📄 中文摘要
Anthropic推出了Claude Code的新功能“自动模式”，该工具允许人工智能在用户的授权级别上做出决策。该功能为程序员提供了一种更安全的选择，避免了在不断的指导和赋予模型过高自主权之间的两难。Claude Code能够独立代表用户行动，这在某些情况下非常实用，尤其是在需要快速决策或处理复杂任务时。通过这一新模式，用户可以在保持一定控制的同时，享受AI带来的便利。
Anthropic的Claude Code推出更安全的自动模式
出处: Anthropic’s Claude Code gets ‘safer’ auto mode
发布: 2026年3月25日
📄 English Summary
Anthropic’s Claude Code gets ‘safer’ auto mode
Anthropic has introduced a new feature called 'auto mode' for Claude Code, a tool that allows AI to make permission-level decisions on behalf of users. This feature provides a safer alternative for programmers, navigating the dilemma between constant guidance and granting the model excessive autonomy. Claude Code is capable of acting independently on behalf of users, which can be particularly useful in situations requiring quick decisions or handling complex tasks. With this new mode, users can maintain a degree of control while benefiting from the convenience offered by AI.