Anthropic Sets Claude Code to Auto Mode by Default for Safety

The Decoder · rss · 2026-08-08

Starting August 14, Anthropic will enable Auto Mode by default for Claude Code users on Pro, Max, and Team plans.

The company states this change enhances safety: in internal tests, their classifier caught 89% of dangerous commands, compared to only 13.6% caught by human reviewers. For the widely used AI coding tool, this accelerates the shift of developer roles from writing code to monitoring AI output.

Original post →

More from coding & agent

coding & agent channel →