I feel like the LLMs really encourage that, too. They’ll deliver some garbage and then you tell them to make it less garbage and they’ll be like “You clever son of a removed, why didn’t I think of that?”.
I’ve had some success taking the buggy output of Claude (which Claude gets stuck in a loop trying to fix), fixing it with GoogleAI, then feeding the result back to Claude which can then follow the working patterns and make working extensions…
Still, anything past “microservices” seems to be inadviseable to trust to any current AI.
TBF I’ve met scrum masters and product owners who think they’ve hacked the system by adding this to story AC, so…
Vibe parenting: “Drive carefully! Be safe!“
You get AC? You’re lucky if you get a meaningful title…
Story title: User sees error
Story description: One user reported seeing an error once
AC: fix error
Famous criticism from the testing department “we don’t write the buggy code…”
Yeah wish it was that easy…
I’m glad it’s not
It is, as long as you dont care about… anything.
ha, this is what my boss tells me… oh wait a minute