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

6 weeks of Claude Code

blog.puzzmo.com

Post reply on HN
Print view View original

351–360 of 603 posts

Re: 6 weeks of Claude Code

#351

Post by hansvm »

AndyNemmity wrote: post #340
calrain wrote: post #338

Lets stop calling it Vibe Coding. I'm a heavy user of Claude Code and I use it like a coding assistant. How well you can manage a development team in real life has strong correlations on how much value you get out of an LLM based coding assistant. If you can't describe what success looks like, expect people to read your mind, and get angry at validating questions, then you will have problems both with coding assistan…

Well said. The skills involved are actually quite a bit different than coding. It's about how clearly and accurately you can describe things. how good you are at understanding what tooling you need to build to improve your experience. It's a different skillset.

I don't think that's true with current-gen models. You can even go so far as to write pseudocode for the LLM to translate to a real language, and for anything out-of-the-box my experience is that it will blatantly ignore your instructions. A baseline-competent junior at least has the context to know that if there are 5 steps listed and they only did 3 then there's probably a problem.

Prompting an LLM is definitely a different skillset from actually coding, but just "describing it better" isn't good enough.

Re: 6 weeks of Claude Code

#352

Post by brundolf »

giancarlostoro wrote: post #169
lukaslalinsky wrote: post #57

I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…

If you are a Senior Developer, who is comfortable giving a Junior tips, and then guiding them to fixing them (or just stepping in for a brief moment and writing where they missed something) this is for you. I'm hearing from Senior devs all over thought, that Junior developers are just garbage at it. They product slow, insecure, or just outright awful code with it, and then they PR the code they don't even understand.…

I find the "killer app" right now is anything where you need to integrate information you don't already have in your brain. A new language or framework, a third-party API, etc. Something straightforward but foreign, and well-documented. You'll save so much time because Claude has already read the docs

Re: 6 weeks of Claude Code

#353

Post by AndyNemmity »

hansvm wrote: post #351
AndyNemmity wrote: post #340

Earlier quoted context omitted.

Well said. The skills involved are actually quite a bit different than coding. It's about how clearly and accurately you can describe things. how good you are at understanding what tooling you need to build to improve your experience. It's a different skillset.

I don't think that's true with current-gen models. You can even go so far as to write pseudocode for the LLM to translate to a real language, and for anything out-of-the-box my experience is that it will blatantly ignore your instructions. A baseline-competent junior at least has the context to know that if there are 5 steps listed and they only did 3 then there's probably a problem. Prompting an LLM is definitely a…

I don't believe it is good enough, it's also not as relevant.

my prompts have gotten less and less. It's the hooks and subagents, and using the tools that matter far more.

This is a thread about claude code. the other LLms don't matter. Nothing ever blatantly ignores my instructions in claude code. that's a thing of the past.

Of course, not using claude code, for sure. But all my instructions are followed with my setup. That really isn't an issue for me personally anymore.

Re: 6 weeks of Claude Code

#354

Post by kelnos »

GiorgioG wrote: post #73
cmrdporcupine wrote: post #70

Earlier quoted context omitted.

You're not setting good enough boundaries or reviewing what it's doing closely enough. Police it, and give it explicit instructions. Then after it's done its work prompt it with something like "You're the staff engineer or team lead on this project, and I want you to go over your own git diff like it's a contribution from a junior team member. Think critically and apply judgement based on the architecture of the proj…

Ah yes…the old “you’re holding it wrong”. The problem is these goddamn things don’t learn, so you put in the effort to police it…and you have to keep doing that until the end of time. Better off training someone off the street to be a software engineer.

Yes, sometimes you are actually indeed holding it wrong. Sometimes a product has to be used in a certain way to get good results. You're not going to blame the shampoo when someone uses only a tiny drop of it, and the hair remains dirty.

This is still early days with LLMs and coding assistants. You do have to hold them in the right way sometimes. If you're not willing to do that, or think that provides less value than doing it another way... great, good for you, do it the way you think is best for you.

I've been a coding assistant skeptic for a long time. I just started playing with Claude Code a month or so ago. I was frustrated for a bit until I learned how to hold it the right way. It is a long, long way from being a substitute for a real human programmer, but it's helpful to me. I certainly prefer it to pair programming with a human (I hate pair programming), so this provides value.

If you don't care to figure out for yourself if it can provide you value, that's your choice. But this technology is going to get better, and you might later find yourself wishing you'd looked into it earlier. Just like any new tool that starts out rough but eventually turns out to be very useful.

Re: 6 weeks of Claude Code

#355

Post by kelnos »

GiorgioG wrote: post #249
zmj wrote: post #197

Earlier quoted context omitted.

