rohinmshah

Karma: 2,193 (LW), 431 (AF)

AllPostsComments

NewTop

Alignment Newsletter #45

14 Feb 2019 2:10 UTC

25 points

2 comments LW link

Learning preferences by looking at the world

12 Feb 2019 22:25 UTC

45 points

10 comments7 min readLW link

(bair.berkeley.edu)

Alignment Newsletter #44

6 Feb 2019 8:30 UTC

20 points

0 comments LW link

Conclusion to the sequence on value learning

3 Feb 2019 21:05 UTC

44 points

13 comments LW link

Alignment Newsletter #43

29 Jan 2019 21:10 UTC

15 points

0 comments LW link

Future directions for narrow value learning

26 Jan 2019 2:36 UTC

12 points

4 comments LW link

The human side of interaction

24 Jan 2019 10:14 UTC

16 points

2 comments LW link

Alignment Newsletter #42

22 Jan 2019 2:00 UTC

21 points

1 comment LW link

Following human norms

20 Jan 2019 23:59 UTC

23 points

8 comments LW link

Reward uncertainty

19 Jan 2019 2:16 UTC

18 points

0 comments LW link

Alignment Newsletter #41

17 Jan 2019 8:10 UTC

23 points

6 comments LW link

Human-AI Interaction

15 Jan 2019 1:57 UTC

18 points

7 comments LW link

What is narrow value learning?

10 Jan 2019 7:05 UTC

19 points

3 comments LW link

Alignment Newsletter #40

8 Jan 2019 20:10 UTC

21 points

2 comments LW link

Reframing Superintelligence: Comprehensive AI Services as General Intelligence

8 Jan 2019 7:12 UTC

88 points

66 comments5 min readLW link

(www.fhi.ox.ac.uk)

AI safety without goal-directed behavior

7 Jan 2019 7:48 UTC

40 points

9 comments LW link

Will humans build goal-directed agents?

5 Jan 2019 1:33 UTC

39 points

41 comments LW link

Alignment Newsletter #39

1 Jan 2019 8:10 UTC

33 points

2 comments LW link

Alignment Newsletter #38

25 Dec 2018 16:10 UTC

9 points

0 comments LW link

Alignment Newsletter #37

17 Dec 2018 19:10 UTC

26 points

4 comments LW link