Sharp Left Turn

Edited by Multicore, et al. last updated 30th Dec 2024

Sharp Left Turn is a scenario where, as an AI trains, its capabilities generalize across many domains while the alignment properties that held at earlier stages fail to generalize to the new domains.

See also: Threat Models, AI Takeoff, AI Risk

Posts tagged Sharp Left Turn

7

74A central AI alignment problem: capabilities generalization, and the sharp left turn

So8res

3y

18

2

37Refining the Sharp Left Turn threat model, part 1: claims and mechanisms

Vika, Vikrant Varma, Ramana Kumar, Mary Phuong

3y

3

1

16We may be able to see sharp left turns coming

Ethan Perez, Neel Nanda

3y

25

2

86“Sharp Left Turn” discourse: An opinionated review

Steven Byrnes

10mo

13

1

23We don't understand what happened with culture enough

Jan_Kulveit

2y

3

1

30Reframing inner alignment

davidad

3y

9

1

19Refining the Sharp Left Turn threat model, part 2: applying alignment techniques

Vika, Vikrant Varma, Ramana Kumar, Rohin Shah

3y

5

1

66Evolution provides no evidence for the sharp left turn

Quintin Pope

3y

12

1

46Response to Quintin Pope's Evolution Provides No Evidence For the Sharp Left Turn

Zvi

2y

0

1

23Smoke without fire is scary

Adam Jermyn

3y

9

1

22It matters when the first sharp left turn happens

Adam Jermyn

3y

1

10Disentangling inner alignment failures

Erik Jenner

3y

4

AI ALIGNMENT FORUM
AF

AI ALIGNMENT FORUM
AF

Sharp Left Turn