AI ALIGNMENT FORUM
AF

Library Questions All Posts

Top Questions

21Best reasons for pessimism about impact of impact measures?

1y

44

18How common is it for one entity to have a 3+ year technological lead on its nearest competitor?

Daniel Kokotajlo

3mo

0

16Does Agent-like Behavior Imply Agent-like Architecture?

Scott Garrabrant

6mo

2

19How does Gradient Descent Interact with Goodhart?

Scott Garrabrant

1y

4

Recent Activity

4What is the difference between robustness and inner alignment?

13d

2

4Does iterated amplification tackle the inner alignment problem?

13d

3

18Instrumental Occam?

1mo

11

9What are some non-purely-sampling ways to do deep RL?

3mo

7

21Best reasons for pessimism about impact of impact measures?

1y

44

18How common is it for one entity to have a 3+ year technological lead on its nearest competitor?

Daniel Kokotajlo

3mo

0

11What are the differences between all the iterative/recursive approaches to AI alignment?

5mo

4

9What are concrete examples of potential "lock-in" in AI research?

6mo

3

16Does Agent-like Behavior Imply Agent-like Architecture?

Scott Garrabrant

6mo

2

19How does Gradient Descent Interact with Goodhart?

Scott Garrabrant

1y

4

6Would an option to publish to AF users only be a useful feature?

9mo

0

12What's wrong with these analogies for understanding Informed Oversight and IDA?

1y

3