We train a computer model to imitate human behaviour, and they end up acting human like. How strange…

But did they act like real players and: steal from innocent villagers, imprison the villagers and start forcibly breeding and enslaving them, create iron farms by exploiting game mechanics and mudding golems, and start randomly blowing shit up with TNT?

How do they translate between the continuous character movements, the 60fps 3D world and the words that go in and out of a LLM?