LESSWRONG
LW

Alignment Newsletter

I publish the Alignment Newsletter, a weekly publication with recent content relevant to AI alignment. You can sign up here to get emails every week, subscribe to the RSS feed or skim through the spreadsheet of all summaries that have ever been in the newsletter.

8The Alignment Newsletter #1: 04/09/18Ω

1y

Ω

3

8The Alignment Newsletter #2: 04/16/18Ω

1y

Ω

0

8The Alignment Newsletter #3: 04/23/18Ω

1y

Ω

0

8The Alignment Newsletter #4: 04/30/18Ω

1y

Ω

0

8The Alignment Newsletter #5: 05/07/18Ω

1y

Ω

0

8The Alignment Newsletter #6: 05/14/18Ω

1y

Ω

0

8The Alignment Newsletter #7: 05/21/18Ω

1y

Ω

0

8The Alignment Newsletter #8: 05/28/18Ω

1y

Ω

0

8The Alignment Newsletter #9: 06/04/18Ω

1y

Ω

0

16The Alignment Newsletter #10: 06/11/18Ω

1y

Ω

0

8The Alignment Newsletter #11: 06/18/18Ω

1y

Ω

0

15The Alignment Newsletter #12: 06/25/18Ω

1y

Ω

0

74Alignment Newsletter #13: 07/02/18Ω

1y

Ω

12

15Alignment Newsletter #14Ω

1y

Ω

0

42Alignment Newsletter #15: 07/16/18Ω

1y

Ω

0

44Alignment Newsletter #16: 07/23/18Ω

1y

Ω

0

35Alignment Newsletter #17Ω

1y

Ω

0

19Alignment Newsletter #18Ω

10mo

Ω

0

19Alignment Newsletter #19Ω

10mo

Ω

0

13Alignment Newsletter #20Ω

10mo

Ω

2

26Alignment Newsletter #21Ω

10mo

Ω

0

15Alignment Newsletter #22Ω

9mo

Ω

0

17Alignment Newsletter #23Ω

9mo

Ω

0

10Alignment Newsletter #24Ω

9mo

Ω

3

22Alignment Newsletter #25Ω

9mo

Ω

3

14Alignment Newsletter #26Ω

9mo

Ω

0

16Alignment Newsletter #27Ω

8mo

Ω

0

11Alignment Newsletter #28Ω

8mo

Ω

0

16Alignment Newsletter #29Ω

8mo

Ω

0

31Alignment Newsletter #30Ω

8mo

Ω

2

19Alignment Newsletter #31Ω

7mo

Ω

0

20Alignment Newsletter #32Ω

7mo

Ω

0

25Alignment Newsletter #33Ω

7mo

Ω

0

26Alignment Newsletter #34Ω

7mo

Ω

0

15Alignment Newsletter #35Ω

6mo

Ω

0

22Alignment Newsletter #36Ω

6mo

Ω

0

26Alignment Newsletter #37Ω

6mo

Ω

4

9Alignment Newsletter #38Ω

6mo

Ω

0

33Alignment Newsletter #39Ω

6mo

Ω

2

21Alignment Newsletter #40Ω

5mo

Ω

2

23Alignment Newsletter #41Ω

5mo

Ω

6

21Alignment Newsletter #42Ω

5mo

Ω

1

15Alignment Newsletter #43Ω

5mo

Ω

2

20Alignment Newsletter #44Ω

4mo

Ω

0

26Alignment Newsletter #45Ω

4mo

Ω

2

18Alignment Newsletter #46Ω

4mo

Ω

0

21Alignment Newsletter #47Ω

3mo

Ω

0

31Alignment Newsletter #48Ω

3mo

Ω

14

26Alignment Newsletter #49Ω

3mo

Ω

1

16Alignment Newsletter #50Ω

3mo

Ω

2

28Alignment Newsletter #51Ω

3mo

Ω

2

20Alignment Newsletter #52Ω

2mo

Ω

1

93Alignment Newsletter One Year RetrospectiveΩ

2mo

Ω

31

22Alignment Newsletter #53

2mo

0

21[AN #54] Boxing a finite-horizon AI system to keep it unambitiousΩ

2mo

Ω

0

17[AN #55] Regulatory markets and international standards as a means of ensuring beneficial AIΩ

1mo

Ω

0

21[AN #56] Should ML researchers stop running experiments before making hypotheses?Ω

1mo

Ω

8

26[AN #57] Why we should focus on robustness in AI safety, and the analogous problems in programmingΩ

12d

Ω

8