Post #4443484

@ramin_hal9001@fe.disroot.org The worst part about it is that the LLM never really “learns.” I’ve had a few new contributors to some of my projects and the first few code reviews are exhausting. You need multiple rounds and they end up rewriting almost everything from the first submission. But the second one is better and needs some tweaks. And, after a few, you get to ones where you think ‘huh, I wouldn’t have thought of doing that, that’s neat’ and now you’re in a state where not only is it faster than if you’d done it yourself, it’s better because they’re much closer to the specific bit of the code that they’re touching and you’re trying to hold the whole system in your head. With an LLM, you’re stuck in that first-submission process, all of the time. And it might still be faster, because having someone else go and write the code after you’ve gone through all of the design iterations and feedback on early drafts might be quicker than writing it yourself.