RSS

rohinmshah

Karma: 2,193 (LW), 431 (AF)
AllPostsComments
NewTop
Page 1

Refram­ing Su­per­in­tel­li­gence: Com­pre­hen­sive AI Ser­vices as Gen­eral Intelligence

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

Learn­ing prefer­ences by look­ing at the world

rohinmshah
12 Feb 2019 22:25 UTC
45 points
10 comments7 min readLW link
(bair.berkeley.edu)

Con­clu­sion to the se­quence on value learning

rohinmshah
3 Feb 2019 21:05 UTC
44 points
13 commentsLW link

AI safety with­out goal-di­rected behavior

rohinmshah
7 Jan 2019 7:48 UTC
40 points
9 commentsLW link

Will hu­mans build goal-di­rected agents?

rohinmshah
5 Jan 2019 1:33 UTC
39 points
41 commentsLW link

Align­ment Newslet­ter #39

rohinmshah
1 Jan 2019 8:10 UTC
33 points
2 commentsLW link

Align­ment Newslet­ter #37

rohinmshah
17 Dec 2018 19:10 UTC
26 points
4 commentsLW link

Align­ment Newslet­ter #45

rohinmshah
14 Feb 2019 2:10 UTC
25 points
2 commentsLW link

Fol­low­ing hu­man norms

rohinmshah
20 Jan 2019 23:59 UTC
23 points
8 commentsLW link

Align­ment Newslet­ter #41

rohinmshah
17 Jan 2019 8:10 UTC
23 points
6 commentsLW link

Align­ment Newslet­ter #36

rohinmshah
12 Dec 2018 1:10 UTC
22 points
0 commentsLW link

Align­ment Newslet­ter #42

rohinmshah
22 Jan 2019 2:00 UTC
21 points
1 commentLW link

Align­ment Newslet­ter #40

rohinmshah
8 Jan 2019 20:10 UTC
21 points
2 commentsLW link

Align­ment Newslet­ter #44

rohinmshah
6 Feb 2019 8:30 UTC
20 points
0 commentsLW link

What is nar­row value learn­ing?

rohinmshah
10 Jan 2019 7:05 UTC
19 points
3 commentsLW link