What helped me in my project was a RAG implementation. So instead of trying to have all the information in the prompt, which becomes inconsistent if it becomes too big (especially when working on local llm), I can have quite a big knowledge base in a RAG. Then when being promoted it’s a two step process, first search the RAG for the best match in the knowledge base, then Feed that to the LLM to generate the answers. You could also store noteworthy stuff in the rag on the fly.

Because it’s difficult to fit to a world. You need a pretty good GPU of which a lot of the memory will be take up by the LLM running locally. That means you basically can not use it while also having other fancy graphics at the same time. So you would basically have a not so demanding looking game with high GPU requirements.

Also it’s quite difficult to steer the NPCs to be consistent. In my free time I’m working on a small project right now to have a game centered around llm NPCs, but it’s a lot of work to steer them to be consistent with the world you place them in. Because they always go with a “yes and” approach, so it’s easy to end up in a situation where they make up things that contradict the reality of the game.

But the importance of food can be very different still. As a German I would say food is not a huge part of social culture. Like yes we eat together when we celebrate, but the food is usually just a necessity instead of the main focus

But the people that already own the game never have to pay that increase, that’s what I mean

Isn’t that how early access works?

Imagine you where in their shoes and you do value human life. What would you realistically do? Honest question, I’d like to think I’d do something different then them, but I can not think of a way that does not cut ties completely. I think the best I could do, is secretly support opposition behind the scenes, not sure how much of that is happening though.

I think for a lot of them, they don’t agree with most of his policies, but as CEO of such big companies you can not openly oppose him. They would lose a fortune, so instead they try to get the most out of it for their company.

Also, you gotta see it from their view. They are stuck with him now for 3 more years. In 3 years AI will keep getting bigger and may change a lot, loosing those 3 years because of trying to make a stand, might mean lossing your position on the table and your influence on its development completely.

All that said, I’m not saying it’s good that that’s what they are doing, but I can see some strategy in doing it like that