Neuralink Subject Uses Thoughts to Wake Grok Agent and Control Computer

All the patient has to do is silently think “Hey Neuralink” in his head, then think about the task he wants done, and the Grok Agent on the computer is instantly awakened.

Next, Grok takes over the screen fully automatically and goes straight onto YouTube.

There is also a particularly touching moment: a very special phone call.

The chip in the brain of a severely paralyzed and speech-impaired patient directly converts the “words he wants to say” into a pure audio stream, injected in real time into the underlying microphone audio layer of an iPhone call.

After seven years, he finally used his thoughts to call his wife.

Humanity has taken another extremely wild step toward true “mechanical ascension.”

A 72-hour record of deification

The most ruthless upgrade of “brain-computer interface”

All of this was made possible by a “hard battle” the Neuralink team fought a few days ago.

Several core engineers packed their bags and moved into the subject’s home, eating and living together with him, and carried out a full 72-hour extreme closed-door development sprint.

For three full days and nights, they forced work that normally takes several weeks into just a few hours, and in one burst cranked out 8 brand-new features.

In the past, our understanding of brain-computer interfaces was still stuck at “using thoughts to move the mouse cursor.”

After these 72 hours, the brain has officially become AI’s native input source.

The patient’s name is Kenneth. He was diagnosed with ALS seven full years ago and is a Neuralink P21 subject.

Along the way he has remained especially optimistic, just as he often says: “ALS sucks, but my life doesn’t.”

Say the word in your head, and Grok takes over

The most sci-fi feature this time is, of course, Grok.

A brain-computer patient only needs to imagine saying “Hey Neuralink” in his head, plus the task he wants completed, to trigger a Grok agent, which then autonomously executes it on the computer.

No hands need to type, and the mouth does not need to actually speak; the command is issued from neural activity.

Break this chain apart and it becomes easy to understand: the brain-computer interface is responsible for turning expressed intent into usable input, and the Grok agent catches the task and then operates the computer.

So-called “access” is essentially a complete reconstruction of the dimension of interaction:

Thought-controlled cursor: the brain outputs low-level actions such as “a little to the left, click once,” and completing a task requires dozens or hundreds of steps, with the person having to watch the whole time;

Thought-driven Agent: the brain outputs only one sentence of “intent,” and step decomposition and interface operation are all handed over to AI.

The biggest bottleneck of brain-computer interfaces has always been bandwidth: both the number of electrodes and decoding speed have physical limits.

The value of an Agent is that it “amplifies” one sentence into a series of operations—without adding a single electrode, it multiplies what can be accomplished with each thought.

As Neuralink itself said, this is only an early exploration, but it has genuinely proven that:

as long as communication between the brain and the computer becomes smoother, the barrier between “thinking of it” and “doing it” can be erased.

Deconstructing the eight core technologies

The 8 technical prototypes born during these 72 hours run from low-level signal capture all the way through system-level interaction, ultimately connecting to top-level AI large models.

Neural voice activity detection (VAD): completely throw away the physical switch

Before this hackathon, if Kenneth wanted to speak with his thoughts, he still faced a very awkward paradox—you first had to manually press a button to tell the software “I’m about to start thinking,” and after speaking you had to press again to stop recording.

For patients with ALS or high-level paraplegia, pressing this button is itself a huge burden.

To solve this, the engineers directly rewrote a “Neural VAD” system from the ground up.

This algorithm is like a neural sentinel on duty 24 hours a day, monitoring in real time the stream of brain signals sent back by the implant.

English text is being prepared.

Once the intent pulse to speak is captured, the APP automatically starts decoding within milliseconds; as soon as the words end, the system automatically goes dormant.

The whole process has zero button presses and zero hand movement, truly achieving pure thought-based “speaking as soon as you open your mouth.”

Real-time neural signal visualization: patients and models “train together”

The brain-computer interface field has always had a headache-inducing black-box problem: even the subject himself does not know how exactly to “think” in his head to stimulate the strongest and clearest neuron firing.

