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
- WorldMemArena Accepted at NeurIPS: Memory Storage ≠ Memory Use — xwang_lk · 2026-10-16
- Mech Interp Veteran Rethinks Alignment, Misgeneralization, CoT Oversight — akbirthko · 2026-10-16
- WEDGE paper generates training environments conditioned on navigation agent failures — _akhaliq · 2026-10-16
- RExBench: best coding agent completes only 33% of autonomous research extensions — najoungkim · 2026-10-16
- Google's CLASHarness benchmarks multi-agent conflicts in computer use, finds frontier VLMs struggle — google · 2026-10-16
- Tsinghua team proves vanilla flow-matching sampling can't exceed constant-depth expressive power — SQZ · 2026-10-16