Re:Ask HN: Who's Winning with AI-Coding?
by unclebucknasty on Monday November 16, 2026 @07:04PM
(#50525444)
>in my experience...if you are exceedingly disciplined and are actually reviewing the lines that the LLM is trying to edit
Have you found the effort to review the reams of code it so easily produces significantly more productive than just writing the code yourself?
And, given the frequently difficult to read/maintain code it produces, is it worth it—even if you are seeing some gains with code review time included?
Just really hard to glean what the net impact really is, in order to calibrate expectations accordingly.
In my experience you can maintain a large codebase if you are exceedingly disciplined and are actually reviewing the lines that the LLM is trying to edit but beyond that you're just pulling a slot machine handle and hoping for good results. That works well with small programs and sometimes people get lucky with the repeated coin flips on larger ones but eventually it breaks down.