AI 导读
AI 开发者想要打造自动化的 AI 研究员。他们离这个目标还有多远？ 为了找到答案，我们构建了 InnovationEval，用来测试 AI 能否产出与近期已发表进展量级相当的后训练创新。到目前为止，智能体的表现不尽如人意。
正文
AI developers aim to create an automated AI researcher. How close are they?
To find out, we built InnovationEval, which tests whether AI can produce post-training innovations comparable in magnitude to a recently published advance. So far, agents’ results are underwhelming.
来源：Epoch AI · x.com