Logan Kilpatrick：新 Gemini 版本发布前经数千名 SWE 测试数周
@ishuagra02 We have gotten much better at testing our models at scale across Google now, so assume most new Gemini revs go through thousands of SWEs for weeks b
AI 导读
@ishuagra02 我们现在在 Google 内部对模型进行大规模测试的能力已大幅提升，所以可以认为大多数新的 Gemini 版本在发布前都会经过数千名 SWE 数周的测试，希望这能在很大程度上帮助缩小 benchmark 与现实之间的差距！
正文
当前显示原文，中文全文译文尚未就绪。
@ishuagra02 We have gotten much better at testing our models at scale across Google now, so assume most new Gemini revs go through thousands of SWEs for weeks before getting released, hopefully has helped close the benchmark to reality gap by a real margin!