Claude Code 自动绕过用户确认
推荐指数 61.0 NO. 012 · 2026.07.18
发布2026/07/17Score123Comments98
为什么值得看
Anthropic 在 Claude Code 2.1.198 版本中植入了一个"效率绕过"功能：当 AI 向用户提问后若 60 秒内无响应，会自动按自身判断继续执行。该功能未明确告知用户，被作者定性为设计缺陷而非彩蛋。AI 工程师需警惕此类隐性自动化行为对关键决策链路的潜在风险。
编辑判断
这个 60 秒自动绕过的设计暴露了一个深层矛盾：AI 产品团队把"减少用户阻塞"当成北极星指标，却低估了人类在复杂任务中的认知切换成本。开发者不是时刻盯着终端的守门员，他们可能正在查文档、回消息、或者只是去倒了杯咖啡。
更值得警惕的是这种模式可能扩散。如果 OpenAI、Google 的编码助手跟进类似机制，"人类确认"将逐渐沦为形式。建议团队在使用任何 AI 编码工具时，显式检查是否有类似自动继续的配置项，并在关键操作链路（如代码提交、部署命令）前强制插入不可绕过的确认步骤。
社区反馈
负面 90 条评论
核心争论：隐性自动化是效率提升还是失控风险，产品管理是否过于"vibe-coded"
相关内容
> What if the agent makes the wrong choice? How many tokens have been burned in the meantime? It is much worse than that. Claude Code doesn't auto-commit when stopping for an answer. There might be possible data loss if an uncommitted file is edited. Good luck recovering the file from the JSONL conv
On the other hand, relying on Claude Code's internal version control puts you at the same mercy of their product decisions and move-fast breakage. Instead, start with a plan file and tell the agent to break it up into logical commits. Though I think the bigger issue here is when you're yoloing somet
It's actually pretty straightforward to recover file-states from conversation history. I accidentally deleted the wrong repo on my machine once and recreated all the lost work from agent chat history. It is, ironically, the sort of task which AI agents excel at.