LESSWRONGTags
LW

Sharp Left Turn

Contributors

You are viewing revision 1.0.0, last edited by Multicore

A 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

279A central AI alignment problem: capabilities generalization, and the sharp left turn

So8res

85Refining the Sharp Left Turn threat model, part 1: claims and mechanisms

Vika, Vikrant Varma, Ramana Kumar, Mary Phuong

53We may be able to see sharp left turns coming

Ethan Perez, Neel Nanda

86We don't understand what happened with culture enough

Jan_Kulveit

6mo

53Reframing inner alignment

davidad

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

Michaël Trazzi

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

Vika, Vikrant Varma, Ramana Kumar, Rohin Shah

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

avturchin

10mo

20Evolution Solved Alignment (what sharp left turn?)

jacob_cannell

6mo

14How is the "sharp left turn defined"?

Chris_Leong

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

fowlertm

6mo

5A few Alignment questions: utility optimizers, SLT, sharp left turn and identifiability

Igor Timofeev

7mo

193Evolution provides no evidence for the sharp left turn

Quintin Pope

51Smoke without fire is scary

Adam Jermyn

47Goal Alignment Is Robust To the Sharp Left Turn

Thane Ruthenis