EA & LW Fo­rums Weekly Sum­mary (5 − 11 Sep 22′)

Zoe WilliamsSep 12, 2022, 11:24 PM
24 points
0 comments13 min readLW link

Time is not the bot­tle­neck (on mak­ing progress think­ing about difficult things)

kmanSep 12, 2022, 8:45 PM
30 points
10 comments1 min readLW link

[Linkpost] A sur­vey on over 300 works about in­ter­pretabil­ity in deep networks

scasperSep 12, 2022, 7:07 PM
97 points
7 comments2 min readLW link
(arxiv.org)

[Question] Why do Peo­ple Think In­tel­li­gence Will be “Easy”?

DragonGodSep 12, 2022, 5:32 PM
15 points
32 comments2 min readLW link

Align­ment via proso­cial brain algorithms

Cameron BergSep 12, 2022, 1:48 PM
45 points
30 comments6 min readLW link

I’ve writ­ten a Fan­tasy Novel to Pro­mote Effec­tive Altruism

Timothy UnderwoodSep 12, 2022, 12:14 PM
23 points
21 comments13 min readLW link

Ide­olog­i­cal In­fer­ence Eng­ines: Mak­ing Deon­tol­ogy Differ­en­tiable*

Paul BricmanSep 12, 2022, 12:00 PM
6 points
0 comments14 min readLW link

Freeload­ing?

jefftkSep 12, 2022, 11:20 AM
28 points
24 comments3 min readLW link
(www.jefftk.com)

Can you force a neu­ral net­work to keep gen­er­al­iz­ing?

Q HomeSep 12, 2022, 10:14 AM
2 points
10 comments5 min readLW link

Black Box In­ves­ti­ga­tion Re­search Hackathon

Sep 12, 2022, 7:20 AM
9 points
4 comments2 min readLW link

Ar­gu­ment against 20% GDP growth from AI within 10 years [Linkpost]

aogSep 12, 2022, 4:08 AM
59 points
20 comments5 min readLW link
(twitter.com)

AI Safety field-build­ing pro­jects I’d like to see

Orpheus16Sep 11, 2022, 11:43 PM
46 points
8 comments6 min readLW link

Fermi Para­dox: Iron Age Milky Way

Rofel WodringSep 11, 2022, 8:32 PM
−10 points
9 comments3 min readLW link

You Don’t Have To Click The Links

Simon BerensSep 11, 2022, 6:13 PM
25 points
7 comments1 min readLW link

The Ul­ti­mate Step-by-Step Hiring Playbook

intellectronicaSep 11, 2022, 2:39 PM
8 points
2 comments4 min readLW link
(www.intellectronica.net)

[Question] In fore­cast­ing, how do ac­cu­racy, cal­ibra­tion and re­li­a­bil­ity re­late to each other?

amaraiSep 11, 2022, 12:04 PM
3 points
4 comments1 min readLW link

Briefly think­ing through some analogs of debate

Eli TyreSep 11, 2022, 12:02 PM
20 points
3 comments4 min readLW link

Mak­ing a New Table Leaf

jefftkSep 11, 2022, 11:40 AM
19 points
0 comments1 min readLW link
(www.jefftk.com)

AI Risk In­tro 1: Ad­vanced AI Might Be Very Bad

Sep 11, 2022, 10:57 AM
46 points
13 comments30 min readLW link

A Pin and a Bal­loon: An­thropic Frag­ility In­creases Chances of Ru­n­away Global Warm­ing

avturchinSep 11, 2022, 10:25 AM
33 points
23 comments52 min readLW link

[Question] Is there an Ul­ti­mate text ed­i­tor?

Johannes C. MayerSep 11, 2022, 9:19 AM
4 points
10 comments1 min readLW link

Pas­cal: The Great­ness and Lit­tle­ness of Man, A Think­ing Reed

NoBadCakeSep 10, 2022, 8:05 PM
9 points
0 comments1 min readLW link

[Job] Pro­ject Man­ager: Com­mu­nity Health (CEA)

XodarapSep 10, 2022, 6:40 PM
3 points
0 comments1 min readLW link
(www.centreforeffectivealtruism.org)

Un­bounded util­ity func­tions and precommitment

MichaelStJulesSep 10, 2022, 4:16 PM
4 points
3 comments1 min readLW link

[Question] What is the “Less Wrong” ap­proved acronym for 1984-risk?

