ainewsblitz.com

Breaking

Anthropic to Make AI-Judged 'Auto Mode' the Default in Claude Code, Citing Safety and Productivity Gains

Anthropic to Make AI-Judged 'Auto Mode' the Default in Claude Code, Citing Safety and Productivity Gains
  • AI Agents
  • Software Dev & Coding
  • Security

Anthropic will switch its Claude Code developer tool to an automated permission system by default for Pro, Max and Team subscribers starting August 14, 2026, handing safety decisions to an independent AI classifier rather than requiring users to approve each command. The move, first detailed in company engineering materials and reported by security outlets, marks a significant shift away from the manual, click-to-approve workflow that has governed how coding agents execute potentially risky actions.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,900 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year