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

191–200 of 338 posts

Re: Auto mode is now the default in Claude Code

#191

Post by embedding-shape »

binsquare wrote: post #120
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.

What VM do you run it in? as context, I build a light weight portable vm designed for this purpose, so genuinely curious.

I'm using a container. The risk isn't exactly "agent leverages 0-day against you to steal all your data" but more "agent mistakenly though $HOME was theirs and deleted it" so as long as you "copy data in > copy data out" without bind-mounting or automatically sync files, container works just fine for "isolating" them.

Re: Auto mode is now the default in Claude Code

#192

Post by coldtea »

paul_h wrote: post #144
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 think all of Anthropic's own staff use --dangerously else they'd work on the usability of the massively imperfect 1-approve-once and 2-approve-forever multi-choice and outcome.

>else they'd work on the usability of the massively imperfect 1-approve-once and 2-approve-forever multi-choice and outcome.

Their profit motive is in NOT improving that, and luring you to depend all the more automatically to Claude.

Re: Auto mode is now the default in Claude Code

#193

Post by coldtea »

usef- wrote: post #164
paul_h wrote: post #144

Earlier quoted context omitted.

I think all of Anthropic's own staff use --dangerously else they'd work on the usability of the massively imperfect 1-approve-once and 2-approve-forever multi-choice and outcome.

That's exactly why Auto mode was made, and reportedly what they all use. It's the easy option, with a better safety score than human review. (This isn't vibes: they're red-teaming Auto mode heavily)

>with a better safety score than human review.

According to them - for things they care about.

Re: Auto mode is now the default in Claude Code

#194

Post by borzi »

coldtea wrote: post #189
dreadnip wrote: post #176

Earlier quoted context omitted.

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

Isn't that what the people crying over their deleted or leaked data were doing too? "I've been playing Russian roulette with a 1024 chamber gun for a year now, it's fine"

I'm assuming this happens to the people vibe coding and running 30+ agents in parallel that are "coordinating" each other. I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output.

Re: Auto mode is now the default in Claude Code

#195

Post by coldtea »

dyauspitr wrote: post #124
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…

Yeah who cares what it does, everything is backed up, everything can be rolled back. I always run it with the keys to the kingdom.

Yeah, if you don't care if your ssh keys or data are potentially posted all over the internet, more power to you...

Not to mention cases like some comment here:

"I've caught Fable discovering the ip to a production server in documentation and attempting to connect there on its own to run commands without explicitly being prompted to. It didn't work because I was watching it live and and also the key was password protected, but yeah, I do see some danger."

Re: Auto mode is now the default in Claude Code

#196

Post by edukite »

jpnc wrote: post #187
kabes wrote: post #135

Earlier quoted context omitted.

My .bashrc has `alias claude='claude --dangerously-skip-permissions'` 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.

>nothing bad has happened That you're aware of.

Famous last words

Re: Auto mode is now the default in Claude Code

#197

Post by coldtea »

borzi wrote: post #194
coldtea wrote: post #189

Earlier quoted context omitted.

Isn't that what the people crying over their deleted or leaked data were doing too? "I've been playing Russian roulette with a 1024 chamber gun for a year now, it's fine"

I'm assuming this happens to the people vibe coding and running 30+ agents in parallel that are "coordinating" each other. I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output.

>I've never seen Claude do or even suggest anything remotely dangerous when I'm just giving it incremental tasks and reviewing the output.

"I've never had a bullet hit me yet"

Re: Auto mode is now the default in Claude Code

#198

Post by danielbln »

jjav wrote: post #188
kabes wrote: post #135

Earlier quoted context omitted.

My .bashrc has `alias claude='claude --dangerously-skip-permissions'` 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.

> and nothing bad has happened This is the same reasoning for not wearing seat belts or a helmet on a motorcycle. Nothing bad has happened yet so obviously there is no need for any protection.

I've been raw dogging Claude Code for the better part of last year as well, but I'm under no illusion that it's safe to do so, I just cannot approve seven trillion approval prompts and stay sane. I've since. switched to auto mode, however.

Re: Auto mode is now the default in Claude Code

#199

Post by user43928 »

jaggederest wrote: post #173
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…

> Maybe I'm fighting the model here > And no, telling it not to do this does not stick. 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 prom…

I think he has a point. I noticed the same with skills that invoke another agent harness.

I just have a skill to review the changes in the current worktree.

By default, it will put lots of instructions about locating the changes into the prompt, like explaining how to use git diff.

These instructions are obviously unnecessary. I can believe that the same issue of needlessly verbose prompts might exist with subagent spawning.

I would not go to customize that one however. With skills, it is a more natural fix.

Re: Auto mode is now the default in Claude Code

#200

Post by adrian17 »

jaggederest wrote: post #173
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…

> Maybe I'm fighting the model here > And no, telling it not to do this does not stick. 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 prom…

If I ask a model to do a change involving editing a file, and it starts investigating internals of my build system, then sure it might not be counterproductive or break the task, and might have taken only extra 30 seconds; but for all I know, my quick rejection of a shell invocation (with a simple "irrelevant to the task" comment) might have just saved me half of today's Opus tokens, which already makes it worth it.
Post reply on HN