Anthropic’s AI programming tool just made a somewhat big change.
In a blog post, Anthropic announced that “auto mode” will, going forward, be turned on by default in Claude Code for anyone with a Pro, Max, or Team account. The change takes effect on Aug. 14, though you might get a prompt asking if you want to turn on auto mode depending on what settings you’ve chosen for yourself.
Mashable Light Speed
This Tweet is currently unavailable. It might be loading or has been removed.
For the uninitiated (read: me), auto mode in Claude Code stops asking for human prompts at each step of the development process, instead giving the AI agent permission to proceed on its own unless the action it’s taking would be destructive or impossible to reverse. That sounds like it’d be difficult to trust as a programmer, but Anthropic claims that in testing, auto mode caught 89 percent of harmful actions, while real humans only caught 13.6 percent.
And now, that will be the out-of-the-box experience for Claude Code users. As always, though, you can still turn it off.
Topics
Artificial Intelligence
Anthropic