Meta Brain2Qwerty v2 decodes typed sentences from brain scans at 61% accuracy without implants

Meta's Brain2Qwerty reads typed sentences from the brain

Brain2Qwerty v2 decodes typed sentences from brain scans with 61% word accuracy, up from single digits, without an implant. The snag: it needs a room-sized scanner, can't work in real time, and is trained on typing, which its intended users can't do. Meta says it can turn brain activity into typed sentences without opening your skull. The leap is real. So is the catch: the system learns from typing, the one thing its intended users cannot do. On Monday, Meta unveiled the second version of Brain2Qwerty, a system that reads the brain signals people produce while typing and reconstructs the words. It is non-invasive. There is no surgery and no implant. A volunteer wears a magnetoencephalography (MEG) scanner, a helmet-like machine that picks up the tiny magnetic fields the brain gives off. An AI pipeline does the rest. The headline number is a real jump. Brain2Qwerty v2 hit an average word accuracy of 61 per cent, rising to 78 per cent for the best participant, Meta said. Earlier non-invasive systems managed only single digits. Last year's v1 topped out around 48 per cent. To get there, Meta trained the system on roughly 22,000 sentences that nine volunteers typed, each wearing the scanner for about 10 hours. Meta ran the study at a research centre in San Sebastián, Spain, Gizmodo reported. Chatbots for the brain The trick is the same technology behind ChatGPT. The pipeline first turns the scanner's messy signal into characters. A second model stitches those into words. Then a large language model, fine-tuned on the brain data, uses context to guess the sentence the person meant, much like a phone predicting your next word. Meta says this is the first time an LLM has decoded noisy brain activity into whole sentences. It even set AI agents to work refining its own decoding pipeline, though engineers made the final calls. The choice of scanner mattered more than expected. Meta tested both MEG and the cheaper, more common EEG. MEG was far better, with a character error rate of 29 per cent against 65 per cent for EEG. Meta has open-sourced the code and the dataset, echoing a wider push to do AI-for-science in the open. It frames the project as a way to help the millions who lose speech to brain injury or disease. Still stuck in the lab Then come the caveats, and they are big. The system is nowhere near a product. The MEG scanner fills a room, costs a fortune, and belongs in a hospital, not a home. It cannot work in real time either. The models need a full typing session to finish before they produce anything, so there is no live feedback. There is a deeper problem. Brain2Qwerty learns from the brain signals of people typing. Its intended users, those locked in by paralysis or disease, cannot type at all. Meta admits as much. People with limited mobility might benefit, but the fully locked-in are unlikely to. That would take rebuilding the task around imagined movement rather than real keystrokes. The current design even needs to know exactly when the user presses each key, and Meta calls the path to continuous, trigger-free decoding "uncertain." The surgeons are still ahead For now, the invasive approach wins on results. Implanted systems reach far higher accuracy, The Register noted, with recent surgical work hitting 92 per cent sentence-level accuracy. One surgical interface let a man with ALS work a full-time job, decoding his attempted speech with near-perfect precision. Firms from Neuralink to its rivals are racing to commercialise that kind of implant. Meta's pitch is that it can close the gap without the drill, because accuracy climbs steadily as it feeds the models more data. That may prove true, and doing the work in the open should help others test it. But a brain reader that fills a room, waits until you finish, and depends on you being able to type is a long way from a lifeline. Meta's broader AI ambitions tend to arrive loud and early. This one is a real advance in the lab, and an honest reminder of how far the lab still sits from the ward.

Meta's AI Is Getting Better at Reading Your Thoughts -- Without Cracking Open Your Skull

