To me it feels like we're in the VC subsidized days for tools like Claude Code. Given how expensive we know GPU usage is and that it's not likely to come down, and these companies will need to eventually be profitable, I wonder if we're all heading for a point where ultimately Claude Code and the like will be like $2K per month instead of $200 on the high end.
6 weeks of Claude Code
471–480 of 603 posts
Re: 6 weeks of Claude Code
#472I 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.
Critical Skills is spotting the potential bugs before they happen but in order to do that you need to have an extremely acute understanding or a have a lot of experience in the stack, libs and programming language of choice. Something that, ironically, you will not get by "vibe coding".
Re: 6 weeks of Claude Code
#473I see a lot of comments here gushing about CC but I've used and I really don't get it. I find that it takes me just as long to explain to it what I need done as it takes to just do the work myself.
What's happening is that we are being bombarded by marketing on all fronts. These gushing statements are no different from the testimonials and advertorials from the days of yore.
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.
Re: 6 weeks of Claude Code
#474Every time you use these tools irresponsibly, for instance for what I like to call headless programming (vibe coding), understand that you are incurring tech debt. Not just in terms of your project but personal debt regarding what you SHOULD have learned in order to implement the solution.
It’s like using ChatGPT in high school: it can be a phenomenal tutor, or it can do everything for you and leave you worse off.
The general lesson from this is that Results ARE NOT everything.
Re: 6 weeks of Claude Code
#475I 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.…
Can also confirm. Almost any output from claude code needs my careful input for corrections, which you could only spot and provide if you have experience. There is no way a junior is able to command these tools because the main competency to use them correctly is your ability to guide and teach others in software development, which by definition is only possible if you have senior experience in this field. The sycophancy provided by these models will outright damage the skill progression for juniors, but on the other hand there is no way to not use them. So we are in a state where the future seems really uncertain for most of us.
Re: 6 weeks of Claude Code
#476Earlier quoted context omitted.
Fascinating since I found the recent Claude models untrustworthy for writing and editing SQL. E.g. it'd write conditions correctly, but not add parens around ANDs and ORs (which gemini pro then highlighted as a bug, correctly.)
The trick is to have it run it through sqlglot and correct the errors.
This kind of thing is a key point. Tell Claude Code to build the project, run linters, run the tests, and fix the errors. This (in my experience) has a good chance of filtering out mistakes. Claude is fully capable of running all of the tools, reading the output, and iterating. Higher level mistakes will need code written in a way that is testable with tests that can catch them, although you probably want that anyway.
Re: 6 weeks of Claude Code
#477Earlier quoted context omitted.
What's happening is that we are being bombarded by marketing on all fronts. These gushing statements are no different from the testimonials and advertorials from the days of yore.
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.
Re: 6 weeks of Claude Code
#478I 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.…
Yes, this!
A couple of week ago, I had a little down time and thought about a new algorithm I wanted to implement. In my head it seemed simple enough that 1) I thought the solution was already known, and 2) it would be fairly easy to write. So I asked Claude to "write me a python function that does Foo". I spent a whole morning going back and forth getting crap and nothing at all like what I wanted.
I don't know what inspired me, but I just started to pretend that I was talking to one one of my junior engineers. I first asked for a much simpler function that was on the way to what I wanted (well, technically, it was the mathematical inverse of what I wanted), then I asked it to modify it to add one different transform, and then another, and then another. And then finally, once the function was doing what I wanted, I asked it to write me the inverse function. And it got it right.
What was cool about it, is that it turned out to be more complex linear algebra and edge cases than I originally thought, and it would have been weeks for me to figure all of that out. But using it as a research tool and junior engineer in one was the key.
I think if we go down the "vibe coding" route, we will end up with hoards of juniors who don't understand anything and the stuff they produce with AI will be garbage and brittle. But using AI as a tool is starting to feel more compelling to me.
Re: 6 weeks of Claude Code
#479Earlier 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?
The question is not whether you can or can't, but whether it is still worth it long term: - There is a moat of doing so (i.e. will people actually pay for your SaaS knowing that they could do it too via AI) and.. - How many large scale ideas do you need post AI? Many SaaS products are subscription based and loaded with features you don't need. Most people would prefer a simple product that just does what they need wi…
It seems obvious to me it is the consumer who will benefit most.
I had been thinking of buying an $80 license for a piece of software but ended up knocking off a version in Claude Code over a weekend.
It is not even close to something commercial grade that I could sell as a competitor but it is good enough for me to not spend $80 on the license. The huge upside is that I can customize the software in any way I like. I don't care that it isn't maintainable either. Making a new version in ChagGPT5 is going to be my first project.
Just like a few hours ago I was thinking how I would like to customize the fitness/calorie tracking app I use. There are so many features I like that would be tightly coupled to my own situation and not a mass market product.
This to me seems obvious of what the future of software looks like for everything but mission critical software.
Re: 6 weeks of Claude Code
#480Earlier quoted context omitted.
I suppose a more rigorous definition would be useful. We can probably make it more narrow as time goes on To me, the essence of coding is about using formal languages and definable state machines (i.e, your toolchain) to manipulate the state of a machine in a predictable way. C, C++, even with their litany of undefined behavior, are still formal languages, and their compilers can still be predicted and understood (no…
> 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.