13 Hrs
Source:
الخليج
NVIDIA controls AI agents
Nvidia has launched a new security platform called the "Open Agent Safety Platform" to monitor and regulate AI agents in order to prevent them from exceeding their boundaries and accessing unauthorized systems. This move comes after previous incidents revealed that safety controls at the model level alone are insufficient. The platform includes tools such as "Open Shell" and "Sentry" to manage capabilities and enable monitoring. Part of the platform will be open source, and its goal is to protect sensitive data and systems from breaches, thereby reducing security risks as generative AI models continue to evolve.
Size: 120%Text Size
Notice: This Is an AI-Generated Summary
Comments (0)