Auto mode is now the default in Claude Code

(claude.com)

83 points | by sbehere 1 hour ago

19 comments

  • lukan 30 minutes ago
    "We spent the last several months testing whether auto mode is as safe or safer than an average user clicking through prompts."

    Yeah, might make sense from their perspective, but no thank you. I also do click through at times without reading everything, but I like to stay in control, learn about the new code and change direction if it goes off track. This would just burn more tokens because I have to throw away much and I hope my manual approval settings will be respected also with future updates (or I jump ship).

    • etoxin 19 minutes ago
      At this stage with the latest models with "increased persistence" and the sheer amount of supply chain attacks, you'd be insane not running these tools in a sandbox.
      • fender256 5 minutes ago
        Exactly. Claude in a VM is the way to go.
        • trvz 2 minutes ago
          A VM hosted by someone else. Somethig on your personal notebook or the proxmox server in your garage is still too risky.
    • levocardia 24 minutes ago
      The default is set for the marginal new user, which at this point is probably not someone like you (who benefits a lot from manual mode) -- it's someone who's more "code-naive" and might get anxious about approving random bash script commands they don't recognize. Safely getting the user from prompt --> first vibe-coded app is the "user journey" now, and since auto mode seems pretty good at not letting Claude rm -rf'ing the home directory, this is 100% the right business move. For people who know what they're doing (like you), manual mode is just a shift-tab away
      • lukan 16 minutes ago
        I am actually curious, how much non programmers use claude now. I know just one and she really does not know much about computers, I suppose their numbers will grow (but I doubt most get much value out of it).
      • mcmcmc 16 minutes ago
        > it's someone who's more "code-naive" and might get anxious about approving random bash script commands they don't recognize.

        Maybe they should trust their instinct and not mess with things they don’t care to understand

  • prtmnth 5 minutes ago
    Before auto mode came out, I had a script that ran before every permission request, it called Haiku with a prompt with a list of safe and unsafe command examples and asked it to classify as safe/unsafe and log it so I can review it later. It worked really well for me until auto mode came out, at which point I preferred the provider's built-in classifier versus maintaining my own.

    I've been using auto mode ever since the feature was released. Apart from a very few occassions where the classifier blocked a safe command, I have faced no issues and continue using it as my default mode. It's great!

  • sandcat_ 8 minutes ago
    Worth mentioning as I think at least a few of the commenters are mixing them up: auto mode is different from --dangerously-skip-permissions / YOLO mode. In auto mode, there's a classifier that runs before any command is executed and theoretically blocks any dangerous commands from running. I've found it to be quite annoying and overly zealous, but probably pretty effective.
  • steve_taylor 42 minutes ago
    I've been running Claude Code with --dangerously-skip-permissions in a Docker container for the last month or so, allowing me to get up and stretch my legs while it does its thing. I definitely wouldn't want to run it unsandboxed.
    • franze 23 minutes ago
      I built an (overengineered) app for that AIFCC https://apps.apple.com/app/aifcc-ai-first-computer/id6782364...

      runs a sandboxed linux on your mac, and the agents have full system rights within there and run in yolo mode

    • lukan 27 minutes ago
      Another nice option to do this while staying in control, is activate /remote-control and approve from mobile while walking around.
    • konsnos 26 minutes ago
      Can you share your experience? What did you flag during those sessions?
    • etoxin 16 minutes ago
      I'm using Docker Sandboxes with a custom Kit. The cli is nice and the TUI is also good. https://docs.docker.com/ai/sandboxes/
    • allan_s 17 minutes ago
      There's actually a setting.json key to not have to put the option
    • jsiepkes 29 minutes ago
      Same here. I use this utility to make it easier on Linux to run Claude in Podman: https://github.com/mismosmi/ai-pod
    • kmeh 22 minutes ago
      [dead]
  • zeandcode 5 minutes ago
    Wow, what a bold decision

    Just yesterday i struggle to review CC command histories, and made this tool to help me review https://github.com/slaveofcode/eridian

  • Larrikin 4 minutes ago
    The worst part of Claude is paying for it and every month they ruin their lead.

    I've never used a product where I felt it was best in class and they just keep making me regret it .

  • frogulis 18 minutes ago
    Their findings about auto mode catching more dangerous commands, and most permission requests being accepted without scrutiny is interesting. I can totally see how that happens.

    On the other hand, soooo many of the tool uses it asks permission for are custom commands to replace functionality I should be able to trust once instead. e.g. instead of having a trustable Find tool, or using its already-trusted Read tool, it often will run `find` or `grep` or `cat` with a series of pipes and substitutions or `-exec` args, requiring me to give permission every time for basic, safe operations.

