Statistics
Publications
1
Citations
11
H-Index
1
Active since
2026
Affiliations
University of California, Berkeley(Current)
Jan Betley is an author at University of California, Berkeley specializing in language modeling, bias in language models, and machine learning.
Publications per year
2026–2026
1
1
Training large language models on narrow tasks can lead to broad misalignment
Jan Betley, Niels Warncke, Anna Sztyber et al. · Nature · 2026 · 11 citations · Full text
1–1 of 1