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

301–310 of 405 posts

Re: Claude Code on the web

#301

Post by spoiler »

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…

My experience is that if I know what I want, CC will produce better code, given I specify it correctly. The planning mode is great for this too, as we can "brainstorm" and what I have seen help a lot is if I ask questions about why it did a certain way. Often it'll figure out on its own why that's wrong, but sometimes it requires a bit of course correction.

On the other hand, last time I tried GPT-5 from Cursor, it was so disappointing. It kept getting confused while we were iterating on a plan, and I had to explain to it multiple times that it's thinking about the problem the same way. After a while I gave up, opened a new chat and gave it my own summary of the conversation (with the wrong parts removed) and then it worked fine. Maybe my initial prompt was vague, but it continually seemed to forget course corrections in that chat.

I mostly tend to use them more to save me from typing, rather than asking it to design things. Occasionally we do a more open ended discussion, but those have great variance. It seems to do better with such discussions online than within the coding tool (I've bounced maths/implementation ideas off of while writing shaders on a personal project)

Re: Claude Code on the web

#302

Post by baq »

spoiler wrote: post #301
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…

My experience is that if I know what I want, CC will produce better code, given I specify it correctly. The planning mode is great for this too, as we can "brainstorm" and what I have seen help a lot is if I ask questions about why it did a certain way. Often it'll figure out on its own why that's wrong, but sometimes it requires a bit of course correction. On the other hand, last time I tried GPT-5 from Cursor, it w…

gpt-5-high is amazing, but so slow I'll revert to sonnet when I know what I need done on a low level.

when making boilerplatish changes in the product in areas I'm not familiar with (it's a large codebase) gpt-5-high is a monster.

Re: Claude Code on the web

#303

Post by h34t »

bad_haircut72 wrote: post #204
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…

Im not saying this is a paid endorsement but the internet is dead and I wonder what openAI would pay, if they could, to get such a glowing review as top comment on HN

to be fair, they spent a lot on compute.

Re: Claude Code on the web

#304

Post by jessmartin »

paulddraper wrote: post #259
libraryofbabel wrote: post #170

Earlier quoted context omitted.

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…

You can run the Claude code router and choose the model you want (including based on dynamic conditions)

Can you say more? Link?

Re: Claude Code on the web

#305

Post by dns_snek »

hluska wrote: post #284
visiondude wrote: post #238

Earlier quoted context omitted.

Oh cool, can you share concrete examples of times codex out performed Claude Code? I’m my experience both tools needs to be carefully massaged with context to fulfill complex task.

Nobody has to give you examples. People can express opinions. If you disagree, that’s fine but requesting entire prompt and response sets is quite demanding. Who are you to be that demanding?

> Who are you to be that demanding?

Let's call it the skeptical public? We've been listening to a group of people rave about how revolutionary these tools are, how they're able to perform senior level developer work, how good their code is, and how they're able to work autonomously through the use of sub-agents (i.e. vibe coding), without ever providing evidence that would support any of those grandiose claims.

But then I use these tools myself[1] and I speak to real developers who have used them and our evaluation centers around lukewarm, e.g. good at straightforward, junior level tasks, or good for prototyping, or good for initially generating tests, or good for answering certain types of questions, or good for one-off scripts, but approximately none of them would trust these LLMs to implement a more complex feature like a mid-level or senior developer would without very extensive guidance and hand-holding that takes longer than just doing it ourselves.

Given the overwhelming absence of evidence, the most charitable conclusion I can come to is that the vast majority of people making these claims have simply gone from being 0.2X developers to being 0.3X developers who happen to generate 5X more code per unit of time.

[1] e.g. my reply to https://news.ycombinator.com/item?id=45651948

Re: Claude Code on the web

#306

Post by Rebuff5007 »

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…

> We were heavy users of Claude Code ($70K+ spend per year)

Claude code has only been generally available since May last year (a year and half ago)... I'm surprised by the process that you are implying; within a year and a half, you both spent 70k on claude code, and knew enough about it and its competition to switch away from it? I dont think I'd be able to due diligence even if LLM evaluation was my fulltime job. Let alone the fact that the capabilities of each provider are changing dramatically every few weeks.

Re: Claude Code on the web

#307

Post by dakom »

blueside wrote: post #198
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…

As we all know here, if the the title of this post was about Codex on the web, the top comment would have been about using Claude instead. YMMV, but this definitely doesn't track with everything I've been seeing and hearing, which is that Codex is inferior to Claude on almost every measure.

fwiw I'm happy to see this - been trying to tackle a hairy problem (rendering bugs) and both models fail, but:

1. Codex takes longer to fail and with less helpful feedback, but tends to at least not produce as many compiler errors 2. Claude fails faster and with more interesting back-and-forth, though tends to fail a bit harder

Neither of them are fixing the problems I want them to fix, so I prefer the faster iteration and back-and-forth so I can guide it better

So it's a bit surprising to me when so many people are pickign a "clear winner" that I prefer less atm

Re: Claude Code on the web

#308

Post by latexr »

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 AI companies.

https://knowyourmeme.com/editorials/guides/what-is-the-frien...

It’s much more likely commenters are still in the honeymoon hype phase and (again) haven’t found the problems because they’re hyper focused on what the new thing is good at that the previous one wasn’t, ignoring the other flaws. I see that a lot with human relationships as well, where people latch on to new partners because they obviously don’t have the big problem that was a strain on the previous relationship. But eventually something else arises. Rinse and repeat.

Re: Claude Code on the web

#310

Post by dns_snek »

neya wrote: post #278
dns_snek wrote: post #274

Earlier quoted context omitted.

This is hilarious because for me Cursor with GPT-5 often generates Elixir that isn't even syntactically correct. It needs to be told not to use return statements, and not to try to index linked lists as arrays. Code is painfully non-idiomatic to the point of being borderline useless even in the simpler cases. Claude Sonnet 4.5 is marginally better, but not by much. Any ambitious overhaul, refactoring or large feature…

Gemini is also good, I recommend you try it as well. Usually my workflow is GPT-5 as the primary, but yes, as you mentioned it is not perfect. But Gemini surprisingly compliments GPT-5 for my use cases atleast. It's good at LiveView related stuff, whereas GPT-5 is more of architecting side. Both LLMs suck if you let it do everything without architecting the solution first. So, I always instruct the high level archite…

> Both LLMs suck if you let it do everything without architecting the solution first.

I always do that. Last time I spent an hour planning, going through the requirements, having it ask questions, only for it to completely botch the implementation.

Sure, I can treat it like a junior and spend 2-3 hours planning everything down to the individual function level and it's going to implement it alright. The code will work but it won't be idiomatic. Or I can just do it myself in 3 hours total to a much higher standard of quality, without gambling on a successful outcome, while simultaneously improving my own knowledge, understanding, and abilities.

No matter how I try to use them, agentic coding is always a net negative on my productivity (disposable one-off scripts excluded).

Post reply on HN