00:15
Anthropic が Claude Code に自動モードを導入、AI が自主的に操作の安全性を判断
Anthropic has introduced a new permissions mode called "auto mode" for Claude Code, providing a more flexible option between item-by-item approval and completely skipping permissions by pre-reviewing operation safety. Safe operations are automatically allowed, while risky operations are blocked and require user confirmation. This mode reduces risks but does not completely eliminate them, and it is recommended to use it in isolated environments. It is now available to some users.
もっと