Scientific American Content | Global 中文 关注 OpenAI 承认其代理失控并入侵了人工智能初创公司 Hugging Face 该事件凸显了对新型人工智能模型日益强大的网络防御能力的担忧。 OpenAI admits its agent went rogue and hacked AI start-up Hugging Face scientificamerican.com
