A Story of AI Risk: In­struc­tGPT-N

peterbarnettMay 26, 2022, 11:22 PM
24 points
0 comments8 min readLW link

In­fra-Bayesi­anism Distil­la­tion: Real­iz­abil­ity and De­ci­sion Theory

Thomas LarsenMay 26, 2022, 9:57 PM
40 points
9 comments18 min readLW link

The mis­guided pur­suit of ex­is­ten­tial­ism and ab­sur­dism in com­bat­ting nihilism

SundaeMay 26, 2022, 9:17 PM
−3 points
2 comments2 min readLW link

Ex­pe­rience LessWrong with­out the Time-Wast­ing Rab­bitHole Effect

joraineMay 26, 2022, 7:09 PM
4 points
7 comments2 min readLW link

Brass Puppet

abramdemskiMay 26, 2022, 5:42 PM
63 points
4 comments2 min readLW link

Covid 5/​26/​22: I Guess I Should Re­spond To This Week’s Long Covid Study

ZviMay 26, 2022, 5:30 PM
46 points
4 comments11 min readLW link
(thezvi.wordpress.com)

A dis­cus­sion of the pa­per, “Large Lan­guage Models are Zero-Shot Rea­son­ers”

HiroSakurabaMay 26, 2022, 3:55 PM
7 points
0 comments4 min readLW link

Mo­ral Weights of Six An­i­mals, Con­sid­er­ing View­point Uncer­tainty—Seeds of Science call for reviewers

rogersbaconMay 26, 2022, 1:36 PM
9 points
2 comments1 min readLW link

CNN fea­ture vi­su­al­iza­tion in 50 lines of code

StefanHexMay 26, 2022, 11:02 AM
17 points
4 comments5 min readLW link

[Question] How much white col­lar work could be au­to­mated us­ing ex­ist­ing ML mod­els?

AMMay 26, 2022, 8:09 AM
25 points
4 comments1 min readLW link

Benign Boundary Violations

Duncan Sabien (Deactivated)May 26, 2022, 6:48 AM
207 points
84 comments18 min readLW link1 review

Here’s a List of Some of My Ideas for Blog Posts

lsusrMay 26, 2022, 5:35 AM
48 points
7 comments30 min readLW link

View and bet in Man­i­fold pre­dic­tion mar­kets on Lesswrong

Sinclair ChenMay 26, 2022, 2:41 AM
21 points
8 comments1 min readLW link

Test­ing Air Purifiers

jefftkMay 25, 2022, 11:50 PM
35 points
0 comments2 min readLW link
(www.jefftk.com)

Glass Puppet

lsusrMay 25, 2022, 11:01 PM
70 points
8 comments3 min readLW link

How to get peo­ple to pro­duce more great ex­po­si­tion? Some strate­gies and their assumptions

riceissaMay 25, 2022, 10:30 PM
26 points
10 comments3 min readLW link

[Question] Re­quest for small text­book recommendations

Alex_AltairMay 25, 2022, 10:19 PM
12 points
15 comments1 min readLW link

Science-in­formed normativity

Richard_NgoMay 25, 2022, 6:30 PM
32 points
2 comments9 min readLW link
(thinkingcomplete.blogspot.com)

Reflec­tions on a year of college

unoptimalMay 25, 2022, 4:26 PM
35 points
3 comments12 min readLW link

The “Mea­sur­ing Stick of Utility” Problem

johnswentworthMay 25, 2022, 4:17 PM
74 points
25 comments3 min readLW link

[Question] What’s The Best Place to Look When You Have A Ques­tion About x?

