I Want To Believe: Ra­tional Edition

27chaos18 Nov 2014 20:00 UTC
4 points
27 comments1 min readLW link

Meetup : Saint Peters­burg, Rus­sia meetup: “Low hang­ing fruit”

efim18 Nov 2014 18:44 UTC
2 points
0 comments1 min readLW link

Meetup : MelbLW: Novem­ber So­cial Meetup

MelbourneLW18 Nov 2014 12:37 UTC
2 points
0 comments1 min readLW link

[Link] Chalmers on Com­pu­ta­tion: A first step From Physics to Me­taethics?

john_ku18 Nov 2014 10:39 UTC
1 point
2 comments1 min readLW link

Fi­nan­cial Effec­tive­ness Repository

Gunnar_Zarncke18 Nov 2014 9:57 UTC
7 points
62 comments1 min readLW link

Su­per­in­tel­li­gence 10: In­stru­men­tally con­ver­gent goals

KatjaGrace18 Nov 2014 2:00 UTC
13 points
33 comments5 min readLW link

Neo-re­ac­tionar­ies, why are you neo-re­ac­tionary?

Capla17 Nov 2014 22:31 UTC
4 points
621 comments1 min readLW link

Is this dark arts and if it, is it jus­tified?

Gleb_Tsipursky17 Nov 2014 19:00 UTC
4 points
41 comments1 min readLW link

Stable self-im­prove­ment as a re­search problem

paulfchristiano17 Nov 2014 17:51 UTC
8 points
7 comments7 min readLW link

AI caught by a mod­ule that coun­ter­fac­tu­ally doesn’t exist

Stuart_Armstrong17 Nov 2014 17:49 UTC
19 points
22 comments2 min readLW link

Can sci­ence come to un­der­stand con­scious­ness? A prob­lem of philo­soph­i­cal zom­bies (Yes, I know, P-zom­bies again.)

Capla17 Nov 2014 17:06 UTC
4 points
41 comments2 min readLW link

Sys­temic risk: a moral tale of ten in­surance companies

Stuart_Armstrong17 Nov 2014 16:43 UTC
37 points
18 comments2 min readLW link

I just in­creased my Altru­is­tic Effec­tive­ness and you should too

AABoyles17 Nov 2014 15:45 UTC
17 points
7 comments1 min readLW link

Ly­ing in ne­go­ti­a­tions: a max­i­mally bad problem

Stuart_Armstrong17 Nov 2014 15:17 UTC
22 points
3 comments3 min readLW link

Open thread, Nov. 17 - Nov. 23, 2014

MrMind17 Nov 2014 8:25 UTC
6 points
329 comments1 min readLW link

Musk on AGI Timeframes

Artaxerxes17 Nov 2014 1:36 UTC
46 points
72 comments1 min readLW link

Approximability

abramdemski17 Nov 2014 0:41 UTC
3 points
2 comments2 min readLW link

Meetup : MIRIxAt­lanta—MIRI Re­search Guide + Corrigibility

Adele_L16 Nov 2014 22:34 UTC
3 points
0 comments1 min readLW link

Group Ra­tion­al­ity Diary, Novem­ber 16-30

therufs16 Nov 2014 21:16 UTC
5 points
40 comments1 min readLW link

Agency and Life Domains

Gleb_Tsipursky16 Nov 2014 1:38 UTC
8 points
68 comments7 min readLW link

Meetup : Toronto: mak­ing hard decisions

Giles15 Nov 2014 23:41 UTC
3 points
0 comments1 min readLW link

How to build the skill and the habit of ex­per­i­men­ta­tion?

