cross-posted from: https://piefed.ca/c/games@lemmy.world/p/1004331/ai-driving-game-players-are-burning-through-so-many-tokens-its-developer-had-to-take-out-a
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.
In theory it’s less complicated to handle a local AI with local resources. Remote AI would have been far more complex before the current state of AI. This method is just lazey API plugins that probably are asking the same prompts repeatedly. It looks to me to be a game trying to wedge LLMs into the industry. Has there been any effort to reduse the token burn or is it too fundamental to the game?
from the article it sounds like the devs are looking into ways of integrating local AI, but for now its just prompting ChatGPT and Gemini for responses for the little sister character. Basically, the gameplay is you tell the NPC what to do with your microphone, she seems to pause for a sec, then reacts by saying something and maybe carrying out whatever it is you told her to do.
Like you could say “Turn the wheel 50% left and accelerate to 20 km/h” and she would respond. From the gameplay i’ve seen, it seems pretty hit or miss if she reacts correctly. Like I watched a few 2ish hour streams of it and it pretty much took that long to get through the 3 or 4 levels in the demo, and most of that was the NPC not really responding in a consistent way. Basically, the AI reliance seems entirely central to the gameplay loop at this point.