Reaction
Game-playing AI models reportedly have higher win rates than one player, but still make mistakes
A player says the models make clear mistakes about once per act and calls their deck-building choices subpar.
TLDR
A player says the models have noticeably improved at the game and now achieve better win rates than they do. They still spot clear mistakes about once per act and consider the models' deck-building choices subpar.
Combined views
—
1 Source, first seen ago
