We Choose To Align AI

johnswentworth1 Jan 2022 20:06 UTC
277 points
16 comments3 min readLW link1 review

An Ob­ser­va­tion of Vav­ilov Day

Elizabeth3 Jan 2022 21:10 UTC
234 points
42 comments3 min readLW link
(acesounderglass.com)

(briefly) RaDVaC and SMTM, two things we should be doing

Eliezer Yudkowsky12 Jan 2022 6:20 UTC
227 points
79 comments3 min readLW link1 review

Brain Effi­ciency: Much More than You Wanted to Know

jacob_cannell6 Jan 2022 3:38 UTC
196 points
102 comments29 min readLW link

Look For Prin­ci­ples Which Will Carry Over To The Next Paradigm

johnswentworth14 Jan 2022 20:22 UTC
181 points
7 comments5 min readLW link1 review

Post­mortem on DIY Re­com­bi­nant Covid Vaccine

caffemacchiavelli22 Jan 2022 14:12 UTC
179 points
27 comments5 min readLW link1 review

What’s Up With Con­fus­ingly Per­va­sive Goal Direct­ed­ness?

Raemon20 Jan 2022 19:22 UTC
172 points
89 comments4 min readLW link

[In­tro to brain-like-AGI safety] 1. What’s the prob­lem & Why work on it now?

Steven Byrnes26 Jan 2022 15:23 UTC
150 points
19 comments24 min readLW link

Prizes for ELK proposals

paulfchristiano3 Jan 2022 20:23 UTC
150 points
152 comments7 min readLW link

Use Nor­mal Predictions

Jan Christian Refsgaard9 Jan 2022 15:01 UTC
145 points
67 comments6 min readLW link

More Is Differ­ent for AI

jsteinhardt4 Jan 2022 19:30 UTC
139 points
23 comments3 min readLW link1 review
(bounded-regret.ghost.io)

[New Fea­ture] Sup­port for Foot­notes!

Ruby4 Jan 2022 7:35 UTC
132 points
31 comments1 min readLW link

Third Time: a bet­ter way to work

bfinn7 Jan 2022 21:15 UTC
128 points
74 comments8 min readLW link

Long covid: prob­a­bly worth avoid­ing—some considerations

KatjaGrace16 Jan 2022 11:46 UTC
126 points
88 comments14 min readLW link
(worldspiritsockpuppet.com)

Land Ho!

Zvi20 Jan 2022 13:30 UTC
120 points
4 comments4 min readLW link
(thezvi.wordpress.com)

Fu­ture ML Sys­tems Will Be Qual­i­ta­tively Different

jsteinhardt11 Jan 2022 19:50 UTC
118 points
10 comments5 min readLW link
(bounded-regret.ghost.io)

Lives of the Cam­bridge poly­math geniuses

Owain_Evans25 Jan 2022 4:45 UTC
107 points
40 comments3 min readLW link

How To Raise Others’ Aspira­tions in 17 Easy Steps

chanamessinger6 Jan 2022 0:14 UTC
99 points
13 comments1 min readLW link

Try­ing to Keep the Gar­den Well

Tobias H16 Jan 2022 5:42 UTC
98 points
5 comments1 min readLW link

The Liar and the Scold

Tomás B.20 Jan 2022 20:31 UTC
95 points
13 comments12 min readLW link

Im­pli­ca­tions of Civ­i­liza­tional Inad­e­quacy (re­view­ing mazes/​simu­lacra/​etc)

Raemon21 Jan 2022 1:45 UTC
93 points
13 comments10 min readLW link

A one-ques­tion Tur­ing test for GPT-3

22 Jan 2022 18:17 UTC
84 points
25 comments5 min readLW link

Ac­ti­vated Char­coal for Han­gover Preven­tion: Way more than you wanted to know

Maxwell Peterson10 Jan 2022 19:26 UTC
83 points
27 comments31 min readLW link1 review

Cal­ibra­tion proverbs

Malmesbury11 Jan 2022 5:11 UTC
76 points
19 comments1 min readLW link

Sur­vey sup­ports ‘long covid is bad’ hy­poth­e­sis (very ten­ta­tive)

