LESSWRONG
LW

2

Informed Oversight through Generalizing Explanations

24th May 2017

AI Alignment Forum

1 min read

2

Ω 1

This is a linkpost for https://william-r-s.github.io/informed_oversight_generalizing_explanations.html

2

Ω 1

New Comment

More from William_S

248Principles for the AGI Race

8mo

17

104Transformer Circuit Faithfulness Metrics Are Not Robust

Joseph Miller, bilalchughtai, William_S

10mo

5

64Prize for Alignment Research Tasks

stuhlmueller, William_S

3y

38

Curated and popular this week

123Learned pain as a leading cause of chronic pain

42m

14

379Playing in the Creek

5d

16

309Orienting Toward Wizard Power

3d

51