Anthropic is making its Claude Code 'auto mode' the default for all users in five days, a setting that handles tool calls and associated token costs without explicit user approval. This change stems from Anthropic's observation that users overwhelmingly approve permission requests (97%) and that the auto mode is significantly more effective at blocking dangerous commands than human users, especially in longer sessions. The company has also enhanced the auto mode's safety features through testing with AI safety firms and OpenAI, improving its ability to detect and prevent data leaks and prompt injection attacks. AI
IMPACT This shift to default auto mode in Claude Code aims to improve safety and reduce user friction, potentially setting a new standard for AI agent permission handling.
RANK_REASON Product release from a frontier AI lab (Anthropic) detailing a new default mode for their coding assistant. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- Anthropic
- Apollo Research
- Claude Code
- Claude Fable 5
- Claude Opus 4.7
- GPT-5.6 Sol
- OpenAI
- Sonnet 5
- Trajectory Labs
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
