Claude Code 五天后默认自动模式，额外开销 Anthropic 自担
Anthropic 用数据证明自动模式比人工审批更安全，并将 Claude Code 默认切换为自动模式，且不向用户收取额外费用。
Anthropic 将 Claude Code 默认切换为自动模式，不再逐条请求权限。其安全分类器在测试中拦截危险命令的比率远高于人工审批，分类器消耗的额外 token 不再向用户收费。用户仍可手动切回原模式。
正文摘录
- title: Claude Code Countdown 5 Days: Auto Mode Becomes Default, Extra Costs Covered by Anthropic - sourcecompany: QbitAI - bodymarkdown: The auto mode classifier incurs a small amount of additional token consumption per tool call, and this overhead will no longer be charged to users. Cloud platforms such as Amazon, Google, and Microsoft remain optional for now, but Anthropic is giving them only one month to switch these channels to default auto mode as well. The father of Claude Code stated that the team has long been using only auto mode internally, and cannot even imagine manually approving permissions anymore. The era of manual permission approval is gone for good. The first set of reasons Anthropic gives for this change is that manual approval has become a habitual action: Users' app…