[aleph_minus_one]

> Not possible, because can't be guardrailed with 100% accuracy. You'll ask it something outside of the Warcraft world (e.g. US politics), and it'll happily oblige. I imagine NPCs will generate really weird immersion breaking stuff even if you cannot freeform interact with them anyway.

> Not to mention the current token cost.

You of course have to train the AI from ground up and on material that is as much as possible only related to the topics that are in the game world (i.e. don't include real-world events in the training data that has no implications in-universe).

[c0redump]

How much text about the game world do you have? Does this amount compare favorably to the volume of text required to train an LLM?

Answer those two questions and you will realize why your idea doesn’t work.

[aleph_minus_one]

You don't, for example, expect some ordinary farmer or tramp in the game world to know a lot about the (in-game) world or be capable of doing deep conversations about complicated topics.

So I don't think the necessary amount of text that you need to train the AI on is as insanely large as you imagine (but of course nevertheless a lot of texts have to be written - this is the price of having "much more dynamic" AI characters in the game).