[maxweisel]

100% this. I've had more fun using Claude Code because I get to spend more of my time doing the fun parts (design, architecture, problem solving, etc) and less time spent typing, fixing small compilation errors, looking up API docs to figure out that query parameters use camelcase instead of underscores.

[autoexec]

I'd rather spend my time designing and writing code than spending it debugging and reformatting whatever an LLM cobbled together from stack overflow and github. 'Design, architecture, problem solving, etc' all takes a backseat when the LLM barfs out all the code and you have to either spend your time convincing it to output what you could have written yourself anyway or play QA fixing its slop all day long.

[maxweisel]

Back when I would ask ChatGPT to write code, I would agree with you, but using Claude Code's planning mode is a night and day difference. You write out a list of specs, Claude writes up a plan (that for writing backend APIs has always been just about perfect for me if my spec is solid), and then Claude executes that plan to almost perfection, with small nudges along the way.

If you're doing anything UI-based, it hasn't performed well for me, but for certain areas of software development, it's been an absolute dream.

[monster_truck]

You don't have to do any of that if you simply don't make mistakes in the first place FYI

[stackghost]

This is why I exclusively write C89 when handling untrusted user input. I simply never make mistakes and so I don't need to worry about off-by-ones or overflows or memory safety or use after frees.

Garbage collection and managed types are for idiots who don't know what the hell they're doing; I'm leet af. You don't need to worry about accidentally writing heartbleed if you simply don't make mistakes in the first place.

[bugglebeetle]

Attitudes like this one are why people prefer working with AI to code lol.

[tehnub]

It's obviously tongue in cheek