When I decided to bring Legend of the Green Dragon back, I had one rule I wasn't willing to compromise on. I wanted to modernize the game, not turn it into something completely different.
I played the original years ago, and I wanted to preserve what made it worth playing in the first place.
That meant working from the original source, replacing outdated PHP and database code, tightening security, and actually testing the gameplay. Just because a module installed without throwing errors didn't mean I was going to call it supported. It needed to work.
AI helped me do a hell of a lot of the development work, but it didn't eliminate the need for judgment. I still had to make the decisions, define the boundaries, question the results, and decide what was acceptable.
That's something I think gets lost in conversations about AI-assisted development. Generating code is one thing. Building something that actually works, while preserving what matters, is another.
I wrote about the experience and what went into bringing this old game back.
https://jimlunsford.com/i-modernized-legend-of-the-green-dragon-with-ai/
Loading comments...