Cite
Notes
Only stored in your browser.
Attribution
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
arXiv 2025
Tell me about yourself: LLMs are aware of their learned behaviors
from 2 papers
Anna Sztyber-Betley
Jan Betley
Martín Soto
Owain Evans
founder
Daniel Tan
James Chua
Nathan Labenz
Niels Warncke