John-Rosebud
As of right now you still need to be familiar with the code that it gives you. But personally even when I work on a game I resolve bugs by chatting with the AI about it. We're also trying to surface any kind of actual errors that happen so you can feed it back to the AI. So far I haven't seen a bug I can't fix in this way, but then I've been coding for 20+ years.
As for the "//...rest of the code" stuff, yeah it's my white whale. We're just limited by the context size. We have a bunch of things coming up to separate the code into multiple files and various tricks to squeeze more of the context size. It's a constant battle.
Another thing we're toying with is automatic debugging that lets it go back and forth on bugs until it actually works.
We're using our own custom AI Agents to generate the games and what we'll do next is expose them for the games to leverage too. At that point you should be able to have the game self-generate based on rules.
And nice I'll check out that book
We're utilizing AI Agents on two fronts. One is to generate actual games, which is how the user-created game you're playing there was made. And our next step is to enable creators to leverage those agents inside the game itself. When we arrive at that point the scenario you're showing above will be much more dynamic.