This work looks incredible! The elo rating is that good even considering the model lost if it has a hallucinated nonlegal step.
I'm excited to share a new paper: "Mastering Board Games by External and Internal Planning with Language Models"
storage.googleapis.com/deepmind-med...
(also soon to be up on Arxiv, once it's been processed there)
storage.googleapis.com/deepmind-med...
(also soon to be up on Arxiv, once it's been processed there)
storage.googleapis.com
December 6, 2024 at 8:06 AM
This work looks incredible! The elo rating is that good even considering the model lost if it has a hallucinated nonlegal step.