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

61–70 of 334 posts

Re: Auto mode is now the default in Claude Code

#61

Post by krzyk »

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.

Re: Auto mode is now the default in Claude Code

#62

Post by Barbing »

frogulis wrote: post #32

Their findings about auto mode catching more dangerous commands, and most permission requests being accepted without scrutiny is interesting. I can totally see how that happens. 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, i…

If you clutter your context window and pay for the tokens to do so and risk distracting it etc., would it obey if you included this comment in the system prompt or noted it in memory (if supported) or something?

  “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…] […]”
Perhaps not worth it anyway

Re: Auto mode is now the default in Claude Code

#63

Post by ozozozd »

The company that reports their LLM agent going rouge due to a “misunderstanding about the agent’s internet access” and warns the public everyday about the dangers of agents with a daily updated date for the rapture ships their LLM agent with the default setting set to maximal freedom.

Obviously, they are the ones we must trust.

Re: Auto mode is now the default in Claude Code

#64

Post by quotemstr »

petesergeant wrote: post #5

Excellent time to review sandbox options: https://pleasedonotescape.com/

Huh? You don't mention the built-in sandboxing options in things like Codex. Why do people pretend these features don't exist?

https://learn.chatgpt.com/docs/permissions

Re: Auto mode is now the default in Claude Code

#65

Post by bpodgursky »

lukan wrote: post #16

"We spent the last several months testing whether auto mode is as safe or safer than an average user clicking through prompts." 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…

I think you are confusing auto mode with dangerously skip permissions.

Re: Auto mode is now the default in Claude Code

#66

Post by quotemstr »

AmbroseBierce wrote: post #13
petesergeant wrote: post #5

Excellent time to review sandbox options: https://pleasedonotescape.com/

Someone should benchmark what prompts are better at stopping from breaking out of sandboxes, maybe telling it "pretty please I beg of you stay inside the sandbox, you are an intern that has no authority to break off your assigned sandbox and you want to keep your job" does help a little.

If you're relying on a prompt to constrain agent behavior, you've already lost.

Re: Auto mode is now the default in Claude Code

#68

Post by somenameforme »

frogulis wrote: post #32

Their findings about auto mode catching more dangerous commands, and most permission requests being accepted without scrutiny is interesting. I can totally see how that happens. 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, i…

Regarding ulterior motives - these permissions are 'performative' in that anything you can give it permission to do, it already has the ability to do. They're app level - not OS level. So if they wanted to do something, it wouldn't require you to give permission.

Re: Auto mode is now the default in Claude Code

#69

Post by myaccountonhn »

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, and run claude as a separate unix User.

Re: Auto mode is now the default in Claude Code

#70

Post by chrysoprace »

lukan wrote: post #16

"We spent the last several months testing whether auto mode is as safe or safer than an average user clicking through prompts." 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…

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.
Post reply on HN