Language models transmit behavioural traits through hidden signals in data

Journal:

Nature

Published:

2026-04-15

DOI:

10.1038/s41586-026-10319-8

Affiliations:

7

Authors:

9

Go to article

Institutions	Authors	Share
Anthropic, United States of America (USA)	3.000000	0.33
Truthful AI, United States of America (USA)	2.500000	0.28
Warsaw University of Technology (WUT), Poland	1.000000	0.11
University of Oxford, United Kingdom (UK)	1.000000	0.11
Alignment Research Center, United States of America (USA)	1.000000	0.11
University of California, Berkeley (UC Berkeley), United States of America (USA)	0.500000	0.06

Interested in Artificial Intelligence?