Most of us have at one point or another had a dream in which we were unable to speak or move; to wake up from such a nightmare -- and to recall what it's like to be able to freely use your voice -- feels like a liberation. Now, Meta says it's getting closer to helping people who actually live with this paralyzing condition to communicate through the use of brainwave-decoding AI. On Monday, the company introduced Brain2Qwerty v2, its latest effort to translate noisy brain activity into coherent text: think of it like a rudimentary form of algorithmically mediated mind-reading. While the research is still in its early stages, it offers a glimpse of a perhaps not-so-distant future in which patients suffering from anarthria, locked-in syndrome, amyotrophic lateral sclerosis (ALS), and other paralyzing neurodegenerative disorders are able to communicate via thought without the need for neuroprosthetics, which typically require extremely invasive, complex, and expensive brain surgery. "We believe this research has the potential to make a real difference for the millions of people who suffer from brain lesions that prevent them from communicating," Meta wrote in its announcement. The underlying code for Brain2Qwerty v2, as well as that of its predecessor, v1, have been made available online. "Our hope is that this work, done in the open, advances neuroscience to identify, diagnose, and treat neurological disorders faster than in siloes," the company wrote, echoing a burgeoning movement within the AI industry to provide scientists with access to open source AI in the name of accelerating the pace of discovery. How Meta trained Brain2Qwerty v2 The training for the new model, which was conducted at the Basque Center on Cognition, Brain, and Language in San Sebastián, Spain, involved nine healthy volunteers between the ages of 25 and 56 who were asked to type more than 2,500 sentences over the course of ten sessions. Throughout these sessions, their brain activity was monitored via magnetoencephelography (MEG), which measures the minuscule electric fields produced by neuronal activity in the brain. All of those typed sentences and brainscans then served as the raw training data that was fed into Brain2Qwerty. In its most successful experiment, Brain2Qwerty v2 achieved a word accuracy -- meaning more than half of the sentences that were decoded from brain activity contained no more than one word error -- of 78%. In contrast, Brain2Qwerty v1 (which was released last year) achieved a score of 48% in its most successful case. The researchers also found that the accuracy of the new system's decoding ability increased alongside the amount of training data it was provided with, suggesting that simple scaling laws could be applied to build more capable systems in the future: "if extended training on non-invasive MEG data can eventually obviate the need for neurosurgery," the researchers wrote in their technical paper, "it would represent a transformative shift in patient care." From brainwaves to LLM to communication Brain2Qwerty v2's unprecedented decoding accuracy was achieved in large part by leveraging the same pattern-recognition technology behind chatbots like ChatGPT and Meta's Llama. In the first two stages of the decoding process, subjects' brainwaves measured by MEG were translated via AI into tokens representing individual characters, at which point another AI system -- called an aligner -- organized the individual characters into complete words. A large language model takes over from there, turning the other AI's jumble of characters and words into coherent sentences. The results mark the first time an LLM has been successfully deployed to translate noisy brain activity into structured, intelligible sentences. It could also offer a valuable new model for future researchers trying to build new brain-machine interfaces, be they physical or virtual, in which multiple AI systems are used to decode brain activity in a hierarchical and cooperative fashion. Alongside that multi-tiered AI-driven decoding system, Brain2Qwerty also relies upon a contingent of "auto-research" AI agents, whose task is to autonomously hone the decoding process in order to boost its accuracy and efficiency; think of them like worker bees continually making structural refinements to the hive, so that all the vital activity happening inside can keep going on without a hitch. The agents were trained "to iteratively change our code base to invent novel, better architectures," the researchers wrote in the paper, producing "a substantial improvement" in word error rate (WER). The paper also noted, however, that while the agents were helpful in identifying new optimization strategies, they were a long way from replacing human researchers wholesale: "while AI agents may serve as a powerful force multiplier, human research remains, for now, a critical part of the scientific process."

Meta's Brain2Qwerty v2 turns thoughts into text, and it doesn't need brain implants

The latest AI model decodes brain signals into coherent sentences using external scanners. Artificial intelligence is getting surprisingly good at understanding humans. Now, Meta wants it to understand our brains too. The company has unveiled Brain2Qwerty v2, an upgraded AI system that can translate brain activity into full sentences, all without requiring brain implants or surgery. The goal isn't mind reading for the masses. Instead, it's to help people who have lost the ability to speak communicate again. How a Brain-powered keyboard works The easiest way to think about Brain2Qwerty v2 is as an incredibly advanced brain-powered keyboard. Volunteers wear a Magnetoencephalography (MEG) scanner, which measures tiny magnetic signals produced by the brain while they type. Instead of watching the keyboard, the AI watches those brain signals and predicts what the person intended to type. The biggest leap over the original Brain2Qwerty is that it no longer tries to decode one letter at a time. Instead, it looks at characters, words, and entire sentences, using large language models to fill in the blanks, much like your smartphone predicts the next word while typing. Meta even describes the system as adding semantic understanding, allowing it to recover coherent sentences from extremely noisy brain signals. Recommended Videos Under the hood, the AI combines deep learning models such as Transformers and Convolutional Neural Networks with fine-tuned language models that act almost like a spellchecker for the brain. If the neural signal is incomplete or distorted, the language model uses context to infer what the user most likely intended to say. Meta also used AI agents to optimize the decoding pipeline itself, helping improve real-time performance. As highlighted in the official research paper, the system was trained using around 22,000 typed sentences collected from nine volunteers, each of whom spent roughly 10 hours wearing an MEG scanner while typing. Brain2Qwerty v2 currently achieves an average 61% word accuracy, while the best participant reached 78% accuracy, with more than half of their decoded sentences containing one word error or less. Meta has also open-sourced both the training code and dataset so other researchers can build on the work. The magic of skipping surgery The funny thing is that the biggest breakthrough here isn't the AI. It's the fact that it works without opening someone's skull. Most high-performance brain-computer interfaces today, including Elon Musk's Neuralink, rely on surgically implanted electrodes to achieve high accuracy. Brain2Qwerty v2 takes a very different approach by using a completely external Magnetoencephalography (MEG) scanner to read brain activity, eliminating the risks associated with intracranial implants while still achieving surprisingly strong results. Meta is still a long way from building a consumer product, and nobody should expect to type emails using their thoughts anytime soon. The MEG scanners used by Brain2Qwerty are massive, expensive machines that belong in research labs, not living rooms. But by combining advances in neuroscience with modern AI, Meta is showing that non-invasive brain-computer interfaces may not be as far away as they once seemed. And for people who have lost the ability to communicate, that could end up being far more meaningful than any chatbot or image generator.

