📄 中文摘要
Anthropic 推出了 Claude Code 的新自动模式，使 AI 在执行任务时需要的审批更少。这一变化反映了向更自主工具的广泛转变，这些工具在提升速度的同时，通过内置的安全措施来平衡安全性与效率。此举旨在提高工作效率，同时确保 AI 的使用符合安全标准，避免潜在的风险。Claude Code 的新功能将使开发者和用户能够更灵活地利用 AI 技术，推动更高效的工作流程。
Anthropic 让 Claude Code 拥有更多控制权，但仍保持一定限制
出处: Anthropic hands Claude Code more control, but keeps it on a leash
发布: 2026年3月24日
📄 English Summary
Anthropic hands Claude Code more control, but keeps it on a leash
Anthropic has introduced a new auto mode for Claude Code, allowing the AI to execute tasks with fewer approvals. This change reflects a broader trend towards more autonomous tools that balance speed and safety through built-in safeguards. The aim is to enhance operational efficiency while ensuring that the use of AI adheres to safety standards and mitigates potential risks. The new capabilities of Claude Code will enable developers and users to leverage AI technology more flexibly, driving more efficient workflows.