AI ALIGNMENT FORUMTags
AF

AI Risk

EditHistorySubscribe

Help improve this page (2 flags)

EditHistorySubscribe

Help improve this page (2 flags)

Contributors

AI Risk is analysis of the risks associated with building powerful AI systems.

Posts tagged AI Risk

Most Relevant

3

73What failure looks like

Paul Christiano

3y

27

3

17Specification gaming examples in AI

4y

8

2

66Discussion with Eliezer Yudkowsky on AGI interventions

Rob Bensinger, Eliezer Yudkowsky

6mo

91

4

17Intuitions about goal-directed behavior

3y

5

4

24Epistemological Framing for AI Alignment Research

1y

7

3

38What can the principal-agent literature tell us about AI risk?

2y

11

1

67Another (outer) alignment failure story

Paul Christiano

1y

25

1

36Developmental Stages of GPTs

2y

28

2

15Will OpenAI's work unintentionally increase existential risks related to AI?Q

Adam Shimi, Matthew "Vaniver" Graves

2y

41

2

95Soft takeoff can still lead to decisive strategic advantage

Daniel Kokotajlo

3y

32

1

38On Solving Problems Before They Appear: The Weird Epistemologies of Alignment

7mo

10

1

16A Gym Gridworld Environment for the Treacherous Turn

Michaël Trazzi

4y

0

3

34Truthful LMs as a warm-up for aligned AGI

4mo

10

1

23Are minimal circuits deceptive?

3y

9

1

76Ngo and Yudkowsky on alignment difficulty

Eliezer Yudkowsky, Richard Ngo

6mo

47