Meta Unveils New Tech That Uses AI to Translate Brain Activity Into Text -- Without Surgery

Meta released the training code for Brain2Qwerty v1 and v2, while its research partner is releasing the v1 dataset. Meta on Monday introduced Brain2Qwerty v2, an AI system that translates brain activity into text using non-invasive brain recordings. The company said the research is intended to help people who have lost the ability to communicate because of brain lesions. The system records brain activity using a helmet-like magnetoencephalography (MEG) scanner, a non-invasive brain imaging device commonly used in neuroscience research. It then feeds those raw neural signals into an end-to-end AI model that reconstructs the sentences a person is trying to type. Meta said it further improves accuracy by fine-tuning large language models on neural data, allowing the system to use semantic context when interpreting noisy brain recordings. "We trained Brain2Qwerty v2 on approximately 22,000 sentences from nine volunteer participants, each recorded for 10 hours wearing a magnetoencephalography (MEG) device while actively typing," Meta wrote. "Instead of relying on hand-crafted pipelines to detect neural events, we use end-to-end deep learning to decode directly from raw brain signals." Meta said Brain2Qwerty achieved a 61% average word accuracy, compared with roughly 8% for previous non-invasive methods. The company is releasing the system's code and dataset as part of its Digital Brain Project, which also includes a $5 million fund to support open neuroscience datasets. Meta also said decoding accuracy improved as the amount of training data increased, suggesting additional data could further improve performance. The company said AI agents explored possible optimizations for the decoding pipeline before engineers selected the final training configuration. In an accompanying paper published in Nature Neuroscience, Meta researchers argued that while AI has significantly improved brain-to-text decoding, most high-performing brain-computer interfaces still depend on surgically implanted electrodes, making them difficult to scale because of the risks tied to brain surgery and the challenges of maintaining implants over time. Meta said Brain2Qwerty v2 approaches levels of accuracy previously achieved only with techniques requiring brain surgery. The company said its non-invasive approach could help bridge the gap between invasive neuroprosthetics and communication systems that do not require surgery. "Our hope is that this work, done in the open, advances neuroscience to identify, diagnose, and treat neurological disorders faster than in siloes," Meta wrote. The announcement comes as brain-computer interface research accelerates, including by Elon Musk's Neuralink and Merge Labs, backed by OpenAI CEO Sam Altman, developing technology to help restore communication for people with neurological disorders. While companies such as Neuralink and Synchron are pursuing implanted interfaces that require surgery, a growing number of researchers and startups are using AI to improve the performance of non-invasive systems. In September 2024, startup Neurable introduced AI-powered EEG headphones designed to monitor focus and cognitive fatigue. A year later, MIT spinout AlterEgo unveiled a wearable that converts silent neuromuscular signals from the face and throat into text and commands, positioning it as a practical alternative to implanted brain-computer interfaces. Meta did not immediately respond to a request for comment by Decrypt.

