Hey everyone! I think LLMs like GPT-4 are going to completely change gaming by providing the ability for games to have open-ended, real-time conversations, as well as massive multi-agent simulations that lead beautifully chaotic and emergent situations. I've been working on this prototype for the past few months and just released this devlog, with plans to post more frequently.

At the moment I use Unity for much of the game's frontend and core logic, but have a websocket connection to a Node server which handles GPT-4 requests, and connecting to a db. Right now it can be quite expensive at $100/day of R&D, but I'm saving every single request and response, with the goal to finetune a 3.5-turbo or other model in the future, which should significantly decrease costs.

Happy to answer any questions!