Researchers have made a breakthrough in using artificial intelligence (AI) to translate brain activity into a continuous text stream. An AI-based semantic decoder can translate brain activity into a continuous array of texts, allowing non-invasive thoughts to be converted into written language, changing the field of communication for those with severe neurological conditions. AI algorithms can automate and streamline the complicated process of interpreting brain activity, enabling more accurate and reliable inferences about brain function. However, researchers also note that functional magnetic resonance imaging, which measures changes in blood flow to different brain areas, is comparatively slow. AI developments have trained large language models to generate human-like responses to a wide range of inputs, enabling researchers to understand neuronal activity patterns corresponding to a string of words. The team aims to bolster the technique’s utility in other portable brain-imaging systems, such as functional near-infrared spectroscopy.