Re:Ask HN: How should junior programmers use and/or not use ...
by xnorswap on Monday March 24, 2025 @10:04AM
(#43461245)
What about the cases where the AI doesn't hallucinate, produces working code, but the code is just about good enough?
I've just written about that exact scenario. A shoddy piece of code that's just about okay: https://richardcocks.github.io/2025-03-24-PasswordGen
If you're a junior, you might not realise there's anything wrong with the generated code at all.
Re:Ask HN: How should junior programmers use and/or not use ...
by meccabrepapa on Monday March 24, 2025 @01:12PM
(#43463234)
So which event make you change your approach
Now I use AI to go asap to 70% of my code. The last 30% is a manual, low AI, approach where I fix the hallucinations, file structure and do the stuff AI is failing me at.
I use Claude Chat, ChatGPT, Claude Code and Windsurf (switching between those all the time)