The developer behind Teach My Little Sister How to Drive, a driving instruction sim where you instruct a generative-AI-powered, dynamic NPC, has been spending $1,000 dollars a day to keep the demo working.
The developer behind Teach My Little Sister How to Drive, a driving instruction sim where you instruct a generative-AI-powered, dynamic NPC, has been spending $1,000 dollars a day to keep the demo working.
Given that people playing this have GPUs, why not run the AI model locally? I can’t imagine it needs to be a very large model.
Because even very small models will take up a large chunk of your cards VRAM, if not all of it. And then you still have to render the game on top of it.
There are 1-2gb vram models that should fit in anything. Game doesn’t appear to be texture heavy, and targetting a 6gb gpu, would cover anything less than 10-12 years old.
A 1-2 min vram model would probably not be sufficient for what the game is trying to do. Those micro models aren’t really for anything beyond basic object image recognition or RAG searching
Actually sounds like the perfect use case for a model like Jev. I think Jevos should be able to handle that locally.