Have we been measuring AI political bias wrong? A better approach is possible

· David Rozado · June 22, 2026, 9:18 p.m.
Machine Learning AI large language models Political Bias
Summary
This blog post by David Rozado explores the differences between ideological preferences and epistemic failures in large language models (LLMs) and argues for a more nuanced approach to measuring political bias in AI systems.
Read full post on davidrozado.substack.com →
AUTHOR
Advertise
Sponsor diff.blog
Put your product in front of developers who read and write about their craft. One exclusive sponsor at a time.
Become a sponsor →