Anthropic announced that auto mode will become the default for Claude Code on Pro, Max, and Team accounts starting August 14. The feature, first tested in March, is designed to balance speed and control by allowing Claude Code to proceed with actions unless they are deemed “irreversible, destructive, or aimed outside your environment.” According to the company, testing showed auto mode outperformed manual review: in a study with 1,053 paid testers, it caught 89% of harmful actions compared to 13.6% for human review. Anthropic also highlighted that manual review can become habitual, with users approving 97% of permission prompts. New safety features, including prompt injection screening and customizable hard deny rules, are being added to prevent issues like data exfiltration. Claude Code Head Boris Cherny noted that the team has used auto mode exclusively for months and would not return to permission prompts.

Disclaimer: This post is for informational purposes only and is based on publicly available reports. The image is AI generated and is just for reference.
#Anthropic, #ClaudeCode, #AI, #Technology