ViridianAIQualityAssurance/viridian-assurance-research

Independent research on AI evaluation validity, LLM-as-a-judge reliability, benchmark comparability and experimental assurance.

1 best points · 0 comments · 1 Hacker News post · 0 GitHub stars · View on GitHub

Hacker News discussions

• We tried to reproduce LLM judge position bias (1 points, 0 comments, by viridianassuran, 2026-10-07)