François Chollet· @fchollet · X·· 1 天前AI 评分22
AI 导读
有什么方法可以测试人工智能的人类级通用性？ “能够一发布就通过 ARC-AGI-(n+1) 的元基准”
正文
What is a way to test human-level generality in artificial intelligence?
"The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release"
@Jabaluck @DAcemogluMIT The meta-benchmark of being able to pass ARC-AGI-(n+1) immediately upon release. Though presumably that won't last forever.在 X 查看被引用的帖子
来源：François Chollet · x.com