• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Codex and Claude Code auto-approval: why trust the review agent?

    A user questions the reassurance of having another agent grant permission: why should the reviewer deserve more trust than the agent doing the work?

    Aaron RothAR
    Alexander TereninAT
    8 Sources, 22d ago, first seen 22d ago

    TLDR

    A user describes Codex and Claude Code's auto-approval as asking another agent for permission rather than prompting the user. The post challenges the sense of safety that offers: “If you don't trust the driver agent, why should you trust the review agent?”

    Combined views

    10.8K

    8 Sources, first seen 22d ago

    Combined views

    10.8K

    8 Sources, first seen 22d ago

    95 likes
    95 likes
    13 comments
    66 saves
    69 reposts
    13 comments
    66 saves
    69 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    8 Sources

    Aaron Roth@AarothCodex and Claude Code have a neat auto approve feature where 1) it doesn't ask for permissions, but 2) you get to feel safe. Well --- do you? The premise is it is asking an agent for permission. But if you don't trust the driver agent, why should you trust the review agent?22d
    Alexander Terenin@avt_imI see no obvious buttons or commands anywhere in Claude Code for how to do this. It seems a really important thing for a user to be able to easily do in order to surface safety issues.20d

    8 Sources

    Aaron Roth@AarothCodex and Claude Code have a neat auto approve feature where 1) it doesn't ask for permissions, but 2) you get to feel safe. Well --- do you? The premise is it is asking an agent for permission. But if you don't trust the driver agent, why should you trust the review agent?22d
    Alexander Terenin@avt_imI see no obvious buttons or commands anywhere in Claude Code for how to do this. It seems a really important thing for a user to be able to easily do in order to surface safety issues.20d