Auto mode is now the default in Claude Code for Pro, Max, and Team plans

Anthropic announced that new Claude Code sessions on Pro, Max and Team plans would default to auto mode from August 14, 2026, while preserving pinned defaults. Auto mode routes proposed actions through a classifier instead of routinely asking users to approve each one. The company's announcement presents this as a response to habitual approval of permission prompts.

In its controlled study, 1,053 paid testers encountered a dangerous command substituted into a permission prompt. Human review caught 13.6% of those commands; auto mode blocked 89% of the same commands. These results support automated screening over the manual behavior observed in that experiment, while the remaining misses show why fewer interruptions should not be read as complete protection.

“We’re going to publish some evals in the coming weeks, but we’ve pretty much mitigated every attack.”

Cat Wu

“Only 13.6% of the humans refused that harmful action. Auto mode would have blocked 89% of those actions.”

“In this evaluation, none of the 720 attack attempts succeeded against Claude Fable 5, Opus 5, or Sonnet 5 running auto mode.”

“Confirmation fatigue is real, and asking humans to click "OK" every few steps is clearly not going to result in safe behavior.”

“But... I'd like to see more independent confirmation of this.”