High-Throughput Generative Inference of Large Language Models with a Single GPU

Re:High-Throughput Generative Inference of Large Language Mo... by orbital-decay on Tuesday March 14, 2023 @12:35AM (#35147490)

People are trying to build games based on LLM generation since 2019. Problem is, the models are too flexible for this purpose - you can easily break the world rules and make the game look like nonsense. And games are all about comprehensible rules and properly placed restrictions.

So these attempts are currently concentrated on two things:

1. How to make the model play by the rules.

2. How to translate the model output into something concrete in terms of game mechanics.

[ Parent | on HN ]

Re:High-Throughput Generative Inference of Large Language Mo... by imtringued on Tuesday March 14, 2023 @03:32AM (#35148376)

ChatGPT is an instruction fine tuned version of GPT3 with RLHF. You could train an AI game master that tries to maintain coherence within a story or game world. The only problem is fine tuning the GM for each individual game and making it reproducible for debugging.

[ Parent | on HN ]