Starting August 14, Claude's coding assistant will automatically start working on tasks without you needing to manually approve each step. This makes it feel more like an automated helper.
The change applies to Pro, Max, and Team accounts.
The company also said it’s been adding new safety features like prompt injection screening and customizable hard deny rules to prevent things like data exfiltration.
Original reportingAnthropic is turning Claude Code’s auto mode on by default | TechCrunchRead original ↗