LESSWRONG
LW

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

2

2

Posts tagged Sharp Left Turn

275A central AI alignment problem: capabilities generalization, and the sharp left turn

3y

55

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

Vika, Vikrant Varma, Ramana Kumar, Mary Phuong

3y

4

54We may be able to see sharp left turns coming

Ethan Perez, Neel Nanda

3y

29

216“Sharp Left Turn” discourse: An opinionated review

7mo

31

87We don't understand what happened with culture enough

2y

22

53Reframing inner alignment

3y

13

40Victoria Krakovna on AGI Ruin, The Sharp Left Turn and Paradigms of AI Alignment

Michaël Trazzi

3y

3

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

Vika, Vikrant Varma, Ramana Kumar, Rohin Shah

3y

9

38The Sharp Right Turn: sudden deceptive alignment as a convergent goal

2y

5

23Evolution Solved Alignment (what sharp left turn?)

2y

89

14How is the "sharp left turn defined"?

3y

4

11[Interview w/ Quintin Pope] Evolution, values, and AI Safety

2y

0

6A few Alignment questions: utility optimizers, SLT, sharp left turn and identifiability

2y

1

6Superintelligence's goals are likely to be random

6mo

6

206Evolution provides no evidence for the sharp left turn

2y

65

Load More (15/25)

Add Posts