What are the limits of su­per­in­tel­li­gence?

rainyApr 27, 2023, 6:29 PM
4 points
3 comments5 min readLW link

A Pro­posal for AI Align­ment: Us­ing Directly Op­pos­ing Models

Arne BApr 27, 2023, 6:05 PM
0 points
5 comments3 min readLW link

My views on “doom”

paulfchristianoApr 27, 2023, 5:50 PM
250 points
37 comments2 min readLW link1 review
(ai-alignment.com)

[un­ti­tled post]

NeuralSystem_e5e1Apr 27, 2023, 5:37 PM
3 points
0 comments1 min readLW link

An In­ter­na­tional Man­hat­tan Pro­ject for Ar­tifi­cial Intelligence

Glenn ClaytonApr 27, 2023, 5:34 PM
−11 points
2 comments5 min readLW link

Quote quiz: “drift­ing into de­pen­dence”

jasoncrawfordApr 27, 2023, 3:13 PM
7 points
6 comments1 min readLW link
(rootsofprogress.org)

Se­cond-Level Em­piri­cism: Refram­ing the Two-Child Puzzle

Richard HenageApr 27, 2023, 3:04 PM
16 points
5 comments3 min readLW link

In­ter­view with Paul Chris­ti­ano: How We Prevent the AI’s from Killing us

DalmertApr 27, 2023, 2:39 PM
12 points
0 comments1 min readLW link
(www.youtube.com)

AI #9: The Merge and the Million Tokens

ZviApr 27, 2023, 2:20 PM
36 points
8 comments53 min readLW link
(thezvi.wordpress.com)

AI doom from an LLM-plateau-ist perspective

Steven ByrnesApr 27, 2023, 1:58 PM
161 points
24 comments6 min readLW link

Ro­mance, mi­s­un­der­stand­ing, so­cial stances, and the hu­man LLM

Kaj_SotalaApr 27, 2023, 12:59 PM
75 points
32 comments16 min readLW link

“A Note on the Com­pat­i­bil­ity of Differ­ent Ro­bust Pro­gram Equil­ibria of the Pri­soner’s Dilemma”

the gears to ascensionApr 27, 2023, 7:34 AM
18 points
5 comments1 min readLW link
(arxiv.org)

AI chat­bots don’t know why they did it

skybrianApr 27, 2023, 6:57 AM
18 points
11 comments2 min readLW link
(skybrian.substack.com)

The Great Ide­olog­i­cal Con­flict: In­tu­ition­ists vs. Establishmentarians

Thoth HermesApr 27, 2023, 1:49 AM
3 points
0 comments11 min readLW link
(thothhermes.substack.com)

Au­tomat­ing the Breath Pulse

jefftkApr 27, 2023, 12:10 AM
11 points
0 comments1 min readLW link
(www.jefftk.com)

Free­dom Is All We Need

Leo GlisicApr 27, 2023, 12:09 AM
−1 points
8 comments10 min readLW link

Con­tra Yud­kowsky on Doom from Foom #2

jacob_cannellApr 27, 2023, 12:07 AM
94 points
76 comments6 min readLW link

A very non-tech­ni­cal ex­pla­na­tion of the ba­sics of in­fra-Bayesianism

David MatolcsiApr 26, 2023, 10:57 PM
62 points
9 comments9 min readLW link

LM Si­tu­a­tional Aware­ness, Eval­u­a­tion Pro­posal: Vio­lat­ing Imitation

Jacob PfauApr 26, 2023, 10:53 PM
16 points
2 comments2 min readLW link

Re­cent Database Mi­gra­tion—Re­port Bugs

RobertMApr 26, 2023, 10:19 PM
38 points
2 comments1 min readLW link

In­fra-Bayesi­anism nat­u­rally leads to the mono­ton­ic­ity prin­ci­ple, and I think this is a problem

David MatolcsiApr 26, 2023, 9:39 PM
22 points
6 comments4 min readLW link

Un­der­stand­ing new terms via etymology

corruptedCatapillarApr 26, 2023, 8:48 PM
4 points
1 comment2 min readLW link
(forum.effectivealtruism.org)

Chad Jones pa­per mod­el­ing AI and x-risk vs. growth

jasoncrawfordApr 26, 2023, 8:07 PM
39 points
7 comments2 min readLW link
(web.stanford.edu)

I was Wrong, Si­mu­la­tor The­ory is Real

Robert_AIZIApr 26, 2023, 5:45 PM
75 points
7 comments3 min readLW link
(aizi.substack.com)

$250 prize for check­ing Jake Can­nell’s Brain Efficiency

Alexander Gietelink OldenzielApr 26, 2023, 4:21 PM
123 points
170 comments2 min readLW link

My ver­sion of Si­mu­lacra Levels

Daniel KokotajloApr 26, 2023, 3:50 PM
42 points
15 comments3 min readLW link

[Question] Is the fact that we don’t ob­serve any ob­vi­ous glitch ev­i­dence that we’re not in a simu­la­tion?