Logan ZoellnerSep 10, 2022, 2:38 PM
5 points
8 comments1 min readLW link

Find out how util­i­tar­ian you are—a mega thread of philos­o­phy polls

spencergSep 10, 2022, 2:05 PM
8 points
3 comments1 min readLW link
(twitter.com)

Put Dirty Dishes in the Dishwasher

jefftkSep 10, 2022, 1:10 PM
37 points
16 comments1 min readLW link
(www.jefftk.com)

Join ASAP! (AI Safety Ac­countabil­ity Pro­gramme) 🚀

CallumMcDougallSep 10, 2022, 11:15 AM
19 points
0 comments3 min readLW link

Quintin’s al­ign­ment pa­pers roundup—week 1

Quintin PopeSep 10, 2022, 6:39 AM
120 points
6 comments9 min readLW link

Path de­pen­dence in ML in­duc­tive biases

Sep 10, 2022, 1:38 AM
68 points
13 comments10 min readLW link

Keep­ing Time in Epoch Seconds

Gordon Seidoh WorleySep 10, 2022, 12:28 AM
11 points
2 comments2 min readLW link

Ought will host a fac­tored cog­ni­tion “Lab Meet­ing”

Sep 9, 2022, 11:46 PM
35 points
1 comment1 min readLW link

Web4/​Heaven—The Simulation

Dunning K.Sep 9, 2022, 10:58 PM
26 points
2 comments1 min readLW link

Eval­u­a­tions pro­ject @ ARC is hiring a re­searcher and a web­dev/​engineer

Beth BarnesSep 9, 2022, 10:46 PM
99 points
7 comments10 min readLW link

Swap and Scale

Stephen FowlerSep 9, 2022, 10:41 PM
17 points
3 comments1 min readLW link

My emo­tional re­ac­tion to the cur­rent fund­ing situation

Sam F. BrownSep 9, 2022, 10:02 PM
105 points
36 comments5 min readLW link
(sambrown.eu)

Alex­aTM − 20 Billion Pa­ram­e­ter Model With Im­pres­sive Performance

MrThinkSep 9, 2022, 9:46 PM
5 points
0 comments1 min readLW link

[Fun][Link] Align­ment SMBC Comic

Gunnar_ZarnckeSep 9, 2022, 9:38 PM
7 points
2 comments1 min readLW link
(www.smbc-comics.com)

Gate­keeper Vic­tory: AI Box Reflection

Sep 9, 2022, 9:38 PM
6 points
6 comments9 min readLW link

In­ter­pret­ing Afford­able Housing

jefftkSep 9, 2022, 7:40 PM
16 points
0 comments1 min readLW link
(www.jefftk.com)

Lon­don Ra­tion­al­ish Meetup 2022-09-11

calmiguanaSep 9, 2022, 6:39 PM
1 point
0 comments1 min readLW link

AI al­ign­ment with hu­mans… but with which hu­mans?

geoffreymillerSep 9, 2022, 6:21 PM
12 points
33 comments3 min readLW link

[Question] Should you re­frain from hav­ing chil­dren be­cause of the risk posed by ar­tifi­cial in­tel­li­gence?

MientrasSep 9, 2022, 5:39 PM
17 points
31 comments1 min readLW link

Notes on Resolve

David GrossSep 9, 2022, 4:42 PM
9 points
3 comments31 min readLW link

Over­sight Leagues: The Train­ing Game as a Feature

Paul BricmanSep 9, 2022, 10:08 AM
20 points
6 comments10 min readLW link

Un­der­stand­ing and avoid­ing value drift

TurnTroutSep 9, 2022, 4:16 AM
48 points
14 comments6 min readLW link

Samotsvety’s AI risk forecasts

eliflandSep 9, 2022, 4:01 AM
44 points
0 comments4 min readLW link

Most Peo­ple Start With The Same Few Bad Ideas

johnswentworthSep 9, 2022, 12:29 AM
165 points
30 comments3 min readLW link

Mon­i­tor­ing for de­cep­tive alignment

evhubSep 8, 2022, 11:07 PM
135 points
8 comments9 min readLW link

[An email with a bunch of links I sent an ex­pe­rienced ML re­searcher in­ter­ested in learn­ing about Align­ment /​ x-safety.]

David Scott Krueger (formerly: capybaralet)Sep 8, 2022, 10:28 PM
47 points
1 comment5 min readLW link