Quanta Magazine(@QuantaMagazine):After over a century of studying introspection in humans and animals, researchers are beginning to explore the phenomenon in unlikely new subjects — large language models. These systems, which are based on mathematical structures called neural networks, excel at cognitive tasks that until recently seemed exclusive to humans. Can they introspect as well? @benbenbrubaker reports:

Quanta Magazine

@QuantaMagazine

Illuminating math and science. Supported by @SimonsFdn. 2022 Pulitzer Prize in Explanatory Reporting.

加入 October 2012

615 正在關注 368.7K 粉絲

Quanta Magazine@QuantaMagazine

2026.11.04 15:36

After over a century of studying introspection in humans and animals, researchers are beginning to explore the phenomenon in unlikely new subjects — large language models. These systems, which are based on mathematical structures called neural networks, excel at cognitive tasks that until recently seemed exclusive to humans. Can they introspect as well? @benbenbrubaker reports: