加州大学圣克鲁斯分校的本杰明·布林(Benjamin Breen)(之前)探讨了当前一批顶级法学硕士(GPT-4o、o1 和 Claude Sonnet 3.5)如何证明自己能够胜任与学术历史学家相关的各种不同任务。
视觉模型现在能够转录和翻译历史文献的扫描件 – 在本例中是 16 世纪的意大利草书笔迹和 1770 年代墨西哥的医学食谱。
更有趣的是,o1 推理模型能够根据这样的提示为历史解释提供真正有用的建议:
Here are some quotes from William James' complete works, referencing Francis galton and Karl Pearson. What are some ways we can generate new historical knowledge or interpretations on the basis of this? I want a creative, exploratory, freewheeling analysis which explores the topic from a range of different angles and which performs metacognitive reflection on research paths forward based on this, especially from a history of science and history of technology perspectives. end your response with some further self-reflection and self-critique, including fact checking. then provide a summary and ideas for paths forward. What further reading should I do on this topic? And what else jumps out at you as interesting from the perspective of a professional historian?
有多好?他接着要求“ the most creative, boundary-pushing, or innovative historical arguments or analyses you can formulate based on the sources I provided
”,并描述了最终的输出,如下所示:
它所产生的所谓“突破边界”的想法几乎都是一班研究生会想出的——水平高、消息灵通,但可以预测。
正如本杰明指出的,这在某种程度上是意料之中的:法学硕士“是经过精心调校的机器,可以找到特定问题的中间观点”——他的本科生的相同工作已经说明了这一点,他们显然得到了 ChatGPT 的帮助。
我很高兴听到计算机科学领域之外的学者更多地讲述这些新工具正在以类似的深度探索这些新工具。
通过黑客新闻
标签:历史,生成式人工智能,本杰明-布林, LLMS ,视觉-LLMS , o1 ,推理缩放, ai
原文: https://simonwillison.net/2025/Jan/26/ai-models-are-now-very-good-historians/#atom-everything