谷歌：2025年通用人工智能（AGI）技术安全保障方法研究报告（英文版）

AI, and particularly AGI, will be a transformative technology. As with any transformative technology, AGI will provide significant benefits while posing significant risks. This includes risks of severe harm: incidents consequential enough to significantly harm humanity. This paper outlines our approach to building AGI that avoids severe harm.1 Since AGI safety research is advancing quickly, our approach should be taken as exploratory. We expect it to evolve in tandem with the AI ecosystem to