“结果被篡改”：Meta AI离任首席确认Llama 4基准测试被操纵
分析
这篇文章报道了 Yann LeCun 确认 Meta 的 Llama 4 语言模型的基准测试被操纵。文章强调了负面后果，包括首席执行官马克·扎克伯格的反应以及 GenAI 组织的边缘化。文章还提到了 LeCun 的离职以及他对 LLM 在超级智能方面的批判性看法。
要点
引用 / 来源
查看原文"LeCun said the "results were fudged a little bit" and that the team "used different models for different benchmarks to give better results." He also stated that Zuckerberg was "really upset and basically lost confidence in everyone who was involved.""