原帖引用 · AI 翻译
> 如今，AI 在临床试验论文中发现的错误远多于人类同行评审员：接受测试的全部 15 个模型在识别预先植入的错误时，得分为 53% 至 96%，而未经培训的人类评审员平均仅为 27%。
> 在 2026 年发表的 58 项新试验中，结果依然如此，因此模型并非只是回忆训练时见过的旧论文；Claude Opus 5.5 得分最高，为 99%。
> 人类漏掉了最能改变试验含义的错误：他们发现正文与表格矛盾的概率仅为 7%；每次评审需花费 5 至 8.5 小时，而 AI 只需 1.4 至 16.3 分钟。
原文
> AI now catches far more errors in clinical trial papers than human peer reviewers: all 15 models tested scored 53% to 96% on planted errors, while untrained human reviewers averaged just 27%. > The result held on 58 new trials published in 2026, so the models weren’t simply recalling old papers they had seen in training; Claude Opus 5.5 scored highest at 99%. > Humans miss the errors that most change a trial’s meaning, catching text-table contradictions only 7% of the time, and they take 5 to 8.5 hours per review against AI’s 1.4 to 16.3 minutes.
本周，关于期刊是否应禁止在同行评审中使用 AI，出现了大量讨论。
我们实际上在新的预印本中测试了这一点，结果在我看来相当明确。
作为背景，我为大多数大型期刊做过评审，并且作为编辑评估过 1,000 份人类评审意见。我喜欢阅读和评估科学研究。
太长不看：从现在起，我不会在不使用 AI 的情况下做任何同行评审。对于临床试验，我甚至会说仅由人类进行评审是危险的 🧵
原文
Lots of debate this week on whether journals should ban AI in peer review. We actually tested this in our new preprint, and the results were pretty clear to me. For context, I've reviewed for most of the big journals and evaluated 1,000 human reviews as an editor. I love to read and evaluate science. TLDR: From now on I won't do any peer review without AI. For clinical trials, I'd even call human-only review dangerous 🧵