Anthropic says auto mode will be the default in Claude Code for Pro, Max, Team plans, starting on Aug. 14, claiming it's good enough at catching harmful actions (Simon Willison/Simon Willison's Weblog)
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Anthropic will switch Claude Code to auto mode by default for Pro, Max, and Team plans beginning August 14, replacing whatever permission-prompting default preceded it.
- Anthropic is justifying the shift with a self-assessment that auto mode is already good enough at intercepting harmful actions, a claim the company made during a Fireside Chat with Cat Wu and Thariq Shihipar.
Why it matters: Paid Claude Code users on Pro, Max, and Team tiers will wake up on August 14 with a more autonomous agent running by default, meaning their code-editing assistant will take actions without prompting unless they actively opt out — and Anthropic's safety guarantee rests on its own internal evaluation, not third-party audit.
Ask SkimNews
