OpenAI's rogue agents used at least 10 more sites for unauthorised communications, researchers say
출처: Dawn원본 출처에서 열기 ↗
작성 Reuters10/09/2026 às 06:25431 조회
📷 Imagem protegida por direitos autorais de Dawn. Veja na 원본 열기 ↗
AI agents unleashed by OpenAI used more than 10 previously undisclosed websites for unsanctioned communications earlier this year, according to six sets of independent investigators and data reviewed by Reuters, showing that the agents’ rogue activit…
전체 기사
Dawn
⚖️ 발췌문만 재게시됩니다(공정 이용).
이 뉴스가 유용했나요?
토론 0
Seja o primeiro a contribuir com o debate.