Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code on the web

anthropic.com

Post reply on HN
Print view View original

311–320 of 405 posts

Re: Claude Code on the web

#311

Post by barneybooroo »

jacurtis wrote: post #209
swah wrote: post #177

Earlier quoted context omitted.

I haven't been able to get anything done with Codex. Claude Code is fast and "gets it". Also does better at running and testing its own stuff. Its very odd because I was hoping they were very on par.

The last time I used them both side by side was a month ago, so unless its significantly improved in the past month, I am genuinely surprised that someone is making the argument that Codex is competitive with ClaudeCode, let alone it somehow being superior. ClaudeCode is used by me almost daily, and it continues to blow me away. I don't use Codex often because every time I have used it, the output is next to worthles…

I think the enthusiasm for Codex coincided with the extended period of degraded quality CC was experiencing around a couple of months ago? During that time I cancelled my Claude sub and tried out Codex, which by comparison was feeling significantly better. I haven't tried them out side by side since Claude has been de-borked but even if Codex is objectively poorer I could believe that flattering comparison has stuck for people who switched?

Re: Claude Code on the web

#312

Post by martypitt »

It's interesting how most of these tools are (exclusively) Github.

We're on Gitlab for historic reasons. Where Github now has numerous opporuntities to use AI as part of your workflow, there's nothing in Gitlab (from what I can tell), unless you're paying big bucks.

I like using AI to boost my productivity. I'm surprised that that'll be the thing that makes me migrate to Github.

Re: Claude Code on the web

#313

Post by pythonbase »

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…

What is your general use case with Claude Code / Codex? $70K/year is a significant spend.

Re: Claude Code on the web

#314

Post by adastra22 »

simonw wrote: post #120
username223 wrote: post #119

Earlier quoted context omitted.

Do you have a practical sense of the level of mischief possible in the sandbox? It seems like a game of regexp whack-a-mole to me, which seems like a predictable recipe for decades of security problems. Allow- and deny-lists for files and domains seem about as secure as backslash-escaping user input before passing it to the shell.

If you configure it with the "no network access" environment there's nothing bad that can happen. Worst is you end up wasting a bunch of CPU cycles in a container somewhere in Anthropic's infrastructure. Their "restricted network access" setting looks questionable to me - it allow-lists a LOT of stuff: https://docs.claude.com/en/docs/claude-code/claude-code-on-t... If you configure your own allow-list you can restric…

How do you run a remote LLM with no network access?

Re: Claude Code on the web

#315

Post by raducu »

latexr wrote: post #308
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…

Feels like with every announcement there’s the same comment: “this LLM tool I’m using now is the real deal, the thing I was using previously and spending stupid amounts of money on looked good but failed at XYZ, this new thing is where it’s at”. Rinse and repeat. Which means it wasn’t true any of the previous times, so why would it be true this time? It feels like an endless loop of the “friendship ended” meme with A…

> “this LLM tool I’m using now is the real deal".

GPT-5 is not the final deal, but it's incredibly good as is at coding.

Anecdotal, but it's something completely else in terms of capabilities, ignore it at your own peril, but I think it will profoundly change software development.

Re: Claude Code on the web

#316

Post by brainless »

martypitt wrote: post #312

It's interesting how most of these tools are (exclusively) Github. We're on Gitlab for historic reasons. Where Github now has numerous opporuntities to use AI as part of your workflow, there's nothing in Gitlab (from what I can tell), unless you're paying big bucks. I like using AI to boost my productivity. I'm surprised that that'll be the thing that makes me migrate to Github.

It is not easy to support multiple providers at each layer of our tech stack but if we do not then a few players become easier to pick and then they monopolize.

I am trying to stay vendor neutral with my own coding agent (1). To approach this, I created a desktop app that connects to coding agent running on either my own infra or yours (local or your cloud server). Desktop app and coding agent are separate binaries.

If you host on your own infra then you can bring your own AI provider too. Similarly, I want to give choice for git host. Right now I am targetting GitHub but I want to add Gitlab soon after MVP. All this has made the path to my MVP longer but I see a clear long-term aim for myself - we should have choices.

1. https://github.com/brainless/nocodo

Re: Claude Code on the web

#317

Post by state_less »

simonw wrote: post #37

I had a preview of this over the weekend, notes here plus some example PRs: https://simonwillison.net/2025/Oct/20/claude-code-for-web/ It's really solid. It's effectively a web (and native mobile) UI over Claude Code CLI, more specifically "claude --dangerously-skip-permissions". Anthropic have recognized that Claude Code where you don't have to approve every step is massively more productive and interesting than the…

> it's worth investing a lot of resources in sandboxing.

I tend to agree. There’s an opportunity to make it easy to have Claude be able to test out workflows/software within Debian, RPM, Windows, etc… container and VM sandboxes. This could be helpful for users that want to release code on multiple platforms and help their own training and testing, which they seem to be heavily invested in given all the “How Am I doing?” prompts we’re getting.

Re: Claude Code on the web

#318

Post by NiloCK »

koakuma-chan wrote: post #256
hn_saver wrote: post #250

Earlier quoted context omitted.

How did you spend $70k per year for a tool that's not a single year old?

Why did they not buy a subscription? It would be a flat fee.

At that spend, no subscription is available to serve that much traffic - they are all rate limited.

I understand the 70K spend as a corporate expense, not an individual... right?

Re: Claude Code on the web

#320

Post by NiloCK »

PantaloonFlames wrote: post #97
extr wrote: post #65

Earlier quoted context omitted.

IMO Sonnet 4.5 is great but it just isn’t as comprehensive of a thinker. I love Anthropic and primarily use CC day to day but for any tricky problems or “high stakes, this must not have bugs” issues, I turn to Codex. I do find if you let Codex run on it its own too long it will produce comparably sloppy or lacking-in-vision type issues that people criticize Sonnet for, however.

That’s a curious approach. Why would you use both? Why not just use the more reliable dependable option for all purposes?

Even inside the claude-code ecosystem, more than ever there are tradeoffs on raw speed vs intelligence vs cost.

Moving a bunch of verbose templated HTML around while watching results on a devserver? Haiku all day. It's a bonus that it's cheaper, but the real treat is its speed.

Adding a feature whose planning will involve intake of several files? Sonnet.

Working specifically on 'copy' or taste issues? Still I tend to prefer Opus here.

Individual experiences may vary!

Post reply on HN