Anthropic 為科學實驗室中的 AI 代理設定規則
anthropic 發布模型硬體標準，以安全地指導人工智慧代理與物理系統（如顯微鏡和製造機器）的交互。這旨在防止風險，同時實現科學研究和行業的自動化。
anthropic has developed a new framework, model hardware standard, to guide the interaction between ai agents and physical systems such as microscopes, liquid-handling equipment, and manufacturing machines. this framework aims to balance the potential of ai to automate scientific research and manufacturing with new risks. anthropic will collaborate with trusted partners to determine how to maximize safety before making it generally available. the standard will allow scientists and engineers to specify how ai models should avoid using different hardware to prevent mishaps. this development is part of anthropic's efforts to advance the safe use of ai in various industries.