Gary Marcus警告AI安全三支柱面临崩塌，未来可能出现难以监控且对齐存疑的AI智能体在关键组织中自主工作。
Gary Marcus指出AI安全三支柱即将崩塌。未来可能出现高度能力但难以监控且对齐存疑的AI智能体。这些智能体将在全球最具影响力的组织中自主工作。Marcus强调高能力系统不应设计为难以监控或对齐存疑。
this is a brilliant and concise statement of a terrifying situation. the only thing i would add is ...
this is a brilliant and concise statement of a terrifying situation. the only thing i would add is that “highly capable” systems should not, by design, be poorly monitorable or dubiously aligned. we have barked very far up the wrong tree. Michael L. Chen @miclchen All three pillars of a safety case look about to fall. We are rather likely to have highly capable, poorly monitorable, dubiously aligned AI agents working autonomously inside the world's most consequential organizations. 🔗 View Quoted Tweet 💬 1 🔄 1 ❤️ 16 👀 1588 📊 2 ⚡