Georgetown's AI referee leaderboard has Claude Opus 4.8 scoring finance papers

emollick · x · 2026-09-07

Ethan Mollick highlighted Georgetown's "AI Referee Paper Leaderboard," where Claude Opus 4.8 acts as an AI referee scoring the top 100 finance and economics working papers against a fixed rubric across significance, originality, correctness, data & methodology, and exposition, with full public reports. He frames it as both an experiment and a sign of a coming tsunami for academia: AIs retroactively reading published research and publicly flagging opportunities and flaws.

Original post →

More from AGI Musings

AGI Musings channel →