Fork the consciousness, or download the project and create your own.

Nicholas Card

UC Davis Neuroprosthetics Lab

Builder The claim is about what the hardware does, and the philosophy is left open

Nicholas Card led the study that turned the attempted speech of a man with ALS into text at 97.5% word accuracy across a 125,000-word vocabulary, held over 8.4 months. The system reached 99.6% on a 50-word set after 30 minutes of calibration on the first day, which made fast calibration as central to the result as peak accuracy.

The decoder he describes reads spiking activity from the left ventral precentral gyrus, turns it into phoneme probabilities with a recurrent neural network, and joins the phonemes into words with a language model. Card is also a co-author of the 2025 Nature study that turned the same signals into a synthesized voice, and of the 2025 Cell study on inner speech in motor cortex.

For consciousness research, his results set a measured baseline for how much of an intention can be read from a few hundred points of motor cortex, and how much stays out of reach.

The speech neuroprosthesis article puts his 2024 study beside the other two. A short film shows the work on a glass brain. Watch Can a machine hear the words your brain tries to say? on YouTube.

Known for. First author of the 2024 NEJM speech neuroprosthesis study that decoded attempted speech at 97.5% accuracy across 125,000 words

Coverage on this site

Related researchers