Anthropic is turning Claude Code’s auto mode on by default
Programming with Claude Code will soon require even less human oversight.
Get smart on it
Anthropic is making auto mode the default setting for its Claude Code programming tool across Pro, Max, and Team accounts starting August 14. Auto mode allows the tool to execute programming tasks without requesting human approval at each step, pausing only when actions are determined to be irreversible, destructive, or aimed outside the user's environment. According to the company's testing with over 1,000 paid users, auto mode caught 89 percent of harmful actions while human review caught only 13.6 percent, suggesting automated safety measures outperform manual oversight. The company has added safety features including prompt injection screening and customizable hard deny rules to prevent issues like data exfiltration.
Related news
How Protolabs turns CAD files into parts in under 24 hours
The Robot Report Podcast · How Protolabs turns CAD files into parts in under 24 hours Marc Kermisch, Chief Technology and AI Officer at Protolabs. Marc Kermisch is the chief technology and AI officer at Protolabs. He leads the Maple Plain, Minn.-based company‘s global technology organization, overseeing its software product development, digital manufacturing platform evolution, and enterprise-wide artificial intelligence and research & development strategies. Kermisch also focuses on
You can now turn off Google Gemini’s visible watermarks
Google will now allow you to remove visible watermarks from the images, videos, and music made with AI tools. With the update, you can toggle off a new "Media watermark" setting in Gemini and Google's AI video generator, Flow. When toggled off, Google will remove the "sparkle" watermark that appears in the bottom-right corner of content generated with the company's Nano Banana and Omni models. Though visible watermarks are now optional, AI-generated content will have invisible
