A Sketch of Good Communication

Ben PaceMar 31, 2018, 10:48 PM
208 points
36 comments3 min readLW link1 review

Harry Pot­ter and the Method of En­tropy 1 [LessWrong ver­sion]

habrykaMar 31, 2018, 8:38 PM
6 points
0 comments3 min readLW link

Harry Pot­ter and the Method of Entropy

alkjashMar 31, 2018, 8:10 PM
11 points
12 comments1 min readLW link
(radimentary.wordpress.com)

Salience

TueskesMar 31, 2018, 7:52 PM
6 points
1 comment4 min readLW link

Op­por­tu­ni­ties for in­di­vi­d­ual donors in AI safety

Alex FlintMar 31, 2018, 6:37 PM
30 points
3 comments11 min readLW link

Time in Ma­chine Metaethics

Razmęk MassaräinenMar 31, 2018, 3:02 PM
2 points
1 comment6 min readLW link

Nice Things

ZviMar 31, 2018, 12:30 PM
14 points
0 comments2 min readLW link
(thezvi.wordpress.com)

Re­duc­ing Agents: When ab­strac­tions break

HazardMar 31, 2018, 12:03 AM
13 points
10 comments8 min readLW link

Syd­ney Ra­tion­al­ity Dojo—April

luminosityMar 30, 2018, 2:18 PM
1 point
0 comments1 min readLW link

The Eter­nal Grind

ZviMar 30, 2018, 11:40 AM
10 points
1 comment17 min readLW link
(thezvi.wordpress.com)

Re­ward hack­ing and Good­hart’s law by evolu­tion­ary algorithms

Jan_KulveitMar 30, 2018, 7:57 AM
18 points
5 comments1 min readLW link
(arxiv.org)

Ra­tion­al­ist Lent is over

Qiaochu_YuanMar 30, 2018, 5:57 AM
20 points
16 comments1 min readLW link

Re­solv­ing hu­man val­ues, com­pletely and adequately

Stuart_ArmstrongMar 30, 2018, 3:35 AM
32 points
30 comments12 min readLW link

Chart­ing Deaths: Real­ity vs Reported

lifelonglearnerMar 30, 2018, 12:50 AM
13 points
1 comment1 min readLW link
(owenshen24.github.io)

Site search will be down for a few hours

habrykaMar 30, 2018, 12:43 AM
4 points
0 comments1 min readLW link

Hufflepuff Cyn­i­cism on Hypocrisy

abramdemskiMar 29, 2018, 9:01 PM
21 points
78 comments5 min readLW link

2018 Pre­dic­tion Con­test—Propo­si­tions Needed

jbeshirMar 29, 2018, 3:02 PM
7 points
6 comments4 min readLW link

A frame­work for think­ing about AI timescales

Tobias_BaumannMar 29, 2018, 9:29 AM
7 points
0 commentsLW link
(s-risks.org)

Every Im­ple­men­ta­tion of You is You: An In­tu­ition Ladder

lolbifronsMar 29, 2018, 5:14 AM
3 points
47 comments3 min readLW link

Wash­ing­ton, D.C.: Meta-Meta Meetup

RobinZMar 28, 2018, 6:54 PM
2 points
0 comments1 min readLW link

Open-Cat­e­gory Classification

TurnTroutMar 28, 2018, 2:49 PM
14 points
6 comments10 min readLW link

*Deleted*

Martin BernstorffMar 28, 2018, 10:22 AM
−5 points
21 comments1 min readLW link

‘Triv­ial In­con­ve­nience Day’ Retrospective

namespaceMar 28, 2018, 5:14 AM
32 points
3 comments6 min readLW link

Karnofsky on fore­cast­ing and what sci­ence does

Rob BensingerMar 28, 2018, 1:55 AM
14 points
0 comments8 min readLW link
(80000hours.org)

The fun­da­men­tal com­ple­men­tar­ity of con­scious­ness and work

KatjaGraceMar 28, 2018, 1:20 AM
16 points
5 comments2 min readLW link
(meteuphoric.wordpress.com)

Defin­ing the ways hu­man val­ues are messy

Stuart_ArmstrongMar 27, 2018, 10:42 PM
9 points
6 comments2 min readLW link

Op­ti­mal level of hi­er­ar­chy for effec­tive al­tru­ism?

