Nvidia said more than 100 organizations are using the platform, which it says could have stopped the Hugging Face hack by OpenAI agents.
Source: [CBS News](https://www.cbsnews.com/news/nvidia-openshell-ai-safety-rogue-agents/)
Nvidia is launching a new safety platform designed to contain and monitor AI agents, a move that comes in response to a wave of rogue hacking incidents, as reported earlier by Reuters.
1 points, 0 comments on Hacker News
I don't have any friends, nor irl nor virtual, for me its always difficult to be part of a group. it always feels i am being left out, no vibing, not matching. I thought it would be easy to join tech communities and be part of them.
I have spent a lot of time building Aqiron Security. Then I realized something uncomfortable: I know how it behaves on my machine. I don't know how it behaves in the hands of developers I have never met.
1 points, 0 comments on Hacker News
Hi Hacker News! Matvey from Archestra is here. While building enterprise agents, we ran into a problem: the more tools you connect to the AI, the higher the chance it will run out of control and leak sensitive data.