The con­ver­gent dy­namic we missed

RemmeltDec 12, 2023, 11:19 PM
2 points
2 commentsLW link

A Kind­ness, or The Inevitable Con­se­quence of Perfect In­fer­ence (a short story)

samhealyDec 12, 2023, 11:03 PM
6 points
0 comments9 min readLW link

Love, Rev­er­ence, and Life

Dec 12, 2023, 9:49 PM
36 points
9 comments28 min readLW link2 reviews

Ta­boo “pro­cras­ti­na­tion”

Neil Dec 12, 2023, 9:33 PM
19 points
7 comments1 min readLW link

En­hanc­ing in­tel­li­gence by bang­ing your head on the wall

BezziDec 12, 2023, 9:00 PM
38 points
26 comments1 min readLW link

Yamaha P-Series Overview

jefftkDec 12, 2023, 8:30 PM
10 points
1 comment1 min readLW link
(www.jefftk.com)

Balsa Up­date and Gen­eral Thank You

ZviDec 12, 2023, 8:30 PM
61 points
8 comments8 min readLW link
(thezvi.wordpress.com)

Towards an Ethics Calcu­la­tor for Use by an AGI

sweenesmDec 12, 2023, 6:37 PM
3 points
2 comments11 min readLW link

Why Psy­chol­o­gists Are Wrong About The Illu­sion Of Ex­plana­tory Depth

moses onyedikachukwuDec 12, 2023, 6:32 PM
1 point
0 comments4 min readLW link

A de­sign con­cept for su­per­in­tel­li­gent ma­chines (and Pop­per’s cri­tique of in­duc­tion)

tiplur-bilrexDec 12, 2023, 6:31 PM
−7 points
6 comments1 min readLW link
(tiplur-bilrex.tlon.network)

Sig­nifi­cantly En­hanc­ing Adult In­tel­li­gence With Gene Edit­ing May Be Possible

Dec 12, 2023, 6:14 PM
459 points
206 comments33 min readLW link2 reviews

[Question] Why No Au­to­mated Plagerism De­tec­tion For Past Papers?

Lao MeinDec 12, 2023, 5:24 PM
7 points
10 comments1 min readLW link

OpenAI: Leaks Con­firm the Story

ZviDec 12, 2023, 2:00 PM
77 points
9 comments16 min readLW link
(thezvi.wordpress.com)

Nav­i­gat­ing the Attackspace

Jonas KgomoDec 12, 2023, 1:59 PM
1 point
0 comments2 min readLW link

Non­lin­ear’s Ev­i­dence: De­bunk­ing False and Mislead­ing Claims

KatWoodsDec 12, 2023, 1:16 PM
104 points
171 commentsLW link

AI In­sti­tu­tion De­sign Hackathon (EAG Bay Area Satel­lite Event)

Dec 12, 2023, 1:10 PM
1 point
0 comments1 min readLW link

Fund­ing case: AI Safety Camp 10

Dec 12, 2023, 9:08 AM
66 points
5 comments6 min readLW link
(manifund.org)

What is the next level of ra­tio­nal­ity?

Dec 12, 2023, 8:14 AM
48 points
24 comments7 min readLW link

Embed­ded Agents are Quines

Dec 12, 2023, 4:57 AM
11 points
7 comments8 min readLW link

Pre­dict the fu­ture! Earn fake in­ter­net points! Get a (free) gam­bling ad­dic­tion!

Robert CousineauDec 12, 2023, 4:39 AM
3 points
0 comments1 min readLW link

The likely first longevity drug is based on sketchy sci­ence. This is bad for sci­ence and bad for longevity.

BobBurgersDec 12, 2023, 2:42 AM
161 points
34 comments5 min readLW link

When will GPT-5 come out? Pre­dic­tion mar­kets vs. Extrapolation

MalteDec 12, 2023, 2:41 AM
12 points
9 comments3 min readLW link

On plans for a func­tional society

Dec 12, 2023, 12:07 AM
41 points
8 comments13 min readLW link

Se­condary Risk Markets

VaniverDec 11, 2023, 9:52 PM
35 points
4 comments4 min readLW link

Has any­one ex­per­i­mented with Do­drio, a tool for ex­plor­ing trans­former mod­els through in­ter­ac­tive vi­su­al­iza­tion?