Meta says new AI system can convert brain activity into text without surgery

Meta's new AI, Brain2Qwerty v2, decodes brain signals into text without surgery, achieving 61% word accuracy. This non-invasive technology nears surgical implant performance, offering hope for communication-impaired individuals. Meta is releasing the code to foster open neuroscience research and advance understanding of neurological disorders. Meta has unveiled Brain2Qwerty v2, a new artificial intelligence (AI) system that can decode brain activity into text without requiring any surgical implant, marking a significant step forward in brain-computer interface research. According to the company, Brain2Qwerty v2 is the highest-performing end-to-end pipeline capable of real-time sentence decoding from non-invasive brain recordings. Meta said the technology is approaching levels of accuracy that were previously possible only through techniques involving brain surgery. It stated "Brain2Qwerty v2, the highest-performing end-to-end pipeline capable of real-time sentence decoding from non-invasive brain recordings, approaching levels of accuracy previously exclusive to techniques that require brain surgery". The company said the research could help millions of people suffering from brain lesions and other conditions that prevent them from communicating. Unlike invasive methods such as stereotactic electroencephalography and electrocorticography, which require surgical implants to capture brain signals, Brain2Qwerty uses non-invasive recordings to decode intended text. Meta said it trained Brain2Qwerty v2 using around 22,000 sentences collected from nine volunteer participants. Each participant spent about 10 hours wearing a magnetoencephalography (MEG) device while actively typing. The company explained that the system uses end-to-end deep learning to decode language directly from raw brain signals instead of relying on manually designed pipelines to identify neural events. According to Meta, large language models were fine-tuned on neural data, enabling the system to use semantic context to bridge the gap between noisy brain signals and coherent language. The company also deployed AI agents to explore optimizations in the decoding process, with final training configurations selected by engineers. Meta said the new system achieved a word accuracy rate of 61 per cent, a significant improvement over the 8 per cent word accuracy achieved by other non-invasive methods. For the best-performing participant in the study, the system reached a word accuracy rate of 78 per cent, with more than half of all decoded sentences containing one word error or less. The company also found that decoding accuracy improved as more training data became available, suggesting that the performance gap between non-invasive and surgical approaches could be reduced further through larger datasets. To support further research, Meta announced that it is releasing the full training code for Brain2Qwerty v1 and v2. Its research partner, the Basque Center on Cognition, Brain and Language (BCBL), will also release the Brain2Qwerty v1 dataset. Meta said the work forms part of its broader efforts to develop open foundational models of the brain and advance neuroscience research aimed at improving the diagnosis, treatment and understanding of neurological disorders. Meta also said the research is part of its broader effort to build open foundational models of the brain. The company highlighted its TribeV2 model for perception encoding, NeuralSet for processing brain data at scale, and NeuralBench for systematically evaluating brain models. Meta said these initiatives form part of its Digital Brain Project, under which it recently announced a USD 5 million fund to support the creation of open neuroscience datasets.

