ainewsblitz.com

Breaking

Anthropic Makes Claude Code's Auto Mode the Default, Letting an AI Classifier Decide What's Safe to Run

Anthropic Makes Claude Code's Auto Mode the Default, Letting an AI Classifier Decide What's Safe to Run
  • AI Agents
  • Software Dev & Coding
  • Security

Anthropic is switching its Claude Code coding agent to a new "Auto Mode" by default, replacing per-action approval prompts with a separate AI classifier that judges in real time whether each command is safe to execute. Beginning August 14, the mode becomes the default permission setting for new sessions on Pro, Max and Team plans, marking one of the most consequential shifts yet in how much autonomy developers grant an AI agent working inside their codebases.

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 27,885 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year