We may not cooperate with friendly machines

Research output: Contribution to journalComment/debate

Abstract / Description of output

In cooperative games, humans are biased against AI systems even when such systems behave better than our human counterparts. This raises a question: should AI systems ever be allowed to conceal their true nature and lie to us for our own benefit?
Original languageEnglish
Number of pages2
JournalNature Machine Intelligence
DOIs
Publication statusPublished - 12 Nov 2019

Fingerprint

Dive into the research topics of 'We may not cooperate with friendly machines'. Together they form a unique fingerprint.

Cite this