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

171–180 of 388 posts

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

#171

Post by nikcub »

Imanari wrote: post #65

PSA: you can use CC with any model via https://github.com/musistudio/claude-code-router The recent Kimi-K2 supposedly works great.

> The recent Kimi-K2 supposedly works great.

My own experience is that it is below sonnet and opus 4.0 on capability - but better than gemini 2.5 pro on tool calling. It's really worth trying if you don't want to spend the $100 or $200 per month on Claude Max. I love how succinct the model is.

> you can use CC with any model via

Anthropic should just open source Claude Code - they're in a position to become the VS Code of cli coding agents.

Shout out to opencode:

https://github.com/sst/opencode

which supports all the models natively and attempts to do what CC does

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

#172

Post by nikcub »

dude250711 wrote: post #86
kypro wrote: post #61

HN has flipped so quickly on saying how AI produces unreliable slop, to most people using it to replace junior devs at their org – something I was heavily criticised for saying orgs should be doing a few months back. Progress doesn't end here either, imo CC is more a mid-level engineer with a top-tier senior engineer's knowledge. I think we're getting to the point where we can begin to replace the majority of enginee…

How come CC is a crappy terminal instead of some super-nice environment built by Anthropic via CC itself? It should be capable of rebuilding VS Code but better, no?

because their philosophy is that developers are tied to their editors and IDE's so you should be able to bring you're own. and they're right.

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

#173

Post by otabdeveloper4 »

djaychela wrote: post #155

Can someone offer me some help? I've just been messing about "vibe coding" little python apps with local llm, continue and vscode. And I got so far with it. Then I found the free tier of claude so I fed in the "works so far" version with the changes that the local llm made, and it fixed and updated all the issues (with clear explanation) in one go. Success! So my next level attempt was to get all the spec and prompts…

> Any ideas how to progress from this?

You can't. This is a limitation of LLM technology. They can output the most likely token sequence, but if "likely" doesn't match "correct" for your problem then there's nothing you can do.

Also, each LLM has its own definition of what "likely" is - it comes from the training and finetuning secret sauce of that particular LLM.

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

#174

Post by otabdeveloper4 »

ipaddr wrote: post #98

What I wonder is how is the interview process now? Are they testing you with AI or without? Is leet code being asked with AI proving the answer? Is there a bigger disconnect on how you are judged in an interview vs the job now? How are the AI only developers handling this?

Same as it always was, you ask the candidate to explain his reasoning process in detail and ask questions along the way.

AI can't think or reason, LLMs are still mostly useless for gaming interviews.

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

#175

Post by RamblingCTO »

deeshee wrote: post #31
ardit33 wrote: post #21

Earlier quoted context omitted.

1.So far, it is great if you know what you want, and tell it exactly how you want it, and AI can help you on that (basically intern level work). 2. When you are in a new area, but you don't want to dive deep and just want something quick and it is not core of the app/service. But, if you are experienced, you can see how AI can mess things up pretty quickly, hence for me it has been best used to 'fill in clear and wel…

I agree. But it's also a mindset game. Experienced devs often approach AI with preconceptions that limit its utility - pride in "craftsmanship, control issues, and perfectionism can prevent seeing where AI truly shines. I've found letting go of those instincts and treating AI as a thought partner rather than just a code generator be super useful. The psychological aspects of how we interact with these tools might be…

> pride in "craftsmanship, control issues, and perfectionism

sounds like you can't code for shit. guidelines, standards, and formatting have developed for a reason. the reason is: less bugs and maintainability. you sound like the average cocky junior to me.

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

#176

Post by RamblingCTO »

kypro wrote: post #61

HN has flipped so quickly on saying how AI produces unreliable slop, to most people using it to replace junior devs at their org – something I was heavily criticised for saying orgs should be doing a few months back. Progress doesn't end here either, imo CC is more a mid-level engineer with a top-tier senior engineer's knowledge. I think we're getting to the point where we can begin to replace the majority of enginee…

> CC is more a mid-level engineer with a top-tier senior engineer's knowledge.

care to provide any proof for that? in my experience it's neither.

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

#178

Post by rantallion »

crinkly wrote: post #170
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 go for a walk and have a coffee. It feels less intellectually dishonest. Best to solve human problems with human solutions.

The best part is that you can do both. Give the agent a prompt, go for a walk, come back to see how well it did.

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

#179

Post by imiric »

libraryofbabel wrote: post #78
imiric wrote: post #71

Earlier quoted context omitted.

It's telling that you ask these details from a comment describing a negative experience, yet the top-most comment full of praises and hyperbole is accepted at face value. Let's either demand these things from both sides or from neither. Just because your experience matches one side, doesn't mean that experiences different from yours should require a higher degree of scrutiny. I actually think it's more productive to…

I should have been clearer - I'd like to see this kind of information from positive comments as well. It's just as important. If someone is having success with Claude Code while vide-coding a toy app, I don't care. If they're having success with it on a large legacy codebase, I want them to write a blog post all about what they're doing, because that's extremely useful information.

I jumped the gun a bit in my comment, since you did mention you want to see this from both sides. So it was clear, and I apologize.

The thing is that I often read this kind of response only to comments with negative experiences, while positive ones are accepted as fact. You can see this reinforced in the comments here as well. A comment section is not the right place to expand on these details, but I agree that blog posts should have them, regardless of the experience type.

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

#180

Post by darkwater »

serf wrote: post #107
dawnerd wrote: post #80

Earlier quoted context omitted.

By the time you do all of that you might as well just write code by hand.

that's really just a scale question. Yes, I would write a 4 line bash script by myself. But if you're trading a 200 line comprehensive claude.md document for a module that might be 20k LoC? it's a different value proposition.

And how do you actually know that those 20k line of codes have no glaring bugs, or bugs that you can find yourself, or be able to understand it completely at some point?
Post reply on HN