Comment by 2001zhaozhao
11 hours ago
A dream of mine is to be able to host a LLM-powered video game that I can host on a home server running a decent mid-range GPU like the RTX 5060, and the LLM is fast and intelligent enough to make for a fun game experience for a few dozen concurrent players. People can ask for features and they just get made and added to the game on the fly for the lobby to enjoy. The hosting costs would be manageable enough that I don't have to charge anything for the game.
I think with one more year or so of small model progress, that might just be possible to accomplish.
I’m doing this now. Homebrew DnD engine and mobile app chat interface. Rich 3d sim and haptics for the dice rolls. But otherwise no fancy graphics rendering. The juice is in the imaginative generate group story telling. Local real time STT on self hosted video chat, to convert the banter and side talk into next player action dice rolls. Qwen on an m3 ultra 96gb handles NPC, dm, bot party members, arc, consistency, history, memory, adventure beats. There’s even a mechanic for bards to compose an end-of-adventure ballad that compresses the shenanigans into verse.
Bootstrapped it with fable, opus or sol 5.6 when I had extra usage to burn over the last month. Playtesting it solo as both DM and PC was fun too. Character consistency and originality is remarkably compelling.
Upshot is that for the gaming hours that my friends have available, the social interpersonal gaming experience competes well for their AAA gaming time. There’s even some good async passive campaign continuation patterns that run in our signal thread to keep things going between sync sessions.
And players have requested features directly in the session transcript that have been direct implemented.
Lol