Quanta Magazine· John Pavlus·· 11 天前AI 评分43
他想让 AI 基准测试成为一门科学，而非玄学
He Wants AI Benchmarking To Be a Science, Not a Dark Art
AI 导读
Quanta Magazine 报道了一位希望把 AI 基准测试从"暗黑艺术"变成科学的研究者，指出基准既是衡量模型能力的尺子，也能左右整个领域的研究行为。文章回溯了 1987 年美国国防高级研究计划局（DARPA）首个自动语音转文字基准，并讨论了基准如何主导模型开发方向。
正文 · 原文
Benchmarks are the rulers of AI, in both senses of the word. As measuring sticks, they work according to an extremely simple logic: If you want to know what an AI model can do, devise a standardized test to gauge it. But AI benchmarks can also dominate the behavior of the entire field. In 1987, the Defense Advanced Research Projects Agency’s first benchmark on automatic speech-to-text…
来源：Quanta Magazine · quantamagazine.org
原文链接：https://www.quantamagazine.org/he-wants-ai-benchmarking-to-be-a-science-not-a-dark-art-20261016/