Think the key on this one is, as what others have said, that graphical and artistic choices still have to be made. We're still porting to a standard platform with a standard set of performance in the GBA, so if the AI gives you slop that doesn't perform, you're gonna know it.
Let the AI do the boring parts, optimize it with your own knowledge, give it your own touch and review so that AI is a tool and not the solution. That's what it should be for and it looks like that's how it's used here.
Comments 1
Re: "I'd Rather Disappoint Some People" - Dev Behind Tool That "Ports" Game Boy Games To GBA Pivots To AI
Think the key on this one is, as what others have said, that graphical and artistic choices still have to be made. We're still porting to a standard platform with a standard set of performance in the GBA, so if the AI gives you slop that doesn't perform, you're gonna know it.
Let the AI do the boring parts, optimize it with your own knowledge, give it your own touch and review so that AI is a tool and not the solution. That's what it should be for and it looks like that's how it's used here.