Karina· @karinanguyen · X·· 13 天前AI 评分56
AI 导读
Epoch AI 推出 Benchmark Reviews 计划，对 AI 基准进行审计，首批覆盖 15 个基准，其中 4 个 Verified、9 个 Flawed、2 个信息不足。Karina Nguyen 转发并称赞这一举措能激励行业构建真正高质量的基准，并感谢其审计了 PostTrainBench、挖掘出旧的 SimpleQA。
正文
Great initiative to eval the evals. It incentivizes the industry to build genuinely high-quality benchmarks.
Ty for auditing PTB and digging up the old SimpleQA too :)
Introducing Benchmark Reviews: our new initiative to audit AI benchmarks. We are launching with 15 benchmarks: 4 Verified, 9 Flawed, and 2 with not enough information for a review.在 X 查看被引用的帖子
来源：Karina · x.com