AIThe Registerabout 4 hours ago
Meta's Brain2Qwerty v2 hits 61% word accuracy
4 min read
Meta announced Brain2Qwerty v2, a noninvasive BCI that decodes brain signals during typing. The system achieved 61% average word accuracy, up from single-digit accuracy in prior systems. It relies on MEG headsets and deep learning, but still requires users to type and cannot support real-time communication.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyMeta
