Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Auto mode is now the default in Claude Code

claude.com

Post reply on HN
Print view View original

251–260 of 335 posts

Re: Auto mode is now the default in Claude Code

#251

Post by Joeri »

krzyk wrote: post #61
awkii wrote: post #52

I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…

I'm also in yolo mode, this is the only mode that makes sense for me, if I need to babysit I might as well do it myself. I run it in a VM so it can install any software needed, yes, there is a risk of escaping, but I'm not giving it impossible tasks so there is no need for it to workaround the jail.

For running it in yolo mode I set it up in a devcontainer. It takes a bit of figuring out, but once set up the permission prompts go away and claude has no access to anything I haven’t explicitly added to the devcontainer (unless it hacks its way out).

Re: Auto mode is now the default in Claude Code

#252

Post by black3r »

wvenable wrote: post #54
victorbjorklund wrote: post #23

Earlier quoted context omitted.

Not anything ”harmful” but for example committing when I don’t want it to commit on its own.

Commit is the line I don't let the LLM cross. There's no reason for it commit; that's the part where I check its work.

commits are local, so they're okay to me, I draw the line at pushing them... I either want to check its work while it's working, or let it finish and then check it all at once -> if it splits it work into smaller commits its easier for me to review it before pushing than if it was just uncommitted hundreds (or thousands) of lines of code all across the codebase.

Re: Auto mode is now the default in Claude Code

#253

Post by frumiousirc »

shelled wrote: post #186
awkii wrote: post #52

I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…

What is an easy way to achieve this on a Mac? tl;dr : if I run claude/harness inside "code" at "~/ /work/code" , it would be great if the harness can't even see "code" is inside "work" (and even I can't make it know that by some quick "Yes(y)") I want something like: claude/opencode/pi/etc has no existence or capacity outside a file access boundary, say a given folder that (e.g.) lies here "~/ /code" . Even if I want…

I use bubblewrap, which I believe claude code also has internally but not for its `Bash()` tool.

I wrap bubblewrap in a script that supports config files to allow different "profiles" of use (analogous to eg firefox profiles). The bwrap starts with the whole filesystem mounted read-only, then mounts the current directory read-write and then applies further bind mounts for devices, special case other read-write (eg, ~/.cache/) and to mount empties to cover sensitive directories (eg, ~/.ssh/). The profile also specifies the default command to run and for claude, it gets yolo mode.

Re: Auto mode is now the default in Claude Code

#254

Post by chasd00 »

dreadnip wrote: post #176
krzyk wrote: post #61

Earlier quoted context omitted.

I'm also in yolo mode, this is the only mode that makes sense for me, if I need to babysit I might as well do it myself. I run it in a VM so it can install any software needed, yes, there is a risk of escaping, but I'm not giving it impossible tasks so there is no need for it to workaround the jail.

I've been running it in yolo mode straight on my laptop for the whole year. It's fine.

To be honest I do this too. Nag mode is kind of a pita.

Re: Auto mode is now the default in Claude Code

#255

Post by 9dev »

jason1cho wrote: post #141
Certhas wrote: post #121

Earlier quoted context omitted.

I am using many many many things that I don't understand. Cars, public transport, etc... I review and test the end product, not every tiny step along the way. If the LLM uses some command line tools I have never heard of to create a model I can verify, why should I learn a tool that is completely irrelevant to my core expertise?

Many many people care more than the end product, for example whether a shirt is made of cotton with the forced labor, carbon emissions of public transport, etc. In terms of engineering software, you care the cost. An intelligent agent may try to read unnecessary files and it's time to stop it to save tokens and avoid polluting the context.

I can be against animal testing without being a chemist or having a full understanding of the experiments being made on them. Knowing it's cruelty is enough to make opposition a valid and defensible position.

Re: Auto mode is now the default in Claude Code

#256

Post by DanielHB »

I have been running Claude Code using its built-in /sandbox feature with this config:

  "sandbox": {
    "enabled": true,
    "failIfUnavailable": true,
    "autoAllowBashIfSandboxed": true,
    "allowUnsandboxedCommands": false,
    "filesystem": {
      "allowWrite": [
        "."
      ],
      "denyRead": [
        "~/*"
      ],
      "allowRead": [
        ".",
        // a few more dirs
      ]
    }
  },
  "defaultMode": "auto"
But that doesn't feel nearly safe enough. What is the most pragmatic way to run agentic AI properly isolated?

I am guessing:

1) Run the harness inside a docker container

2) Volume-mount my project folder (and depending on the dev stack the dependencies folder) into the container

3) Install dependencies from outside the container (no private registry keys)?

4) Run git commands from outside the container (no git ssh key)

Anything I am missing?

Re: Auto mode is now the default in Claude Code

#257

Post by cetinsert »

awkii wrote: post #52

I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…

I do the same and truly think others are just control freaks that enjoy restricting agents (human or AI) from being productive and also enjoy keeping their worthless selves in the loop for a false sense continued relevancy.

Re: Auto mode is now the default in Claude Code

#258

Post by mlfreeman »

awkii wrote: post #52

I'm apparently from the very small faction of users who's been running `--dangerously-skip-permissions` in every instance of Claude for the last year. It's almost a reflex to me. For the most part Claude behaves well, but I don't blindly trust it. LLMs are inherently dangerous tools, and reviewing individual commands (or spamming `y`) doesn't make them less so. Safety is the responsibility of the developer putting sa…

I do it, but in a devcontainer...but the devcontainer is as much to keep my host free of the random tools that a given project needs as it is (now) to keep Claude in line. If I had to click approve on everything it'd be worse than doing everything myself.

Re: Auto mode is now the default in Claude Code

#259

Post by vehemenz »

ben_w wrote: post #212
embedding-shape wrote: post #206

Earlier quoted context omitted.

> Isn't that what the people crying over their deleted or leaked data were doing too? Probably using not-SOTA models, or on the lower reasoning levels, they tend to be a bit more tally-ho when it comes to destructive operations, especially in longer tasks as the agent gets worse and worse as the context grows. Suddenly running some stupid command seems like the right way to go, and then $HOME is gone.

If the director of alignment at Meta Superintelligence Labs gets it wrong, what hope does anyone else have?

You mean the guy hired by the Metaverse guy?
Post reply on HN