Meta says it can read your thoughts without surgery

Your own head has always felt like the last place no one else can get into. You can lie with your face, edit your words, delete a text before you hit send. But the half-formed sentence sitting behind your eyes, the one you have not decided to share yet, has stayed yours alone for the entire history of the species. That privacy has had exactly one serious threat, and it came with a scalpel. For years, the only way a computer could reliably turn brain activity into language was to get inside the skull. Elon Musk's Neuralink drills a coin-sized hole and lays electrodes directly on the brain. Companies like Synchron thread sensors through blood vessels. The results can be remarkable, and so are the risks: infection, scarring, a device that degrades over months. High accuracy meant surgery, full stop. I have covered enough Musk brain-implant promises to treat any "mind reading" claim with a raised eyebrow. So when Meta Platforms (META) said on June 29, 2026, that it can now decode the sentences you type straight from your brain signals, with no implant and no incision, I went looking for the catch. What Meta's Brain2Qwerty v2 actually decodes The system is called Brain2Qwerty v2, and the name is a tell. It does not pluck free-floating dreams out of your head. It reconstructs the sentences you are actively trying to type, reading the brain activity that fires while your fingers move. Here is how it works. * A volunteer sits inside a magnetoencephalography (MEG) scanner, a machine that picks up the faint magnetic fields thrown off by neurons, and types memorized sentences. * The AI model reads those raw signals and rebuilds the words as they form. Two things make that work. The model learns straight from raw brain signals instead of hand-built rules. A fine-tuned language model rides on top, using context to repair the gaps and guess the likeliest word when the neural read comes back noisy. It is the "highest-performing end-to-end pipeline capable of real-time sentence decoding," according to Meta. The accuracy is the part that stopped me. When I lined up the new figures against what non-invasive decoding could manage a year ago, the jump was not incremental. * Older non-invasive methods landed near 8% word accuracy, Meta confirmed. * Brain2Qwerty v2 averaged 61% word accuracy across nine volunteers, Meta said. * The best participant reached 78% word accuracy, with more than half of sentences decoded with one word error or less, Digital Trends reported. * The model was trained on roughly 22,000 sentences gathered over 10-hour scanning sessions, according to Meta. That 61% figure means the system now "approaches levels of accuracy previously achieved only with techniques requiring brain surgery," Decrypt explained. For a method that touches nothing and cuts nothing, that is a real leap. The earlier version, whose findings appeared in the journal Nature Neuroscience, could only spell out characters one at a time, according to Meta. Yuichiro Chino / Getty Images Why this brain-reading milestone still needs a room-sized machine Before anyone panics about Mark Zuckerberg downloading their inner monologue, look at the hardware. A MEG scanner is not a headband. It is a multimillion-dollar instrument that sits in a magnetically shielded room and weighs about as much as a small car. Those scanners are "massive, expensive machines that belong in research labs, not living rooms," according to Digital Trends. More Artificial Intelligence: There is a second limit that matters just as much. The system decodes typing, not unspoken thought. It leans on the brain's motor signals as your hands move, which makes it closer to a very advanced read of your keystrokes than a window into your imagination. That distinction matters, because every leap in this field gets sold as telepathy long before it earns the word. Meta has announced no product, no timeline, and no plan to put this on a shopper's head. The gap between a lab result and a thing you can buy is where most brain-computer breakthroughs go to wait. The invasive route shows why. Musk's Neuralink gets clean signals because it lays electrodes on the brain itself, and it has shown a paralyzed patient move a cursor by thinking, as TheStreet covered in 2024. The price of that fidelity is a hole in the skull. What Meta stock and the brain-computer race signal next For Meta Platforms shareholders, Brain2Qwerty is not a revenue story. It is a flag planted in a field everyone suddenly wants to own. For Zuckerberg, that is partly the point. He has spent heavily to recast Meta as a frontier research lab rather than a social network with an ad engine bolted on, and a brain-decoding milestone buys exactly that kind of credibility. The company open-sourced the training code and is funding open neuroscience data through a new Digital Brain Project carrying a $5 million commitment, according to Meta. The competitive map is filling in fast. Neuralink and Synchron are pushing implants you have to be cut open to receive. Merge Labs, a startup backed by OpenAI chief executive Sam Altman, is chasing the same prize from another direction, Decrypt noted. Meta's wager is that it can get most of the way there without the scalpel, and that giving the work away will pull the whole field forward faster than guarding it would. I keep coming back to the uncomfortable part, the one Meta's careful framing does not erase. This is the company whose business runs on knowing what you want before you do. The stated goal, restoring a voice to people who have lost the ability to speak, is real and worth cheering. But the same plumbing that gives someone their words back can, pointed differently, model intent. Anyone who shrugs at one more ad-targeting story should notice that the signal being decoded here is not a click. It is a sentence forming in your head. Where the brain-to-text race goes from here The most important number in the research is not the accuracy rate. It is the slope. Accuracy kept climbing as Meta fed the model more data, with no sign of leveling off, according to Meta. That is the same scaling logic that turned chatbots from novelties into tools, now aimed at the brain. So the honest forecast is patience, and then, all at once, none. For now, the MEG scanner keeps this locked inside the lab. The day a wearable version closes even part of that accuracy gap, the question stops being whether a machine can read the words in your head and becomes whether you ever agreed to let it. I would start deciding your answer now. The Arena Media Brands, LLC THESTREET is a registered trademark of TheStreet, Inc. This story was originally published June 30, 2026 at 4:37 PM.

Meta Introduces Brain2Qwerty V2: A Non-Invasive AI That Translates Brain Signals to Text

Meta has developed Brain2Qwerty v2, an advanced AI software that translates brain waves into text and does not require surgery or implants. This development is a big leap in BCI technology and can one day help people who cannot communicate due to neurological disorders. This technology uses (MEG). It is an invasive procedure that records the minute magnetic fields generated by brain activity. The participants put on a helmet with sensors that detect brain activity as they type, thereby decoding their thoughts into text through AI. claims that Brain2Qwerty v2 is its best-performing end-to-end sentence decoder ever, significantly surpassing its predecessor. It is believed that this technology will someday help people with paralysis, brain damage, or speech disorders to convey messages by thought alone. While the shows great promise, Meta admitted that it is still a work in progress. The MEG technology used in the system is bulky, expensive, and requires specialized conditions, making it currently unfit for daily use. More advancements in both hardware and artificial intelligence will be needed to make this a reality.