I told the AI to stop building and polish the worlds it had. A few days later, I noticed that instead of hundreds of new worlds a day, it was making about a dozen. I asked a few agents to explore what had happened, and they found something surprising.
The AI had built a bureaucracy.
[…]
Rules were added as the AI encountered issues, and no text was ever cut. After twelve days, it had 204 sections and 87,500 words. Soon, launching a new world required an approved idea, three AI judges and a full code review against the rule book. All told, that took about a day. Reading the rule book alone used up a large part of an agent’s working context.
[…]
Knowing when your own work is not good enough is a large part of what makes someone an expert, and it is the part Fable does least reliably.
Maybe I’m just focusing on the things I want to see, but this is exactly how I feel about working with AI – it’s powerful, comprehensive, and yet blissfully unaware of itself and its failures.
It still needs steering.