The easy goal in­fer­ence prob­lem is still hard

paulfchristiano3 Nov 2018 14:41 UTC
59 points
20 comments4 min readLW link

My In­tu­itions on Coun­ter­log­i­cal Reasoning

DragonGod2 Nov 2018 21:36 UTC
4 points
0 comments5 min readLW link

Embed­ded World-Models

2 Nov 2018 16:07 UTC
96 points
16 comments1 min readLW link

Kansas City SSC Read­ers Meetup

Todd3262 Nov 2018 10:45 UTC
2 points
0 comments1 min readLW link

Meta-execution

paulfchristiano1 Nov 2018 22:18 UTC
20 points
1 comment5 min readLW link

Dis­cus­sion on the ma­chine learn­ing ap­proach to AI safety

Vika1 Nov 2018 20:54 UTC
27 points
3 comments4 min readLW link

What is am­bi­tious value learn­ing?

Rohin Shah1 Nov 2018 16:20 UTC
55 points
28 comments2 min readLW link

Im­ple­men­ta­tions of immortality

Richard_Ngo1 Nov 2018 14:20 UTC
20 points
11 comments5 min readLW link
(thinkingcomplete.blogspot.com)

Linkpost: Arena’s New Open­ing Hand Rule Has Huge Im­pli­ca­tions For How We Play the Game

Zvi1 Nov 2018 12:30 UTC
11 points
1 comment1 min readLW link
(thezvi.wordpress.com)

Good­hart’s Law and Genies

thomascolthurst1 Nov 2018 1:38 UTC
15 points
5 comments9 min readLW link

Oc­to­ber gw­ern.net links

gwern1 Nov 2018 1:11 UTC
29 points
8 comments1 min readLW link
(www.gwern.net)

De­ci­sion Theory

31 Oct 2018 18:41 UTC
120 points
45 comments1 min readLW link

Two Ap­proaches to Struc­tured Concurrency

Martin Sustrik31 Oct 2018 16:20 UTC
19 points
4 comments5 min readLW link
(250bpm.com)

Prince­ton Univer­sity- En­vi­sion Con­fer­ence App Due Sun­day!

noazarur31 Oct 2018 4:39 UTC
−6 points
1 comment1 min readLW link

Open Thread Novem­ber 2018

Ben Pace31 Oct 2018 3:39 UTC
14 points
43 comments1 min readLW link

Thoughts on “On­tolog­i­cal Crises”

thomascolthurst31 Oct 2018 2:39 UTC
20 points
1 comment4 min readLW link

De­bate Rules In Ben­jamin Fran­klin’s Junto

namespace30 Oct 2018 23:42 UTC
77 points
8 comments1 min readLW link

Good Sa­mar­i­tans in experiments

Bucky30 Oct 2018 23:34 UTC
125 points
14 comments9 min readLW link

Pre­face to the se­quence on value learning

Rohin Shah30 Oct 2018 22:04 UTC
70 points
6 comments3 min readLW link

De­con­struct­ing Bi­ases In Media

Apollo1330 Oct 2018 22:03 UTC
1 point
0 comments1 min readLW link
(umich.edu)

writ­ing as the thinker’s canvas

brown30 Oct 2018 21:05 UTC
7 points
1 comment1 min readLW link

An Un­der­grad­u­ate Read­ing Of: Se­man­tic in­for­ma­tion, au­tonomous agency and non-equil­ibrium statis­ti­cal physics

ryan_b30 Oct 2018 18:36 UTC
29 points
2 comments5 min readLW link

SSC Meetup in Wash­ing­ton, DC

Robi Rahman30 Oct 2018 12:29 UTC
3 points
0 comments1 min readLW link

SSC Meetup in Rockville, MD

Robi Rahman30 Oct 2018 12:27 UTC
2 points
0 comments1 min readLW link

In­tro­duc­ing the AI Align­ment Fo­rum (FAQ)

