Monday, August 10, 2026
Anthropic makes Claude Code's auto mode the default
Anthropic said on August 7 that new Claude Code sessions on Pro, Max, and Team plans will default to auto mode starting August 14, letting Claude act without step-by-step approval unless a classifier flags a command as destructive, irreversible, or reaching outside the user's environment. Anthropic said its classifier blocked 937 of 1,053 planted dangerous commands in testing (89%) versus just 143 (13.6%) caught by paid human testers reviewing manually, attributing the gap to approval fatigue; enterprise and API accounts get the change in September or later.
/ Sources
/ Related
- Anthropic to embed invisible watermarks in Claude's textWednesday, August 12, 2026
- Anthropic signs $9.1B, 20-year compute deal with Riot PlatformsWednesday, August 12, 2026
- Anthropic forms Theseus data center venture with Macquarie, GICMonday, August 10, 2026
- Sanders tells OpenAI, Anthropic, Meta CEOs to pause AI developmentMonday, August 10, 2026