KatjaGrace14 Jan 2022 14:50 UTC
76 points
10 comments3 min readLW link
(worldspiritsockpuppet.com)

Challenges with Break­ing into MIRI-Style Research

Chris_Leong17 Jan 2022 9:23 UTC
75 points
15 comments3 min readLW link

Lat­eral Think­ing (AI safety HPMOR fan­fic)

SlytherinsMonster2 Jan 2022 23:50 UTC
75 points
9 comments5 min readLW link

Covid 1/​13/​22: Endgame

Zvi13 Jan 2022 18:10 UTC
75 points
2 comments10 min readLW link
(thezvi.wordpress.com)

Omicron Post #12

Zvi4 Jan 2022 15:50 UTC
75 points
21 comments11 min readLW link
(thezvi.wordpress.com)

Why do we need a NEW philos­o­phy of progress?

jasoncrawford25 Jan 2022 17:28 UTC
75 points
26 comments8 min readLW link
(rootsofprogress.org)

2020 Re­view Article

Vaniver14 Jan 2022 4:58 UTC
74 points
3 comments7 min readLW link

Covid 1/​6/​22: The Blip

Zvi6 Jan 2022 18:30 UTC
68 points
21 comments25 min readLW link
(thezvi.wordpress.com)

Why ra­tio­nal­ists should care (more) about free software

RichardJActon23 Jan 2022 17:31 UTC
66 points
42 comments5 min readLW link

List of Prob­a­bil­ity Cal­ibra­tion Exercises

Isaac King23 Jan 2022 2:12 UTC
66 points
12 comments1 min readLW link

ELK First Round Con­test Winners

26 Jan 2022 2:56 UTC
65 points
6 comments1 min readLW link

Truth­ful LMs as a warm-up for al­igned AGI

Jacob_Hilton17 Jan 2022 16:49 UTC
65 points
14 comments13 min readLW link

Omicron Post #13: Outlook

Zvi7 Jan 2022 21:20 UTC
63 points
24 comments11 min readLW link
(thezvi.wordpress.com)

Long Term Char­i­ties: Ap­ply for SFF Funding

Zvi25 Jan 2022 17:00 UTC
62 points
0 comments23 min readLW link
(thezvi.wordpress.com)

How Bad Is QWERTY, Really? A Re­view of the Liter­a­ture, such as It Is

Erich_Grunewald15 Jan 2022 12:07 UTC
61 points
11 comments15 min readLW link
(www.erichgrunewald.com)

Ap­ply for re­search in­tern­ships at ARC!

paulfchristiano3 Jan 2022 20:26 UTC
61 points
0 comments1 min readLW link

You Can Get Fluvoxamine

AppliedDivinityStudies18 Jan 2022 23:48 UTC
60 points
18 comments3 min readLW link

Shad­ows Of The Com­ing Race (1879)

Capybasilisk3 Jan 2022 15:55 UTC
57 points
5 comments7 min readLW link

ML Sys­tems Will Have Weird Failure Modes

jsteinhardt26 Jan 2022 1:40 UTC
57 points
8 comments6 min readLW link
(bounded-regret.ghost.io)

Fore­cast­ing Newslet­ter: Look­ing back at 2021

NunoSempere27 Jan 2022 20:08 UTC
57 points
6 comments9 min readLW link
(forecasting.substack.com)

Sig­nal­ing isn’t about sig­nal­ing, it’s about Goodhart

Valentine6 Jan 2022 18:49 UTC
57 points
31 comments9 min readLW link

Pa­tron Saint Holidays

Raemon26 Jan 2022 9:26 UTC
56 points
13 comments2 min readLW link

Covid 1/​20/​22: Peak Omicron

Zvi20 Jan 2022 16:20 UTC
56 points
21 comments27 min readLW link
(thezvi.wordpress.com)

Scott Alexan­der 2021 Pre­dic­tions: Mar­ket Prices—Resolution

SimonM2 Jan 2022 11:55 UTC
56 points
12 comments1 min readLW link

How I’m think­ing about GPT-N

delton13717 Jan 2022 17:11 UTC
54 points
21 comments18 min readLW link

Omicron Post #14

Zvi13 Jan 2022 18:00 UTC
53 points
21 comments9 min readLW link
(thezvi.wordpress.com)