Claude Code Goes Autonomous by Default August 14

Anthropic is making auto mode the default for Claude Code on Pro, Max, and Team accounts starting August 14. In auto mode, the AI proceeds without asking for human approval unless an action is deemed irreversible, destructive, or outside the user's environment. The company says testing showed auto mode caught 89% of harmful actions compared to just 13.6% caught by human reviewers, partly because users approved 97% of manual prompts out of habit. New safety features including prompt injection screening and customizable hard deny rules are also being added.