The keyboard is moving inside the head
the keyboard is moving inside the head: meta’s brain2qwerty v2 types from meg signals with 61 percent average word accuracy and no surgery, while its tribe model predicts brain responses to movies and podcasts at 70x the old resolution. a single bci decoded speech and movement for the first time in september.
thought is becoming a data format.
Context
Meta's Brain2Qwerty v2 decodes natural sentences from non-invasive magnetoencephalography recordings. Its page says it was trained on 10 times more data per participant, and the paper (arXiv, Jun 29, 2026) says it decodes sentence production from real-time MEG.
Meta's TRIBE v2, introduced Mar 26, 2026, is a model of how the brain responds to video, audio and language, with a stated 70 times resolution increase over similar models.
TRIBE v2's 70 times resolution increase and Brain2Qwerty v2's non-invasive MEG approach match Meta's pages. The 61 percent average word accuracy and a single BCI decoding speech and movement in September are not seen in the sources read, so unsupported here, not refuted. 'Movies and podcasts' as stimuli is also not seen in the sources read, so unsupported here, not refuted.
Related work
- Brain2Qwerty v2 project page ↗Meta's page.
- arXiv: Accurate decoding of natural sentences from non-invasive brain recordings ↗Jun 29, 2026.
- Meta AI: Introducing TRIBE v2 ↗Mar 26, 2026.
Watch next
- Read the paper for the word accuracy and participant count.
Sources
- Brain2Qwerty v2, Meta project pagefacebookresearch.github.io
- arXiv, Jun 29, 2026arxiv.org
- Meta AI, TRIBE v2, Mar 26, 2026ai.meta.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 2 October 2026 at 10:13 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →