24 Hrs
Source:
وكالة الأنباء القطرية
Anthropic plans default auto mode in Claude Code
Anthropic has announced that it will activate Auto Mode by default in the "Claude Code" tool starting August 14th, aiming to reduce user intervention during programming tasks powered by artificial intelligence on Pro, Max, and Team accounts. Tests have shown that Auto Mode detects 89% of harmful actions, compared to only 13.6% detected through human review. Users agree on 97% of permission requests, which raises concerns about potentially reducing the effectiveness of oversight. Additionally, extra security measures have been implemented, including command injection checks and strict rejection rules to prevent the execution of dangerous operations.
Size: 120%Text Size
Notice: This Is an AI-Generated Summary
Comments (0)