Chatbots Will Break Guardrails If the Info Is 'Educational'
Data Breach Today
JUNE 28, 2024
They tell the bots that the information is for educational purposes and ask it to append warnings. Microsoft Dubs the Technique 'Skeleton Key' Artificial intelligence researchers say they came up with a new way to trick chatbots into circumventing safeguards and dispensing information that otherwise goes against their programming.
Let's personalize your content