Well, to be honest it's kind of like that 90% of the time. You don't actually become more productive but end up cleaning trash most of the time. Anyway, the hardest part is connecting all the pieces properly and understanding how everything fits, handling edge cases, and so on. Writing the code itself is actually the easy part.
Not necessarily, even before having all these models, I spent most of my time thinking rather than coding. The coding part is just the final nail, that's my approach at least.
Surely missing that process, you forget error handling. As you write, its consistently, what if this is null, what if the input is like x. There are many questions you should ask yourself and if you AI it, you'll forget.
It is called sampling and recombination, which is perfectly fine. The only metric should be that the final product masters the testing parkour. And that parkour better be worth its name. :)
I prefer the OG
not really different than the op these days though
Still useful to this day that’s true. But I also like to gamble on my code and argue with AI
I prefer writing code that works and not wasting time with the bullshit generator
Well, to be honest it's kind of like that 90% of the time. You don't actually become more productive but end up cleaning trash most of the time. Anyway, the hardest part is connecting all the pieces properly and understanding how everything fits, handling edge cases, and so on. Writing the code itself is actually the easy part.
That's all part of writing it. Typing gibberish you don't understand or that doesn't work doesn't count.
Not necessarily, even before having all these models, I spent most of my time thinking rather than coding. The coding part is just the final nail, that's my approach at least.
Isnt the thinking part of the coding?
Same here really, i plan the structure, then have ai throw it together, then i clean up and build off of that
I can't say i particularly miss writing the mindless boilerplate stuff
Surely missing that process, you forget error handling. As you write, its consistently, what if this is null, what if the input is like x. There are many questions you should ask yourself and if you AI it, you'll forget.
Claude: "It's a known issue"
ChatGPT: "Ah - now I see the what the problem is you're trying to do such and such" after telling me to do such and such
Gemini: "I see you're trying to bake a lettuce cake with chocolate chip cookies"
More like, Anymodel: "You're absolutely right! What the hell is this?"
Remember when people used to steal code from StackOverflow? Good times
The first generation of vibe coders
Welcome to corporate America. If it works, ship it. Fuck it. It’s not your personal pet project. Give back as much as they care about you.
You not using any libraries? We have like 1100 animals in our software at work (that we know of).
Coder's Ark
Minimal footprint, no dependencies 😇
::: spoiler The stash of awful code the AI blurted out vaguely resembling libraries the AI was trained on
:::
It is called sampling and recombination, which is perfectly fine. The only metric should be that the final product masters the testing parkour. And that parkour better be worth its name. :)
"the natural consequences of your own decisions" is the best answer I have to most things
"""working"""
"\"\" Wokring\"\""