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

481–490 of 603 posts

Re: 6 weeks of Claude Code

#481

Post by cheschire »

a5c11 wrote: post #477
scrollaway wrote: post #473

Earlier quoted context omitted.

It’s absolute lunacy to think everyone lauding Claude code is paid marketing/shilling. What’s actually happening is there’s a divide being created between engineers that know how to use it, and engineers that don’t or want to convince themselves that it’s useless or whatever. Group 2 will not fare well in the coming months.

There is also a group of engineers who like to... engineer stuff? I really do enjoy writing codes by myself, it gives me dopamine. The reason I've learnt talking to machines is that I don't like talking to people, so I don't fancy talking to machines like they were human beings.

If you don't see how that fits into "group 2" in GP's comment even though it wasn't explicitly called out, then we may have identifed why you don't find agentic coding to be enjoyable.

Re: 6 weeks of Claude Code

#482

Post by FirmwareBurner »

sitkack wrote: post #326
willsmith72 wrote: post #284

Earlier quoted context omitted.

Totally agree with the off-shore component of this. I'm already going to have to break a task down into clear detail and resolve any anticipated blocker myself upfront to avoid multi-timezone multi-day back and forth. Now that I'm practiced at that, the off-shored part is no longer valuable

The unemployment in India is going to be catastrophic. Geopolitical.

Unlikely. Microsoft had layoffs everywhere except India. There they keep hiring more. As song as the can keep upskilling themselves while still being much cheaper than US workers they won't fear unemployment.

Just yesterday I saw on X a video of a Miami hotel where the check-in procedure was via a video call to a receptionist in India.

Re: 6 weeks of Claude Code

#483

Post by bamboozled »

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…

The more I use it the more I realise my first two weeks and the amazement I felt were an illusion.

I’m not going to tell you it’s not useful, it is. But then shine wears off pretty fast and when it does, you’re basically left with a faster way to type. At least in my experience.

It’s amazing , but it’s dumb.

Re: 6 weeks of Claude Code

#484

Post by bamboozled »

exfalso wrote: post #396
Aurornis wrote: post #77

Earlier quoted context omitted.

> as a vibe coding skeptic, I was amazed. The interesting thing about all of this vibe coding skepticism, cynicism, and backlash is that many people have their expectations set extremely low. They’re convinced everything the tools produce will be junk or that the worst case examples people provide are representative of the average. Then they finally go out and use the tools and realize that they exceed their (extreme…

Hmm not my experience. I've been aggressively trying to use both Cursor and Claude Code. I've done maybe 20-30 attempts with Code at different projects, a couple of them personal small projects. All of them resulted in sub-par results, essentially unusable. I tried to use it for Python, Rust and Bash. I also tried to use it for crawling and organizing information. I also tried to use it as a debugging buddy. All of t…

Initially I loved it, overtime I agree with people that call it a slot machine, unless you’re very deliberate with it, it’d just that. Gambling.

Re: 6 weeks of Claude Code

#485

Post by azuanrb »

jmtame wrote: post #295
azuanrb wrote: post #53

Earlier quoted context omitted.

Have you tried context7 MCP? For things that are not mainstream (like Javascript, Typescript popularity), LLM might struggle. I usually have better result with using something like context7 where it can pull up more relevant, up to date examples.

I only use 2 MCP servers, and those are context7 and perplexity. For things like updated docs, I have it ask context7. For the more difficult technical tasks where I think it's going to stumble, I'll instruct Claude Code to ask perplexity and that usually resolves it. Or at least it'll surface up to me in our conversation so that we both are learning something new at that point. For some new stuff I'm working on, I u…

Thanks, I’ll check out Perplexity. We seem to be using a similar stack. I’m also on Rails 8 with Stimulus, Hotwire, esbuild, and Tailwind.

Playwright MCP has been a big help for frontend work. It gives the agent faster feedback when debugging UI issues. It handles responsive design too, so you can test both desktop and mobile views. Not sure if you know this, but Claude Code also works with screenshots. In some cases, I provide a few screenshots and the agent uses Playwright to verify that the output is nearly pixel perfect. It has been invaluable for me and is definitely worth a try if you have not already.

Re: 6 weeks of Claude Code

#486

Post by margalabargala »

yumraj wrote: post #262
Aurornis wrote: post #77

Earlier quoted context omitted.

> as a vibe coding skeptic, I was amazed. The interesting thing about all of this vibe coding skepticism, cynicism, and backlash is that many people have their expectations set extremely low. They’re convinced everything the tools produce will be junk or that the worst case examples people provide are representative of the average. Then they finally go out and use the tools and realize that they exceed their (extreme…

> Yeah we all know Claude Code isn’t going to generate a $10 billion SaaS with a team of 10 people… Not trying to argue, since I don’t have counter evidence, but how can you be so sure?

Because if it's generated by Claude Code, then basically any team of 10 people can make a competing service.

Re: 6 weeks of Claude Code

#487

Post by narrator »

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…

Gemini is not that good right now. GLM-4.5, which just came out, is pretty decent and very cheap. I use these with the RooCode plugin for VSCode that connects to it via OpenRouter. $10 of credits lasts a day of coding for me where as Claude would run that out in an hour.

Re: 6 weeks of Claude Code

#489

Post by exe34 »

shortrounddev2 wrote: post #480
exe34 wrote: post #467

Earlier quoted context omitted.

> can still be predicted and understood (no matter how difficult that is). If we're making up hypotheticals, then LLMs can be predicted and understood (no matter how difficult that is). They don't run on pixie dust.

It's qualitatively different to go through source code and specifications to understand how something works than to look at a database with all the weights of an LLM and pretend like you could predict the output.

you don't have to - just run the matrix multiplication. it's no different from using a pocket calculator.

Re: 6 weeks of Claude Code

#490

Post by lbrito »

M4v3R wrote: post #164
lbrito wrote: post #162

It's less that I'm a skeptic, but more that I'm finding I intensely abhor the world we're building for ourselves with these tools (which I admittedly use a lot).

Why abhor specifically?

The answer can and certainly will fill many books, dissertations, PhD thesis etc.

Without going too philosophical, although one is not unjustified in going there, and just focusing on my own small professional corner (software engineering): these llm developments mostly kill an important part of thinking and might ultimately make me dumber. For example, I know what a B tree is and can (could) painstakingly implement one when and if I needed to, the process of which would be long, full of mistakes and learning. Now, just having a rough idea will be enough, and most people will never get the chance to do it themselves. Now B-tree is an intentionally artificial example, but you can extrapolate that to more practical or realistic examples. On a more immediate front, there's also the matter of threat to my livelihood. I have significant expenses for the foreseeable future, and if my line of work gets a 100 or even 10x average productivity boost, there just might be less jobs going around. Farm ox watching the first internal combustion tractors.

I can think of many other reasons, but those are the most pressing and personal to me.

Post reply on HN