The Political Preferences of AIs: When probed with questions with political connotations, LLMs tend to generate responses that are diagnosed by most political orientations tests as manifesting preferences for left-of-center viewpoints, 11 political orientation tests, 24 SOTA LLMs https://t.co/efYnlOsXLt
— David Rozado (@DavidRozado)
Feb 2, 2024
from http://twitter.com/DavidRozado
via IFTTT