This is pretty wild, also another reason zuck wants to be in control of VR’s social spaces. The amount of data to be collected and used for prediction and emulation of human behavior is going to be growing by leaps and bounds as VR tracking tech progresses. Which also means the ability to manipulate that behavior will progress, as well.

They don’t have more articulated gestures down and the model doesn’t do a good job recognizing what part of a motion should be important in a gesture, which is funny because they said they’re better than before with pointing and hand waving and use an Italian style person in that example.

Everything I saw was talking slow and not articulating quickly.