哈佛研究：Claude Opus 4.8 撰写的论文评审在各项指标上优于人类评审
Massive. New Harvard study finds that AI-written paper reviews now beat the best human peer reviews on every measure the authors tested.
一项哈佛研究用 Claude Opus 4.8 对 1124 篇论文生成评审，并与 rapidPeer 的 134 份专家评审做盲评对比，结果显示 AI 评审在作者测试的所有指标上都优于最好的专家评审。GPT-5.5 在全部 132 组已判定配对中都选择了 AI 评审，3 位前期刊编辑有 87% 选择 AI 评审；AI 评审中关于论文的错误陈述占 5.5%，人类评审为 15.9%。作者据此建议依赖专家评审的团队可让 AI 完成首轮完整评审，由人类做最终决定。
推荐理由
AI 评分 54
这项对比给出了 AI 与人类评审在错误率和盲评胜率上的具体差距，可供评估 AI 参与同行评审的边界。
主题
正文
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.