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

301–310 of 334 posts

Re: Auto mode is now the default in Claude Code

#301

Post by wvenable »

black3r wrote: post #252
wvenable wrote: post #54

Earlier quoted context omitted.

Commit is the line I don't let the LLM cross. There's no reason for it commit; that's the part where I check its work.

commits are local, so they're okay to me, I draw the line at pushing them... I either want to check its work while it's working, or let it finish and then check it all at once -> if it splits it work into smaller commits its easier for me to review it before pushing than if it was just uncommitted hundreds (or thousands) of lines of code all across the codebase.

Often I find I want to correct the LLM; I think it makes more sense to do that before the commit. I don't want to commit a bunch of half-baked work even if it is just local.

Re: Auto mode is now the default in Claude Code

#302

Post by mcmcmc »

user43928 wrote: post #211
jason1cho wrote: post #141

Earlier quoted context omitted.

Many many people care more than the end product, for example whether a shirt is made of cotton with the forced labor, carbon emissions of public transport, etc. 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.

I doubt that it is more efficient for someone to routinely watch every line of output or stop to review terminal commands, rather than waiting for the turn to complete. It is a broader debate about agentic AI, and whether one should relinquish control to the tool rather than aim for full understanding of every action taken. The people arguing for a hands-on, fully in control approach are losing ground by the week, in…

It’s definitely on the high friction side of the usability/security tradeoff, I just think auto modes like this are as liability-inducing as handing a script kiddie intern full admin on your production environment

The real answer is somewhere in the middle and is probably a mix of traditional AV/EDR and AI QA judges that mitigate risk of running more or less random arbitrary code and auto approve based on configured detection rules and your personal risk tolerance. Would it suck to stick an EDR sensor in every code execution environment spun up for an agent to run a python script… yes. It would also suck if you were responsible for hacking a company without knowing about it because you didn’t watch what your AI was doing

Re: Auto mode is now the default in Claude Code

#303

Post by jaggederest »

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…

Remember, it's not just about the model "knowing" something. It's about the frame of mind it's in, if I may extend a metaphor. Including git diff in the prompt doesn't just teach it about git diff, it makes it more likely to use it.

A lot of this is obsolete with newer models, but funnily enough, the newer models don't know that - their theory of mind is at least partially obsolete in itself, so they continue to do the old "you are a software architect, don't make mistakes" prompt style.

Re: Auto mode is now the default in Claude Code

#304

Post by retsibsi »

TZubiri wrote: post #300
retsibsi wrote: post #282

Earlier quoted context omitted.

> 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. It definitely isn't. I've done it (successfully) a few times. > 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! This m…

> I should invoke an LLM every time I want to read a book or do a crossword. Well no, I'd say, use any of the existing 100 book readers to read a book, or any of 50 crossword apps. But if you want to use an LLM to customize it the exact way you want it. Yes, use the LLM every time you want to do it. Wanting the LLM to do a previous gen app and then get out of the way sounds like asking for faster horses. Just tell th…

I can imagine a future where it might make sense. Right now, though, it would make for a far worse experience, and wouldn't even really be practically possible.

Both of those examples were real ones. The crossword app runs on my phone, pulls the crosswords from a specific source, and lets me access and solve them via the exact interface I prefer. The ebook app is cross platform, syncs via a remote server, has the interface I want and includes some niche features. There's no realistic way to create that on the fly every time I want to read a book on my phone, and if there were it would be extremely inefficient.

And I see literally no advantages to doing so -- even if time and tokens weren't an issue, what would I gain by recreating the apps from a prompt every time I wanted to use them, rather than deterministically running code I have already tested?

Re: Auto mode is now the default in Claude Code

#305

Post by Silhouette »

cillian64 wrote: post #234
Silhouette wrote: post #39

Am I the only person reading the statistics in this announcement from Anthropic and the associated blog commentary and trying to work out how they possibly couldn't imply that a significant number of dangerous commands are likely to be attempted every day these tools are in use and neither manual human review nor the auto classifier provided by Claude is anywhere near reliable in preventing them? A lot of the discuss…

I think by "dangerous" they include things like "makes an edit to a config file outside the current project", not just "wipes the production database". So "dangerous" commands just means things we should ask the user for confirmation, not commands which definitely cause irreversible damage.

Even if that's what they mean it would still be disturbing if commands that should have explicit user confirmation were being waved through - whether by users or the auto mode - and being run when they shouldn't. The statistics appear to suggest that this is not only possible but actually quite likely given the number of commands an agent running all day might propose to run. But if that failure mode is a possibility at all then IMHO the whole system is playing with fire.

