AI ALIGNMENT FORUMTags
AF

Newsletters

Edit Wiki HistoryStub

Newsletters are collected summaries of recent events, posts, and academic papers.

Less Wrong's most prolific newsletter is Rohin Shah's weekly Alignment Newsletter.

Posts tagged Newsletters

Most Relevant

1

19[AN #102]: Meta learning by GPT-3, and a list of full proposals for AI alignment

2mo

0

1

8Alignment Newsletter #36

2y

0

1

9Alignment Newsletter #47

1y

0

0

23Alignment Newsletter One Year Retrospective

1y

10

0

3Alignment Newsletter #13: 07/02/18

2y

0

0

21[AN #69] Stuart Russell's new book on why we need to replace the standard model of AI

10mo

10

0

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

1y

1

0

1Alignment Newsletter #16: 07/23/18

2y

0

0

14[AN #59] How arguments for AI risk have changed over time

1y

0

0

2Alignment Newsletter #15: 07/16/18

2y

0

0

17[AN #75]: Solving Atari and Go with learned game models, and thoughts from a MIRI employee

8mo

0

0

1Alignment Newsletter #17

2y

0

0

18[AN #80]: Why AI risk might be solved without additional intervention from longtermists

7mo

65

0

9Alignment Newsletter #39

2y

0

0

21[AN #100]: What might go wrong if you learn a reward function while acting

3mo

2