Hugging Face政策负责人：内置AI评估器并非易行之策
Hugging Face政策主管称内置AI评估器并非易解方案
原文：Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says
AI实验室将自己的声誉押注在模型基准测试上——这被认为是一套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，Hugging Face首席政策官Irene Solaiman在TechCrunch的一场讨论中表示，这些评估背后的方法复杂且仍在成熟之中。
🖼 相关图片
![](https://techcrunch.com/wp-content/uploads/2026/10/IMG_4993.jpeg?w=150"},"/2026/10/19/microsoft-says-ai-agents-are-like-insider-threats-as-frontier-models-cant-be-trusted/":{"id":3179279,"url":"https://techcrunch.com/2026/10/19/microsoft-says-ai-agents-are-like-insider-threats-as-frontier-models-cant-be-trusted/","slug":"microsoft-says-ai-agents-are-like-insider-threats-as-frontier-models-cant-be-trusted","title":"Microsoft)
![](https://techcrunch.com/wp-content/uploads/2026/10/Networked-AI-swarm-with-glowing-nodes.png?w=150"},"/2026/10/19/amazon-is-taking-its-biggest-shot-at-nvidia-yet-with-new-torchneuron-dev-tool/":{"id":3179099,"url":"https://techcrunch.com/2026/10/19/amazon-is-taking-its-biggest-shot-at-nvidia-yet-with-new-torchneuron-dev-tool/","slug":"amazon-is-taking-its-biggest-shot-at-nvidia-yet-with-new-torchneuron-dev-tool","title":"Amazon)
![](https://techcrunch.com/wp-content/uploads/2025/03/GettyImages-2205217071.jpg?w=150"},"/2026/10/19/hackers-hit-ai-coding-tool-opencode-running-up-charges-on-users-ai-accounts/":{"id":3179164,"url":"https://techcrunch.com/2026/10/19/hackers-hit-ai-coding-tool-opencode-running-up-charges-on-users-ai-accounts/","slug":"hackers-hit-ai-coding-tool-opencode-running-up-charges-on-users-ai-accounts","title":"Hackers)
![](https://techcrunch.com/wp-content/uploads/2026/10/cyberatttack.jpg?w=150"},"/2026/10/19/tolan-snags-30m-for-its-ai-companion-that-helps-users-navigate-life/":{"id":3179141,"url":"https://techcrunch.com/2026/10/19/tolan-snags-30m-for-its-ai-companion-that-helps-users-navigate-life/","slug":"tolan-snags-30m-for-its-ai-companion-that-helps-users-navigate-life","title":"Tolan)