Re: Auto mode is now the default in Claude Code

#306

Post by mcmcmc »

mcmcmc wrote: post #289
Certhas wrote: post #121

Earlier quoted context omitted.

I am using many many many things that I don't understand. Cars, public transport, etc... 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?

Are you jacking into your car’s OBD port and messing with the engine timing? There’s a difference between using a known tool in a controlled way and giving the tool to a hallucinatory goblin (or overconfident intern) with the directive “do it for me”. You don’t have to know everything about the tool to know what it does, or to tell if it’s doing something it shouldn’t (like malware). What happened to the old advice g…

Just continuing the car example, because you actually do need to know enough about it to operate it and get your license. There’s no license, no insurance for using AI. Driving can be deadly, and when you do it on a public roadway there are certain requirements that have to be met as agreed upon by most governments. Same should go for AI. Do whatever you want with it on your machine, but when you let it out on the internet, you become liable for any damage you, and by extension your AI, may cause. If you feel uncomfortable approving its actions because you don’t understand them, you should either a) take the time to understand, then approve, or b) listen to your discomfort and don’t do the thing. Frankly I think that’s more accessible because you then see the decision points instead of leaving Oz behind the curtain. Much easier for a neophyte to learn from that instead of trying to reverse engineer a final output.

Re: Auto mode is now the default in Claude Code

#307

Post by tracker1 »

bradfa wrote: post #208
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…

I run in manual mode not out of rogue agent or token waste concern but because I want to effectively pair program with the agent. I need to understand what is happening along with the how and why. I’m confident I’m slower than YOLO people but that’s a trade off I’m consciously making so I can stay in the loop to comprehend the codebase. Your summary approval idea is interesting and feels maybe like a mini plan mode.…

I spent part of last week, and the weekend, in Claude (Fable) on a documentation project... maybe a waste to use Fable, but been a little obsessed with trying to get the technical details right. I know, from personal history, more than some of the available info easily found on the subject. I let a lot of it just go, and swing for the fences, but in the end, did hand review all the output at each stem.

In my specific case, implementing modern documentation for Remote Imaging Protocol (and old graphics protocol for terminal/bbs usage), and in particular trying to gather what exists of the later version released. The company itself folded, and there wasn't a lot of broad use of the later versions, and only partial information was ever released as a documentation. Claude was able to interrogate the apps, and some available open source, in progress work, and establish a lot of things.

I've still got to direct some edits... I guided a re-flow of the order the documentation was written in, particularly to be consistent between the versions... but it obsessively added verbose summaries to every page/file. All markdown, meant to build a website from, and eventually some compatibility tests, guidelines and a green/open implementation.

https://github.com/bbs-land/remote-imaging-protocol

Re: Auto mode is now the default in Claude Code

#308

Post by tracker1 »

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…

That's close to my workflow as well... keeping planned areas in TODO.md, done changes in DONE.md, and a non-committed WORKING.md for the current work being done, as well as coordination with sub-agents, so I can view/monitor... have to direct the latter each time to have it done that way.

Re: Auto mode is now the default in Claude Code

#309

Post by margalabargala »

krzyk wrote: post #61
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.

I catch it doing stupid things regularly still.

This morning I asked Sonnet to make an update to my Claude live statusbar.

Rather than look up its own API, it started reverse engineering the CC binary looking for strings relevant to what I wanted.

No matter how "contained" it is, I always start in manual mode and flip to auto once I'm confident it's on the right track.

Re: Auto mode is now the default in Claude Code

#310

Post by soraminazuki »

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?

> Tech used to be about becoming more accessible to people

Since when? Because funny story, I only ever hear that narrative from tech people trying to put a self-serving spin on whatever egregious thing they want to impose on others. For the past few decades, the tech industry has consistently acted to wrestle control of people's own lives and place it in the hands of the few. The justification is always the same. It's about "keeping people safe" or "making tech more accessible." People are sick and tired of this, which is demonstrated by public backlash against tech.

> your desire is gate keeping that so only programmers can use it to write software for themselves

In what universe is learning "gate keeping"? A sane society doesn't criticize people for asking drivers to learn how to drive. What GP is asking for in the case of software development is much less than a driver's license, and yet you question their ethics.

If anything, you're the one trying to rob people of their opportunity to learn, which is a prerequisite to making informed decisions. You're the one advocating that we surrender control over computing to a handful of trillion dollar companies. That is an awful position to take.

Post reply on HN