If you look back in your career, you will find out that most of time you dont write code, you read code. You need to travel back and forth of the logic to understand it, write some piece of code, run it then read it again to understand why a wierd logic happen.
You only feel powerful when you boostrap a project because you wirte a lots of skeleton code or init core logic.
Nowaday we dont have chance to even write those kind of code
I miss writing code too.
yep... we are living in a time that the role of the developer is changing quickly.
Boris (Cherny) wrote about it and the TL;DR:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship
2. Builder: quickly turns a prototype/idea into production-grade product/infra
3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance
4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit
5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
i think this is fine as long as you actually understand what calude code is doing. Because then you are not just using claude code you are using it to automate things that you already know and are just time consuming for you when they dont need to be.
Normally I would still open VS code and use Claude by using terminal.
I care less about the actual code, and more about algorithms, data structures and architectures. I'm glad that AI allow us to think less of syntax and more of logic. My suggestion is that you can use Claude through the terminal and proof read and approve the code, and if time allows it, you can write some of the code you want yourself.
I am very close to uninstalling vscode/cursor and just using some very lightweight editor for the rare times that I need to manually edit files (mostly .env files, etc... not code)
AI allows developers to write less code, but it shouldn't make us understand less. If you miss writing code, it just means you still truly care about the craft itself.
The understanding derived from actually writing the code and making it work is much different and deeper than looking at code written for you, looking at it, and thinking, "yeah, that seems like it makes sense".
Even if I spend a significant amount of time reviewing the code to try and understand every line that was used, I don't necessarily understand why it was chosen, what were the alternatives, what would the trade offs of those alternatives be, what seems like it should work but actually wouldn't, how something might break if a little part is missing... These are all things that are better understood when actually writing the code.
There isn’t a single SOTA model on the market that writes code as nicely as I write it.
I can only suspect these people saying they write no code have zero taste, because that’s the only way I can understand accepting the unsophisticated garbage these models produce.
Interesting take and I don't want to dismiss your experience but it's not mine.
15+ years writing code and refining it, learning. Is AI code as good? Definitely not. Is it 80-90% or the way there with correct linting, agent setup and rules? Absolutely.
If you look back in your career, you will find out that most of time you dont write code, you read code. You need to travel back and forth of the logic to understand it, write some piece of code, run it then read it again to understand why a wierd logic happen.
You only feel powerful when you boostrap a project because you wirte a lots of skeleton code or init core logic.
Nowaday we dont have chance to even write those kind of code I miss writing code too.
yep... we are living in a time that the role of the developer is changing quickly. Boris (Cherny) wrote about it and the TL;DR:
1. Prototyper: comes up with brand new ideas; churns out many ideas, most of which don't ship 2. Builder: quickly turns a prototype/idea into production-grade product/infra 3. Sweeper: cleans up the UI, simplifies the code and system, unships, optimizes performance 4. Grower: takes a product that has been built and iterates on it to improve Product-Market Fit 5. Maintainer: owns a mature system to make it secure, reliable, fast, and efficient as it scales
i think this is fine as long as you actually understand what calude code is doing. Because then you are not just using claude code you are using it to automate things that you already know and are just time consuming for you when they dont need to be.
Normally I would still open VS code and use Claude by using terminal.
I care less about the actual code, and more about algorithms, data structures and architectures. I'm glad that AI allow us to think less of syntax and more of logic. My suggestion is that you can use Claude through the terminal and proof read and approve the code, and if time allows it, you can write some of the code you want yourself.
I am very close to uninstalling vscode/cursor and just using some very lightweight editor for the rare times that I need to manually edit files (mostly .env files, etc... not code)
Weird times
Yes, I no longer derive joy or a sense of accomplishment from coding. I used to enjoy making junk, but now anyone can make those things.
Ask HN isnt really the place for hosting blog posts. Instead why not put this on an external site, expand on it a bit, and submit a link?
AI allows developers to write less code, but it shouldn't make us understand less. If you miss writing code, it just means you still truly care about the craft itself.
> it shouldn't make us understand less
The understanding derived from actually writing the code and making it work is much different and deeper than looking at code written for you, looking at it, and thinking, "yeah, that seems like it makes sense".
Even if I spend a significant amount of time reviewing the code to try and understand every line that was used, I don't necessarily understand why it was chosen, what were the alternatives, what would the trade offs of those alternatives be, what seems like it should work but actually wouldn't, how something might break if a little part is missing... These are all things that are better understood when actually writing the code.
> I miss writing code
This hits hard. I used to feel a joy and sense of pride in finishing a day.
I am trying to find joys in other ways, like shipping quickly while keeping quality but engineering really has changed in a short space of time.
之前一直都是在研究高并发，多线程等技术，现在也很少看了
Who are you people not writing code?
There isn’t a single SOTA model on the market that writes code as nicely as I write it.
I can only suspect these people saying they write no code have zero taste, because that’s the only way I can understand accepting the unsophisticated garbage these models produce.
I still believe that I can write better code compared to what the AI can produce. But is it really... cost-effective? Probably not.
Interesting take and I don't want to dismiss your experience but it's not mine.
15+ years writing code and refining it, learning. Is AI code as good? Definitely not. Is it 80-90% or the way there with correct linting, agent setup and rules? Absolutely.
It's quality vs speed vs cost adage