Bill BenzonDec 11, 2023, 8:34 PM
4 points
0 comments1 min readLW link

[Valence se­ries] 3. Valence & Beliefs

Steven ByrnesDec 11, 2023, 8:21 PM
77 points
12 comments21 min readLW link1 review

[Question] Am I eth­i­cally obli­gated to ex­tend the life of my dog with life-ex­ten­sion treat­ments about to hit the mar­ket?

TrudosKudosDec 11, 2023, 7:41 PM
−3 points
2 comments1 min readLW link

Ad­ver­sar­ial Ro­bust­ness Could Help Prevent Catas­trophic Misuse

aogDec 11, 2023, 7:12 PM
30 points
18 comments9 min readLW link

The Con­scious­ness Box

GradualImprovementDec 11, 2023, 4:45 PM
33 points
24 comments4 min readLW link

Em­piri­cal work that might shed light on schem­ing (Sec­tion 6 of “Schem­ing AIs”)

Joe CarlsmithDec 11, 2023, 4:30 PM
8 points
0 comments21 min readLW link

Into AI Safety: Epi­sode 3

jacobhaimesDec 11, 2023, 4:30 PM
6 points
0 comments1 min readLW link
(into-ai-safety.github.io)

Im­plic­itly Typed C

jefftkDec 11, 2023, 4:10 PM
16 points
0 comments1 min readLW link
(www.jefftk.com)

37C3 Hacker x Ra­tion­al­ist Meetup

Dec 11, 2023, 4:02 PM
5 points
5 comments1 min readLW link

re: Yud­kowsky on biolog­i­cal materials

bhauthDec 11, 2023, 1:28 PM
182 points
30 comments5 min readLW link

Ideoculture

elvDec 11, 2023, 10:29 AM
8 points
2 comments6 min readLW link

Quick thoughts on the im­pli­ca­tions of multi-agent views of mind on AI takeover

Kaj_SotalaDec 11, 2023, 6:34 AM
47 points
14 comments4 min readLW link

Au­dit­ing failures vs con­cen­trated failures

Dec 11, 2023, 2:47 AM
47 points
1 comment7 min readLW link1 review

Deeply Cover Car Crashes?

jefftkDec 10, 2023, 10:20 PM
36 points
32 comments1 min readLW link
(www.jefftk.com)

Prin­ci­ples For Product Li­a­bil­ity (With Ap­pli­ca­tion To AI)

johnswentworthDec 10, 2023, 9:27 PM
37 points
55 comments10 min readLW link

[Question] What do you do to re­mem­ber and refer­ence the LessWrong posts that were most per­son­ally sig­nifi­cant to you, in terms of in­tel­lec­tual de­vel­op­ment or gen­eral use­ful­ness?

lillybaeumDec 10, 2023, 5:52 PM
5 points
7 comments1 min readLW link

[Question] Do web­sites and apps ac­tu­ally gen­er­ally get worse af­ter up­dates, or is it just an effect of the fear of change?

lillybaeumDec 10, 2023, 5:26 PM
36 points
35 comments2 min readLW link1 review

How LDT helps re­duce the AI arms race

Tamsin LeakeDec 10, 2023, 4:21 PM
65 points
13 comments4 min readLW link
(carado.moe)

Un­der­stand­ing Sub­jec­tive Probabilities

Isaac KingDec 10, 2023, 6:03 AM
30 points
16 comments10 min readLW link

Send us ex­am­ple gnarly bugs

Dec 10, 2023, 5:23 AM
77 points
10 comments2 min readLW link

Con­cep­tual co­her­ence for con­crete cat­e­gories in hu­mans and LLMs

Bill BenzonDec 9, 2023, 11:49 PM
13 points
1 comment2 min readLW link

2d ai-part­ners as a com­pre­hen­sive mo­ti­va­tion tool

AiresJLDec 9, 2023, 9:59 PM
3 points
0 comments1 min readLW link

Without—MicroFic­tion 250 words

Carissa CassielDec 9, 2023, 9:49 PM
20 points
1 comment1 min readLW link

Some nega­tive steganog­ra­phy results

Fabien RogerDec 9, 2023, 8:22 PM
60 points
5 comments2 min readLW link

Sum­ming up “Schem­ing AIs” (Sec­tion 5)

Joe CarlsmithDec 9, 2023, 3:48 PM
2 points
1 comment11 min readLW link

The Offense-Defense Balance Rarely Changes

Maxwell TabarrokDec 9, 2023, 3:21 PM
77 points
23 comments3 min readLW link
(maximumprogress.substack.com)