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

251–260 of 603 posts

Re: 6 weeks of Claude Code

#251

Post by arrowsmith »

einpoklum wrote: post #150
danielbln wrote: post #108

Earlier quoted context omitted.

It's the automators dream come true. Anything can be automated, anything scripted, anything documented. Even if we're gonna use other (possibly local) models in the future, this will be my interface of choice. It's so powerful.

It's not a dream come true to have a bunch of GPUs crunching at full power to achieve your minor automation, with the company making them available losing massive amounts of money on it: https://www.wheresyoured.at/the-haters-gui/ ... while also exposing the contents of your computer to surveillence.

[flagged]

Re: 6 weeks of Claude Code

#252

Post by GiorgioG »

MattGaiser wrote: post #98
GiorgioG wrote: post #73

Earlier quoted context omitted.

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.

They don't learn by themselves, but you can add instructions as they make mistakes that are effectively them learning. You have to write code review feedback for juniors, so that s not an appreciable difference. > Better off training someone off the street to be a software engineer. And that person is going to quit and you have to start all over again. They also cost at least 100x the price.

> They also cost at least 100x the price.

Because right now AI companies are losing their asses - it costs significantly more than what they are charging.

Re: 6 weeks of Claude Code

#253

Post by GiorgioG »

hkt wrote: post #86
GiorgioG wrote: post #73

Earlier quoted context omitted.

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.

Not so. Adding to context files helps enormously. Having touchstone files (ARCHITECTURE.md) you can reference helps enormously. The trick is to steer, and create the guardrails. Honestly, it feels like DevOps had a kid with Product.

> Honestly, it feels like DevOps had a kid with Product.

You've just described a match made in hell. DevOps - let's overcomplicate things (I'm looking at you K8s) and Product - they create pretty screenshots and flows but not actually think about the product as a system (or set of systems.)

Re: 6 weeks of Claude Code

#254

Post by aryonoco »

shortrounddev2 wrote: post #215
exe34 wrote: post #163

Earlier quoted context omitted.

Coding can only be done by replicators born out of carbon, I imagine?

No, coding can be done by machines. But if you're telling a machine what to program, you're not coding. The machine is. Youre no longer a programmer, you're just a user.

Unless you’re writing pure assembly, aren’t we all using machines to generate code?

Re: 6 weeks of Claude Code

#255

Post by jaggederest »

globular-toast wrote: post #212
elliotec wrote: post #198

Earlier quoted context omitted.

Is it possible to view the prompt history? I’ve had extreme levels of productivity and would love to list out how I’ve been using it generally for an article like this but it would be incredibly impractical to log it on the side.

Just show the code you've produced.

Right but that's like showing the compiled binary but not the source. With claude code prompt and config is everything.

Re: 6 weeks of Claude Code

#256

Post by jaggederest »

elliotec wrote: post #198
socalgal2 wrote: post #196

I wish I got this level of productivity. I think every article should list exactly what they asked the LLM to do because I'm not getting as much use from it and I don't know if it's because what I work on is rare compared to say website front and backend code and/or if I just suck at prompts/context or I'm using the wrong services or don't have the correct MCPs etc....

Is it possible to view the prompt history? I’ve had extreme levels of productivity and would love to list out how I’ve been using it generally for an article like this but it would be incredibly impractical to log it on the side.

I really want to record a live commentary of me working with claude. Maybe that's something you could think about.

I feel like the results I get are qualitatively superior to anything I've seen anyone I've worked with produce. The fact that it's a lot faster is just gravy on top.

Re: 6 weeks of Claude Code

#257

Post by npilk »

arrowsmith wrote: post #101

The real power of Claude Code comes when you realise it can do far more than just write code. It can, in fact, control your entire computer. If there's a CLI tool, Claude can run it. If there's not a CLI tool... ask Claude anyway, you might be surprised. E.g. I've used Claude to crop and resize images, rip MP3s from YouTube videos, trim silence from audio files, the list goes on. It saves me incredible amounts of tim…

Completely agree. Another use case is a static site generator. I just write posts with whatever syntax I want and tell Claude Code to make it into a blog post in the same format. For example, I can just write in the post “add image image.jpeg here” and it will add it - much easier than messing around with Markdown or Hugo.

Re: 6 weeks of Claude Code

#258

Post by y1n0 »

Freedom2 wrote: post #179
shortrounddev2 wrote: post #158

Earlier quoted context omitted.

That's not what dishonesty means. That's just someone who disagrees with you

Thank you for calling out my inaccuracy. One thing I'm always appreciative for in HN is the level of pedantry day after day.

That's not what pedantry means.

Re: 6 weeks of Claude Code

#259

Post by rmoriz »

I was very, very skeptic. Then a couple of weeks ago I started with Atlassian's Rovo Dev CLI (Sonnet 4) and immediately managed to build and finish a couple of projects. I learned a lot and for sure having experience, decide on stack an architecture is a huge benefit for "guiding" an agentic coding app. I'm not sure if anyone can build and maintain a project without having at least some skills, but If you are an experienced developer, this is kind of magic.

I also appreciate the common best practice to write a requirements document in Markdown before letting the agent start. AWS' kiro.dev is really nice in separating the planning stage from the execution stage but you can use almost any "chatbot" even ChatGPT for that stage. If you suffer from ADHD or lose focus easily, this is key. Even if you decide to finish some steps manually.

It doesn't really matter if you use Claude Code (with Claude LLM), Rovo Dev CLI, Kiro, Opencode, gemini-cli, whatever. Pick the ones that offer daily free tokens and try it out. And no, they will almost never complete without any error. But just copy+paste the error to the prompt or ask some nasty questions ("Did you really implement deduplication and caching?") and usually the agent magically sees the issues and starts to fix it.

Re: 6 weeks of Claude Code

#260

Post by risyachka »

blackqueeriroh wrote: post #174
risyachka wrote: post #135

Earlier quoted context omitted.

"mental strain" in a way of remembering/thinking hard is like muscle strain. You need it to be in shape otherwise it starts atrophying.

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.

I mostly referred to skills, not brain function itself.
Post reply on HN