AI ALIGNMENT FORUMTags
AF

AI Risk

EditHistorySubscribe

Help improve this page (3 flags)

EditHistorySubscribe

Help improve this page (3 flags)

Contributors

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

Related: AI, Orthogonality thesis, Complexity of value, Goodhart's law, Paperclip maximiser

Posts tagged AI Risk

Most Relevant

3

84What failure looks like

Paul Christiano

4y

27

3

18Specification gaming examples in AI

Victoria Krakovna

5y

8

2

65Discussion with Eliezer Yudkowsky on AGI interventions

Rob Bensinger, Eliezer Yudkowsky

1y

105

5

24PreDCA: vanessa kosoy's alignment protocol

7mo

1

4

19Intuitions about goal-directed behavior

4y

5

1

129AGI Ruin: A List of Lethalities

Eliezer Yudkowsky

9mo

137

2

50AGI in sight: our look at the game board

Andrea_Miotti, Gabriel Alfour

1mo

12

4

24Epistemological Framing for AI Alignment Research

2y

7

3

39What can the principal-agent literature tell us about AI risk?

3y

11

1

19Open Problems in AI X-Risk [PAIS #5]

9mo

1

0

86On how various plans miss the hard bits of the alignment challenge

8mo

45

1

69Another (outer) alignment failure story

Paul Christiano

2y

25

1

36Developmental Stages of GPTs

3y

42

1

50AI will change the world, but won’t take it over by playing “3-dimensional chess”.

boazbarak, benedelman

4mo

35

1

16A Gym Gridworld Environment for the Treacherous Turn

Michaël Trazzi

5y

0