AllJan
Page 1

Refram­ing Su­per­in­tel­li­gence: Com­pre­hen­sive AI Ser­vices as Gen­eral Intelligence

rohinmshah
8 Jan 2019 7:12 UTC
83 points
55 comments5 min readLW link
(www.fhi.ox.ac.uk)

The 3 Books Tech­nique for Learn­ing a New Skilll

mr-hire
9 Jan 2019 12:45 UTC
77 points
5 comments2 min readLW link

[Question] Why is so much dis­cus­sion hap­pen­ing in pri­vate Google Docs?

Wei_Dai
12 Jan 2019 2:19 UTC
76 points
18 comments1 min readLW link

Book Re­view: The Struc­ture Of Scien­tific Revolutions

Scott Alexander
9 Jan 2019 7:10 UTC
75 points
23 comments19 min readLW link

Se­quence in­tro­duc­tion: non-agent and mul­ti­a­gent mod­els of mind

Kaj_Sotala
7 Jan 2019 14:12 UTC
74 points
4 comments6 min readLW link

Strat­egy is the De­con­fu­sion of Action

ryan_b
2 Jan 2019 20:56 UTC
73 points
4 comments6 min readLW link

[Question] Does anti-malaria char­ity de­stroy the lo­cal anti-malaria in­dus­try?

Viliam
5 Jan 2019 19:04 UTC
64 points
16 comments1 min readLW link

Com­ments on CAIS

ricraz
12 Jan 2019 15:20 UTC
61 points
12 comments7 min readLW link

[Question] What are the open prob­lems in Hu­man Ra­tion­al­ity?

Raemon
13 Jan 2019 4:46 UTC
59 points
35 comments1 min readLW link

Learn­ing-In­ten­tions vs Do­ing-In­ten­tions

Ruby
1 Jan 2019 22:22 UTC
58 points
14 comments4 min readLW link

Book Sum­mary: Con­scious­ness and the Brain

Kaj_Sotala
16 Jan 2019 14:43 UTC
58 points
5 comments26 min readLW link

Two More De­ci­sion The­ory Prob­lems for Humans

Wei_Dai
4 Jan 2019 9:00 UTC
56 points
12 comments2 min readLW link

I want it my way!

nickhayes
4 Jan 2019 18:08 UTC
49 points
2 comments9 min readLW link

Book Recom­men­da­tions: An Every­one Cul­ture and Mo­ral Mazes

sarahconstantin
10 Jan 2019 21:40 UTC
47 points
13 comments3 min readLW link

Com­bat vs Nur­ture & Meta-Contrarianism

abramdemski
10 Jan 2019 23:17 UTC
46 points
7 comments4 min readLW link

Op­ti­miz­ing for Sto­ries (vs Op­ti­miz­ing Real­ity)

Ruby
7 Jan 2019 8:03 UTC
43 points
11 comments7 min readLW link

CDT=EDT=UDT

abramdemski
13 Jan 2019 23:46 UTC
42 points
9 comments12 min readLW link

AI safety with­out goal-di­rected behavior

rohinmshah
7 Jan 2019 7:48 UTC
40 points
9 comments4 min readLW link

Non-Con­se­quen­tial­ist Co­op­er­a­tion?

abramdemski
11 Jan 2019 9:15 UTC
40 points
15 comments7 min readLW link

Will hu­mans build goal-di­rected agents?

rohinmshah
5 Jan 2019 1:33 UTC
38 points
36 comments6 min readLW link

Me­gapro­ject management

ryan_b
11 Jan 2019 17:08 UTC
37 points
3 comments5 min readLW link

Lit­tle­wood’s Law and the Global Media

gwern
12 Jan 2019 17:46 UTC
37 points
3 commentsLW link
(www.gwern.net)

[Question] What is a rea­son­able out­side view for the fate of so­cial move­ments?

jacobjacob
4 Jan 2019 0:21 UTC
36 points
27 comments1 min readLW link

[Question] What are ques­tions?

