When the System Breaks, the Architecture Shows

Somewhere in a second-grade classroom right now, a child who can recite poetry, build elaborate block towers, and navigate the social dynamics of the lunch table is staring at the number 7 and feeling nothing quantitative at all. The symbol is there. The magnitude isn't. Seven doesn't arrive heavier than three, or lighter than thirty. The numerals float on the page like decorative glyphs in a language nobody ever translated.

This is developmental dyscalculia — a specific learning disability affecting a notable minority of children — and for most of its history, we could describe it from the outside without quite understanding what was actually broken on the inside. General attention? Working memory? Processing speed? The usual suspects, assembled in the usual lineup.

In 2025, a team at Stanford decided to build the failure instead.

Rather than observing dyscalculia children and cataloguing what was missing, Strock et al. (2025) constructed a deep neural network designed to mimic the dorsal visual pathway — the circuit the brain uses for spatial and numerical reasoning — and then broke it in precisely the ways that dyscalculia breaks the biological version. The digital twin reproduced the behavioral and neural signatures of children with dyscalculia almost exactly. More importantly, it told them where the problem lives: not in attention, not in working memory, but in the formation of number-selective representations in parietal cortex analogs. The abstract concept of magnitude — the thing that makes 7 feel heavier than 3 — requires a specialized representational structure in a specific neural circuit, and in dyscalculia, that structure fails to form properly.

This is the logic of lesion studies, applied at a new resolution. Break something precisely; learn what it was for.

---

Developmental science has always learned fastest from where development goes differently — not as a rhetorical claim but as a methodological one. Simon Baron-Cohen's foundational work on autism in the late 1980s didn't just describe a clinical syndrome; it revealed that the capacity to model other minds is a discrete, separable cognitive module that can be selectively spared or impaired independently of general intelligence. Children who could solve complex puzzles couldn't reliably predict that another person might believe something false. The inference that should be automatic — she doesn't know what I know — simply didn't fire. Autism made the mind's social architecture legible by showing it could come apart.

A 2025 paper in npj Artificial Intelligence made a curious echo of that discovery, but from the machine side. Wu et al. (2025) set out to locate exactly where theory-of-mind capabilities are encoded in large language models — to find, in a sense, the neural correlates in silicon. The answer was startling: ToM-like behavior in LLMs is encoded in an extraordinarily sparse subset of the model's parameters. Perturbing even a vanishingly small fraction of those specific weights meaningfully degrades performance on theory-of-mind tasks. And these sensitive parameters cluster in one place — the positional encoding module, particularly in architectures using Rotary Position Embedding.

A remarkably tiny slice. The social reasoning capacity of a large language model hangs on a few parameters out of an enormous total.

This does not settle whether LLMs have theory of mind in any meaningful sense — the question of whether they genuinely model others' beliefs or simply pattern-match on the textual surface features of social reasoning remains genuinely open. But the sparseness is itself informative. In the human brain, theory of mind is distributed across a network: the temporoparietal junction, medial prefrontal cortex, the superior temporal sulcus, the amygdala for emotional inference. It is a system with multiple components that can be separately damaged, as autism research so painstakingly revealed. In a language model, the "equivalent" — if that word applies at all — is a whisper concentrated in how the model tracks positional relationships between tokens.

Different architectures. Different failure modes. The same job done in almost incomparably different ways.

---

Underneath dyscalculia, autism spectrum conditions, language disorders, and the whole taxonomy of developmental divergence runs a more fundamental question: what is the actual engine?

Romberg and Saffran (2025) argue in a comprehensive review that the answer is statistical learning — the ability to extract regularities from environmental input using transition probabilities. An 8-month-old discovers that in the stream of syllables washing over them, certain sounds follow other sounds more predictably than others, and from those regularities, they carve out words. The mechanism is domain-general, operating across auditory, visual, and even social input alike — the same probability-tracking engine, pointed at different streams of the world.

Which brings the whole taxonomy back to a single idea. Dyscalculia, autism, dyslexia — these look like separate conditions, separate lesions, separate stories. But if statistical learning is the shared engine underneath, then each of them is, in part, a window onto what happens when that engine meets a particular kind of input and something in the pipeline doesn't hold. Break it at the numerical stage and magnitude never gets built. Break it at the social stage and other minds stay opaque. Same machinery, different point of failure.

And that is the thread running through all of it — the biological cases and the silicon ones both. You rarely see an architecture clearly while it's working. Working systems are seamless; the seams are exactly what competence hides. It's when something breaks — a parietal circuit that won't represent magnitude, a language model whose theory of mind hangs on a handful of positional weights — that the design finally becomes legible. The failure isn't noise obscuring the system. The failure is the readout. Break it precisely enough, and the architecture has no choice but to show.