Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bakman, Yavuz, Yaldiz, Duygu Nur, Avestimehr, Salman, Karimireddy, Sai Praneeth
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!