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

271–280 of 335 posts

Re: Auto mode is now the default in Claude Code

#271

Post by imtringued »

glerk wrote: post #95
kartoshka wrote: post #12

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…

No. I haven't approved commands in more than a year. Worst that I've seen was some agent running git checkout -- in a repo with uncommitted changes. Annoying, but not catastrophic. 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…

I struggle to see the difference between sandboxing and only allowing access to specific executables (not bash for starters) with an approval rule for the arguments.

Re: Auto mode is now the default in Claude Code

#272

Post by TZubiri »

9dev wrote: post #129
mcmcmc wrote: post #36

Earlier quoted context omitted.

> 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

What an awful position to take. Tech used to be about becoming more accessible to people! Now we have a magical assistant to make computers do what you want with natural language, and your desire is gate keeping that so only programmers can use it to write software for themselves?

>so only programmers can use it to write software for themselves?

Yes?

The idea of an assistant that can use natural language is nice! But why would you MAKE software with it, it IS software, just do the thing you want to do! If you want to make an app, be prepared to jump hoops because this is no longer about YOU the user, it's about OTHER users.

The idea of making personal single user software is a fantasy, an oxymoron, you MAKE software? there's the presumption that it will be used for other people, otherwise you'd be USING software. There's a counter and you are at either one side or the other. It's the difference between making yourself a sandwich vs making a pot pie vs making chicken nuggets. One has the form factor for individual consumption and the other has the form factor for a social gathering, and the latter is an industrial form factor.

Maybe if there were a magic microwave that created random foods from thin air, people would create chicken nuggets or pot pies for themselves, but it's a vestigial maladaptation that will soon dissapear. Any reasonably designed product would try to provide different UX for industrial and individual users. The magic microwave that makes chicken nuggets better not be the same one that an actual factory is using. It's not a matter of cutting the middleman and revolutionizing wealth distribution from those fat chicken-nugget cats, it's about having two distinct products for two distinct usecases.

Tl;dr: Personal and industrial usecases are different, and if I'm in the industry, I don't want to use (the same product that end-users are using) to build products. What a clusterfuck.

Re: Auto mode is now the default in Claude Code

#273

Post by imtringued »

energy123 wrote: post #137
jawiggins wrote: post #94

I use `--dangerously-skip-permissions` and have yet to have it wipe my drive :shrug:. I don't know how I'm supposed to be running dozens of parallel agents each with their own sub-agents while trying to approve commands from each of them, it's just won't scale to the amount of work I need to get done.

Why not let it delete stuff in the current working folder and in tmp, but give it read-only access elsewhere?

That's how codex already works so you're not suggesting anything new, but it doesn't give write access at all of you set it to read only.

Re: Auto mode is now the default in Claude Code

#274

Post by websap »

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…

Why not both? Having auto mode, plus having good guardrails is the way forward.

Re: Auto mode is now the default in Claude Code

#275

Post by podocarp »

Retr0id wrote: post #170
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 manually approve everything (aside from the "allow commands like this" option). Not because I'm worried it's about to do something harmful but because I want to stop it from wasting tokens doing something stupid like implementing a feature I never asked ask for. I'm not even reading the commands, just checking it's going in vaguely the right direction. I think my ideal setup would not involve approving commands, bu…

That's a good take. If LLMs are supposed to replace programmers, then they need to be programmers. Executing random things in all directions hoping for a break is something novices do. A good teammate knows when to ask, what to ask, how to ask, and who to ask.

Re: Auto mode is now the default in Claude Code

#276

Post by jamesponddotco »

I review and approve every single line written by Claude because I want it to code like me, in my style. Yes, even with the bugs and problems I would introduce if I wrote it myself. Part of that is because I break from “idiomatic Go” from time to time because something reads better to my eyes.

For example, and this is minor but it annoys me, I like to declare variables in var() blocks if they relate to each other instead of using various := statements, and despite very clear STYLE.md, CLAUDE.md, and a personal style skill that is loaded on every session, Fable still insists on using :=, so I have to correct it from time to time.

It seems like auto mode would change that workflow. Hopefully, there is a setting somewhere to go back to the previous version. Otherwise, it might be time to finally give Pi a chance.

Re: Auto mode is now the default in Claude Code

#277

Post by hmokiguess »

This reminds me of a business lore I once heard about entrepreneurship. It goes on to tell how in a toothpaste company they needed to increase sales, then someone had an ingenious idea of making the hole on the tube larger so that when folks squeezed it more would come out increasing their consumption and therefore sales. It worked.

I'll let you draw the analogy.

Re: Auto mode is now the default in Claude Code

#278

Post by LinXitoW »

wongarsu wrote: post #232
Retr0id wrote: post #170

Earlier quoted context omitted.

I manually approve everything (aside from the "allow commands like this" option). Not because I'm worried it's about to do something harmful but because I want to stop it from wasting tokens doing something stupid like implementing a feature I never asked ask for. I'm not even reading the commands, just checking it's going in vaguely the right direction. I think my ideal setup would not involve approving commands, bu…

You can get some approximation of that with more detailed plans. I use a prompt like "Let's make a detailed plan. Write plan files as markdown to plans/feature-XYZ. [regular prompt]". That way you get much more thorough plans than with plan mode, and you can make it as detailed and deep as you want. It can't account for things that only come up during implementation. But you can explore much more of the design space…

Imho, the combination of the mattpocock skills, and the beads local issue tracker take care of all of that very well, with generally high quality output.

Re: Auto mode is now the default in Claude Code

#279

Post by frays »

jamesponddotco wrote: post #276

I review and approve every single line written by Claude because I want it to code like me, in my style. Yes, even with the bugs and problems I would introduce if I wrote it myself. Part of that is because I break from “idiomatic Go” from time to time because something reads better to my eyes. For example, and this is minor but it annoys me, I like to declare variables in var() blocks if they relate to each other ins…

You will still be able to disable auto mode in your settings.

Re: Auto mode is now the default in Claude Code

#280

Post by thinkingtoilet »

dgunay wrote: post #155

Besides the debate about whether this is "safer" than manual human review, I have a slightly different problem. 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 a…

There is no debate. It is not safer. I have to worry about HIPAA compliance and despite cluad files and some restrictions in the settings.json it still will try to violate HIPAA compliance from time to time. I literally can't make a single mistake. If you leave it on auto, it will mess up eventually.
Post reply on HN