Damus
note1xppn5...
nostrich profile picture
Nah, even with good coverage (though we aren’t great now) it makes really poor decisions for new API designs sometimes. Just like with English it’s *really* good at writing something that looks very correct. With code that’s often actually correct and pretty decent (if occasionally verbose), but certainly not always, and definitely not always the best or most maintainable design. Sure, you can “prompt better” by giving it the specific design you want, but usually the only way to find the right design is by exploring options. LLMs are useful to speed that process up, of course, but claiming they’re replacing that process today is absurd.
Vitor Pamplona · 16h
There is always the exception, but most of the time is pretty good. At least on my experience, the way AI writes code that is a LOT easier to review/understand than how a human writes. To me it is not even a question of who is better. AI has already won that a couple months ago. Now its about making...