Your claude.md (or equivalent) is the best way to teach them. At the end of any non-trivial coding session, I'll ask for it to propose edits/additions to that file based on both the functional changes and the process we followed to get there.

How do I distill 30 years of experience/knowledge into a Claude.md file? People learn, LLMs don't - end of story.

> People learn, LLMs don't - end of story.

That's not the end of the story, though. LLMs don't learn, but you can provide them with a "handbook" that they read in every time you start a new conversation with them. While it might take a human months or years to learn what's in that handbook, the LLM digests it in seconds. Yes, you have to keep feeding it the handbook every time you start from a clean slate, and it might have taken you months to get that handbook into the complete state it's in. But maybe that's not so bad.

Re: 6 weeks of Claude Code

#356

Post by kelnos »

asdev wrote: post #75
lukaslalinsky wrote: post #57

I have about two weeks of using Claude Code and to be honest, as a vibe coding skeptic, I was amazed. It has a learning curve. You need to learn how to give it proper context, how to chunk up the work, etc. And you need to know how to program, obviously. Asking it to do something you don't know how to do, that's just asking for a disaster. I have more than 25 years of experience, so I'm confident with anything Claude…

I feel like Cursor gives the same experience without having to be in the terminal. I don't see how Claude Code is so much better

I use vim for most of my development, so I'm always in a terminal anyway. I like my editor setup, and getting the benefits of a coding assistant without having to drastically change my editor has huge value to me.

Re: 6 weeks of Claude Code

#357

Post by danielbln »

dbalatero wrote: post #217
blackqueeriroh wrote: post #174

Earlier quoted context omitted.

My friend, there’s no solid evidence that this is the case. So far, there are a bunch of studies, mostly preprints, that make vague implications, but none that can show clear causal links between a lack of mental strain and atrophying brain function from LLMs.

You're right, we only have centuries of humans doing hard things that require ongoing practice to stay sharp. Ask anyone who does something you can't fake, like playing the piano, what taking months off does to their abilities. To be fair, you can get them back much faster than someone that never had the skills to begin, but skills absolutely atrophy if you are not actively engaged with them.

My assembly skills have atrophied terribly, and that's ok.

Re: 6 weeks of Claude Code

#358

Post by kelnos »

lukaslalinsky wrote: post #337
wordofx wrote: post #327

Earlier quoted context omitted.

I don’t know why amp isn’t talked about more. It’s better than Claude code.

It burns through credit too quickly. As a previous Sourcegraph Cody user, I was trying Amp first, but I've spent tens of dollars every day for the trial, and that was with an eye on the usage. It felt horrible seeing how I pay mostly for it's mistakes and the time it takes debugging. With CC, I can let go of the anxiety. I get several hours a day out of the Claude Pro plan and that's mostly good enough for now. If it…

That's the thing for me too: I don't want to pay for the agent's mistakes, even if those mistakes are in part the fault of my prompt. I'm fine with having usage limits if it means I pay a fixed cost per month. Not sure how long this will last, considering how expensive all this is for the companies to run, though.

I feel like Amp's costs are actually in line with Sourcegraph's costs, and eventually Anthropic, OpenAI, et al. will all be charging a lot more than they are now.

It's the classic play to entice people to something for low cost, and then later ramp it up once they're hooked. Right now they can afford to burn VC money, but that won't last forever.

Re: 6 weeks of Claude Code

#359

Post by kelnos »

calrain wrote: post #338

Lets stop calling it Vibe Coding. I'm a heavy user of Claude Code and I use it like a coding assistant. How well you can manage a development team in real life has strong correlations on how much value you get out of an LLM based coding assistant. If you can't describe what success looks like, expect people to read your mind, and get angry at validating questions, then you will have problems both with coding assistan…

Calling what vibe coding, though? If you're reviewing, understanding, and testing everything that the coding assistant outputs, then you aren't vibe coding.

If you're just letting the coding assistant do its thing, uncritically, and committing whatever results, then you're vibe coding.

It sounds like you're not vibe coding. That's good. No need to throw away a useful term (even if it's a weird, gen-Z sounding term) that describes a particular (poor) way to use a LLM.

Re: 6 weeks of Claude Code

#360

Post by kelnos »

dv_dt wrote: post #228
elAhmo wrote: post #214

Earlier quoted context omitted.

Simple task of unzipping with tar is cryptic enough that collecting unix scripts from random people is definitely something people don't want to do in 2025.

Script? I havent used anything more complex than "tar xzf file" in a decade

Ah yes, the "I've never needed X, so clearly no one else in the world will ever need X" rationale. So bulletproof.
Post reply on HN