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

161–170 of 405 posts

Re: Claude Code on the web

#161

Post by p337 »

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…

On the topic of comparing OpenAI models with Anthropocene models, I have a hybrid approach that seems really nice.

I set up an MCP tool to use gpt-5 with high reasoning with Claude Code (like tools with "personas" like architect, security reviewer, etc), and I feel that it SIGNIFICANTLY amplifies the performance of Claude alone. I don't see other people using LLMs as tools in these environments, and it's making me wonder if I'm either missing something or somehow ahead of the curve.

Basically instead of "do x (with details)" I say "ask the architect tool for how you should implement X" and it gets into this back and forth that's more productive because it's forcing some "introspection" on the plan.

Re: Claude Code on the web

#162

Post by nextworddev »

simonw wrote: post #140
nextworddev wrote: post #138

Developers may want to deny this, but it's getting dangerously close to maybe replacing 30% of developers

I continue to believe that making developers 2-3x times more productive makes those developers 2-3x more valuable, and the smart thing for companies to do is to take on 2-3x times the amount of work, or hire MORE developers and finally start crunching through their inevitably years-long backlogs.

Your view doesn’t mesh with conversations I have had with most C-suite. Most firms outside of SV are seeing opportunities for cost reduction mostly.

And you can think through with first principles to see why it won’t expand developer hiring. Since AI progress is jagged, some industries will be affected in outsized ways while others may thrive more. But the increase in demand from new industries won’t absorb the reduction in demand from disrupted industries.

Re: Claude Code on the web

#163

Post by fragmede »

simonw wrote: post #92
extr wrote: post #63

Earlier quoted context omitted.

It’s interesting because I’ve slowly arrived at the opposite conclusion: for much of my practical day to day work, using CC with “allow edits” turned OFF results in a much better end product. I can correct it inline, I pseudo-review the code as it’s produced, etc etc. Codex is better for “fire and forget” features for sure. But Claude remains excellent at grokking intent for problems where you aren’t quite sure what…

That approach should work well for projects where you are directly working on the code in tandem with Claude, but a lot of my own uses are much more research oriented. I like sending Claude Code off on a mission figure out how to do something. Here's an example from this morning, getting CUDA working on a NVIDIA Spark: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co... I have a few more in https://github…

so hey by the way, have you discovered Wispr Flow or something similar so you can talk to your computer like Scotty does?

Re: Claude Code on the web

#164

Post by bahmboo »

lvl155 wrote: post #55
bahmboo wrote: post #15

Earlier quoted context omitted.

Anthropic and Apple have a strategic partnership. It's a bit dicey but still seems to be in play. Which is interesting considering Google is a major investor and Apple is not. Anthropic wants Apple as a paying customer. Apple wants them to bend the knee.

Apple also has relationship with OAI. They’re not preferential.

Yes but the question was why Anthropic is showing more attention to iOS vs Android.

Re: Claude Code on the web

#165

Post by CompoundEyes »

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…

Claude Code is still good but I don’t TRUST it. With Claude Code and Sonnet I’m expecting failure. I can get things done but there’s an administrative overhead of futzing around with markdown files, defensive commit hooks and unit tests to keep it on rails while managing the context panic. Codex CLI with gpt-5-codex high reasoning is next gen. I’m sure Sonnet 5 will match it soon. At that point I think a lot of the workflows people use in Claude Code will be obsolete and the sycophancy will disappear.

Re: Claude Code on the web

#166

Post by mvkel »

F7F7F7 wrote: post #148
mvkel wrote: post #143

Earlier quoted context omitted.

This is why Anthropic is a zombie company. They put all of their eggs in the coding basket, with the rest of their mission couched as "effective altruism," or "safetyism," or "solving alignment," (all terms they are more loudly attempting to distance themselves from[0], because it's venture kryptonite). Meanwhile, all OpenAI had to do was point their training cannon at it for a run, and suddenly Anthropic is irreleva…

For non-vibe coding purposes I've found that my $200 Claude (Claude Code) account regularly outperformed my $200 ChatGPT (Codex) account. This was after 2 months of heavily testing both mostly in Terminal TUI/CLI form and most recently with the latest VSCode/Cursor incarnations. Even with the additional Sora usage and other bells & whistles that ChatGPT @ $200 provides, Claude provides more value for my use cases. Cl…

> There's nothing wrong with Anthropic wanting to completely own that segment and not have aspirations of world domination

It's very clear by their actions (not words) that they are shooting for the moon in order to survive. There is no path to sustainability as a collection of dev tools.

