Emergent misalignment as prompt sensitivity: A research note

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wyse, Tim, Stone, Twm, Soligo, Anna, Tan, Daniel
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Human-Computer Interaction
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.06253