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

111–120 of 405 posts

Re: Claude Code on the web

#111

Post by hugs »

arjie wrote: post #87

A thing I really like with Claude Code is how well it uses the bash scripts you give it. I also have a browser control MCP installed and it's pretty good for it to full-cycle around the approach. I have a staging database that it has the passwords to that it logs in and runs queries on. This whole thing means it loops and delivers good results for me. I'll try this, but the grounding seems crucial for these LLMs to d…

which specific functions/features of the browser control MCP do you lean on the most?

Re: Claude Code on the web

#112

Post by dboreham »

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…

This is going to be situation normal for 10 years: everyone will need to keep track of "model-du-jour" as each vendor makes incremental improvements.

Re: Claude Code on the web

#113

Post by kobe_bryant »

mmaunder wrote: post #83
mmaunder wrote: post #72

Earlier quoted context omitted.

I can not. We're all racing very hard to take full advantage of these new capabilities before they go mainstream. And to be honest, sharing problem domains that are particularly attractive would be sharing too much. Go forth and experiment. Have fun with it. You'll figure it out pretty fast. You can read my other post here about the kinds of problem spaces I'm looking at.

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

Re: Claude Code on the web

#114

Post by simonw »

mdeeks wrote: post #110
justinram11 wrote: post #104

Earlier quoted context omitted.

Have you checked out Ona [1] (gitpod's pivot)? [1] https://ona.com/

This is possibly what I want? It's hard to tell from all of the marketing on the site. I want to run a prompt that operates in an isolated environment that is open in my IDE where I can iterate with the AI. I think maybe it can do this?

Not quite. This doesn't (yet) have an option where you can connect your local IDE to their remote containers to edit files directly. It's more of a fire-and-forget thing where you can eventually suck the resulting code down to your local machine using "claude --teleport ..." - but then it's not running in the cloud any more.

Re: Claude Code on the web

#115

Post by the_duke »

cesarvarela wrote: post #69
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…

Can you share an example of the tasks you found Codex being much better? From my experience Claude Code is much better.

IMO gpt5-codex medium is much better as soon as the task becomes slightly complex, or the context grows a bit.

Sora 4.5 tends to randomly hallucinate odd/inappropriate decisions and goes to make stupid changes that have to be patched up manually.

Re: Claude Code on the web

#116

Post by extr »

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?

Sonnet 4.5/CC is faster, more direct, and is generally better at following my intent rather than the letter of my prompt. A large chunk of my tasks are not "solve this concurrency bug" or "write this entire feature" but rather "CLI ops", merging commits, running a linter, deploying a service, etc. I almost use it like it was my shell.

Also while not quite as smart, it's a better pair programmer. If I'm feeling out a new feature and am not sure how exactly it should work yet, I prefer to work with Sonnet 4.5 on it. It typically gives me more practical and realistic suggestions for my codebase. I've noticed that GPT-5 can jump right into very sophisticated solutions that, while correct, are probably not appropriate.

Sonnet 4.5: "Why don't we just poll at an interval with exponential backoff?"

GPT-5: "The correct solution is to include the data in the event stream...let us begin by refactoring the event system to support this..."

That said, if I do want to refactor the event system, I definitely want to use Codex for that.

Re: Claude Code on the web

#118

Post by shmoogy »

intellectronica wrote: post #99
cesarvarela wrote: post #69

Earlier quoted context omitted.

Can you share an example of the tasks you found Codex being much better? From my experience Claude Code is much better.

Codex works much better for long-running tasks that require a lot of planning and deep understanding. Claude, especially 4.5 Sonnet, is a lot nicer to interact with, so it may be a better choice in cases where you are co-working with the agent. Its output is nicer, it "improvises" really well even if you give it only vague prompts. That's valueable for interactive use. But for delegating complete tasks, Codex is far…

Can / Does Codex actually check docker logs and other things for feedback while iterating on something that isnt working ? That is where the true magic of Claude comes for me. Often things cant be one shot, but being able to iteratively check logs, make an adjustment, rebuild the docker containers, send a curl, and confirm fixed is huge improvement.

Re: Claude Code on the web

#119

Post by username223 »

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…

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.

Re: Claude Code on the web

#120

Post by simonw »

username223 wrote: post #119
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…

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 restrict to just domains that you trust - which is enforced by a separate HTTP/HTTPS proxy, described here: https://docs.claude.com/en/docs/claude-code/claude-code-on-t...

Post reply on HN