Jim BuhlerApr 26, 2023, 2:57 PM
8 points
16 comments1 min readLW link

Tran­script and Brief Re­sponse to Twit­ter Con­ver­sa­tion be­tween Yann LeCunn and Eliezer Yudkowsky

ZviApr 26, 2023, 1:10 PM
190 points
51 comments10 min readLW link
(thezvi.wordpress.com)

What comes af­ter?

rogersbaconApr 26, 2023, 12:44 PM
3 points
0 comments2 min readLW link
(www.secretorum.life)

Ac­ci­den­tal Terraforming

SableApr 26, 2023, 6:49 AM
9 points
16 comments5 min readLW link
(affablyevil.substack.com)

Philos­o­phy by Paul Gra­ham Link

EniScienApr 26, 2023, 5:36 AM
21 points
4 comments1 min readLW link

Box­ing at the gym

yakimoffApr 26, 2023, 5:10 AM
1 point
0 comments1 min readLW link

Si­be­lius + drinks

yakimoffApr 26, 2023, 5:08 AM
1 point
0 comments1 min readLW link

A sim­ple pre­sen­ta­tion of AI risk arguments

Seth HerdApr 26, 2023, 2:19 AM
19 points
0 comments2 min readLW link

Archety­pal Trans­fer Learn­ing: a Pro­posed Align­ment Solu­tion that solves the In­ner & Outer Align­ment Prob­lem while adding Cor­rigible Traits to GPT-2-medium

MiguelDevApr 26, 2023, 1:37 AM
14 points
5 comments10 min readLW link

[Question] How Many Bits Of Op­ti­miza­tion Can One Bit Of Ob­ser­va­tion Un­lock?

johnswentworthApr 26, 2023, 12:26 AM
62 points
32 comments3 min readLW link

Believe in Your­self and don’t stop Improving

Johannes C. MayerApr 25, 2023, 10:34 PM
0 points
0 comments1 min readLW link

Should LW have an offi­cial list of norms?

RubyApr 25, 2023, 9:20 PM
58 points
31 comments5 min readLW link

Im­ple­ment­ing a Trans­former from scratch in PyTorch—a write-up on my experience

Mislav JurićApr 25, 2023, 8:51 PM
20 points
0 comments10 min readLW link

Ex­plor­ing the Lot­tery Ticket Hypothesis

Rauno ArikeApr 25, 2023, 8:06 PM
58 points
3 comments11 min readLW link

Ge­netic Se­quenc­ing of Wastew­a­ter: Prevalence to Rel­a­tive Abundance

jefftkApr 25, 2023, 7:30 PM
17 points
2 comments2 min readLW link
(www.jefftk.com)

[Feed­back please] New User’s Guide to LessWrong

RubyApr 25, 2023, 6:54 PM
38 points
18 comments6 min readLW link

Refram­ing the bur­den of proof: Com­pa­nies should prove that mod­els are safe (rather than ex­pect­ing au­di­tors to prove that mod­els are dan­ger­ous)

Orpheus16Apr 25, 2023, 6:49 PM
27 points
11 comments3 min readLW link
(childrenoficarus.substack.com)

LLMs for on­line dis­cus­sion moderation

Dave LindberghApr 25, 2023, 4:53 PM
12 points
3 comments3 min readLW link

AI Safety Newslet­ter #3: AI policy pro­pos­als and a new challenger approaches

ozhangApr 25, 2023, 4:15 PM
33 points
0 commentsLW link

EA might sys­tem­at­i­cally gen­er­ate a scarcity mind­set that pro­duces low-in­tegrity actors

Severin T. SeehrichApr 25, 2023, 3:50 PM
26 points
2 commentsLW link

Max Teg­mark’s new Time ar­ti­cle on how we’re in a Don’t Look Up sce­nario [Linkpost]

Jonas HallgrenApr 25, 2023, 3:41 PM
39 points
9 comments1 min readLW link
(time.com)

WHO Biolog­i­cal Risk warning

Jonas KgomoApr 25, 2023, 3:10 PM
−6 points
2 comments1 min readLW link

A Rant on Calcu­lus III

WofsenApr 25, 2023, 2:51 PM
−5 points
2 comments1 min readLW link

Briefly how I’ve up­dated since ChatGPT

rimeApr 25, 2023, 2:47 PM
48 points
2 comments2 min readLW link