Re: Claude Code on the web

#167

Post by ewoodrich »

incoming1211 wrote: post #149
intellectronica wrote: post #99

Earlier quoted context omitted.

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…

I disagree, Codex always gets stuck and wants to double check and clarify things, its like "dammit just execute the plan and don't tell me until its completely finished" The output of codex is also not as great. Codex is great at the planning and investigation portion but sucks at execution and code quality.

I've been dealing with this on Codex a lot lately. It confidently wraps up a task, I go to check it's work... and it's not even close.

Then I do a double take and re-read the summary message and realize that it pulled a "and then draw the rest of the owl", seemingly arbitrarily picking and choosing what it felt like doing in that session and what it punted over to "next steps to actually get it running".

Claude is more prone to occasional "cheating" with mocked data or "tbd: make this an actual conditional instead of hardcoded If True" stuff when it gets overwhelmed which is annoying and bad. But it at least has strong task adherence for the user's prompt and doesn't make me write a lawyer-esque contract to avoid any loopholes Codex will use to avoid doing work.

Re: Claude Code on the web

#168

Post by arjie »

hugs wrote: post #111
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?

I don't use it myself so to speak, except to fill in some things sometimes like passwords. The LLM is the user. It just uses the primitives it has (these are my paraphrases): scroll_to, expand_viewport, screenshot, select_dom_element, fill_input. This way I can tell it to implement a feature and verify it and it does so in a Google Chrome testing profile. Without the grounding, I've noticed that LLMs often produce "code that should work" but then something else is missing. This way, by the time I see it, the feature works.

I then have to go in and advise it on factoring and things like that, but the functionality itself is present and working.

Re: Claude Code on the web

#169

Post by preommr »

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…

> I'm seeing the downvotes. I'm sorry folks feel that way. I'm regretting my honesty.

What honesty? We're not at the point of "the Godfather was a good/bad movie", we're at "no, trust, there's a really good movie called the Godfather".

Your honesty means nothing for an issue that isn't about taste or mostly subjectivness. How useful AI is and in what way is a technical discussion where the meat of the subject matter is. You've shared nothing on that front. I am not saying you have to, but like obviously people are going to downvote you - not because they might agree/disagree but because it's contributed nothing different from every other ai-hype man selling a course or something.

Re: Claude Code on the web

#170

Post by libraryofbabel »

jswny wrote: post #144
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…

I find Codex CLI to be very good too, but it’s missing tons of features that I use in Claude Code daily that keep me from switching full time. - Good bash command permission system - Rollbacks coupled with conversation and code - Easy switching between approval modes (Claude had a keybind that makes this easy) - Ability to send messages while it’s working (Codex just queues them up for after it’s done, Claude injects…

I don't think anyone can reasonably argue against Claude Code being the most full-featured and pleasant to use of the CLI coding agent tools. Maybe some people like the Codex user experience for idiosyncratic reasons, but it (like Gemini CLI) still feels to me rather thrown together - a Claude Clone with a lot of rough edges.

But these CLI tools are still fairly thin wrappers around an LLM. Remember: they're "just an LLM in a while loop with access to tool calls." (I exaggerate, and I love Claude Code's more advanced features like "skills" as much as anyone, but at the core, that's what they are.) The real issue at stake is what is the better LLM behind the agent: is GPT-5 or Sonnet 4.5 better at coding. On that I think opinion is split.

Incidentally, you can run Claude Code with GPT-5 if you want a fair(er) comparison. You need a proxy like LiteLLM and you will have to use the OpenAI api and pay per-token, but it's not hard to do and quite interesting. I haven't used it enough to make a good comparison, however.

Post reply on HN