{"slug": "reading-without-a-reader-large-language-models-collapse-reading-and-writing-into", "title": "Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code", "summary": "A new study from arXiv preprint 2607.24797v1 finds that decoder-only large language models (LLMs) such as GPT-2, OPT, and Pythia entangle reading and writing into a single code, unlike the human brain's double dissociation. The researchers measured an entanglement index E between 0.23 and 0.35 across models, with output-side weights drifting 3.2 times farther than input-side weights, and found behavioral coupling in all 12 non-degenerate models (sign test p<0.001), contrasting with the brain's separable systems.", "body_md": "arXiv:2607.24797v1 Announce Type: cross\nAbstract: In the literate human brain, reading and writing are two doubly-dissociable systems: a ventral decoding route (impaired in pure alexia) and a fronto-parietal encoding route (impaired in pure agraphia), sharing a partial orthographic core. A decoder-only large language model (LLM) instead drives both from a single autoregressive path optimized on text, a recent cultural invention rather than an evolved instinct. We ask how entangled that one mechanism is, comparing an input-side \"reading code\" $W_E$ with an output-side \"writing code\" $W_U$ via an entanglement index $E \\in [0,1]$ (CKA, Procrustes residual, mutual $k$-NN) calibrated against an independent-init floor and a tied ceiling. Across nine probes on GPT-2, OPT, Pythia (14M--1.4B), T5, and BERT/RoBERTa (six consolidating established results, three introducing the read/write analysis), two complementary levels agree in direction. In the weights, untied models hold one coupled but sub-ceiling code ($E=0.23$--$0.35$, far above floor) on a non-monotonic couple-then-differentiate trajectory, with $W_U$ drifting $\\sim 3.2\\times$ farther than $W_E$ in every frequency decile. In behaviour, comprehension and production are positively coupled in all 12 non-degenerate models (sign test $p<0.001$), the opposite of the brain's double dissociation. This coupling is general, not decoder-only: encoder--decoders separate the two pathways representationally (up to 0.96) yet stay behaviourally coupled. We report our nulls plainly (the geometry $\\rightarrow$ behaviour bridge is null, $\\rho=0.00$). Because a single forward path makes some coupling expected a priori, our contribution is its quantification and cross-level concordance; by analogy, not homology, this situates LLMs as a distinct point in the space of possible minds.", "url": "https://wpnews.pro/news/reading-without-a-reader-large-language-models-collapse-reading-and-writing-into", "canonical_source": "https://www.machinebrief.com/news/reading-without-a-reader-large-language-models-collapse-read-451w", "published_at": "2026-07-29 04:00:00+00:00", "updated_at": "2026-07-29 07:04:04.400153+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research"], "entities": ["arXiv", "GPT-2", "OPT", "Pythia", "T5", "BERT", "RoBERTa"], "alternates": {"html": "https://wpnews.pro/news/reading-without-a-reader-large-language-models-collapse-reading-and-writing-into", "markdown": "https://wpnews.pro/news/reading-without-a-reader-large-language-models-collapse-reading-and-writing-into.md", "text": "https://wpnews.pro/news/reading-without-a-reader-large-language-models-collapse-reading-and-writing-into.txt", "jsonld": "https://wpnews.pro/news/reading-without-a-reader-large-language-models-collapse-reading-and-writing-into.jsonld"}}