Chloe ThompsonMay 25, 2022, 1:51 PM
39 points
18 comments1 min readLW link

RL with KL penalties is bet­ter seen as Bayesian inference

May 25, 2022, 9:23 AM
114 points
17 comments12 min readLW link

A Quick Note on AI Scal­ing Asymptotes

alyssavanceMay 25, 2022, 2:55 AM
44 points
7 comments1 min readLW link

MERV Filters for Covid?

jefftkMay 25, 2022, 1:50 AM
35 points
11 comments4 min readLW link
(www.jefftk.com)

Visi­ble Home­less­ness in SF: A Quick Break­down of Causes

alyssavanceMay 25, 2022, 1:40 AM
209 points
32 comments2 min readLW link

au­ton­omy: the miss­ing AGI in­gre­di­ent?

nostalgebraistMay 25, 2022, 12:33 AM
69 points
12 comments6 min readLW link

Ex­plain­ing in­ner al­ign­ment to myself

Jeremy GillenMay 24, 2022, 11:10 PM
9 points
2 comments10 min readLW link

Google’s Ima­gen uses larger text encoder

Ben LivengoodMay 24, 2022, 9:55 PM
27 points
2 comments1 min readLW link

End­point Speci­fi­ca­tion, or Good Help is Hard to Find

ACrackedPotMay 24, 2022, 9:00 PM
8 points
0 comments8 min readLW link

Game The­ory and Part­ner Abuse

arielleplusMay 24, 2022, 8:03 PM
−10 points
5 comments16 min readLW link

Manda­tory Post About Monkeypox

ZviMay 24, 2022, 8:00 PM
54 points
17 comments9 min readLW link
(thezvi.wordpress.com)

I only be­lieve in the paranormal

MalmesburyMay 24, 2022, 12:15 PM
94 points
8 comments2 min readLW link

Why I Define My Ex­pe­rience At the Monas­tic Academy As Sex­ual Assault

HS2021May 24, 2022, 8:17 AM
72 points
24 comments15 min readLW link

The No Free Lunch the­o­rems and their Razor

Adrià Garriga-alonsoMay 24, 2022, 6:40 AM
56 points
3 comments9 min readLW link

Syn­thetic Me­dia and The Fu­ture of Film

ifalphaMay 24, 2022, 5:54 AM
35 points
14 comments8 min readLW link

Com­plex Sys­tems for AI Safety [Prag­matic AI Safety #3]

May 24, 2022, 12:00 AM
58 points
3 comments21 min readLW link

Con­tra As­tral Codex Ten’s “On Sexy In-Laws”

Dalton MaberyMay 23, 2022, 10:53 PM
1 point
0 comments5 min readLW link

Why I’m Wor­ried About AI

peterbarnettMay 23, 2022, 9:13 PM
22 points
2 comments12 min readLW link

Bits of Op­ti­miza­tion Can Only Be Lost Over A Distance

johnswentworthMay 23, 2022, 6:55 PM
31 points
18 comments2 min readLW link

[Question] [Align­ment] Is there a cen­sus on who’s work­ing on what?

CedarMay 23, 2022, 3:33 PM
23 points
6 comments1 min readLW link

[fic­tion]A Ques­tion of Perspective

EliasMay 23, 2022, 3:06 PM
17 points
1 comment3 min readLW link

Find­ing Your Voice

EvenflairMay 23, 2022, 2:43 PM
12 points
0 comments1 min readLW link
(guildoftherose.org)

Science for the Pos­si­ble World

Zechen ZhangMay 23, 2022, 2:01 PM
7 points
0 comments3 min readLW link

Mon­key­pox: ex­plain­ing the jump to Europe

DirectedEvolutionMay 23, 2022, 9:53 AM
44 points
10 comments5 min readLW link

AXRP Epi­sode 15 - Nat­u­ral Ab­strac­tions with John Wentworth

DanielFilanMay 23, 2022, 5:40 AM
34 points
1 comment58 min readLW link

PSA: The Se­quences don’t need to be read in sequence

kaveMay 23, 2022, 2:53 AM
87 points
7 comments1 min readLW link

Gra­da­tions of Agency

Daniel KokotajloMay 23, 2022, 1:10 AM
41 points
6 comments5 min readLW link

How cur­ing ag­ing could help progress

jasoncrawfordMay 22, 2022, 10:43 PM
52 points
19 comments1 min readLW link
(rootsofprogress.org)

[Question] Help! What do I say at my wed­ding?

Jonathan TaskMay 22, 2022, 8:08 PM
7 points
10 comments1 min readLW link

Ad­ver­sar­ial at­tacks and op­ti­mal control

JanMay 22, 2022, 6:22 PM
17 points
7 comments8 min readLW link
(universalprior.substack.com)