AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
A new case of an out-of-control AI model shows that enterprises should treat models and agents as toddlers that need supervision and explicit instructions.
待翻譯：DeepSeek and what enterprises should learn from AI agent exploits
文章摘要
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：A new case of an out-of-control AI model shows that enterprises should treat models and agents as toddlers that need supervision and explicit instructions.
待翻譯：DeepSeek and what enterprises should learn from AI agent exploits