Meta's non-invasive brain-reading AI cuts word errors to 39%, closing gap with implants

What happened

Meta researchers released Brain2Qwerty v2, which reconstructs typed sentences from brain signals measured outside the skull using magnetoencephalography (MEG). The system achieves a 39 percent word error rate, compared to 55 percent for previous methods, and requires ten times more training data than its predecessor to work without knowing exact keystroke timing.

Why it matters

Invasive brain implants currently achieve below two percent word error rate, but they require surgery. This non-invasive approach—which works with portable room-temperature MEG sensors—offers a potential path toward clinical brain-to-text communication without surgery, though significant gaps remain and the system is not yet real-time capable.

What to watch

For the best participant, 28 percent of sentences decoded perfectly, and 47 percent contained at most one wrong word. The researchers found that collecting more recordings is a straightforward way to improve accuracy further, with no performance ceiling visible yet. Tests showed that even half the sensors deliver nearly full performance.