DonyChristie
9 Jan 2019 7:37 UTC
35 points
17 comments2 min readLW link

Some Thoughts on My Psy­chi­a­try Practice

Lara_Foster
16 Jan 2019 23:16 UTC
35 points
8 comments4 min readLW link

Align­ment Newslet­ter #39

rohinmshah
1 Jan 2019 8:10 UTC
33 points
2 comments5 min readLW link

Disad­van­tages of Card Rebalancing

Zvi
6 Jan 2019 23:30 UTC
33 points
5 comments18 min readLW link

One Web­site To Rule Them All?

anna_macdonald
11 Jan 2019 19:14 UTC
32 points
17 comments10 min readLW link

Time Biases

PeterMcCluskey
12 Jan 2019 21:35 UTC
31 points
0 comments6 min readLW link
(www.bayesianinvestor.com)

[Question] What ex­er­cises go best with 3 blue 1 brown’s Lin­ear Alge­bra videos?

Raemon
1 Jan 2019 21:29 UTC
30 points
10 comments1 min readLW link

Bay Area SSC Meetup (spe­cial guest Steve Hsu)

Scott Alexander
3 Jan 2019 3:02 UTC
30 points
0 comments1 min readLW link

LW Up­date 2018-1-09 – Ques­tion Up­dates, UserPro­file Sorting

Raemon
9 Jan 2019 22:34 UTC
30 points
0 comments1 min readLW link

And My Ax­iom! In­sights from ‘Com­putabil­ity and Logic’

TurnTrout
16 Jan 2019 19:48 UTC
30 points
7 comments8 min readLW link

[Question] What are the com­po­nents of in­tel­lec­tual hon­esty?

abramdemski
15 Jan 2019 20:00 UTC
30 points
4 comments1 min readLW link

Direc­tions and desider­ata for AI alignment

paulfchristiano
13 Jan 2019 7:47 UTC
29 points
1 comment14 min readLW link

Towards no-math, graph­i­cal in­struc­tions for pre­dic­tion markets

ryan_b
4 Jan 2019 16:39 UTC
29 points
9 comments2 min readLW link

Towards for­mal­iz­ing universality

paulfchristiano
13 Jan 2019 20:39 UTC
29 points
18 comments18 min readLW link

Su­per­vis­ing strong learn­ers by am­plify­ing weak experts

paulfchristiano
6 Jan 2019 7:00 UTC
28 points
0 comments1 min readLW link
(arxiv.org)

Vi­su­al­iz­ing the power of mul­ti­ple step se­lec­tion pro­cesses in JS: Gal­ton’s bean machine

gwern
12 Jan 2019 17:58 UTC
27 points
2 commentsLW link
(www.gwern.net)

AlphaGo Zero and ca­pa­bil­ity amplification

paulfchristiano
9 Jan 2019 0:40 UTC
25 points
23 comments2 min readLW link

CDT Dutch Book

abramdemski
13 Jan 2019 0:10 UTC
25 points
5 comments2 min readLW link

Open Thread Jan­uary 2019

Raemon
9 Jan 2019 20:25 UTC
24 points
46 comments1 min readLW link

[Speech] Wor­lds That Never Were

mingyuan
12 Jan 2019 19:53 UTC
24 points
0 comments3 min readLW link

An­throp­ics: Full Non-in­dex­i­cal Con­di­tion­ing (FNC) is inconsistent

Stuart_Armstrong
14 Jan 2019 15:03 UTC
22 points
4 comments2 min readLW link

What AI Safety Re­searchers Have Writ­ten About the Na­ture of Hu­man Values

avturchin
16 Jan 2019 13:59 UTC
22 points
3 comments15 min readLW link

Align­ment Newslet­ter #40

rohinmshah
8 Jan 2019 20:10 UTC
21 points
2 comments5 min readLW link

De­cem­ber gw­ern.net newsletter

gwern
2 Jan 2019 15:13 UTC
20 points
0 commentsLW link
(www.gwern.net)

Hier­ar­chi­cal sys­tem prefer­ences and sub­agent preferences

Stuart_Armstrong
11 Jan 2019 18:47 UTC
19 points
2 comments4 min readLW link

No sur­jec­tion onto func­tion space for man­i­fold X

Stuart_Armstrong
9 Jan 2019 18:07 UTC
19 points
0 comments6 min readLW link

mindlevelup 3 Year Review

lifelonglearner
9 Jan 2019 6:36 UTC
19 points
0 comments10 min readLW link