News reporting focused on AI and machine learning, covering the companies behind these technologies, their real-world applications, and the ethical concerns they raise. This includes areas like generative AI (large language models, text-to-image and video), speech tech, and predictive analytics.
Anthropic is making auto mode the default permission setting in Claude Code for Pro, Max, and Team plans starting August 14, 2026. The change follows safety testing showing auto mode outperforms human review, catching 89% of dangerous commands versus 13.6% for humans. The company also cites production data and customer testimonials from Adobe, Nuro, Gusto, and Garner Health.
Anthropic will make auto mode the default for Claude Code on Pro, Max, and Team accounts starting August 14, 2026. The change removes manual approval prompts, relying on automated screening that caught 89% of harmful actions in testing, compared to 13.6% for human review. New safety features include prompt injection screening and customizable hard deny rules.
Anthropic claims its Opus 5 model is nearly immune to prompt injection attacks, with a zero percent success rate in browser agent tests across 129 scenarios. The model also leads the Gray Swan IPI benchmark, reducing attacker success to 2.0 percent after 15 attempts. The protection relies on a combination of model improvements and Auto Mode defenses.