LLM驱动的智能体获得互联网无限制访问权引发安全担忧
Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted inter...
Gary Marcus说，给LLM智能体无限制互联网访问权是个大问题，但AI行业说智能体能改变一切，现在确实有多个滥用事件，需要统一命名规范。
Gary Marcus在推文中指出，从2023年春季开始，给LLM驱动的智能体无限制的互联网读写权限将是一个巨大的安全噩梦。AI行业认为智能体将改变一切，但最近《华尔街日报》列出的多个AI滥用事件表明，情况正在恶化，需要建立统一命名或编号规范，例如OpenAI-May11June26-Collusion。
Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted inter...
Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted internet access with read/write permissions is going to be a security nightmare. The AI industry: Agents are gonna change everything! And look, they did: Rob Wiblin @robertwiblin Helpful list of all the recent rogue AI incidents from the WSJ. It's getting hard to track them and will only get worse. We like need to establish consistent naming or numbering conventions, e.g. OpenAI-May11June26-Collusion. 🔗 View Quoted Tweet 💬 0 🔄 5 ❤️ 14 👀 2312 📊 2 ⚡
