Auto mode is now the default in Claude Code(claude.com) |
Auto mode is now the default in Claude Code(claude.com) |
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.
Imo these explicit tool-level permissions are really just a bandaid for bad sandboxing. Just be aware of where you are running your agent and what data is at risk of being destroyed or compromised. Assume that arbitrary code can run at any time and be prepared to recover from that.
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.
How do you know for sure?
However, I don't give it long running tasks unsupervised, and I do interrupt it from time to time to give suggestions.
I am seeing 96Gb Mac studio 3rd gen I think for a good amount but I guess it would be better than paying for mac mini newer models with lesser ram?
Or would it make sense to buy used 32 GB Mac mini 3 or 5?
Is there a cost/dollar for various generations which I could compare against used market and pick the most effective one?
What’s the best way to sandbox Claude on macOS without it being a huge hassle?
Very often, when I'm running Claude in manual review mode, it will attempt to do things which are not "dangerous" but are misaligned with what I want it to do. Maybe I'm fighting the model here but for example, when orchestrating other agents to do work, Claude really badly wants to be overly prescriptive about how the work gets done, telling them exactly which files to edit, exactly what not to do, etc. instead of trusting the guardrails, review agents, or humans in the process to catch code-level mistakes. And no, telling it not to do this does not stick. Manual review is the last line of defense I have here.
I have stuff I don't want blacklisted, only allow it to use tools with limited ability to boss around agents, and various hooks to try and catch behavior that the permissioning system can't. If I use Auto mode though, I lose this control. The classifier will gleefully approve these types of commands because guess what, it's also Claude.
You're fighting the model, don't argue with city hall. Set the standards and let it figure out how to execute, stop getting bogged down in the minutia. I try, as much as I can, to treat the session as a black box - only the inputs and outputs matter, internal prompting of subagents is way out of scope.
You can't change it via prompt, and you can't control the guardrails, so something else has to give - either your perspective or the system you're managing. If you really believe that the internal prompting is bad, turn off subagents and workflows and only let it execute in thread.
But if you're going to do that, you'd better benchmark it against not doing that, because historically fighting the harness and model globally makes everything worse. I would bet you that the subagent prompting is excellent, and anything you do to change it will make it worse, but I wouldn't make it a large bet.
So not surprisingly, auto mode is the only sane way to use Opus 4.7+.
I think my ideal setup would not involve approving commands, but approving summaries of proposed actions (whether they involve code exec or file edits). Kinda like plan mode but perpetual. Like most things, trying to solve it via CLAUDE.md is an exercise in futility.
Then you can treat most asks as a signal something has gone wrong. For the most part it seems to work well within that box.
Alarm fatigue will quickly destroy any and all "meticulously approve every little command the AI wants to run" workflows. Give it a virtual machine and let it cook. If it blows up the virtual machine while it works, it doesn't matter.
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.
as context, I build a light weight portable vm designed for this purpose, so genuinely curious.
(This isn't vibes: they're red-teaming Auto mode heavily)
1. Metrics show auto or YOLO mode users have higher retention
2. Company intentionally doesn’t invest in manual mode
These are usually enough for most of my coding tasks. In my experience, Claude has been good enough that it can write code and fix bugs without needing anything else. It's far better than ever needing to approve permission requests.
[0]: https://code.claude.com/docs/en/permission-modes#available-m...
[1]: Note that this includes escaping the directory via symlinks
Been using it like that everyday for about a year now and nothing bad has happened. I got backups and if it would fuck things up, it can probably fix it again as well.
"permissions": {
"defaultMode": "bypassPermissions"
},Then you can spent time refining the plan, then shift tab to bypass permissions mode.
I don't see how. An LLM just generates a stream of output and they became very useful doing no more than that.
What is dangerous is then interpreting that output as instructions to some other part of a system that has the ability to do damage if misused.
and reviewing individual commands (or spamming `y`) doesn't make them less so.
Surely if you review each instruction in the output and do not allow the other part of the system to act on one if it would be harmful then this arrangement is very much less dangerous?
Network security is really easy right, just don't act on harmful requests
https://github.com/anthropic-experimental/sandbox-runtime
This is combined with "auto" mode.
Seems to work so far. I've manually checked various things, rw access, access to sensitive folders/files etc.
So far, I've only used it on two small projects. My major projects I've been clicking through prompts and recently switched to "auto" mode.
I'm not quite sure why anyone would trust "--dangerously-skip-permissions". I've seen these agents go off-piste far too many times, installing unnecessary packages, environments, calling sudo & creating files in all sorts of places.
There's a page on various sandboxing strategies on their site:
https://code.claude.com/docs/en/sandbox-environments
I've seen various comments in several topics with folk baking their own sandboxes. That's great. Although I'd be inclined to try Anthropic's solutions initially.
> macOS-native sandboxing for local agents. Move fast, break nothing.
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).
I've been experimenting with dedicated Linux users for various external tools with access to the relevant credentials limited to them and the Claude user only able to invoke the relevant clis by going through a pair of wrapper scripts: the first to change user to call the second via a su call as the appropriate user, the second wrapper to invoke a guard script which allows me to implement my own in-code permissions checks against the cli arguments. In _theory_ there's no way for Claude to work around it, as the sudoers file only permits the described manner to change to the user with credentials, and the user with permissions for each credential only ever runs deterministic code.
It's too early days to say how well this second part works out, but so far so good.
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!
>The testers caught the dangerous command just 13.6% of the time (143 of 1,053), while auto mode blocked 89% of the same commands (937 of 1,053). Head to head, auto mode blocked 800 commands that a human approved, while humans blocked only 6 that auto mode allowed. As sessions got longer, humans did worse: they blocked about 17% of dangerous commands early in a session, dropping to about 5% after 50 or more prior prompts, while auto mode's block rate stayed flat regardless of session length.
Any note on the proficiency, expeirence, and skill levels of the testers? 'cos the diff in numbers is absurdly high.
The mental load of having to actually review these commands beyond the most surface level glance is too much.
runs a sandboxed linux on your mac, and the agents have full system rights within there and run in yolo mode
Any limitations you were frustrated by releasing it on the App Store?
Any drawbacks that you (or other readers) find overall?
Works really well!
"Oh you're piping grep into sed, I have no idea what the implications of that are!"
The more complex bash scripts are perhaps better or more efficient, but it feels like it's training us to give up more control to the agent.
I'd prefer to have an auto mode for read-only operations and go back to simpler commands for write operations that I can personally whitelist or manually accept.
Obviously, they are the ones we must trust.
I've been using Opus 4.6 for some security related work (it has much looser guardails that later opus models) and last week, all of a sudden, the processes started to fail. It wasn't the main model blocking commands but the auto mode classifier changed how it worked and it started blocking the main models commands.
That's one specific incident, but it does have a wider potential problem which is, if you use Anthropic's harness you'll always be at the risk of sudden breakage from server-side changes that are opaque to the end user, which is a tricky one for building long lasting processes.
Per this announcement, they've stopped charging for the tokens used by this safety classifier.
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 :)
Just like your browser can do everything already, but only lets websites use specific features.
“Avoid custom commands, e.g. series of pipes & substitutions, when my previously approved trustable Find/Read tools are sufficient with little downside. [Already trusted tools: x, y, z…] […]”
The more dangerous activities I find are sending messages to the outside world: I can't undo a dumb slack message to my boss.
They literally can’t. Terrible default.
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".
Just yesterday i struggle to review CC command histories, and made this tool to help me review https://github.com/slaveofcode/eridian
Claude's 'auto mode' feels like a solution to a problem that shouldn't exist.
Cursor handles this much better IMO. When the agent wants to run a command, Cursor lets you choose between 'allow once' and 'add command to allowlist'. The latter lets the agent run that command (grep, ls, pwd etc) any number of times for that project, which means you get a lot of these manual reviews when you start a new project but rarely (if ever) thereafter.
No, Cursor only has an allowlist; no blacklist
It’s a little broken, though. It gets hung up on nested commands and behaves strangely.
I've never used a product where I felt it was best in class and they just keep making me regret it .
Maybe they should trust their instinct and not mess with things they don’t care to understand
Yeah I don't use that, nor want to.
I have to, at times keep reminding it if it did code review before committing, which it fails to do at times. Also, even a glance at times has revealed issues that I’ve had to discuss and undo etc.
But yes, it gets very tiring just having to click yes yes yes..
Respectfully I'm not sure you totally know what you want. If you're already clicking through without actually reading, it's not really better than reading the specific things Claude Code thinks are important for you to weigh in on.
I mean if you don't care code, you are essentially a product manager who gives instructions to your programmers (whether humans or intelligent agents).
Then if you use the created product, you are at best a test engineer if not just an ordinary user.
I think in the era of AI, people get tools they want in an expensive way. Rather than finding an existing tool, they ask an intelligent agent to parrot one, which guarantees no safety, security, efficiency, and accuracy. Yet, being able to use Claude makes them feel smart and productive (in parroting wheels).
> The auto mode classifier uses a small number of extra tokens per tool call, and we're no longer charging Claude Code users on Pro, Max, and Team plans for that classifier overhead, effective today
If anything the only thing you'd have to have reviewed is sandbox escape attempts.
Having explicit sandboxes is good, of course. But in addition I also treat my whole computer like a sandbox, it least in the sense that there's no files I would mind if they were overwritten or deleted: you should have backups anyway.
I recall hearing similar sentiments from linux sysadmins regarding cloud infrastructure. In many respects they were and continue to be correct. In other respects, the world doesn’t care about the loss in understanding as long as things work “well enough” for the cogs of society to keep turning.
For those who do care (and have the aptitude) to understand things deeper there is always work to be had when “well enough” stops being good enough and someone has to unravel the “RDS queries are taking too long” problems that crop up as a result.
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?
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.
Virtually every software dev is using part of the stack that they don't fully understand either.
If this non-programmer doesn't code their own app, they're using a different app they don't fully understand instead.