Neuralink Pulse

BREAKING: Neuralink has added a new blog update on its website. It details a 72-hour sprint to help people with ALS speak, make calls and use Grok with their thoughts. Engineers worked at a VOICE trial participant’s home, building and testing improvements alongside him. 🧠 SPEECH AND AI • Automatic speech detection: Recognizes when users try to speak, reducing button presses. • Live brain activity: Shows which imagined speaking patterns produce stronger signals. • Grok agent prototype: Think “Hey Neuralink” followed by a task, and Grok carries it out on a computer. 📱 BLOOM MOBILE APP • Everyday use: Tested outside the lab, including ordering coffee. • iPhone keyboard: Write in any app using speech decoded from brain signals. • Faster editing: Easier corrections and keyboard suggestions. • Lock-screen controls: Start speech without unlocking the phone. • Phone calls: Send generated speech directly into calls, with an optional greeting explaining the assistive device. 🤝 BUILT WITH THE PARTICIPANT • He, his wife and caregiver helped shape improvements. • Direct feedback shortened development cycles from weeks to hours. • He and his wife joked together on the phone again. 🧠 CONTINUING DEVELOPMENT • Some demos include improvements made after the sprint. • Neuralink is recruiting engineers. • Devices remain investigational. Neuralink is changing lives ♥️

This is an extremely promising result from Neuralink: Early data from their VOICE speech restoration study shows a participant achieving 75 words per minute (WPM) on a 125,000 word vocabulary. For comparison, the average adult US citizen talks at around 150 WPM on a 40,000 word vocabulary. With future trial participants, Neuralink will leverage their scale to get more data about how the brain produces speech. In turn, this will improve this result enough to surpass able-bodied humans! Consider how meaningful this is- if Neuralink patients can output information from their brain faster than non-Neuralinked patients, they'll have a huge technology advantage. But they also mention a 5.8% word error rate (WER). This is an error every ~17 words. I asked Grok to give us a sense of how good/ bad this is: "In practical terms: - Under ~5–6% is generally considered excellent / high-quality performance (comparable to strong modern automatic speech recognition systems on clean audio). - It is highly usable for communication—listeners or readers can usually follow the meaning with only occasional corrections. - On a large 125k-word vocabulary this is especially notable, as bigger vocabularies normally make accuracy harder." More information about the study can be found in this thread: