← Back to context Comment by prodigycorp 14 hours ago Transparently so. MiMo's training dashboard showed the DeepSWE hillclimb in real time. 1 comment prodigycorp Reply throwa356262 8 hours ago That's not benchmaxing.You need a method to show you RL is improving the model that is separate from the training data.
throwa356262 8 hours ago That's not benchmaxing.You need a method to show you RL is improving the model that is separate from the training data.
That's not benchmaxing.
You need a method to show you RL is improving the model that is separate from the training data.