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

331–340 of 603 posts

Re: 6 weeks of Claude Code

#331

Post by Seattle3503 »

arevno wrote: post #55
jeswin wrote: post #19

Claude Code is ahead of anything else, in a very noticeable way. (I've been writing my own cli tooling for AI codegen from 2023 - and in that journey I've tried most of the options out there. It has been a big part of my work - so that's how I know.) I agree with many things that the author is doing: 1. Monorepos can save time 2. Start with a good spec. Spend enough time on the spec. You can get AI to write most of t…

> 1. Monorepos can save time Yes they can save you some time, but at the cost of Claude's time and lots of tokens making tool calls attempting to find what it needs to find. Aider is much nicer, from the standpoint that you can add the files you need it to know about, and send it off to do its thing. I still don't understand why Claude is more popular than Aider, which is by nearly every measure a better tool, and ca…

As an alternative to monorepos, you can add another repo to your workspace by informing it relevant code is located at XXX path on your machine. Claude will add that code to your workspace for the session.

Re: 6 weeks of Claude Code

#332

Post by stickfigure »

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?

I think it's some variation of the efficient markets hypothesis. There are no problems that are both that lucrative and that easy to solve; if they existed, they would get dogpiled and stop being lucrative. Even in this day and age, $10B of revenue is an incredibly high bar.

On the other hand, $10B as valuation (not revenue) just requires a greater fool. Maybe it's possible, but I doubt there are too many of those fools available.

Re: 6 weeks of Claude Code

#333

Post by jaredsohn »

qsort wrote: post #129
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…

People are using different definitions of "vibe coding". If you expect to just prompt without even looking at the code and being involved in the process the result will be crap. This doesn't preclude the usefulness of models as tools, and maybe in the future vibe coding will actually work. Essentially every coder I respect has an opinion that is some shade of this. There are the social media types you mention and the…

>maybe in the future vibe coding will actually work

Vibe coding works today at small enough of scale.

I'm building a personal app to help me track nutrition and I only needed to get involved in the code when Claude would hit its limits for a single file and produced a broken program (and this was via the UI, not Claude Code.) Now at ~3000 lines of python.

After I told it to split it into a few files I don't think I've had to talk about anything at the code level. Note that I eventually did switch to using Claude Code which might have helped (gets annoying copy/pasting multiple files and then my prompts hit max limits).

I just prompt it like an experienced QA/product person to tell it how to build it, point out bugs (as experienced as a user), point out bad data, etc.

A few of my recent prompts (each is a separate prompt):

>for foods found but not in database, list the number of times each shows up

>sort the list by count descending

>Period surplus/deficit seems too low. looking at 2025/07/24 to 2025/07/31

>do not require beige color (but still track it). combine blue/purple as one in stats (but keep separate colors). data has both white and White; should use standard case and not show as two colors

Re: 6 weeks of Claude Code

#334

Post by yumraj »

stickfigure wrote: post #332
yumraj wrote: post #262

Earlier quoted context omitted.

> 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?

I think it's some variation of the efficient markets hypothesis. There are no problems that are both that lucrative and that easy to solve; if they existed, they would get dogpiled and stop being lucrative. Even in this day and age, $10B of revenue is an incredibly high bar. On the other hand, $10B as valuation (not revenue) just requires a greater fool. Maybe it's possible, but I doubt there are too many of those fo…

Yeah, $10B revenue is insane.

I interpreted the parent as saying $10B valuation.

Re: 6 weeks of Claude Code

#335

Post by iammrpayments »

EFreethought wrote: post #318
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…

> It can, in fact, control your entire computer. Honestly, that sounds like malware.

I also don’t understand how everybody is installing these packages with npm -g and not worrying about anything

Re: 6 weeks of Claude Code

#336

Post by raincole »

_l7dh wrote: post #202
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…

Feels like the most valuable skill to have as a programmer in times of Claude Code is that of carefully reading spec documentation and having an acute sense of critical thinking when reviewing code.

For seniors these skills are very valuable before LLM anyway.

Re: 6 weeks of Claude Code

#337

Post by lukaslalinsky »

wordofx wrote: post #327
sergiotapia wrote: post #294

Earlier quoted context omitted.

I haven't used Claude Code - but have been using Amp a lot recently. Amp always hits on target. They created something really special. Has anyone here used both Claude Code and Amp and can compare the two's effectiveness? I know one is CLI and the other an editor extensions. I'm looking for comparisons beyond that. Thanks!

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's not, I'll upgrade to Max, as at $100 that's still less than what I'd have spent on Amp.

Re: 6 weeks of Claude Code

#338

Post by calrain »

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 assistants and leading teams of developers.

Re: 6 weeks of Claude Code

#339

Post by ako »

everforward wrote: post #290
ako wrote: post #226

Earlier quoted context omitted.

Ask it to document the code with design documents and mermaid diagrams. Much faster to review.

I might have to try this. Without having tried it, it feels like the context I think I lack is more nitty gritty than would be exposed like this. It's not like I'm unsure of how a request ends up in a database transaction, but more "do we need or already have an abstraction over paging in database queries?". It doesn't feel like mermaid diagrams or design documents would include that, but I'm open to being wrong ther…

If you have a question like that, just ask.

Re: 6 weeks of Claude Code

#340

Post by AndyNemmity »

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.
Post reply on HN