施教于考。
Taught to the test.
机构信息
Matthew Hutson is a journalist in New York City.
出版信息
Science. 2022 May 6;376(6593):570-573. doi: 10.1126/science.abq7833. Epub 2022 May 5.
PMID:35536899
Abstract
AI software clears high hurdles on IQ tests but still makes dumb mistakes. Can better benchmarks help?
摘要
人工智能软件在智商测试中克服了高难度障碍，但仍会犯愚蠢的错误。更好的基准测试能有所帮助吗？
Zotero 插件