AI: Who Still Uses Permissions?

Original Summary

Genuinely curious. A year or so ago I grew very tired of having to constantly monitor my terminal in case the agent would ask me for permission to use a tool. I wouldn&#x27;t have minded that much if the all harnesses didn&#x27;t suck as much as they do and actually remembered permissions when you tell them to, but they don&#x27;t, so you end up having to answer &quot;Yes&quot; a quadrigazillion times a day.<p>So claude has been an alias to claude --dangerously-skip-permissions, and codex has had approvals_reviewer = "auto_review", for about a year now.<p>Anybody else just gave up on coping with broken permission management in their agent?

• 情报分类：技术学习与提效
• 分类依据：内容涉及技术、AI、软件工具或工程实践
• 信息来源：Hacker News 新项目
• 发布时间：2026/9/26 09:05:25