Claude Code on the web • Hacker News Board

Re: Claude Code on the web

#41

Post by mmaunder » Mon, Oct 20, 2025, 7:51 PM UTC

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 Code was amazing and a "just take my frikkin money" product. Then Codex overtook CC and is much better at longer runs on hard problems. I've seen Claude Code literally just give up on a hard problem and tell me to buy something off the shelf. Whereas Codex's ability to profoundly increase the capabilities of a software org is a secret that's slowly getting out.

I don't have any relationship with any AI company, and honestly I was rooting for Anthropic, but Codex CLI is just way way better.

Also Codex CLI is cheaper than Claude Code.

I think Anthropic are going to have to somehow leapfrog OpenAI to regain the position they were in around June of this year. But right now they're being handed their hat.

Re: Claude Code on the web

#42

Post by fragmede » Mon, Oct 20, 2025, 7:53 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…

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.

Re: Claude Code on the web

#43

Post by mrcwinn » Mon, Oct 20, 2025, 7:54 PM UTC

We’re moving almost entirely to Codex, first because often it’s just better, and second because it’s much cheaper. It’s a bet that they’re better now, but given capacity and funding, they’ll be better later too.

The only edge Claude has is context window, which we do sometimes hit, but I’m sure that gap will close.

Re: Claude Code on the web

#44

Post by poly2it » Mon, Oct 20, 2025, 7:56 PM UTC

outime wrote: post #8

charlesabarnes wrote: post #6

It's pretty frustrating that every release is IOS first without any timeline or expectation for Android

This may explain it: https://9to5mac.com/2023/09/06/iphone-users-spend-apps/

It is also relevant to know if a user who'd otherwise use app X on iOS would use X less on Android.

Re: Claude Code on the web

#45

Post by maherbeg » Mon, Oct 20, 2025, 7:56 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…

Yeah this has been my experience as well. The Claude Code UI is still so much better, and the permissioning policy system is much better. Though I'm working on closing that gap by writing a custom policy https://github.com/openai/codex/blob/main/codex-rs/execpolic...

Kinda sick of Codex asking for approval to run tests for each test instance

Re: Claude Code on the web

#46

Post by durron » Mon, Oct 20, 2025, 7:57 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…

Do you find this to still be true with the Sonnet 4.5 model?

Re: Claude Code on the web

#47

Post by hmokiguess » Mon, Oct 20, 2025, 7:57 PM UTC

ea016 wrote: post #13

No relations to them, but I've started using Happy[0]'s iOS app to start and continue Claude Code sessions on my iPhone. It allows me to run sessions on a custom environment, like a machine with a GPU to train models [0] https://github.com/slopus/happy/

This seems to be the only solution still if using bedrock or direct API access instead of Pro / Max plan, the Claude Code for Web doesn't seem to let you use it that way.

Re: Claude Code on the web

#48

Post by GreekPete » Mon, Oct 20, 2025, 7:58 PM UTC

cube2222 wrote: post #24

This is quite nice! I'm using Claude Code locally a lot, occasionally with a couple parallel session. I was very happy when they made the GitHub Action - I used it quite a bit, but in practice I got frustrated that I effectively only get a single back-and-forth out of it, I can't really "continue the conversation without losing context" - Sure, I can respond to it in the PR it makes, but that will be a fresh session…

https://docs.github.com/en/actions/tutorials/use-containeriz...

Re: Claude Code on the web

#49

Post by spondyl » Mon, Oct 20, 2025, 7:58 PM UTC

alwillis wrote: post #22

charlesabarnes wrote: post #6

It's pretty frustrating that every release is IOS first without any timeline or expectation for Android

Not unusual; most high profile apps ship on iOS first, going back to Instagram [1], which was released October 10, 2010. Instagram shipped their Android version 1.5 years later. [1]: https://www.techtarget.com/searchcio/definition/Instagram

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.

Re: Claude Code on the web

#50

Post by shireboy » Mon, Oct 20, 2025, 8:00 PM UTC

I really want this but for Azure Devops. If you're not familiar, Microsoft owns both Github and Azure Devops, and both do similar: git repos and project management. I can use Github Copilot, Claude Code CLI, etc. against code on my disk, including Azure Devops MCP. But what I can't easily do is like Github Copilot Agent and apparently this Claude Code on Web: Assign a ticket to @SomeAi and have a PR show up in a few minutes. Can't change to github for _reasons_.

Would love any suggestions if anyone in a similar story.