Crises Don’t Need Your Software

GabrielExistsMay 10, 2022, 9:06 PM
59 points
18 comments6 min readLW link

Ceiling Fan Air Filter

jefftkMay 10, 2022, 2:20 PM
18 points
9 comments1 min readLW link
(www.jefftk.com)

The limits of AI safety via debate

Marius HobbhahnMay 10, 2022, 1:33 PM
35 points
8 comments10 min readLW link

Ex­am­in­ing Arm­strong’s cat­e­gory of gen­er­al­ized models

Morgan_RogersMay 10, 2022, 9:07 AM
14 points
0 comments7 min readLW link

Dath Ilani Rule of Law

David UdellMay 10, 2022, 6:17 AM
24 points
25 comments4 min readLW link

AI safety should be made more ac­cessible us­ing non text-based media

MassimogMay 10, 2022, 3:14 AM
2 points
4 comments4 min readLW link

LessWrong Now Has Dark Mode

jimrandomhMay 10, 2022, 1:21 AM
135 points
31 comments1 min readLW link

Con­di­tions for math­e­mat­i­cal equiv­alence of Stochas­tic Gra­di­ent Des­cent and Nat­u­ral Selection

Oliver SourbutMay 9, 2022, 9:38 PM
70 points
19 comments8 min readLW link1 review
(www.oliversourbut.net)

AI Align­ment YouTube Playlists

May 9, 2022, 9:33 PM
30 points
4 comments1 min readLW link

When is AI safety re­search harm­ful?

NathanBarnardMay 9, 2022, 6:19 PM
2 points
0 comments8 min readLW link

A Bird’s Eye View of the ML Field [Prag­matic AI Safety #2]

May 9, 2022, 5:18 PM
163 points
8 comments35 min readLW link

In­tro­duc­tion to Prag­matic AI Safety [Prag­matic AI Safety #1]

May 9, 2022, 5:06 PM
80 points
3 comments6 min readLW link

Jobs: Help scale up LM al­ign­ment re­search at NYU

Sam BowmanMay 9, 2022, 2:12 PM
60 points
1 comment1 min readLW link

Micro­phone on Elec­tric Mandolin

jefftkMay 9, 2022, 2:00 PM
16 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] Thought ex­per­i­ment: Imag­ine you were as­signed to help a ran­dom per­son in your com­mu­nity be­come as peace­ful and joyful as the most peace­ful and joyful per­son you’d ever met. What would you try?

nonzerosumMay 9, 2022, 1:53 PM
5 points
5 comments1 min readLW link

[Question] Willing to be your mu­sic men­tor in ex­change for video edit­ing mentorship

monkymindMay 9, 2022, 11:57 AM
8 points
0 comments1 min readLW link

Up­dat­ing Utility Functions

May 9, 2022, 9:44 AM
41 points
6 comments8 min readLW link

Tran­scripts of in­ter­views with AI researchers

Vael GatesMay 9, 2022, 5:57 AM
170 points
9 comments2 min readLW link

[Scrib­ble] Bad Rea­sons Be­hind Differ­ent Sys­tems and a Story with No Good Moral

Rana DexsinMay 9, 2022, 5:21 AM
9 points
0 comments5 min readLW link

[Question] What is the best day to cel­e­brate Smal­lpox Erad­i­ca­tion Day?

OrbordeMay 9, 2022, 4:02 AM
7 points
6 comments1 min readLW link

A rea­son be­hind bad sys­tems, and moral im­pli­ca­tions of see­ing this reason

Edward PascalMay 9, 2022, 3:16 AM
4 points
12 comments2 min readLW link

An Alter­na­tive In­ter­pre­ta­tion of Physics

dadadarrenMay 9, 2022, 12:52 AM
18 points
10 comments5 min readLW link
(www.sleepingbeautyproblem.com)

Ion Im­plan­ta­tion: The­ory, Equip­ment, Pro­cess, Alternatives

nomagicpillMay 8, 2022, 10:30 PM
5 points
0 comments16 min readLW link
(210ethan.github.io)

[Question] Long COVID risk: How to main­tain an up to date risk as­sess­ment so we can go back to nor­mal life?

