How does ChatGPT 'think'? Psychology and neuroscience crack open AI large language models

成果类型：

News Item

署名作者：

Hutson, Matthew

刊物名称：

Nature

ISSN/ISSBN：

0028-6035

DOI：

10.1038/d41586-024-01314-y

发表日期：

2024-05-30

页码：

986-988

关键词：

摘要：

Researchers are striving to reverse-engineer artificial intelligence and scan the 'brains' of LLMs to see what they are doing, how and why.