Got a pretrained music transformer to jam with me live, no fine-tuning, just steering the sampling [P]

I wanted to see how far you can get making a pretrained symbolic music model "listen" to a live player without training it. Turns out pretty far. Setup: I play a MIDI keyboard, the Anticipatory Music Transformer (Thickstun et al., music-medium-800k) plays a second piano. While I play I track my key, the chord I'm holding and my tempo, and add biases to the logits before sampling. Out-of-key notes get pushed down, chord tones and tensions get pushed up, the keys right around my hands get pushed down so it doesn't step on me, and when I stop it gets pulled up to where a melody would be. There's