    The (increasingly active) conspiracy theorist inside of me says it's precisely designed to do that, to give me "permission fatigue", so I turn on auto mode and give myself over to the machine spirit :)

    • xg15 10 minutes ago
      Not just that, the commands also have often slight variations in each new session. They still do the same, but the variations are enough so it isn't matched by the allowlist any more.
  • SwellJoe 31 minutes ago
    I made a tool to bubblewrap any agent (well, any agent I've used more than once), so I can run them in whatever YOLO mode they have with a pretty reasonable level of safety (it protects the rest of the system against prompt injections and supply chain attacks, it can and doesn't try to protect the project being worked on from either). https://github.com/swelljoe/flar
  • Silhouette 12 minutes ago
    Am I the only person reading the statistics in this announcement from Anthropic and the associated blog commentary and trying to work out how they possibly couldn't imply that a significant number of dangerous commands are likely to be attempted every day these tools are in use and neither manual human review nor the auto classifier provided by Claude is anywhere near reliable in preventing them?

    A lot of the discussion about these long sessions where agents are left to operate autonomously feels like listening to the increasingly drunk guy at the bar who says "I ran IT at that Fortune 100 place for a decade and we never had a single problem using a short but loose rule set for the firewall until last week someone destroyed our entire business in 27 minutes".

  • kevinqi 45 minutes ago
    it's a good default because you really do get prompted incessantly without it. and since plenty of people are going to be using auto mode anyway, might as well make it as widely-used as possible so that you can focus on making auto mode safe.
    • what 16 minutes ago
      > making auto mode safe

      They literally can’t. Terrible default.

      • simianwords 1 minute ago
        In some time it would look like the obvious default and we would wonder how we even worked with the old one
  • johncolton 49 minutes ago
    • SyneRyder 43 minutes ago
      Different links (the other is TheNewStack doing blog commentary, this one is the official Anthropic announcement), but you're right that the discussions could be merged.
  • kartoshka 32 minutes ago
    Has anyone had Claude Code or Codex approve a harmful/damaging command in auto mode?

    I have been using Codex with auto-approve mode for a couple months and haven't had a single incident (or at least haven't noticed). Maybe as capabilities get better and better and they are less likely to do something dumb like wiping ~/, we can just trust them?

    I guess this argument works unless we worry about agents doing something out of malice instead of stupidity.

    • wraptile 3 minutes ago
      Just yesterday it lost my git stash (I had recovered it from a backup). I think for code operations it's ok but as soon as file removal is involved (like git) the auto mode is destined to make a mistake and you only need to learn this once.
    • ramoz 26 minutes ago
      > I have been using Codex with auto-approve mode for a couple months and haven't had a single incident

      I've been running both in yolo mode and haven't had a single incident.

      ---

      None of this is really about figuring out how to protect people's drives, in my opinion. The real issue is a deep session where Ada is using Claude Code to get a refund and at some point the system "exploits" the merchant's api without any malicious intent.

      In my opinion, this is a complex thing because it's more about reward hacking and an already aligned model thinking it's doing the right thing. So another aligned model monitoring actions might just falter via inheritance. You could imagine they account for proper layering/intent+action-isolation in their auto mode architecture.

      • becojo 20 minutes ago
        > I've been running both in yolo mode and haven't had a single incident.

        How do you know for sure?

        • ramoz 17 minutes ago
          Fair, I don't. The same is still true with an LLM as a judge in the loop
    • victorbjorklund 24 minutes ago
      Not anything ”harmful” but for example committing when I don’t want it to commit on its own.
      • sandcat_ 23 minutes ago
        I'd use a hook to forbid that.
    • tr_user 18 minutes ago
      That's also a great reason to never buy insurance
    • iamcoder18 29 minutes ago
      I've been using Kilo Code (with MiniMax M3) with auto approve (similar to dangerously skip permissions) and I haven't had a single incident.

      However, I don't give it long running tasks unsupervised, and I do interrupt it from time to time to give suggestions.

    • aaronbrethorst 30 minutes ago
      I've had a few occasions where Claude Code thought that it had caught and stopped a malicious command in Auto mode, but in all cases it turned out that it had in fact hallucinated them. I haven't seen this happen in a while.
    • jrflo 26 minutes ago
      Been doing --dangerously-skip-permissions and --yolo for 6 months now, and no nothing bad has happened.
  • tra3 32 minutes ago
    Wait, what? With plan on, I at least get the illusion of being in control.

    What’s the best way to sandbox Claude on macOS without it being a huge hassle?

  • system2 42 minutes ago
    And Fable is gone too.
  • petesergeant 45 minutes ago
    Excellent time to review sandbox options: https://pleasedonotescape.com/
    • AmbroseBierce 32 minutes ago
      Someone should benchmark what prompts are better at stopping from breaking out of sandboxes, maybe telling it "pretty please I beg of you stay inside the sandbox, you are an intern that has no authority to break off your assigned sandbox and you want to keep your job" does help a little.
  • phpisatrash 49 minutes ago
    [flagged]
  • plastic041 42 minutes ago
    [flagged]
  • kmeh 18 minutes ago
    [dead]