Human brain aligns with LLMs, real-time scans reveal next-token prediction
maier_ak · x · 2026-08-24
A study using EEG and MEG scans on 29 people listening to an audiobook found that the human brain pre-activates expected syntactic and semantic structures before a word is spoken, essentially performing "next-token prediction."
When researchers fed the same audiobook into a Transformer model (Llama) and extracted its hidden representations, they found that the predictive patterns and representational structures in the biological brain aligned perfectly with those in the AI.
More from Research
- Cornell and Amazon revisit the 16x pretraining compute gap: diffusion LMs need only 3-8x — LucaAmb · 2026-10-16
- AI trained on the fraction of human intelligence that fit the page — r0ck3t23 · 2026-10-16
- Quotient Recurrent Reasoners hit 97.9% on Sudoku-Extreme with 78% fewer loops — burny_tech · 2026-10-16
- Mathematicians publish explainer for the Egyptian fraction proof in OpenAI's proofs collection — burny_tech · 2026-10-16
- Robin Hanson: a neural network is almost 'a fractal of explanations' — burny_tech · 2026-10-16
- 'Neural networks really are super simple': a takes on features, concepts and connectionism — burny_tech · 2026-10-16