Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time
Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time
www.pcgamer.com
Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time
Edit: After I posted this, I found out there are serious questions about how true any of this is. See here for more info. But also, self-serving propaganda is pretty strongly on-brand for anything in the "aRtIfIcIaL iNtElLiGeNce"(tm) space.