D&D.Sci De­cem­ber 2022: The Boojumologist

abstractapplicDec 2, 2022, 11:39 PM
32 points
9 comments2 min readLW link

Sub­sets and quo­tients in interpretability

Erik JennerDec 2, 2022, 11:13 PM
26 points
1 comment7 min readLW link

Re­search Prin­ci­ples for 6 Months of AI Align­ment Studies

Shoshannah TekofskyDec 2, 2022, 10:55 PM
23 points
3 comments6 min readLW link

Three Fables of Mag­i­cal Girls and Longtermism

Ulisse MiniDec 2, 2022, 10:01 PM
33 points
11 comments2 min readLW link

Brun’s the­o­rem and sieve theory

Ege ErdilDec 2, 2022, 8:57 PM
31 points
1 comment73 min readLW link

Ap­ply for the ML Up­skil­ling Win­ter Camp in Cam­bridge, UK [2-10 Jan]

hannah wing-yeeDec 2, 2022, 8:45 PM
3 points
0 comments2 min readLW link

Take­off speeds, the chimps anal­ogy, and the Cul­tural In­tel­li­gence Hypothesis

NickGabsDec 2, 2022, 7:14 PM
16 points
2 comments4 min readLW link

[ASoT] Fine­tun­ing, RL, and GPT’s world prior

JozdienDec 2, 2022, 4:33 PM
45 points
8 comments5 min readLW link

NeurIPS Safety & ChatGPT. MLAISU W48

Dec 2, 2022, 3:50 PM
3 points
0 comments4 min readLW link
(newsletter.apartresearch.com)

[Question] Is ChatGPT rigth when ad­vis­ing to brush the tongue when brush­ing teeth?

ChristianKlDec 2, 2022, 2:53 PM
13 points
14 comments2 min readLW link

Jailbreak­ing ChatGPT on Re­lease Day

ZviDec 2, 2022, 1:10 PM
242 points
77 comments6 min readLW link1 review
(thezvi.wordpress.com)

De­con­fus­ing Direct vs Amor­tised Optimization

berenDec 2, 2022, 11:30 AM
134 points
19 comments10 min readLW link

In­ner and outer al­ign­ment de­com­pose one hard prob­lem into two ex­tremely hard problems

TurnTroutDec 2, 2022, 2:43 AM
149 points
22 comments47 min readLW link3 reviews

New Fea­ture: Col­lab­o­ra­tive edit­ing now sup­ports logged-out users

RobertMDec 2, 2022, 2:41 AM
10 points
0 comments1 min readLW link

Mas­ter­ing Strat­ego (Deep­mind)

svemirskiDec 2, 2022, 2:21 AM
6 points
0 comments1 min readLW link
(www.deepmind.com)

Up­date on Har­vard AI Safety Team and MIT AI Alignment

Dec 2, 2022, 12:56 AM
60 points
4 comments8 min readLW link

Quick look: cog­ni­tive dam­age from well-ad­ministered anesthesia

ElizabethDec 2, 2022, 12:40 AM
28 points
0 comments4 min readLW link
(acesounderglass.com)

Against meta-eth­i­cal hedonism

Joe CarlsmithDec 2, 2022, 12:23 AM
24 points
5 comments35 min readLW link

Lu­me­na­tors for very lazy Bri­tish people

shakeelhDec 2, 2022, 12:18 AM
16 points
3 comments1 min readLW link

Un­der­stand­ing goals in com­plex systems

Johannes C. MayerDec 1, 2022, 11:49 PM
9 points
0 comments1 min readLW link
(www.youtube.com)

A challenge for AGI or­ga­ni­za­tions, and a challenge for readers

Dec 1, 2022, 11:11 PM
302 points
33 comments2 min readLW link

Play­ing with Ae­rial Photos

jefftkDec 1, 2022, 10:50 PM
9 points
0 comments1 min readLW link
(www.jefftk.com)

Take 1: We’re not go­ing to re­verse-en­g­ineer the AI.

