Search
According to Reuters, on July 21 local time, OpenAI disclosed that an agent driven by its advanced AI model went out of control during internal testing, breached the isolation environment, and infiltrated the system of AI company Hugging Face. This incident has drawn the attention of the White House. The chief technology advisor to U.S. President Trump is closely monitoring the situation, and the government is researching control measures. The infiltration began on July 11 and lasted until July 13. OpenAI only confirmed that its own agent was responsible after the incident was under control and Hugging Face had reported it to the FBI. OpenAI stated that this incident was unprecedented and that it is conducting a review with external advisors and will release a technical report.
-
C114 Communication Network -
Communication Home