SameerishereMay 8, 2022, 7:56 PM
19 points
34 comments1 min readLW link

De­mon­strat­ing MWI by in­terfer­ing hu­man simulations

Yair HalberstadtMay 8, 2022, 5:28 PM
12 points
25 comments2 min readLW link

Notes from a con­ver­sa­tion with Ing. Agr. Adri­ana Balzarini

Pablo RepettoMay 8, 2022, 3:56 PM
5 points
0 comments2 min readLW link
(pabloernesto.github.io)

Ele­men­tary In­fra-Bayesianism

JanMay 8, 2022, 12:23 PM
41 points
3 comments7 min readLW link
(universalprior.substack.com)

Cam­bridge LW Meetup: Books That Change

May 8, 2022, 5:23 AM
5 points
0 comments1 min readLW link

Video and Tran­script of Pre­sen­ta­tion on Ex­is­ten­tial Risk from Power-Seek­ing AI

Joe CarlsmithMay 8, 2022, 3:50 AM
20 points
1 comment29 min readLW link

[Question] Al­gorith­mic for­mal­iza­tion of FDT?

ShmiMay 8, 2022, 1:36 AM
12 points
8 comments1 min readLW link

Ex­pe­rience on Meloxicam

jefftkMay 8, 2022, 12:30 AM
9 points
5 comments1 min readLW link
(www.jefftk.com)

[Question] Best open-source text­books (goal: make them col­lab­o­ra­tive)?

shuffled-cantaloupeMay 7, 2022, 11:40 PM
8 points
6 comments1 min readLW link

[Question] What does Func­tional De­ci­sion The­ory say to do in im­perfect New­comb situ­a­tions?

Daniel_EthMay 7, 2022, 10:26 PM
4 points
4 comments1 min readLW link

The glo­ri­ous en­ergy boost I’ve got­ten by ab­stain­ing from coffee

SameerishereMay 7, 2022, 8:21 PM
31 points
27 comments3 min readLW link

Sealed pre­dic­tions thread

Zach Stein-PerlmanMay 7, 2022, 6:00 PM
23 points
7 comments1 min readLW link

Min­i­mum Vi­able Alignment

HunterJayMay 7, 2022, 1:18 PM
11 points
7 comments1 min readLW link

[Linkpost] diffu­sion mag­ne­tizes man­i­folds (DALL-E 2 in­tu­ition build­ing)

Paul BricmanMay 7, 2022, 11:01 AM
1 point
0 comments1 min readLW link
(paulbricman.com)

scipy.op­ti­mize.curve_fit Is Awesome

niplavMay 7, 2022, 10:57 AM
20 points
4 comments1 min readLW link

[Question] Quote re­quest: “if even the Sun re­quires proof”

Smaug123May 7, 2022, 10:30 AM
11 points
3 comments1 min readLW link

But What’s Your *New Align­ment In­sight,* out of a Fu­ture-Text­book Para­graph?

David UdellMay 7, 2022, 3:10 AM
26 points
18 comments5 min readLW link

Seat­tle Robot Cult

lsusrMay 7, 2022, 12:25 AM
15 points
1 comment1 min readLW link

D&D.Sci Div­ina­tion: Nine Black Doves

aphyerMay 6, 2022, 11:02 PM
42 points
13 comments4 min readLW link

[Question] Is there a con­ve­nient way to make “sealed” pre­dic­tions?

Daniel KokotajloMay 6, 2022, 11:00 PM
32 points
20 comments1 min readLW link

In­no­va­tion, Stag­na­tion, and Para­trooper Operations

Davis_KingsleyMay 6, 2022, 8:59 PM
52 points
3 comments16 min readLW link

Up­grad­ing Imag­i­na­tion: The Promise Of DALL-E 2 As A Tool For Thought

TharinMay 6, 2022, 6:12 PM
10 points
0 comments5 min readLW link
(echoesandchimes.com)

Con­tra Dance Mask Policy

jefftkMay 6, 2022, 3:10 PM
14 points
10 comments2 min readLW link
(www.jefftk.com)

The case for be­com­ing a black-box in­ves­ti­ga­tor of lan­guage models

BuckMay 6, 2022, 2:35 PM
126 points
20 comments3 min readLW link

Open Prob­lems in Nega­tive Side Effect Minimization

May 6, 2022, 9:37 AM
12 points
6 comments17 min readLW link

Your Utility Func­tion is Your Utility Function

David UdellMay 6, 2022, 7:15 AM
39 points
17 comments2 min readLW link

Get­ting GPT-3 to pre­dict Me­tac­u­lus questions

MathiasKBMay 6, 2022, 6:01 AM
69 points
9 comments2 min readLW link