Claude web, desktop, and mobile will enable auto mode by default

Oct 23

1. 09:05

   Sina Technology

   Anthropic to enable Claude auto mode by default next week; METR report discloses OpenAI monitoring gaps

   Anthropic announced that starting next week, Claude will enable auto mode by default, with another AI judging whether each step is permitted, no longer popping up a prompt to ask the user each time. The original article cites Anthropic's tests, saying that of 1,053 paid testers, only 13.6% blocked a dangerous command inserted midway, while the AI blocked 89%; after clicking through more than 50 consecutive pop-up prompts, the human interception rate dropped to about 5%. The article also relays METR and Redwood researchers' three-week audit of OpenAI's internal monitoring, saying that about one-tenth of qualifying internal Codex traffic bypassed monitoring, and lists multiple bypass paths such as trigger mechanisms, context compression, and request header settings.

   Expand summary
2. 09:05

   Sina TechRelated discussion

   Sina Tech joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

3. 05:27

   Testing Catalog

   Starting next week, Claude will enable automatic permission mode by default on Pro, Max, and Team plans

   Anthropic announced that starting next week, Claude on web, desktop, and mobile will run in automatic mode by default on Pro, Max, and Team plans. This mode no longer asks for user approval at each step; instead, automated checks block risky actions, and users can switch back to manual mode at any time.

   Expand summary
4. 05:27

   Testing CatalogRelated discussion

   Testing Catalog joined this discussion ↗

   This post contributes to heat; it is not a formal report or confirmed fact.

5. 04:04

   Claude

   Claude web, desktop, and mobile to enable auto mode by default starting next week

   Claude announced that starting next week, in the Pro, Max, and Team plans, web, desktop, and mobile sessions will run in auto mode by default. This mode no longer requests user approval step by step; instead, automatic checks block risky actions, and users can switch back to manual mode at any time. The quoted content mentions that Claude Code has used auto mode by default since August 14, and its separate classifier blocked 89% of dangerous commands in testing, compared with 14% for manual approval.

   Expand summary