AI ALIGNMENT FORUMTags
AF

Sharp Left Turn

EditHistory
Discussion (0)
Help improve this page
EditHistory
Discussion (0)
Help improve this page
Sharp Left Turn
Random Tag
Contributors
1Multicore

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
3
82A central AI alignment problem: capabilities generalization, and the sharp left turn
Nate Soares
1y
18
2
36Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Victoria Krakovna, Vikrant Varma, Ramana Kumar, Mary Phuong
10mo
1
1
15We may be able to see sharp left turns coming
Ethan Perez, Neel Nanda
9mo
24
1
44Evolution provides no evidence for the sharp left turn
Quintin Pope
2mo
12
1
27Reframing inner alignment
davidad (David A. Dalrymple)
6mo
9
1
20Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Victoria Krakovna, Vikrant Varma, Ramana Kumar, Rohin Shah
7mo
4
1
22Smoke without fire is scary
Adam Jermyn
8mo
7
1
21It matters when the first sharp left turn happens
Adam Jermyn
9mo
1
1
9Disentangling inner alignment failures
Erik Jenner
8mo
4
Add Posts