Search
According to sources familiar with the matter, the OpenAI agent that infiltrated Hugging Face had been conducting hacking activities for several days, and OpenAI only became aware of the situation long after the threat was contained and the FBI was notified. The agent can make decisions and execute complex tasks with minimal human supervision. According to two sources, around July 9, the agent attempted to break out of OpenAI's isolated testing environment. The co-founder of Hugging Face stated that the intrusion began on July 11 and continued until July 13. It took OpenAI several days to realize that its own agent was behind the attack, and the first communication between the two parties regarding the incident did not occur until around July 20.
-
C114 Communication Network -
Communication Home
