AI ALIGNMENT FORUM
AF

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.

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

1y

0

0The Alignment Newsletter #2: 04/16/18

1y

0

0The Alignment Newsletter #3: 04/23/18

1y

0

0The Alignment Newsletter #4: 04/30/18

1y

0

0The Alignment Newsletter #5: 05/07/18

1y

0

0The Alignment Newsletter #6: 05/14/18

1y

0

0The Alignment Newsletter #7: 05/21/18

1y

0

0The Alignment Newsletter #8: 05/28/18

1y

0

0The Alignment Newsletter #9: 06/04/18

1y

0

0The Alignment Newsletter #10: 06/11/18

1y

0

0The Alignment Newsletter #11: 06/18/18

1y

0

0The Alignment Newsletter #12: 06/25/18

1y

0

3Alignment Newsletter #13: 07/02/18

1y

0

0Alignment Newsletter #14

1y

0

2Alignment Newsletter #15: 07/16/18

1y

0

1Alignment Newsletter #16: 07/23/18

1y

0

1Alignment Newsletter #17

1y

0

1Alignment Newsletter #18

1y

0

1Alignment Newsletter #19

10mo

0

1Alignment Newsletter #20

10mo

0

0Alignment Newsletter #21

10mo

0

0Alignment Newsletter #22

10mo

0

0Alignment Newsletter #23

10mo

0

1Alignment Newsletter #24

9mo

0

6Alignment Newsletter #25

9mo

3

2Alignment Newsletter #26

9mo

0

1Alignment Newsletter #27

9mo

0

5Alignment Newsletter #28

8mo

0

4Alignment Newsletter #29

8mo

0

10Alignment Newsletter #30

8mo

0

7Alignment Newsletter #31

8mo

0

5Alignment Newsletter #32

7mo

0

5Alignment Newsletter #33

7mo

0

7Alignment Newsletter #34

7mo

0

5Alignment Newsletter #35

7mo

0

8Alignment Newsletter #36

7mo

0

7Alignment Newsletter #37

6mo

2

5Alignment Newsletter #38

6mo

0

9Alignment Newsletter #39

6mo

0

7Alignment Newsletter #40

6mo

0

8Alignment Newsletter #41

5mo

6

10Alignment Newsletter #42

5mo

0

6Alignment Newsletter #43

5mo

2

8Alignment Newsletter #44

5mo

0

10Alignment Newsletter #45

4mo

0

10Alignment Newsletter #46

4mo

0

9Alignment Newsletter #47

4mo

0

13Alignment Newsletter #48

4mo

14

11Alignment Newsletter #49

3mo

0

6Alignment Newsletter #50

3mo

0

10Alignment Newsletter #51

3mo

0

9Alignment Newsletter #52

3mo

1

23Alignment Newsletter One Year Retrospective

3mo

10

8Alignment Newsletter #53

2mo

0

10[AN #54] Boxing a finite-horizon AI system to keep it unambitious

2mo

0

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

2mo

0

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

1mo

6

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

21d

14

18[AN #58] Mesa optimization: what it is, and why we should care

3d

1