On Defense Mechanisms

Quaerendo4 Mar 2018 18:53 UTC
25 points
22 comments3 min readLW link

Cor­rect Models Are Bad

sapphire4 Mar 2018 16:51 UTC
2 points
6 comments1 min readLW link
(brianlui.dog)

[Paper] Sur­viv­ing global risks through the preser­va­tion of hu­man­ity’s data on the Moon

avturchin4 Mar 2018 7:07 UTC
4 points
5 comments1 min readLW link

Beta-Beta – Re­cent Discussion

Radmin4 Mar 2018 5:34 UTC
12 points
6 comments1 min readLW link

Mur­phy’s Quest Ch 1: Ex­po­sure Therapy

alkjash4 Mar 2018 4:50 UTC
25 points
5 comments3 min readLW link
(radimentary.wordpress.com)

Mur­phy’s Quest Ch 2: Empiricism

alkjash4 Mar 2018 4:50 UTC
24 points
4 comments5 min readLW link
(radimentary.wordpress.com)

Is there a Con­nec­tion Between Great­ness in Math and Philos­o­phy?

Scott Garrabrant3 Mar 2018 23:25 UTC
13 points
6 comments1 min readLW link

Fund­ing for AI al­ign­ment research

paulfchristiano3 Mar 2018 21:52 UTC
39 points
24 comments1 min readLW link
(docs.google.com)

Fund­ing for in­de­pen­dent AI al­ign­ment research

paulfchristiano3 Mar 2018 21:44 UTC
4 points
1 comment1 min readLW link
(docs.google.com)

The Jor­dan Peter­son Mask

Jacob Falkovich3 Mar 2018 19:49 UTC
54 points
154 comments12 min readLW link

Sa­cred Cash

Zvi3 Mar 2018 13:20 UTC
27 points
29 comments3 min readLW link
(thezvi.wordpress.com)

In­ter­ac­tive Bayes The­o­rem Visualization

Allen Kim3 Mar 2018 4:00 UTC
14 points
5 comments1 min readLW link
(allenkim67.github.io)

Monthly Meta: Com­mon Knowledge

Chris_Leong3 Mar 2018 0:05 UTC
17 points
14 comments1 min readLW link

So­cial Technology

Samo Burja2 Mar 2018 19:54 UTC
13 points
3 comments11 min readLW link

Im­proved re­gret bound for DRL

Vanessa Kosoy2 Mar 2018 12:49 UTC
0 points
0 comments1 min readLW link

March 2018 Me­dia Thread

ArisKatsaris2 Mar 2018 1:06 UTC
1 point
15 comments1 min readLW link

Quick Nate/​Eliezer com­ments on discontinuity

Rob Bensinger1 Mar 2018 22:03 UTC
43 points
1 comment2 min readLW link

Ham­mer­time In­ter­mis­sion #2

alkjash1 Mar 2018 18:20 UTC
23 points
7 comments1 min readLW link
(radimentary.wordpress.com)

Ms. Blue, meet Mr. Green

alexei1 Mar 2018 13:43 UTC
38 points
27 comments12 min readLW link

Beyond al­gorith­mic equiv­alence: self-modelling

Stuart_Armstrong1 Mar 2018 13:31 UTC
0 points
0 comments1 min readLW link
(www.lesserwrong.com)

Beyond al­gorith­mic equiv­alence: al­gorith­mic noise

Stuart_Armstrong1 Mar 2018 13:31 UTC
0 points
0 comments1 min readLW link
(www.lesserwrong.com)

Friendship

alkjash1 Mar 2018 6:00 UTC
23 points
16 comments3 min readLW link
(radimentary.wordpress.com)

Kid­neys, trade, sa­cred­ness, and space travel

Benquo1 Mar 2018 5:20 UTC
15 points
34 comments3 min readLW link
(benjaminrosshoffman.com)

Am­bi­guity Detection

TurnTrout1 Mar 2018 4:23 UTC
11 points
8 comments4 min readLW link

Ex­tended Quote on the In­sti­tu­tion of Academia

Ben Pace1 Mar 2018 2:58 UTC
54 points
23 comments9 min readLW link

How safe “safe” AI de­vel­op­ment?

