[sdenton4]

There is/was an AI Dungeon app running in the early/pre-ChatGPT days using GPT 3-ish, I think? Long term context was a real problem - story arcs were very.... drifty. A more modern agentic approach might help with this, doing multiple passes over the work to achieve consistency.

[DiscourseFan]

Nah, it wouldn't work. LLMs don't have coherent, total concepts of things in the same way humans do.

[vunderba]

AIDungeon was built on a fine-tuned version of GPT-2. Less coherent but infinitely more fun than later models.