Anthropic is turning on auto mode by default in Claude Code, ending the practice of requiring users to approve every file edit and shell command and instead relying on a lightweight safety classifier to decide what is safe to run. The change, detailed on the company's blog, begins rolling out on August 14 as the default for new sessions on Pro, Max and Team plans, while accounts that have already set their own defaults may be left unchanged.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.