logoalt Hacker News

SpicyLemonZesttoday at 2:37 AM2 repliesview on HN

It's not really a hypothetical. I work with one junior who's submitted an incorrect bugfix 3 times and counting; he seems genuinely incapable of processing the idea that there's a correctness issue he has to resolve, rather than a prompt engineering issue that will allow Claude to figure it out if only he asks in the right way.


Replies

jfredstoday at 3:08 AM

To be fair this was a thing before AI as well…

ookblahtoday at 3:45 AM

that's not the tooling's fault i feel. i've used LLMs to help explore and debug issues, point me to the right documentation to investigate, etc. I WISH i had something like this 30 years ago.