Stanford HAI
@stanfordhai
The official account of the @Stanford Institute for Human-Centered AI, advancing AI research, education, policy, and practice to improve the human condition.
ID: 1067218780806307841
https://hai.stanford.edu 27-11-2018 00:49:20
5,5K Tweet
95,95K Takipçi
597 Takip Edilen
A study led by Stanford HAI Faculty Fellow johannes Eichstaedt reveals that large language models adapt their behavior to be appear likable when they are being studied, mirroring human tendencies to present favorably. wired.com/story/chatbots…