(OLD) An Ex­tremely Opinionated An­no­tated List of My Favourite Mechanis­tic In­ter­pretabil­ity Papers

Neel NandaOct 18, 2022, 9:08 PM
72 points
5 comments12 min readLW link
(www.neelnanda.io)

Distil­led Rep­re­sen­ta­tions Re­search Agenda

Oct 18, 2022, 8:59 PM
15 points
2 comments8 min readLW link

Draft­ing a Covid Survey

jefftkOct 18, 2022, 7:30 PM
15 points
2 comments2 min readLW link
(www.jefftk.com)

How To Make Pre­dic­tion Mar­kets Use­ful For Align­ment Work

johnswentworthOct 18, 2022, 7:01 PM
97 points
18 comments2 min readLW link

A con­ver­sa­tion about Katja’s coun­ter­ar­gu­ments to AI risk

Oct 18, 2022, 6:40 PM
43 points
9 comments33 min readLW link

ACX Zurich Oc­to­ber Meetup

MBOct 18, 2022, 6:24 PM
1 point
1 comment1 min readLW link

Un­tapped Po­ten­tial at 13-18

belkarxOct 18, 2022, 6:09 PM
82 points
53 comments1 min readLW link

[Question] How easy is it to su­per­vise pro­cesses vs out­comes?

Noosphere89Oct 18, 2022, 5:48 PM
3 points
0 comments1 min readLW link

Is GitHub Copi­lot in le­gal trou­ble?

tcelferactOct 18, 2022, 4:19 PM
35 points
2 comments1 min readLW link

Me­tac­u­lus is build­ing a team ded­i­cated to AI forecasting

ChristianWilliamsOct 18, 2022, 4:08 PM
3 points
0 comments1 min readLW link

How to Take Over the Uni­verse (in Three Easy Steps)

WriterOct 18, 2022, 3:04 PM
47 points
17 comments12 min readLW link
(youtu.be)

Science of Deep Learn­ing—a tech­ni­cal agenda

Marius HobbhahnOct 18, 2022, 2:54 PM
36 points
7 comments4 min readLW link

My search for a re­li­able breakfast

tomdekanOct 18, 2022, 9:42 AM
6 points
17 comments3 min readLW link
(www.tomdekan.com)

In­finite Pos­si­bil­ity Space and the Shut­down Problem

magfrumpOct 18, 2022, 5:37 AM
9 points
0 comments2 min readLW link
(www.magfrump.net)

Au­di­tion to perform in Bay Sec­u­lar Solstice

mingyuanOct 18, 2022, 3:10 AM
25 points
3 comments1 min readLW link

De­ci­sion the­ory does not im­ply that we get to have nice things

So8resOct 18, 2022, 3:04 AM
171 points
73 comments26 min readLW link2 reviews

South Bay ACX/​LW Meetup

ISOct 18, 2022, 2:50 AM
2 points
1 comment1 min readLW link

Ver­ti­cal Flutes

jefftkOct 18, 2022, 1:40 AM
10 points
4 comments1 min readLW link
(www.jefftk.com)

Why Weren’t Hot Air Bal­loons In­vented Sooner?

Lost FuturesOct 18, 2022, 12:41 AM
115 points
52 comments6 min readLW link
(lostfutures.substack.com)

Is GPT-N bounded by hu­man ca­pa­bil­ities? No.

Cleo NardoOct 17, 2022, 11:26 PM
49 points
8 comments2 min readLW link

EA & LW Fo­rums Weekly Sum­mary (10 − 16 Oct 22′)

Zoe WilliamsOct 17, 2022, 10:51 PM
12 points
4 comments1 min readLW link

A prag­matic met­ric for Ar­tifi­cial Gen­eral Intelligence

lorepieriOct 17, 2022, 10:07 PM
6 points
0 comments1 min readLW link
(lorenzopieri.com)

They gave LLMs ac­cess to physics simulators

ryan_bOct 17, 2022, 9:21 PM
50 points
18 comments1 min readLW link
(arxiv.org)

Com­bat­ting perfectionism

tomdekanOct 17, 2022, 8:58 PM
6 points
0 comments2 min readLW link
(tomdekan.com)

Open Prob­lem in Vot­ing Theory

Scott GarrabrantOct 17, 2022, 8:42 PM
75 points
16 comments6 min readLW link

Max­i­mal Lot­tery-Lotteries

Scott GarrabrantOct 17, 2022, 8:39 PM
72 points
15 comments4 min readLW link

[Question] Creat­ing su­per­in­tel­li­gence with­out AGI

AntbOct 17, 2022, 7:01 PM
7 points
3 comments1 min readLW link

AI Safety Ideas: An Open AI Safety Re­search Platform

Esben KranOct 17, 2022, 5:01 PM
24 points
0 comments1 min readLW link

ACX/​SSC/​Ra­tion­al­ist Meetup Madi­son 10/​22

svfritzOct 17, 2022, 4:06 PM
1 point
0 comments1 min readLW link

Balsa FAQ

ZviOct 17, 2022, 12:40 PM
19 points
5 comments1 min readLW link
(thezvi.wordpress.com)

Max­i­mal Lotteries

Scott GarrabrantOct 17, 2022, 8:54 AM
77 points
11 comments7 min readLW link

Vot­ing The­ory Introduction

Scott GarrabrantOct 17, 2022, 8:48 AM
80 points
8 comments6 min readLW link

Space

Jarred FilmerOct 17, 2022, 6:34 AM
47 points
0 comments3 min readLW link

GD’s Im­plicit Bias on Separable Data

Xander DaviesOct 17, 2022, 4:13 AM
25 points
0 comments7 min readLW link

Cal­ling my First Fam­ily Dance

jefftkOct 17, 2022, 2:40 AM
6 points
0 comments3 min readLW link
(www.jefftk.com)

The harms you don’t see

ViktoriaMalyasovaOct 16, 2022, 11:45 PM
63 points
54 comments10 min readLW link

Max­i­mal lot­ter­ies for value learning

ViktoriaMalyasovaOct 16, 2022, 11:44 PM
17 points
1 comment5 min readLW link

Pop­u­lar Per­sonal Fi­nan­cial Ad­vice ver­sus the Pro­fes­sors (James Choi, NBER)

BrownHairedEeveeOct 16, 2022, 10:21 PM
17 points
5 comments2 min readLW link
(spinup-000d1a-wp-offload-media.s3.amazonaws.com)

Life, Death, and Fi­nance in the Cos­mic Mul­ti­verse

peterbOct 16, 2022, 6:57 PM
2 points
1 comment1 min readLW link

[Question] Sig­nifi­cance of the Lan­guage of Thought Hy­poth­e­sis?

DrFlaggstaffOct 16, 2022, 6:09 PM
2 points
3 comments1 min readLW link

Luck based medicine: my re­sent­ful story of be­com­ing a med­i­cal miracle

ElizabethOct 16, 2022, 5:40 PM
485 points
121 comments12 min readLW link3 reviews
(acesounderglass.com)

Age changes what you care about

DentinOct 16, 2022, 3:36 PM
141 points
37 comments2 min readLW link

Hal­i­fax, NS – Monthly Ra­tion­al­ist, EA, and ACX Meetup Kick-Off

IdeopunkOct 16, 2022, 1:17 PM
10 points
0 comments1 min readLW link

Cruxes in Katja Grace’s Counterarguments

azsantoskOct 16, 2022, 8:44 AM
16 points
0 comments7 min readLW link

Build­ing the Loft Beds

jefftkOct 16, 2022, 1:10 AM
10 points
4 comments1 min readLW link
(www.jefftk.com)

[Question] Best re­source to go from “typ­i­cal smart tech-savvy per­son” to “per­son who gets AGI risk ur­gency”?

LironOct 15, 2022, 10:26 PM
16 points
8 comments1 min readLW link

Bounded dis­trust or Bounded trust?

M. Y. ZuoOct 15, 2022, 4:41 PM
2 points
12 comments3 min readLW link

I learn bet­ter when I frame learn­ing as Vengeance for losses in­curred through ig­no­rance, and you might too

chaosmageOct 15, 2022, 12:41 PM
82 points
9 comments3 min readLW link1 review

James Nor­ris from Upgrad­able on “What is Beyond Liv­ing a Prin­ci­pled Life”—OpenPrin­ci­ples Speaker Session

ti_guoOct 15, 2022, 3:27 AM
2 points
0 comments1 min readLW link

Quick Mock Brownie

jefftkOct 15, 2022, 3:00 AM
8 points
0 comments1 min readLW link
(www.jefftk.com)