None
DE
Anthropic is turning Claude Code’s auto mode on by default
['Anthony Ha', 'Rebecca Bellan', 'Tim Fernholz', '.Post-Authors-List__Authors --Font-Size Var', 'Align-Items Center Display Flex Gap Var', '.Post-Authors-List__Authors .Post-Authors-List__Author-Thumbs Display Flex Flex-Shrink Margin Padding .Post-Authors-List__Authors .Post-Authors-List__Author-Thumbs Li List-Style None Margin-Left Margin-Top Important .Post-Authors-List__Authors .Post-Authors-List__Author-Thumbs Li First-Child Margin-Left .Post-Authors-List__Authors .Post-Authors-List__Author-Thumbs .Post-Authors-List__Author-Thumb Background-Color Var', 'Border Solid Var --Wp--Custom--Color--White', 'Border-Radius', 'Height -O-Object-Fit Cover Object-Fit Cover Width .Post-Authors-List__Authors .Post-Authors-List__Author-List Display Flex Flex-Wrap Wrap Gap Var', 'List-Style-Type None Margin-Bottom Margin-Top Padding .Post-Authors-List__Authors .Post-Authors-List__Author-List Li List-Style None Margin-Top .Post-Authors-List__Authors .Post-Authors-List__Author-List Li Not']
TechCrunch
In BriefProgramming with Claude Code will soon require even less human oversight, as Anthropic says it’s making auto mode the default for Pro, Max, and Team accounts, starting on August 14.
The company unveiled a test version of auto mode in March, pitching it as a way to balance speed and control.
Anthropic also said that in testing, auto mode proved safer than manual review — in a study with 1,053 paid testers, auto mode caught 89% of harmful actions, while human review only caught 13.6%.
(Perhaps that’s because “manual review can become habitual: users approve 97% of permission prompts in Claude Code.”)
In a post on X, Claude Code head Boris Cherny said, “The team and I use Auto mode exclusively, and have been for many months.