News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.

“The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serving/training LLMs.

This study presents a valuable advance in reconstructing naturalistic speech from intracranial ECoG data using a dual-pathway model. The evidence supporting the claims of the authors is solid, ...