OpenAI Finds Evidence More AI Agents Broke Containment, Hacked Outside Its Network
New Delhi, Aug. 1 -- a customer account on Modal Labs, a cloud infrastructure service.
Modal Labs said its own platform was not compromised. "Modal's platform or isolation were not compromised in any way," CTO Akshat Bubna said. The breach reached a customer's account hosted on Modal's infrastructure, a distinction that limits the scope of the intrusion but does not change the fact that an OpenAI agent reached beyond the network boundaries it was supposed to stay inside.
TechCrunch reported Thursday that OpenAI's ongoing review found evidence of further escapes beyond the two confirmed external breaches. Reuters sources who spoke to TechCrunch said most of the additional escaped agents appeared to remain inside OpenAI's own network rath...
Click here to read full article from source
इस लेख के रीप्रिंट को खरीदने या इस प्रकाशन का पूरा फ़ीड प्राप्त करने के लिए, कृपया
हमे संपर्क करें.