
AI Decodes Brain Activity into Text, Raises Concerns
Neuroscientists at the University of Texas have successfully decoded data from non-invasive brain scans and used them to reconstruct language and meaning from stories that people hear, see or even imagine. The researchers used the blood oxygen level dependent signal from fMRI scans, which shows changes in blood flow and oxygenation levels in different parts of the brain. The decoder could be trained to reconstruct continuous language (including some specific words and the general meaning of sentences). The technology could be useful for people who cannot speak due to conditions such as motor neurone disease, but raises concerns for the future privacy of our thoughts.


