLW link
(www.jefftk.com)

Em­piri­cal Find­ings Gen­er­al­ize Sur­pris­ingly Far

jsteinhardtFeb 1, 2022, 10:30 PM
47 points
1 comment6 min readLW link
(bounded-regret.ghost.io)

Is there a bet­ter choice than “Stop After Win” (or does dou­ble-check­ing lead to failure loops)?

Nicole DiekerFeb 1, 2022, 8:33 PM
11 points
12 comments4 min readLW link

2022 ACX Pre­dic­tions: Buy/​Sell/​Hold

ZviFeb 1, 2022, 8:30 PM
30 points
2 comments18 min readLW link
(thezvi.wordpress.com)

Re­vis­it­ing Brave New World Re­vis­ited (Chap­ter 3)

Justin BullockFeb 1, 2022, 5:17 PM
5 points
0 comments10 min readLW link

Be­fore Colour TV, Peo­ple Dreamed in Black and White

Sam EnrightFeb 1, 2022, 12:50 PM
60 points
24 comments2 min readLW link

SIA be­comes SSA in the multiverse

avturchinFeb 1, 2022, 11:31 AM
7 points
35 comments5 min readLW link