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

My experience with Claude Code after two weeks of adventures

sankalp.bearblog.dev

Post reply on HN
Print view View original

321–330 of 388 posts

Re: My experience with Claude Code after two weeks of adventures

#321

Post by eric_cc »

ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

I’m not a vim and eMacs guys - or terminal guy.

Claude Code + Cursor is my setup. Claude Code is my workhorse that I use for most tasks.

For small tiny quick changes, I use Cursor in auto.

For architecture consulting I use Cursor chat with Grok 4.

Claude Code is much better at banging out features than Cursor’s Claude. And Claude itself is better than other models as a coding workhorse.

All that said: while we may all code, we are building wildly different things that have much different specific problems to solve so it doesn’t surprise me that there isn’t a universal setup that works best for everybody.

Re: My experience with Claude Code after two weeks of adventures

#322

Post by solumunus »

ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

I would wager that you’re either not leveraging custom context files or you’re doing it very poorly.

Re: My experience with Claude Code after two weeks of adventures

#323

Post by kingofheroes »

hamandcheese wrote: post #168

For me the best part about AI is that when I'm feeling lazy, I can tell the AI to do it. Whether it gives me gold or gives me shit, it doesn't matter, because I have now started my work.

I've had great success using AI to translate my thoughts into actual words on a page (not just for software development, but also amateur writing). Bridging the vocabulary gap.

Re: My experience with Claude Code after two weeks of adventures

#324

Post by WXLCKNO »

eric_cc wrote: post #321
ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

I’m not a vim and eMacs guys - or terminal guy. Claude Code + Cursor is my setup. Claude Code is my workhorse that I use for most tasks. For small tiny quick changes, I use Cursor in auto. For architecture consulting I use Cursor chat with Grok 4. Claude Code is much better at banging out features than Cursor’s Claude. And Claude itself is better than other models as a coding workhorse. All that said: while we may al…

What did you use before Grok 4 came out for architecture consulting, Gemini 2.5 Pro?

Re: My experience with Claude Code after two weeks of adventures

#325

Post by nico »

Wowfunhappy wrote: post #302
nico wrote: post #281

Earlier quoted context omitted.

> some of the individual changes it asks me to approve are too small for me to make a decision. There are cases where I almost denied a change initially, then realized Claude's approach made sense once I saw the full change set Yes, I've adapted to just review quickly, then if it makes sense as part of the task, let it keep going until it's done with the whole thing. Most of the times, by the end it does the right th…

> I love that it doesn't auto-commit everything, ala aider, so it's pretty painless to undo stuff. Yeah, I'm definitely glad it doesn't commit for me. The main issue I have is that I'm never sure how granular to make my commits. Sometimes I make them very granular because I'm experimenting with Claude and I want to be able to revert to any point in the conversation—but now I have to write a message each time to keep…

Yeah, sometimes I love it when it checks the git log and properly finds reference code for what I’m trying to implement, but other times I really want it to just do it differently and can get annoying

Other times I’ll tell it about an issue that I want to solve and it will come up with a solution I don’t want. I’ll tell it to take a different approach and it will listen for a bit, then all of a sudden just try to go back to its first approach and I need to steer it again, multiple times even

> but now I have to write a message each time to keep track of which is which

I ask it to write my commits. Usually it’s also pretty smart about which files to include based on the most recently addressed tasks. I have it run git add and git commit under my supervision

A repo Im working on, has some rather annoying hooks that check linting when committing (and aggressively modify the files to fix formatting). If I forget to manually check before committing, then I end up with a “wrong” commit containing the incorrectly formatted files, and a bunch of uncommitted files with the formatting changes. CC most of the times will see the error messages, and automatically propose the proper commands to run for undoing or amending the commit to include the formatting changes

Re: My experience with Claude Code after two weeks of adventures

#326

Post by eric_cc »

WXLCKNO wrote: post #324
eric_cc wrote: post #321

Earlier quoted context omitted.

I’m not a vim and eMacs guys - or terminal guy. Claude Code + Cursor is my setup. Claude Code is my workhorse that I use for most tasks. For small tiny quick changes, I use Cursor in auto. For architecture consulting I use Cursor chat with Grok 4. Claude Code is much better at banging out features than Cursor’s Claude. And Claude itself is better than other models as a coding workhorse. All that said: while we may al…

What did you use before Grok 4 came out for architecture consulting, Gemini 2.5 Pro?

Yes 2.5 pro and o3. I’ve been very impressed with Grok 4 so far for this purpose. It’s very thorough and accurate. Granted my time with grok 4 is limited to a few days but I’ve already given it challenging problems and the results were exceptional.

Re: My experience with Claude Code after two weeks of adventures

#327

Post by mountainriver »

ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

You gotta hand it to anthropic for being able to build a demonstrably worse interface yet convince whole swaths of the eng community that its better.

I also suspect a lot of this is paid for or just terminal die hards.

Re: My experience with Claude Code after two weeks of adventures

#328

Post by mountainriver »

phito wrote: post #298
ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

I just feel sad for all the professional developers out there that are still scared of the terminal.

it's just a worse interface for writing code, no one is scared of anything

Re: My experience with Claude Code after two weeks of adventures

#329

Post by awacs »

ianberdin wrote: post #232

Reading all these glowing reviews of Claude Code, I still get the feeling that either everyone’s been paid off or it’s just the die-hard fans of terminal windows and editors like Emacs and Vim. Using the terminal is right up their alley—it’s in their DNA. Every time I read comments saying Claude Code is far better than Cursor, I fire it up, pay for a subscription, and run it on a large, complex TypeScript codebase. F…

I think you need to be a bit more explicit in your usage. I use Claude Code as the plugin in Cursor, to me the marriage of all the great, tastes great, less filling. You see all the changes as you normally would in VSCode / Cursor, but the Claude Code command line UI is absolutely bonkers better than the Cursor native one. They really have it dialed in beautifully in my opinion.

Re: My experience with Claude Code after two weeks of adventures

#330

Post by _se »

Aeolun wrote: post #230
_se wrote: post #44

Earlier quoted context omitted.

It's always POC apps in js or python, or very small libraries in other popular languages with good structure from the start. There are ways to make them somewhat better in other cases (automated testing/validation/linting being a big one), but for the type of thing that 95% of developers are doing day to day (working on a big, sprawling code base where none of those attributes apply), it's not close to being there. T…

Hmm, I got Claude Opus to build me a game in Rust. I don’t think it really counts as POC app any more at that point.

It absolutely counts as a POC app until it's production grade, deployed, being used by people, maintained over time, etc.

This doesn't mean that it's not useful, or that you shouldn't be happy with what the LLM built. I also had Claude Code build me a web app for my own personal use in Rust this week. It's very useful to me. But it is 100% of POC/MVP quality, and always will be, because the code that it created is abjectly awful and I would never be able to scale it into a real world service without rewriting 50+% of it.

Post reply on HN