帖子称哈佛研究比较 AI 与专家的论文评审质量

@rohanpaul_ai Worth knowing the AI reviews were written by Opus 4.8 and judged by GPT-5.5. Opus 5.5 is already out, so the gap is probably even wider now. I'd like to see them rerun it on current models.

Massive. New Harvard study finds that AI-written paper reviews now beat the best human peer reviews on every measure the authors tested. Peer review is slow and often misses errors. Earlier studies concluded AI should only assist human reviewers, not replace them. They used 134 reviews from rapidPeer, a Harvard service that pays expert reviewers well. Claude Opus 4.8 reviewed the same 1124 papers, and GPT-5.5 plus 3 former journal editors judged the pairs blind. GPT-5.5 picked the AI review in all 132 decided pairs, and the editors picked it 87% of the time. Only 5.5% of the AI's claims about the paper were wrong, versus 15.9% for the human reviews. Teams that depend on expert critique can now let AI do the first full review pass, and keep a human for the final decision.