Anthropic 将默认启用 Claude Code 的自动模式

随着 Anthropic 宣布将从 8 月 14 日起为 Pro、Max 和 Team 账户默认启用自动模式，使用 Claude Code 编程将很快需要更少的人为监督。

该公司最初于今年 3 月发布了自动模式的测试版本，并将其定位为在速度与控制之间取得平衡的方式。正如 Anthropic 在周五发布的公告中解释的那样，当 Claude Code 处于自动模式时，不会在每一步都显示请求人工批准的提示；除非某项操作被判定为“不可逆、具有破坏性，或指向你的环境之外”，否则它将继续执行。

Anthropic 还表示，在测试中，自动模式被证明比人工审查更安全：在一项有 1,053 名付费测试者参与的研究中，自动模式识别出 89% 的有害操作，而人工审查仅识别出 13.6%。这一结果或许是因为，“人工审查可能会形成习惯：用户会批准 Claude Code 中 97% 的权限提示。”

在一则 X 平台帖子中，Claude Code 负责人 Boris Cherny 表示：“团队和我完全只使用自动模式，而且已经持续使用了很多个月。我无法想象再回到权限提示的方式！”

该公司还表示，已经新增了提示注入筛查、可自定义硬拒绝规则等安全功能，以防止数据外泄等问题。

Programming with Claude Code will soon require even less human oversight, as Anthropic says it’s making auto mode the default for Pro, Max, and Team accounts, starting on August 14.

The company first unveiled a test version of auto mode in March, pitching it as a way to balance speed and control. As Anthropic explained in its announcement on Friday, when Claude Code is in auto mode, instead of presenting prompts asking for human approval at each step, it will proceed unless an action is determined to be “irreversible, destructive, or aimed outside your environment.”

Anthropic also said that in testing, auto mode proved safer than manual review — in a study with 1,053 paid testers, auto mode caught 89% of harmful actions, while human review only caught 13.6%. (Perhaps that’s because “manual review can become habitual: users approve 97% of permission prompts in Claude Code.”)

In a post on X, Claude Code Head Boris Cherny said, “The team and I use Auto mode exclusively, and have been for many months. I couldn’t imagine going back to permission prompts!”

The company also said it’s been adding new safety features like prompt injection screening and customizable hard deny rules to prevent things like data exfiltration.