Viewing profile — KMcPheeters

When the performance of Godot's physics engine has been mentioned before I've seen https://github.com/godot-jolt/godot-jolt pointed to as a drop in more performant solution. Haven'…

I’ve added some simple memory handling so it should be able to continue stories passed the token limit now

The biggest trade off is you sometimes get invalid JSON. So I try repairing the JSON with some regex and also just retry a few times if it returns invalid JSON that can't be repair…

I think this is the simplest "jailbreak" jailbreak I've seen work so far - clever!

Thanks for trying it out! Right now we give the game engine some initial examples, and some character details are stored outside of the LLM context. The token limit problem / memor…

Currently using gpt-3.5-turbo. All state has a json representation that gets based between the game engine and the LLM. In v0.2 not handling the context window super well, planning…

This weekend at the NYC GPT/LLM Hackathon, we built rpgGPT, a text-based RPG set in the world of Occidaria (think fall of the Western Roman Empire, with a slightly magical twist). …