I think there is a skyrim mod that lets hook up an LLM to the NPCs so you can talk to them, the problem is that the rest of the game design doesn't really support that. So the novelty wears off quite quick.

There is probably some limited utility for using ML in games, lifelike multiplayer bots trained on behaviour of different types of players.

I think in most scenarios good gameplay comes from iteration which comes from tweak-ability, you see players get stuck in area x so you do a minor or major adjustment to area layout, enemy composition, or give the players more tools. If something is controlled by an LLM it becomes unpredictable and hard to reason about for both player and designer, and consequently also hard to adjust.

I think it is possible there is some role for LLM's in games, like how Left 4 Dead had an AI (this is classic AI not ML) director who would decide how to structure enemy waves and for example send a boss after a player who strays too far from the rest. But even there rules based AI is probably easier to adjust for the designer.

I've only seen proof-of-concepts, like Vaudeville[1]. I think more work is currently done in the modding scene, for example with Mantella[2] which, "brings every NPC in Skyrim and Fallout 4 to life with AI."

[1] https://store.steampowered.com/app/2240920/Vaudeville/ [2] https://art-from-the-machine.github.io/Mantella/

I don't know of any that use LLMs and my educated opinion would be that there won't be any in the next decade or ever. The main reasons are that games already run with tight margins of both frame time and memory consumption, and that designers/game developers want to control the interactions with the player and what the player experiences in the game. So an LLM won't be used for any story relevant NPCs in the game as what they say is tightly curated, and it's never going to be good/fast/slim enough to get used for crowd NPCs.

Using machine learning to make enemies smarter has been thought about and talked about for decades, but I don't see it being used either for similar reasons. Training a ML algorithm takes resources which are in short supply and time which could take longer than for the player to finish the game (if you want smarter enemies play against real human players). There's also the fact that the game has to run on the minimum specification computer, which means different players will have differently skilled enemies and their experience of the game will suffer.

There have been some games in the past which used some form of machine learning as a core gameplay feature, but they have been pet breeding simulators.

Right until you release it and a minor gets the NPC to talk about rape or something.