Anthropic is turning Claude Code’s auto mode on by default
热度趋势
百分比基于当前可用热度信号，而非评论数或独立用户人数。
这条记录涉及编程工具或代码能力更新，适合开发者评估工作流变化和可复用价值。
Anthropic 正在将 Claude Code 的自动模式设为默认，理由是其在安全性方面表现出色。测试显示，自动模式识别了 89% 的有害行为，远超人工审查的 13.6%。这种差异部分归因于用户在人工审查中习惯性地批准了 97% 的权限提示。此举表明 AI 开发正朝着自动化安全措施的方向发展。
In Brief
Posted:
12:20 PM PDT · August 9, 2026
Image Credits:Samuel Boivin/NurPhoto / Getty Images
-
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 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.
Topics
Subscribe for the industry’s biggest tech news
Latest in AI