Charlie SteinerDec 1, 2022, 10:41 PM
38 points
4 comments4 min readLW link

Re-Ex­am­in­ing LayerNorm

Eric WinsorDec 1, 2022, 10:20 PM
127 points
12 comments5 min readLW link

The LessWrong 2021 Re­view: In­tel­lec­tual Cir­cle Expansion

Dec 1, 2022, 9:17 PM
95 points
55 comments8 min readLW link

The Plan − 2022 Update

johnswentworthDec 1, 2022, 8:43 PM
239 points
37 comments8 min readLW link1 review

Find­ing gliders in the game of life

paulfchristianoDec 1, 2022, 8:40 PM
104 points
8 comments16 min readLW link
(ai-alignment.com)

The Ma­chine Stops (Chap­ter 9)

Justin BullockDec 1, 2022, 7:20 PM
3 points
0 comments47 min readLW link

Covid 12/​1/​22: China Protests

ZviDec 1, 2022, 5:10 PM
38 points
2 comments10 min readLW link
(thezvi.wordpress.com)

ChatGPT: First Impressions

specbugDec 1, 2022, 4:36 PM
18 points
2 comments13 min readLW link
(sixeleven.in)

[LINK] - ChatGPT discussion

JanBDec 1, 2022, 3:04 PM
13 points
8 comments1 min readLW link
(openai.com)

Re­search re­quest (al­ign­ment strat­egy): Deep dive on “mak­ing AI solve al­ign­ment for us”

JanBDec 1, 2022, 2:55 PM
16 points
3 comments1 min readLW link

The­o­ries of im­pact for Science of Deep Learning

Marius HobbhahnDec 1, 2022, 2:39 PM
24 points
0 comments11 min readLW link

Safe Devel­op­ment of Hacker-AI Coun­ter­mea­sures – What if we are too late?

Erland WittkotterDec 1, 2022, 7:59 AM
3 points
0 comments14 min readLW link

Did ChatGPT just gaslight me?

TW123Dec 1, 2022, 5:41 AM
123 points
45 comments9 min readLW link
(aiwatchtower.substack.com)

SBF’s com­ments on ethics are no sur­prise to virtue ethicists

c.troutDec 1, 2022, 4:18 AM
36 points
30 comments16 min readLW link

Notes on Caution

David GrossDec 1, 2022, 3:05 AM
14 points
0 comments19 min readLW link

Reestab­lish­ing Reli­able Sources: A Sys­tem for Tag­ging URLs

Riley MuellerDec 1, 2022, 2:27 AM
7 points
1 comment3 min readLW link

Seek­ing sub­mis­sions for short AI-safety course proposals

SergioDec 1, 2022, 12:32 AM
4 points
0 comments1 min readLW link

SBF’s re­cent live in­ter­view at the DealBook Summit

agucovaNov 30, 2022, 11:11 PM
12 points
0 commentsLW link

An­nounc­ing the in­com­ing CEO for The Roots of Progress

jasoncrawfordNov 30, 2022, 11:04 PM
16 points
0 comments1 min readLW link
(rootsofprogress.org)

Has AI gone too far?

Boston AndersonNov 30, 2022, 6:49 PM
−15 points
3 comments1 min readLW link

AGI Im­pos­si­ble due to En­ergy Constrains

TheKlausNov 30, 2022, 6:48 PM
−11 points
13 comments1 min readLW link

Bi­ases are en­g­ines of cognition

Nov 30, 2022, 4:47 PM
46 points
7 comments1 min readLW link

[Question] Open phone recom­men­da­tion for Elon.

YimbyGeorgeNov 30, 2022, 3:20 PM
−13 points
3 comments1 min readLW link

Be less scared of overconfidence

benkuhnNov 30, 2022, 3:20 PM
163 points
22 comments9 min readLW link
(www.benkuhn.net)

LessWrong Lurk­shop (ap­ply by Dec 1st)

GradientDissenterNov 30, 2022, 11:41 AM
3 points
0 comments1 min readLW link

AI takeover table­top RPG: “The Treach­er­ous Turn”

Daniel KokotajloNov 30, 2022, 7:16 AM
53 points
5 comments1 min readLW link

Master plan spec: needs au­dit (logic and co­op­er­a­tive AI)

QuinnNov 30, 2022, 6:10 AM
17 points
5 comments7 min readLW link

Ne­glected cause: au­to­mated fraud de­tec­tion in academia through image analysis

Lao MeinNov 30, 2022, 5:52 AM
11 points
1 comment2 min readLW link