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

291–300 of 388 posts

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

#291

Post by AndrewKemendo »

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…

Is your complaint about specifically claude or about GPT assistants generall?

I’m curious what this means:

> run it on a large, complex TypeScript codebase

What do you mean by “run it?”

Are you putting the entire codebase all at once into the context window? Are you giving context and structure prompts or a system architecture first?

Most of the people I see fail to “get” GPT assistants is because they don’t give context and general step-by-step instructions to it.

If you treat it like a really advanced rubber duck it’s straight up magic but you still have to be the senior engineer guiding the project or task.

You can’t just dump a 10,000 LOC file into it ask some vague questions and expect to get anything of value out of it.

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

#292

Post by quesera »

aniforprez wrote: post #164
quesera wrote: post #97

Earlier quoted context omitted.

My current working theory is this: People who enjoy mentoring juniors are generally satisfied with the ROI of iterating through LLM code generation. People who find juniors sort-of-frustrating-but-part-of-the-job-sometimes have a higher denominator on that ROI calc, and ask themselves why they would keep banging their head against the LLM wall. The first group is probably wiser and more efficient at multiplying their…

It's the complete opposite for me. I enjoy the process of mentoring juniors and am usually sought out for a lot of little issues like fixing git workflows or questions on how a process works. Working with an LLM is absolutely not what I want to do because I'd much rather mentees actually learn and ask me less and less questions. My experience with AI so far is that it never learns at all and it has never felt to me l…

You're right, I'm probably lumping the first group over-broadly, since I understand them less well.

It would make sense for there to be subgroups within the first group. It sounds like you prioritize results (mentee growth, possibly toward long-term contribution), and it's also likely that some people just enjoy the process of mentoring.

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

#293

Post by intrasight »

two_tasty wrote: post #268
intrasight wrote: post #239

Earlier quoted context omitted.

this desire to understand code will be soon be seen as rather anachronistic. What's important is that you understand your tests. Let the AI generate the code. The spec and the test are your human contribution.

Ah yes, can't wait to tell my auditor / regulator "I don't understand the code because Claude wrote it, but it's fine, because understand the code is for boomers." That will get a big laugh in a deposition.

That'll be anachronistic too obviously. Your tests will be audited.

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

#294

Post by moffkalast »

midasz wrote: post #285
moffkalast wrote: post #273

Earlier quoted context omitted.

That's funny I always considered Sublime to be more in my face, begging for money every time I opened it.

There's a neat trick to remove the nag screen

Yeah installing vscode, quite the neat trick indeed.

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

#295

Post by quesera »

moomoo11 wrote: post #150
quesera wrote: post #97

Earlier quoted context omitted.

My current working theory is this: People who enjoy mentoring juniors are generally satisfied with the ROI of iterating through LLM code generation. People who find juniors sort-of-frustrating-but-part-of-the-job-sometimes have a higher denominator on that ROI calc, and ask themselves why they would keep banging their head against the LLM wall. The first group is probably wiser and more efficient at multiplying their…

I'm cynical person, and IME the former are some of the most annoying and usually the worst engineers I've met. Most people who "mentor" other people (like, make it a pride and distinction part of their identity) are usually the last people you want to take advice from. Actual mentors are the latter group, who juniors seek out or look up to. In other words, the former group is akin to those people on YouTube who try t…

That's the extreme end of the first-group spectrum, but I definitely agree that they exist!

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

#296

Post by jcelerier »

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…

> Second, the learning curve is steep: you have to work through the terminal and type commands.

that's supposed to be part of CS101

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

#297

Post by javier2 »

Waterluvian wrote: post #267
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 it’s because a lot of people deeply misunderstand what the hard parts of software development actually are. Most of the time, programs won’t involve novel or complicated algorithms or whatnot. It’s mostly just gluing ideas together. But that all comes after the specification, design, architecture, planning, etc. I think it can also be deceptive the same way it can be in basically any trade: it’s easy for the…

Yeah, writing code has been near trivial since I started working 12 years ago. Used Intellij since 2012. The difficult part was always reading old code and figure out the boundaries where backward comparibility breaks and figure out how to execute a rollout safely.

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

#298

Post by phito »

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.

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

#299

Post by corytheboyd »

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 very effective with JetBrains IDEs, VSCode is not in the same league. I’m very effective with a terminal. Claude Code is just enough of a bridge between models and my IDE to enhance my workflow without ruining my IDE. That’s it. I don’t pay $200.

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

#300

Post by 93po »

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 hate terminal stuff and refuse to write code in terminals, and i still think claude code has better results than cursor IDE with sonnet 4. it might be a mixture of it mixing in opus (which i never really used with cursor) or it might be that there's a bigger context window or its agentic process is somewhat different. im not entirely sure. but i feel like it gets things right more consistently and introduces fewer issues. it might also be the use of CLAUDE.md which i think has helped a ton in consistently making sure its following best practices for my project
Post reply on HN