29 Oct 2018 21:07 UTC
87 points
8 comments6 min readLW link

Embed­ded Agents

29 Oct 2018 19:53 UTC
228 points
41 comments1 min readLW link2 reviews

For­mal­iz­ing Ideal Generalization

Logan Riggs29 Oct 2018 19:46 UTC
3 points
0 comments5 min readLW link

East Coast Ra­tion­al­ist Megameetup 2018

metaperture29 Oct 2018 17:46 UTC
12 points
0 comments1 min readLW link

Align­ment Newslet­ter #30

Rohin Shah29 Oct 2018 16:10 UTC
29 points
2 comments6 min readLW link
(mailchi.mp)

Bos­ton Sols­tice 2018

jefftk28 Oct 2018 20:37 UTC
26 points
5 comments1 min readLW link

On Do­ing the Improbable

Eliezer Yudkowsky28 Oct 2018 20:09 UTC
129 points
36 comments1 min readLW link1 review

East Coast Ra­tion­al­ist Megameetup 2018

metaperture28 Oct 2018 19:23 UTC
34 points
16 comments1 min readLW link

Schools Pro­lifer­at­ing Without Practicioners

Davis_Kingsley26 Oct 2018 5:25 UTC
32 points
46 comments1 min readLW link
(www.thelastrationalist.com)

[Beta] Post-Read-Sta­tus on Lessestwrong

Raemon25 Oct 2018 23:13 UTC
21 points
4 comments1 min readLW link

In fa­vor of taboo­ing the word “val­ues” and us­ing only “pri­ori­ties” instead

chaosmage25 Oct 2018 22:28 UTC
21 points
11 comments2 min readLW link

Kansas City SSC Meetup

Todd32625 Oct 2018 9:46 UTC
2 points
0 comments1 min readLW link

Re­mem­ber­ing names and us­ing Ham­ming prompts: Ra­tion­al­ity Dojo

Chriswaterguy25 Oct 2018 5:50 UTC
2 points
0 comments1 min readLW link

When EDT=CDT, ADT Does Well

Diffractor25 Oct 2018 5:03 UTC
13 points
1 comment7 min readLW link

What will the long-term fu­ture of em­ploy­ment look like?

Richard_Ngo24 Oct 2018 19:58 UTC
10 points
8 comments6 min readLW link
(thinkingcomplete.blogspot.com)

In praise of heuristics

Bucky24 Oct 2018 15:44 UTC
39 points
27 comments7 min readLW link

Start­ing Meditation

Hazard24 Oct 2018 15:09 UTC
26 points
18 comments2 min readLW link

Games in Kocherga club: Fal­la­cy­ma­nia, Tower of Chaos, Scien­tific Discovery

Alexander23024 Oct 2018 14:48 UTC
2 points
0 comments1 min readLW link

play and spin­ning plates

brown23 Oct 2018 23:17 UTC
14 points
0 comments1 min readLW link

Cog­ni­tive En­hancers: Mechanisms And Tradeoffs

Scott Alexander23 Oct 2018 18:40 UTC
43 points
3 comments8 min readLW link
(slatestarcodex.com)

Thoughts on short timelines

Tobias_Baumann23 Oct 2018 15:54 UTC
6 points
11 comments1 min readLW link
(s-risks.org)

Mark Eichen­laub: How to de­velop sci­en­tific intuition

Kaj_Sotala23 Oct 2018 13:30 UTC
78 points
6 comments8 min readLW link
(kajsotala.fi)

Uniker­nels: No Longer an Aca­demic Exercise

Martin Sustrik23 Oct 2018 11:40 UTC
27 points
1 comment3 min readLW link
(250bpm.com)

Kansas City SSC Sun­day Meetup

Todd32623 Oct 2018 10:47 UTC
1 point
0 comments1 min readLW link

Kansas City SSC Meetup

Todd32623 Oct 2018 10:33 UTC
1 point
0 comments1 min readLW link

Pos­si­ble Dangers of the Un­re­stricted Value Learners

avturchin23 Oct 2018 9:15 UTC
11 points
4 comments5 min readLW link