LESSWRONG
LW

DeepMind Alignment Team on Threat Models and Plans

A collection of posts presenting our understanding of and opinions on alignment threat models and plans.

150DeepMind is hiring for the Scalable Alignment and Alignment Teams

Rohin Shah, Geoffrey Irving

3y

34

396DeepMind alignment team opinions on AGI ruin arguments

3y

37

133Will Capabilities Generalise More?

3y

39

127Clarifying AI X-risk

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar, Elliot Catt

3y

24

78Threat Model Literature Review

zac_kenton, Rohin Shah, David Lindner, Vikrant Varma, Vika, Mary Phuong, Ramana Kumar, Elliot Catt

3y

4

86Refining the Sharp Left Turn threat model, part 1: claims and mechanisms

Vika, Vikrant Varma, Ramana Kumar, Mary Phuong

3y

4

39Refining the Sharp Left Turn threat model, part 2: applying alignment techniques

Vika, Vikrant Varma, Ramana Kumar, Rohin Shah

3y

9

93Categorizing failures as “outer” or “inner” misalignment is often confused

2y

21

43Definitions of “objective” should be Probable and Predictive

2y

27

56Power-seeking can be probable and predictive for trained agents

2y

22

53Paradigms of AI alignment: components and enablers

3y

4

128[Linkpost] Some high-level thoughts on the DeepMind alignment team's strategy

Vika, Rohin Shah

2y

13