Meta Unveiled Brain2Qwerty 2.0: Reads Brain Signals During Typing Without Surgery

On June 30, 2026, Meta presented the second version of Brain2Qwerty — a system that decodes brain signals at the moment of text typing and transforms them into entire sentences without any surgical procedures. The key technical achievement: this level of accuracy in decoding brain activity has been realized for the first time using a fully non-invasive method — all sensors are attached to the outside of the skull.

How the System Works

Brain2Qwerty 2.0 operates without implants and surgery. Sensors attached to the scalp surface capture the electrical activity of the brain while the user types text. Meta's specialized algorithms process these signals, match them with neural patterns characteristic of specific keys, and transform the sequence of patterns into readable sentences.

The first version of Brain2Qwerty operated at the level of individual characters — the system attempted to guess one letter at a time. The second version transitions to the level of complete sentences: the system analyzes signal sequences holistically and reconstructs meaningful text as a single output unit. This fundamentally changes the accuracy and practical applicability of the neural interface.

Key parameters of Brain2Qwerty 2.0:

• Announcement date — June 30, 2026
• Fully non-invasive technology: sensors outside the skull, no surgery needed
• New decoding level — entire sentences (the previous version worked with individual characters)
• Developer — Meta AI Research
• Target audience — people with movement disorders who have lost the ability to type

Why Can't the System Be Trained Without Text Input?

The fundamental problem of Brain2Qwerty 2.0 is paradoxical. The system is not universal: it is trained personally for each user, analyzing their brain signals during text typing. The user must type a sufficiently large volume of text for the algorithm to build their personal neural profile.

This is precisely what people cannot do who need the neural interface most. People with amyotrophic lateral sclerosis (ALS), stroke consequences, or severe spinal injuries have physically lost the ability to type — this is why they need this technology. The neural interface is needed by those who cannot train it — a classic problem of first-generation BCI systems.

Meta has not yet announced an approach to solving this problem. In an academic context, alternatives are being discussed: pretraining on data from healthy subjects and the motor imagery method, when a person mentally imagines hand movement without physically performing it.

Who Competes with Meta in Developing Neural Interfaces?

Several major players are working in this segment with fundamentally different approaches. Neuralink uses invasive chips with high spatial precision and has already conducted initial clinical trials on humans. Synchron works with a stent inserted through brain blood vessels — a less risky option, but still requiring a medical procedure. Meta — the only one among major technology companies betting on fully external sensors.

If the non-invasive approach reaches the required accuracy, it opens an entirely different market trajectory: a product without surgery does not need approval as a medical implant and theoretically could reach the consumer market significantly faster than competitors' solutions.

What This Means

Meta has confirmed: a non-invasive neural interface that decodes sentences is real technology, not exotica. The next key question is whether it will be possible to develop a method for training the system without keyboard input. Until this is achieved, Brain2Qwerty remains an impressive academic achievement. If the task is solved — the technology will truly change the lives of people with movement disorders.

*Meta is recognized as an extremist organization and banned in the Russian Federation.