Nathan Lambert：私有基准与开源基准各有取舍
Private benchmarks often show open models are further behind, but the problem with private benchmarks is you don’t have the community to squash the inevitable b
AI 导读
Nathan Lambert 指出，私有基准测试往往显示开源模型落后更多，但私有基准的问题在于没有社区帮忙发现并修复不可避免的 bug。他表示，自己对于私有基准和开源基准哪种方式更好，持 50/50 的态度。
正文
Private benchmarks often show open models are further behind, but the problem with private benchmarks is you don’t have the community to squash the inevitable bugs for you. I'm 50/50 on if I think private or open-source is the best approach. https://t.co/DbvE6Tk5qL