Capla15 Nov 2014 16:08 UTC
7 points
12 comments1 min readLW link

Belief Chains

ShannonFriedman15 Nov 2014 11:09 UTC
13 points
13 comments11 min readLW link

My new pa­per: Con­cept learn­ing for safe au­tonomous AI

Kaj_Sotala15 Nov 2014 7:17 UTC
26 points
16 comments1 min readLW link

Topolog­i­cal truth pred­i­cates: Towards a model of perfect Bayesian agents

Benya_Fallenstein15 Nov 2014 6:39 UTC
14 points
8 comments9 min readLW link

Or­a­cle ma­chines in­stead of topolog­i­cal truth predicates

Benya_Fallenstein15 Nov 2014 6:39 UTC
2 points
13 comments7 min readLW link

Sim­plic­ity pri­ors with re­flec­tive oracles

Benya_Fallenstein15 Nov 2014 6:39 UTC
1 point
0 comments6 min readLW link

A primer on prov­abil­ity logic

Benya_Fallenstein15 Nov 2014 6:39 UTC
8 points
3 comments4 min readLW link

Main vs. Discussion

Benya_Fallenstein15 Nov 2014 6:38 UTC
4 points
0 comments1 min readLW link

An op­ti­mal­ity re­sult for modal UDT

Benya_Fallenstein15 Nov 2014 6:38 UTC
6 points
0 comments6 min readLW link

Main vs. Discussion

Benya_Fallenstein15 Nov 2014 6:35 UTC
0 points
1 comment1 min readLW link

Pre­dic­tors that don’t try to ma­nipu­late you(?)

Benya_Fallenstein15 Nov 2014 5:53 UTC
3 points
1 comment7 min readLW link

Dumb­ing Down Hu­man Values

leplen15 Nov 2014 2:53 UTC
5 points
6 comments3 min readLW link

Op­ti­miz­ing ways to con­vey ra­tio­nal think­ing strate­gies to broad audience

Gleb_Tsipursky15 Nov 2014 1:37 UTC
9 points
22 comments1 min readLW link

Weekly LW Meetups

FrankAdamek14 Nov 2014 16:49 UTC
4 points
0 comments2 min readLW link

Meetup : A Ra­tion­al­ist’s Guide to Strength (Vienna)

AnnaLeptikon14 Nov 2014 10:52 UTC
2 points
1 comment1 min readLW link

Meetup : Ra­tion­al­ity Week­end Vienna

AnnaLeptikon14 Nov 2014 10:43 UTC
2 points
0 comments1 min readLW link

Meetup : West LA: Lin­guis­tic Relativity

abramdemski14 Nov 2014 9:46 UTC
2 points
0 comments1 min readLW link

Meetup : Wash­ing­ton, D.C.: To-Do List Hacking

RobinZ14 Nov 2014 8:27 UTC
3 points
0 comments1 min readLW link

[Link] Physics-based an­throp­ics?

Brian_Tomasik14 Nov 2014 7:02 UTC
8 points
13 comments1 min readLW link

The “best” math­e­mat­i­cally-in­formed top­ics?

Capla14 Nov 2014 3:39 UTC
24 points
113 comments3 min readLW link

The best math­e­mat­i­cally-in­formed topics

Capla14 Nov 2014 3:38 UTC
1 point
0 comments3 min readLW link

In­ten­tion­ally Rais­ing the San­ity Waterline

Gleb_Tsipursky13 Nov 2014 20:25 UTC
13 points
89 comments5 min readLW link

The germ of an idea

Stuart_Armstrong13 Nov 2014 18:58 UTC
12 points
11 comments1 min readLW link

The Athe­ist’s Tithe

Alsadius13 Nov 2014 17:22 UTC
16 points
69 comments3 min readLW link

Meetup : Bos­ton: Self Therapy

Anders_H13 Nov 2014 17:20 UTC
3 points
2 comments1 min readLW link

Link: Rob Bens­inger on Less Wrong and vegetarianism

Sysice13 Nov 2014 17:09 UTC
23 points
77 comments1 min readLW link

Meetup : Can­berra: Liar’s Dice!

DanielFilan13 Nov 2014 12:36 UTC
2 points
0 comments1 min readLW link

Others’ pre­dic­tions of your perfor­mance are usu­ally more accurate

Natha13 Nov 2014 2:17 UTC
26 points
16 comments2 min readLW link

Deriv­ing prob­a­bil­ities from causal diagrams

Manfred13 Nov 2014 0:28 UTC
10 points
8 comments3 min readLW link