The authors updated their title so I've updated it here too. Previous title was "Good code will still win" - but it was leading to too much superficial discussion based entirely on the phrase "good code" in the title. It's amazing how titles do that!
(Confession: "good code will still win" was my suggestion- IIRC they originally had "Is AI slop the future?". You win some you lose some.)
I don't fully agree this optimistic view. Unfortunately, for now, coding agents produce code that, if not further optimized upon "human" request, often generates more complexity than necessary.
It's true that this requires more computational effort for the agents themselves to debug or modify it, but it's also true that the computational cost is negligible compared to the benefit of having features working quickly.
In other words: agents quickly generate hyper-complex and unoptimized code. And the speed of delivery provides more immediate benefits than the costs resulting from bad code.
On the other hand, it's also true that the "careful eye" of an experienced developer can optimize and improve the output in a few simple iterations.
So overall (and unfortunately) the "bad code", if it immediately works, can wins against (or with) a good code.
Never considered that the mods of this site are literally discussing with the people heading yc companies how to game their hn-titles for better interaction. How naive I am.
(I know you know this, since you submitted it! but others might want to know)
reply