ToolsThe story, in brief
Meta's Noninvasive Brain–Computer Interface Brain2Qwerty Achieves 61% Accuracy
61% accuracy. Meta just open-sourced a brain-computer interface that decodes thoughts into text—7.6x better than prior non-invasive methods.
The KeyNews take
Why it matters
Meta's Brain2Qwerty demonstrates a significant leap in non-invasive BCI performance, opening new possibilities for AI-assisted human-computer interaction and accessibility applications. This open-source release could accelerate BCI research across the industry.
The key facts
6 to knowBrain2Qwerty v2 achieves 61% word accuracy on average
Prior non-invasive methods: 8% accuracy
7.6x performance improvement over baseline
Uses EEG and MEG signal decoding
Open-sourced by Meta
Published July 2026
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: Meta recently open-sourced Brain2Qwerty v2, a noninvasive Brain–Computer Interface (BCI) that can decode sentences from thoughts using electroencephalography (EEG) or magnetoencephalography (MEG) signals from the brain. In evaluations, the system achieved a word accuracy rate 61% on average,…