TechCrunch· @TechCrunch · X·· 3 小时前AI 评分42
AI 导读
AI 实验室已将声誉押注在模型基准评测上——这套本应中立且准确的评估体系，旨在衡量一个 AI 产品是否优于另一个。然而，这些评估背后的方法却 https://spr.ly/6015BHrx7S
正文
AI labs have staked their reputations on model benchmarking — the supposedly neutral and accurate system of evaluations that are designed to measure whether one AI product is better than another. However, the methods behind these evaluations are
https://spr.ly/6015BHrx7S
来源：TechCrunch · x.com