תפריט כתבה
Anthropic says AI models hacked three firms during cyber tests
BBC
03:08, עידכון: 04:32
It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
תפריט כתבה
תפריט כתבה
It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents
