CSET’s Helen Toner shared her expert insight in an article published by The New York Times. The article examines the challenges of creating a “kill switch” that could quickly power down an A.I. system that has gone rogue, as policymakers consider new measures to regulate increasingly capable A.I. systems.
Something that a lot of people expect you will see if you have a very capable A.I. system that is going rogue is that it is going to try to prevent itself from being shut down.CSET Executive Director, Helen Toner
On the potential for a future A.I. system to resist being shut down, Toner said, “Something that a lot of people expect you will see if you have a very capable A.I. system that is going rogue is that it is going to try to prevent itself from being shut down.”
To read the full article, visit The New York Times.