One thing I have learned using GPT-style models in my game development workflow is that they are most powerful when used to accelerate experimentation rather than replace playtesting. I have had much better results letting AI help me explore many small variations quickly, then using real player behavior to decide what survives. Optimizing for “least resistance” in tools often produces systems that are efficient to build but lifeless to play — so I now treat friction as something to relocate into play rather than eliminate.
I am curious how other developers are handling the tension between AI-assisted ideation and real playtesting in their projects.