Jan_KulveitMar 27, 2018, 10:38 PM
3 points
0 comments2 min readLW link
(effective-altruism.com)

Learn Bayes Nets!

abramdemskiMar 27, 2018, 10:00 PM
54 points
8 comments2 min readLW link

Eval­u­at­ing Ex­ist­ing Ap­proaches to AGI Alignment

Gordon Seidoh WorleyMar 27, 2018, 7:57 PM
12 points
0 comments4 min readLW link
(mapandterritory.org)

The mas­ter skill of match­ing map and territory

Rafael HarthMar 27, 2018, 12:06 PM
14 points
13 comments1 min readLW link

[Preprint for com­ment­ing] Digi­tal Im­mor­tal­ity: The­ory and Pro­to­col for Indi­rect Mind Uploading

avturchinMar 27, 2018, 11:49 AM
8 points
5 comments1 min readLW link

Prob­lems with Am­plifi­ca­tion/​Distillation

Stuart_ArmstrongMar 27, 2018, 11:12 AM
29 points
7 comments10 min readLW link

GreaterWrong—sev­eral new fea­tures & enhancements

Said AchmizMar 27, 2018, 2:36 AM
15 points
3 comments1 min readLW link

Non-Ad­ver­sar­ial Good­hart and AI Risks

DavidmanheimMar 27, 2018, 1:39 AM
22 points
11 comments6 min readLW link

A Difficulty With Den­sity-Zero Exploration

DiffractorMar 27, 2018, 1:03 AM
0 points
1 comment2 min readLW link

My Thoughts on Take­off Speeds

tristanmMar 27, 2018, 12:05 AM
11 points
2 comments7 min readLW link

Helsinki SSC March meetup

Kaj_SotalaMar 26, 2018, 7:27 PM
4 points
1 comment1 min readLW link

Ba­sic model of Send­ing a Mes­sage (Com­mu­ni­ca­tion 101)

EloMar 25, 2018, 11:55 PM
4 points
5 comments3 min readLW link

On Cog­ni­tive Distortions

QuaerendoMar 25, 2018, 10:44 PM
5 points
2 comments5 min readLW link

Bro­ken images in the sequences

sfreeMar 25, 2018, 2:41 PM
7 points
5 comments1 min readLW link

The Art of the Ar­tifi­cial: In­sights from ‘Ar­tifi­cial In­tel­li­gence: A Modern Ap­proach’

TurnTroutMar 25, 2018, 6:55 AM
31 points
8 comments15 min readLW link

Diffus­ing “I can’t be that stupid”

HazardMar 24, 2018, 2:49 PM
23 points
5 comments2 min readLW link

The most im­por­tant step

JsevillamolMar 24, 2018, 12:34 PM
19 points
5 comments1 min readLW link

Idea: Open Ac­cess AI Safety Journal

Gordon Seidoh WorleyMar 23, 2018, 6:27 PM
28 points
11 comments1 min readLW link

Sys­tem­iz­ing and Hacking

SatvikBeriMar 23, 2018, 6:01 PM
40 points
1 comment1 min readLW link

LessWrong.com URL trans­fer com­plete, data im­port will run for the next few hours

habrykaMar 23, 2018, 2:40 AM
28 points
64 comments1 min readLW link

Bug Hunt—Lesser­wrong/​Less­wrong.com Browser Compatibility

RaemonMar 22, 2018, 11:24 PM
0 points
0 comments1 min readLW link

Browser Bug Hunt for LessWrong.com migration

RaemonMar 22, 2018, 11:23 PM
9 points
13 comments1 min readLW link

My Ham­mer­time Fi­nal Exam

moridinamaelMar 22, 2018, 6:40 PM
16 points
2 comments2 min readLW link

Ham­mer­time Postmortem

alkjashMar 22, 2018, 6:10 PM
40 points
13 comments4 min readLW link
(radimentary.wordpress.com)