Gordon Seidoh Worley28 Feb 2018 23:21 UTC
9 points
1 comment1 min readLW link

Beyond al­gorith­mic equiv­alence: self-modelling

Stuart_Armstrong28 Feb 2018 16:55 UTC
10 points
3 comments1 min readLW link

Beyond al­gorith­mic equiv­alence: al­gorith­mic noise

Stuart_Armstrong28 Feb 2018 16:55 UTC
10 points
4 comments2 min readLW link

Us­ing the uni­ver­sal prior for log­i­cal un­cer­tainty (re­tracted)

cousin_it28 Feb 2018 13:07 UTC
15 points
13 comments2 min readLW link

2/​27/​08 Up­date – Front­page 3.0

Raemon28 Feb 2018 6:26 UTC
15 points
21 comments1 min readLW link

TDT for Humans

alkjash28 Feb 2018 5:40 UTC
26 points
7 comments5 min readLW link
(radimentary.wordpress.com)

Set Up for Suc­cess: In­sights from ‘Naïve Set The­ory’

TurnTrout28 Feb 2018 2:01 UTC
30 points
40 comments3 min readLW link

In­tu­ition should be ap­plied at the low­est pos­si­ble level

Rafael Harth27 Feb 2018 22:58 UTC
10 points
9 comments1 min readLW link

The sad state of Ra­tion­al­ity Zürich—Effec­tive Altru­ism Zürich included

roland27 Feb 2018 14:51 UTC
−8 points
50 comments3 min readLW link

The worst trol­ley prob­lem in the world

CronoDAS27 Feb 2018 3:56 UTC
1 point
1 comment1 min readLW link

Cat­e­gories of Sacredness

Zvi27 Feb 2018 2:00 UTC
21 points
35 comments8 min readLW link
(thezvi.wordpress.com)

More on the Lin­ear Utility Hy­poth­e­sis and the Lev­er­age Prior

AlexMennen26 Feb 2018 23:53 UTC
16 points
4 comments9 min readLW link

Goal Factoring

alkjash26 Feb 2018 23:30 UTC
27 points
4 comments2 min readLW link
(radimentary.wordpress.com)

In­con­ve­nience Is Qual­i­ta­tively Bad

Alicorn26 Feb 2018 23:27 UTC
82 points
52 comments2 min readLW link

The Ham­ming Prob­lem of Group Rationality

PDV26 Feb 2018 18:59 UTC
6 points
36 comments1 min readLW link

Focusing

alkjash26 Feb 2018 6:10 UTC
20 points
21 comments3 min readLW link
(radimentary.wordpress.com)

Map­ping the Archipelago

alkjash26 Feb 2018 5:09 UTC
14 points
24 comments1 min readLW link

Ex­per­i­men­tal Open Threads

Chris_Leong26 Feb 2018 3:13 UTC
22 points
5 comments1 min readLW link

Walk­through of ‘For­mal­iz­ing Con­ver­gent In­stru­men­tal Goals’

TurnTrout26 Feb 2018 2:20 UTC
10 points
2 comments10 min readLW link

Will AI See Sud­den Progress?

KatjaGrace26 Feb 2018 0:41 UTC
27 points
11 comments1 min readLW link1 review

Self-reg­u­la­tion of safety in AI research

Gordon Seidoh Worley25 Feb 2018 23:17 UTC
12 points
6 comments2 min readLW link

The abrupt­ness of nu­clear weapons

paulfchristiano25 Feb 2018 17:40 UTC
47 points
35 comments2 min readLW link

Like­li­hood of dis­con­tin­u­ous progress around the de­vel­op­ment of AGI

vedevazz25 Feb 2018 15:13 UTC
4 points
2 comments1 min readLW link
(aiimpacts.org)

Open-Source Monasticism

Nathan Rosquist25 Feb 2018 13:52 UTC
25 points
7 comments4 min readLW link

Pass­ing Troll Bridge

Diffractor25 Feb 2018 8:21 UTC
11 points
2 comments10 min readLW link