How well does AI peer review work?
2 outlets - including Marginalrevolution and Feedblitz - are covering this story. Claude and I planted 100 known errors into 10 open-access psychology papers and then ran them through frontier models and two commercial AI review tools. In brief: The best single system caught 71 of 100 errors, while the worst caught 30. P…
Covered by 2 outlets
All coverage · 2 articles
How well does AI peer review work?
Claude and I planted 100 known errors into 10 open-access psychology papers and then ran them through frontier models and two commercial AI review tools. In brief: The best single system caught 71 of 100 errors, while the worst caught 30. P…
How well does AI peer review work?
Claude and I planted 100 known errors into 10 open-access psychology papers and then ran them through frontier models and two commercial AI review tools. In brief: The best single system caught 71 of 100 errors, while the worst caught 30. P…