That is incredible! Thanks for the explanation.

This work looks incredible! The elo rating is that good even considering the model lost if it has a hallucinated nonlegal step.

Super cool work! Does hallucination happen when running evaluation of elo rating? How does it handle that case?

Hi Marc could you add me? Thanks!!

Hi, could you add me? Thank you!

Hi! would love to be added

Thanks!

would love to be added!