LW Up­date 2018-10-01 – Pri­vate Mes­sag­ing Works

Raemon1 Oct 2018 21:28 UTC
32 points
16 comments1 min readLW link

What the Haters Hate

Jacob Falkovich1 Oct 2018 20:29 UTC
29 points
36 comments8 min readLW link

The tails com­ing apart as a strat­egy for success

Bucky1 Oct 2018 15:18 UTC
36 points
7 comments4 min readLW link

GreaterWrong—new theme and many enhancements

Said Achmiz1 Oct 2018 7:22 UTC
35 points
21 comments1 min readLW link

it’s hard to look at re­al­ity when you’ve already de­cided what re­al­ity looks like

brown1 Oct 2018 2:53 UTC
−7 points
0 comments3 min readLW link

Leto among the Machines

Virgil Kurkjian30 Sep 2018 21:17 UTC
57 points
20 comments13 min readLW link

The Un­rea­son­able Effec­tive­ness of Deep Learning

Richard_Ngo30 Sep 2018 15:48 UTC
86 points
5 comments13 min readLW link
(thinkingcomplete.blogspot.com)

An In­vi­ta­tion to Mea­sure Meditation

justinpombrio30 Sep 2018 15:10 UTC
8 points
33 comments2 min readLW link

The differ­ent kinds of confidence

masasin30 Sep 2018 14:16 UTC
6 points
5 comments6 min readLW link

What is be­ing done?

marcus_gabler30 Sep 2018 13:20 UTC
0 points
9 comments1 min readLW link

Am I un­der­stand­ing the prob­lem of fully up­dated defer­ence cor­rectly?

Davide_Zagami30 Sep 2018 10:55 UTC
3 points
1 comment1 min readLW link

EDT solves 5 and 10 with con­di­tional oracles

jessicata30 Sep 2018 7:57 UTC
61 points
8 comments13 min readLW link

bump­ing into fi­nan­cial un­known un­knowns

brown30 Sep 2018 2:39 UTC
9 points
0 comments2 min readLW link

Case Study II

abstractapplic30 Sep 2018 0:37 UTC
9 points
0 comments8 min readLW link

Crit­i­cism Schedul­ing and Privacy

Lulie29 Sep 2018 13:50 UTC
41 points
9 comments14 min readLW link

Analysing AI Actors

DragonGod29 Sep 2018 6:48 UTC
4 points
0 comments1 min readLW link
(youtu.be)

other peo­ple are oc­ca­sion­ally rather weird

brown29 Sep 2018 2:25 UTC
−5 points
1 comment2 min readLW link

Code Switch

Elo29 Sep 2018 0:32 UTC
3 points
0 comments1 min readLW link

Three Levels of Motivation

DragonGod28 Sep 2018 10:48 UTC
6 points
2 comments1 min readLW link
(docs.google.com)

Law with­out law: from ob­server states to physics via al­gorith­mic in­for­ma­tion theory

avturchin28 Sep 2018 10:07 UTC
16 points
6 comments2 min readLW link
(arxiv.org)

give the ev­i­dence not the theory

brown28 Sep 2018 4:52 UTC
2 points
3 comments1 min readLW link

At­tack­ing enlightenment

Elo28 Sep 2018 1:18 UTC
35 points
49 comments3 min readLW link

New Deep­Mind AI Safety Re­search Blog

Vika27 Sep 2018 16:28 UTC
43 points
0 comments1 min readLW link
(medium.com)

Prevent­ing s-risks via in­dex­i­cal un­cer­tainty, acausal trade and dom­i­na­tion in the multiverse

avturchin27 Sep 2018 10:09 UTC
11 points
6 comments4 min readLW link

Anti-so­cial Punishment

Martin Sustrik27 Sep 2018 7:08 UTC
309 points
66 comments6 min readLW link3 reviews

Asymp­totic De­ci­sion The­ory (Im­proved Wri­teup)

