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

221–230 of 338 posts

Re: Auto mode is now the default in Claude Code

#221

Post by mlrtime »

coldtea wrote: post #197
borzi wrote: post #194

Earlier quoted context omitted.

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"

I run in auto permission mode and it will run with 1 task and end to completion. On the rare event it needs to rmdir or rm -r a dir, the permission mode will stop the agent. Sometimes annoyingly... so its more like. "I've never had a bullet hit me yet inside a office building on the 42nd floor".

Re: Auto mode is now the default in Claude Code

#222

Post by drdec »

dist-epoch wrote: post #134
__MatrixMan__ wrote: post #82

Earlier quoted context omitted.

This is the only kind of agent security that makes sense to me. Constrain it like you would any other subprocess. Unprivileged OS users, SELinux, firewalls, VMs... Unikernels? eBPF?

Escalations to root are a dime the bucket.

That argument is letting the perfect be the enemy of the good.

There is no perfect security.

Re: Auto mode is now the default in Claude Code

#223

Post by lyu07282 »

jmward01 wrote: post #169

It goes off the rails too quick too often right now for this. Sure, you got something easy in 5 files? You are building throwaway prototypes or proof of concept? Go for it. You have a real project you expect to maintain and work with others on? Well, say goodby to any actual architectural design. It is hard keeping these things building scalable maintainable code right now. It is like letting a junior dev come up wit…

True its is like a junior dev with brain damage and insane ego (especially Fable who thinks its a rockstar programmer for some reason), but you have to use plans, anything else turns into a turd way to quickly. Write a summary of what you want to happen, have it plan it (this is where the architecture decision gets made) then iterate on that plan until its detailed enough and the design is sound. Let it work in auto mode on the plan then review the changes. This only really works if you have a good mental model of the codebase.

Its still a lot of work, just less than having to code literally everything yourself. I agree though it feels to me 99% of discussions on LLMs is either marketing bullshit or junior devs talking out of their asses about LLM coding, who anyway feel that

> "different implementation of security for every endpoint in your app"

is perfectly reasonable. It also seems as if people haven't sandboxed claude already (WTF), that says a lot too about the competence of people speaking here.

Re: Auto mode is now the default in Claude Code

#224

Post by mlrtime »

coldtea wrote: post #195
dyauspitr wrote: post #124

Earlier quoted context omitted.

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 prot…

How are ssh keys going to be leaked, the agent never needs to read them.

Re: Auto mode is now the default in Claude Code

#225

Post by mlrtime »

thunfischtoast wrote: post #105
Silhouette wrote: post #73

Earlier quoted context omitted.

LLMs are inherently dangerous tools 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 outpu…

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.

Depending on the company, that sounds like a bad environment more than a agent issue, no dev/prod network isolation?

Re: Auto mode is now the default in Claude Code

#226

Post by happosai »

dist-epoch wrote: post #136
Silhouette wrote: post #73

Earlier quoted context omitted.

LLMs are inherently dangerous tools 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 outpu…

> do not allow the other part of the system to act on one if it would be harmful Network security is really easy right, just don't act on harmful requests

Yeah, just drop when you see the RFC3514 evil bit

Re: Auto mode is now the default in Claude Code

#227

Post by cillian64 »

rcfox wrote: post #150

Auto mode feels like a solution to a problem they created. Whitelisting commands used to work fairly well until the agents started generating complex bash commands that it gave up trying to classify. "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 ag…

sed can be used to edit files (with the -i option). Not sure how this interacts with piping to its STDIN, but I wouldn't automatically assume `grep | sed` is safe.

I was thinking about this the other day, standard UNIX utilities seem poorly suited for this because they have so many weird options/flags with "unsafe" side effects. I have no idea if grep, for example, has some niche option to make it write/edit/delete files, so I wouldn't be comfortable blanket whitelisting it.

Re: Auto mode is now the default in Claude Code

#228

Post by drdec »

user43928 wrote: post #199
jaggederest wrote: post #173

Earlier quoted context omitted.

> 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 s…

IMHO, the verbosity is an attempt to make the results more deterministic. The more specific the prompt, the less wiggle room.

Re: Auto mode is now the default in Claude Code

#229

Post by dan_t »

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…

[dead]

Re: Auto mode is now the default in Claude Code

#230

Post by chrysoprace »

lukan wrote: post #72
chrysoprace wrote: post #70

Earlier quoted context omitted.

Having used a bit of a mix of Claude Desktop and Claude Code lately, I discovered that Claude Desktop just times out when it asks you for a decision, and just goes ahead with the action anyway. There is no way to turn this off that I've found, unlike Claude Code where you can ask it to never time out.

Oh yes, over this I also stumbled recently (with Claude CLI) and was annoyed much by it. Is there really no setting to turn it off?

There is for Claude Code[0], but not for Desktop. It's `askUserQuestionTimeout` and you can set it to `never`.

[0] https://code.claude.com/docs/en/settings

Post reply on HN