注册并分享邀请链接,可获得视频播放与邀请奖励。

Ofir Press
@OfirPress
SWE-bench, ProgramBench, SWE-sweep. Postdoc @Princeton. PhD @nlpnoah @UW.
加入 June 2016
10K 正在关注    20.4K 粉丝
When we were at human-level AI we could take human tasks and translate them into benchmarks. In many domains, we can't do that anymore, those tasks are too easy. Here are my guidelines on how to build benchmarks in this new era:
显示更多
0
11
96
10
转发到社区