Hugging Face 政策负责人：嵌入式 AI 评估者并非易解方案
原标题：Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says
AI 摘要
Hugging Face 首席政策官 Irene Solaiman 在 TechCrunch Disrupt 上表示，当前 AI 模型评测方法仍不成熟，可复现性存疑，评测之间难以有效比较，且失效速度快。她指出业界对「嵌入式评估者」（第三方观察员进驻 AI 机构）需求旺盛，但评估者资质标准亟需统一；同时评测对象正从模型本身扩展到包含 harness 与 agent 的完整系统，而 agentic 评测成本高、难度大。
正文节选
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 complicated and still maturing, said Irene Solaiman, Hugging Face’s chief policy officer, during a discussion at TechCrunch Disrupt last week. Testing needs to come together into a more consistent science if the industry is to rely on them in the future.