Elon Musk proposes adversarial peer reviews for AI safety
1Sep 15 1:24 AM · 12d ago · 2 posts · 1 source · development 1 of 1
Musk suggests major AI competitors should test each other's models as a security measure, with each company running its own security test harness against rivals' systems.
x.com
“What I think would be wise to do as soon as possible, if not immediately, would be to have the major AI competitors test each other's models. So that you would have everyone's security test harness testing”
Sep 16Sep 17Sep 18Sep 19Sep 20Sep 21Sep 22Sep 23Sep 24Sep 25Sep 26now · 12:34 AM ET
What people said 2 voices · verbatim
@
Elon Proposes Adversarial Peer Reviews for AI Safety @elonmusk: “What I think would be wise to do as soon as possible, if not immediately, would be to have the major AI competitors test each other's models. So that you would have everyone's security test harness testing