Diffractor27 Sep 2018 5:17 UTC
39 points
14 comments13 min readLW link

Thoughts on tack­ling blindspots

Hazard27 Sep 2018 1:06 UTC
41 points
7 comments1 min readLW link

Mo­ral differ­ences in mediocristan

Benquo26 Sep 2018 20:39 UTC
24 points
0 comments3 min readLW link
(benjaminrosshoffman.com)

Obli­ga­tory Altruism

manoj-nathwani25 Sep 2018 21:13 UTC
7 points
0 comments3 min readLW link
(manoj.ninja)

The Tails Com­ing Apart As Me­taphor For Life

Scott Alexander25 Sep 2018 19:10 UTC
158 points
38 comments7 min readLW link4 reviews
(slatestarcodex.com)

Direct Pri­mary Care

sarahconstantin25 Sep 2018 18:00 UTC
42 points
5 comments1 min readLW link
(srconstantin.wordpress.com)

Au­gust gw­ern.net links

gwern25 Sep 2018 15:57 UTC
17 points
0 comments1 min readLW link
(www.gwern.net)

Wire­head­ing as a po­ten­tial prob­lem with the new im­pact measure

Stuart_Armstrong25 Sep 2018 14:15 UTC
25 points
20 comments4 min readLW link

A prob­a­bil­is­tic off-switch that the agent is in­differ­ent to

Ofer25 Sep 2018 13:13 UTC
11 points
13 comments3 min readLW link

AI Read­ing Group Thoughts (2/​?): Re­con­struc­tive Psychosurgery

Alicorn25 Sep 2018 4:25 UTC
27 points
6 comments3 min readLW link

Deep learn­ing—deeper flaws?

Richard_Ngo24 Sep 2018 18:40 UTC
39 points
17 comments4 min readLW link
(thinkingcomplete.blogspot.com)

Align­ment Newslet­ter #25

Rohin Shah24 Sep 2018 16:10 UTC
18 points
3 comments9 min readLW link
(mailchi.mp)

Bridg­ing syn­tax and se­man­tics with Quine’s Gavagai

Stuart_Armstrong24 Sep 2018 14:39 UTC
19 points
2 comments2 min readLW link

Reflec­tive AIXI and Anthropics

Diffractor24 Sep 2018 2:15 UTC
18 points
14 comments8 min readLW link

Colum­bus SSC Oct. Meetup

Jim Hays24 Sep 2018 1:39 UTC
1 point
0 comments1 min readLW link

Book re­view: Hap­piness by Design

Richard_Ngo23 Sep 2018 4:30 UTC
12 points
1 comment4 min readLW link
(thinkingcomplete.blogspot.com)

Rat­pack: Book Club

two-ox-heads22 Sep 2018 22:02 UTC
1 point
0 comments1 min readLW link

(Some?) Pos­si­ble Multi-Agent Good­hart Interactions

Davidmanheim22 Sep 2018 17:48 UTC
20 points
2 comments5 min readLW link

Ad­vice Wanted; Rec­on­cile with re­li­gious parent

ChaosHufflepuff22 Sep 2018 9:54 UTC
14 points
8 comments2 min readLW link

An­nihilat­ing aliens & Rare Earth sug­gest early filter

rk21 Sep 2018 15:33 UTC
9 points
10 comments4 min readLW link

South Bay Meetup

DavidFriedman21 Sep 2018 7:05 UTC
2 points
0 comments1 min readLW link

Quan­tum the­ory can­not con­sis­tently de­scribe the use of itself

avturchin20 Sep 2018 22:04 UTC
7 points
16 comments1 min readLW link
(foundations.ethz.ch)

Memetic Tribes and Cul­ture War 2.0

Eneasz Brodski20 Sep 2018 17:58 UTC
21 points
4 comments1 min readLW link
(medium.com)

Against the bar­bell strategy

Benquo20 Sep 2018 15:19 UTC
21 points
16 comments3 min readLW link
(benjaminrosshoffman.com)

In Log­i­cal Time, All Games are Iter­ated Games

abramdemski20 Sep 2018 2:01 UTC
94 points
10 comments5 min readLW link