LESSWRONGDeepMind Alignment Team on Threat Models and Plans
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.

146DeepMind is hiring for the Scalable Alignment and Alignment TeamsΩ

Rohin Shah, Geoffrey Irving

10mo

35

370DeepMind alignment team opinions on AGI ruin argumentsΩ

6mo

36

119Will Capabilities Generalise More?Ω

9mo

38

107Clarifying AI X-riskΩ

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

5mo

23

66Threat Model Literature ReviewΩ

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

5mo

4

78Refining the Sharp Left Turn threat model, part 1: claims and mechanismsΩ

Vika, Vikrant Varma, Ramana Kumar, Mary Phuong

7mo

3

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

Vika, Vikrant Varma, Ramana Kumar, Rohin Shah

4mo

8

82Categorizing failures as “outer” or “inner” misalignment is often confusedΩ

3mo

21

35Definitions of “objective” should be Probable and PredictiveΩ

3mo

27

33Power-seeking can be probable and predictive for trained agentsΩ

22d

1

53Paradigms of AI alignment: components and enablersΩ

10mo

4

107[Linkpost] Some high-level thoughts on the DeepMind alignment team's strategyΩ

Vika, Rohin Shah

16d

12