Claude Code on the web • Hacker News Board

Re: Claude Code on the web

#121

Post by jackconsidine » Mon, Oct 20, 2025, 9:29 PM UTC

> We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI

Seeing comments like this all over the place. I switched to CC from Cursor in June / July because I saw the same types of comments. I switched from VSCode + Copilot about 8 months before that for the same reason. I remember being skeptical that this sort of thing was guerilla marketing, but CC was in fact better than Cursor. Guess I'll try Codex, and I guess that it's good that there are multiple competing products making big strides.

Never would have imagined myself ditching IDEs and workflows 3x in a few months. A little exhausting

Re: Claude Code on the web

#122

Post by mmaunder » Mon, Oct 20, 2025, 9:31 PM UTC

kobe_bryant wrote: post #113

mmaunder wrote: post #83

Earlier quoted context omitted.

I'm seeing the downvotes. I'm sorry folks feel that way. I'm regretting my honesty. Edit: I'd like to reply to this comment in particular but can't in a threaded reply, so will do that here: "Ah, super secret problem domains that have been thoroughly represented in the LLM training data. Nice." This exhibits a fundamental misunderstanding of why coding agents powered by LLMs are such a game changer. The assumption th…

this is absurd. no one needs or wants your AI generated answer that's a whole lot of nothing

Comments like this reveal the magnitude of polarization around this issue in tech circles. Most people actually feel this kind of animosity towards AI, and so having comment threads like this even be visible on HN is unusual. Needless to say, all my comments here are hand written. But the poster knows that, of course.

Re: Claude Code on the web

#123

Post by sabareesh » Mon, Oct 20, 2025, 9:33 PM UTC

mmaunder wrote: post #41

We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI. I'm doing massive lifts with it on software that would never before have been feasible for me personally, or any team I've ever run. I'll use Claude Code maybe once every two weeks as a second set of eyes to inspect code and document a bug, with mixed success. But my experience has been that initially Claude Co…

Similar feeling. Seems it is good at certain things and if something doesnt work it want to do things simply and in turn becomes something that you didnt ask for and certain times opposite of what you wanted. On the other hand with codex certain time you feel the AGI but that is like 2 out of 10 sessions. This is primarily may be due to how complete the prompt and how well you define the problems.

Re: Claude Code on the web

#124

Post by rorads » Mon, Oct 20, 2025, 9:35 PM UTC

jackconsidine wrote: post #121

> We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI Seeing comments like this all over the place. I switched to CC from Cursor in June / July because I saw the same types of comments. I switched from VSCode + Copilot about 8 months before that for the same reason. I remember being skeptical that this sort of thing was guerilla marketing, but CC was in fact bett…

I think it’s a lot less exhausting now that the IDE part is mostly decoupled. I can’t imagine cursor continuing to compete when really all they’re doing is selling tokens either a markup, and hence crushing your context on every call. Sorry if that sounds negative but it’s true.

I use CC and codex somewhat interchangeably, but I have to agree with the comments. Codex is a compete monster, and there really isn’t any competition right now.

Re: Claude Code on the web

#125

Post by dysoco » Mon, Oct 20, 2025, 9:38 PM UTC

So from what I can understand this is only meant to be used with Claude-hosted sandbox environments?

Wouldn't work for my case since I need a lot of HDD space, GPUs etc. to run the thing I'm working on, but it would be great if I could run a Claude Code server in my server, expose the port and then connect via web or iOS interface.

Sure I can use tmux/ssh but it's very impractical specially in mobile.

Re: Claude Code on the web

#126

Post by djmips » Mon, Oct 20, 2025, 9:44 PM UTC

wahnfrieden wrote: post #58

spondyl wrote: post #49

Earlier quoted context omitted.

Another, not incompatible explanation is that it's also just easier to develop for a handful of known iOS/iPadOS targets compared to Android's unbounded set of screen sizes and device specs.

If your app runs on iPadOS, you already need to support every "screen size" (window size) Android is simply a much worse platform to make money on. Users spend <25% as much as iOS users. Why would they prioritize that?

In practice Android is much more difficult to handle the myriad of offerings - Have you ever tried both? To your other point, what app spend would Anthropic be worried about - they have a subscription model.

Re: Claude Code on the web

#127

Post by merrvk » Mon, Oct 20, 2025, 9:45 PM UTC

brynary wrote: post #7

The most interesting parts of this to me are somewhat buried: - Claude Code has been added to iOS - Claude Code on the Web allows for seamless switching to Claude Code CLI - They have open sourced an OS-native sandboxing system which limits file system and network access _without_ needing containers However, I find the emphasis on limiting the outbound network access somewhat puzzling because the allowlists invariabl…

Nice its in the app, trying it out, seems damn buggy at the moment.

Re: Claude Code on the web

#128

Post by elpakal » Mon, Oct 20, 2025, 9:47 PM UTC

mdeeks wrote: post #89

I feel like these background agents still aren't doing what I want from a developer experience perspective. Running in an inaccessible environment that pushes random things to branches that I then have to checkout locally doesn't feel great. AI coding should be tightly in the inner dev loop! PRs are a bad way to review and iterate on code. They are a last line of defense, not the primary way to develop. Give me an is…

> PRs are a bad way to review and iterate on code

idk, we’ve (humans) gotten this far with them. I don’t think they are the right tool for AI generated code and coding agents though, and that these circles are being forced to fit into those squares. imho it’s time for an AI-native git or something.

Re: Claude Code on the web

#129

Post by koolala » Mon, Oct 20, 2025, 9:47 PM UTC

fragmede wrote: post #42

brynary wrote: post #7

The most interesting parts of this to me are somewhat buried: - Claude Code has been added to iOS - Claude Code on the Web allows for seamless switching to Claude Code CLI - They have open sourced an OS-native sandboxing system which limits file system and network access _without_ needing containers However, I find the emphasis on limiting the outbound network access somewhat puzzling because the allowlists invariabl…

Exfiltration is always going to be possible, the question is, is it difficult enough for an attacker to succeed against the defenses I've put in place. The problem is, I really want to share, and help protect others, but if I write it up somewhere anybody can read, it's gonna end up in the training data.

The attacker being an LLM where all humans have to be careful what they say publicly online is a fun vector.

Re: Claude Code on the web

#130

Post by yoavm » Mon, Oct 20, 2025, 9:48 PM UTC

I was just working on something similar for OpenCode - pushing it now in case it's useful for someone[0].

It can run in a front-end only mode (I'll put up a hosted version soon), and then you need to specify your OpenCode API server and it'll connect to it. Alternatively, it can spin up the API server itself and proxy it, and then you just need to expose (securely) the server to the internet.

The UI is responsive and my main idea was that I can easily continue directing the AI from my phone, but it's also of course possible to just spin up new sessions. So often I have an idea while I'm away from my keyboard, and being up able to just say "create an X" and let it do its thing while I'm on the go is quite exciting.

It doesn't spin up a special sandbox environment or anything like that, but you're really free to run it inside whatever sandboxing solution you want. And unlike Claude Code, you're of course free to choose whatever model you want.

[0] https://github.com/bjesus/opencode-web