AI ALIGNMENT FORUMDeepMind Alignment Team on Threat Models
AF

DeepMind Alignment Team on Threat Models

Nov 25, 2022 by Victoria Krakovna

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

107DeepMind alignment team opinions on AGI ruin arguments

Victoria Krakovna

5mo

5

45Will Capabilities Generalise More?

7mo

28

37Clarifying AI X-risk

Zachary Kenton, Rohin Shah, David Lindner, Vikrant Varma, Victoria Krakovna, Mary Phuong, Ramana Kumar, Elliot Catt

3mo

14

32Threat Model Literature Review

Zachary Kenton, Rohin Shah, David Lindner, Vikrant Varma, Victoria Krakovna, Mary Phuong, Ramana Kumar, Elliot Catt

3mo

3

32Refining the Sharp Left Turn threat model, part 1: claims and mechanisms

Victoria Krakovna, Vikrant Varma, Ramana Kumar, Mary Phuong

6mo

1

20Refining the Sharp Left Turn threat model, part 2: applying alignment techniques

Victoria Krakovna, Vikrant Varma, Ramana Kumar, Rohin Shah

2mo

4