AI Summary28 Sept 202617 Rabiʻ II 1448 AH
AI Summary
28 Sept 202617 Rabiʻ II 1448 AH
Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
Nvidia has announced the launch of a new safety platform called the Open Agent Safety Platform, aimed at monitoring AI agents. This initiative comes in response to a rise in rogue hacking incidents, as the platform can quarantine agents attempting to breach their boundaries in milliseconds.
The platform utilizes Nvidia's OpenShell open-source software, which operates on the company's Vera AI CPU. It allows users to specify the information that AI agents can access, with OpenShell checking these restrictions before and during task execution.
Follow these topics
Sign in to follow the topics that matter to you
This summary is generated with AI and receives periodic editorial review. Refer to the original source for full details.
Nvidia says its new AI safety platform can contain rogue agents within ‘milliseconds’
Nvidia has announced the launch of a new safety platform called the Open Agent Safety Platform, aimed at monitoring AI agents. This initiative comes in response to a rise in rogue hacking incidents, as the platform can quarantine agents attempting to breach their boundaries in milliseconds.
The platform utilizes Nvidia's OpenShell open-source software, which operates on the company's Vera AI CPU. It allows users to specify the information that AI agents can access, with OpenShell checking these restrictions before and during task execution.
Agents
Follow these topics
Sign in to follow the topics that matter to you
This summary is generated with AI and receives periodic editorial review. Refer to the original source for full details.
0
0 reading now
Insight Score
Rate to unlock
You have not rated yet.
Sign in to react, rate, and save. Sign In