You have to know that the higher the signal-to-noise ratio of the input signal, the more outrageously accurate the backend machine-learning decoder becomes.

The team turned the signal strength and spatial distribution detected by the implant into real-time visual feedback for Kenneth. He could “pronounce in his head” in different ways and immediately see which method mobilized the most neural activity.

In neuroscience this is closed-loop neurofeedback: not only is the model adapting to the brain, the brain is also adapting to the model in turn.

What was originally invisible and untouchable parameter tuning has become a “level-clearing game” with instant feedback.

Order coffee on a phone with no hands at all

Over the past few months, Neuralink has been quietly polishing an exclusive app called Bloom internally, with only one goal: to fit the massive speech brain-computer decoding system into a phone.

Taking advantage of this hackathon, the engineers simply pushed Kenneth to leave home, bring Bloom, and head straight to a noisy public place.

In a real café, for the first time Kenneth didn't rely on someone else to relay his words—instead, through Bloom on his phone, he ordered himself a coffee with his thoughts.

And that was only the beginning.

For ALS patients, Apple's built-in software keyboard and Siri voice dictation are practically unusable. So the team directly called low-level iOS interfaces and hand-built a system-level brain-computer input method: BCI Keyboard Dictation.

As soon as the keyboard is brought up, the words Kenneth wants to say in his mind are neurally decoded and flow like a stream into any app on the iPhone.

Writing memos, replying to messages, scrolling social networks—no need to switch back and forth between different modes the whole time; point and it's done.

Of course, decoding inevitably makes mistakes.

To address this, during the hackathon the engineers iterated through several versions of a correction interface, and ultimately embedded a predictive editing workflow directly into the keyboard: once recognition deviates, several high-probability candidate words immediately pop up above the keyboard, and with a glance of his thoughts Kenneth can complete “light-speed replacement” in any app.

There was one more detail that lowered the threshold for starting everyday communication to almost zero.

The engineers cleverly borrowed the iPhone's Live Activities and Dynamic Island mechanisms to keep Bloom resident on the lock screen.

Kenneth doesn't need to unlock the phone; as soon as the screen lights up, he can see the current brain-computer connection status; with a flicker of thought, he can start “speaking” directly from the lock screen, truly achieving “instant replies.”

Paralyzed for seven years

he finally made a phone call with his thoughts

Among all the features, “making a phone call with your thoughts” was not the highest in technical difficulty, yet it became the tearjerker of the whole event.

Technically, the team connected Bloom with iPhone calls, routing the speech generated by the brain-computer interface directly into the call's microphone audio stream.

But the weight of this matter lies not in the technology, but in the story.

Kenneth and his wife's love began over the phone. When they first met, their relationship was slowly built through one phone call after another. That telephone line was once the most important thread between them.

Later, illness made it hard for him to speak. That thread, too, gradually fell silent.

This time, as soon as the engineers finished building the call feature, he picked up the phone and dialed his wife.

She answered. He didn't open his mouth. The words he wanted to say in his mind were captured by the implant, translated by the decoder, synthesized into speech, and sent directly into the call line.

On the other end of the line came his wife's laughter.

The two began teasing and bickering with each other, just like when they were dating over the phone back then.

The engineers just stood by and watched. Neuralink later said this was one of the most unforgettable moments of the entire week.

In engineering, there is rarely anything more rewarding than this. You watch a person use code you wrote that very morning to talk to the person they love.

In the past, the brain's bandwidth was too narrow, and a person could only “squeeze toothpaste” to the machine one letter and one click at a time.

This will become a major leap in human-computer interaction.

In the future, as electrodes become more numerous, decoding becomes faster, and agents become smarter, “think it and it's done” may move from the lab into more people's daily lives.

In “The Matrix,” Neo plugs into a line and learns kung fu in seconds; in “Transcendence,” human consciousness connects to the network and can directly mobilize the entire digital world.

These imaginings that once belonged only to the screen are being written into reality bit by bit.