1 story in the last 7 days
The latest peer review news, distilled by AI into sharp ~100-word summaries. ByteBrief tracks peer review across dozens of tech sources and brings you only what matters, updated hourly. Tap any story for the full brief, or open the original source.
The author tested Gemini, Refine, Claude, and ChatGPT Pro on four published economics papers with known errors. ChatGPT Pro performed best, occasionally constructing counterexamples and corrected proofs. No model located a true error without substantial human guidance. The author argues a competent human paired with a frontier model can outperform current peer review.
Summaries by ByteBrief