The paper was just published in Nature https://www.nature.com/articles/s41586-025-09255-w (the preprint was out almost 18 months ago)

Having tried prototypes at neuroscience conferences where their team attended, I can tell you that the device was incredibly brittle (e.g. damp wrist, interference from even the metal table or a nearby computer).

As it says in the article, the device seems to be more robust, and ready for the market soon. After having used ML to tune the decoding model on many participants contributing EMG data.

You’re correct that this was publicly announced last fall along with Orion. This is back in the news now because of the recent Nature paper demonstrating the performance of general models on new participants without additional training data. It has nothing to do with PC drivers.