Why broca? On Aphasia, LLMs, and Finding Language

Broca’s area. It’s a region in the frontal lobe — responsible for language production, for turning thought into speech. Damage it, and you get Broca’s aphasia: you know exactly what you want to say, but the words won’t come. The thoughts are intact. The language is not.

I first learned about Broca’s area in medical school. It was one of those facts you memorize for an exam and then file away — a curiosity of neuroanatomy, a named structure among thousands. I never imagined it would become the name of my blog, or that it would describe, with unsettling precision, a frustration I’d carry for years.

The programmer’s aphasia

For years, I felt a version of Broca’s aphasia. Not the clinical kind — my speech was fine. But when it came to building things with code, I was stuck. I knew what I wanted to build. I could see it clearly: the shape of it, how it should work, why it mattered. I could describe it in plain language — in the same words I used to think about it. But translating those thoughts into code required a fluency I didn’t have.

The frameworks, the tooling, the sheer volume of syntax between idea and execution — they formed a barrier. I’d spend hours on something that should have taken minutes. I’d abandon ideas not because they were bad but because the distance between what I meant and what I could make was too far to cross.

This wasn’t a lack of ideas. It was a lack of language. A programmer’s aphasia.

I suspect I’m not alone in this. How many people have ideas for software, for tools, for websites, for automations — clear, useful, fully-formed ideas — and never build them because they can’t speak the language? How much potential sits dormant not for lack of imagination but for lack of syntax?

The bridge arrives

Then large language models arrived. Not gradually — suddenly. One day I was staring at blank editor panes, and the next I was describing what I wanted in plain English and watching it materialize.

The first time it worked, I felt something I can only describe as relief. I described a component — a button group with a specific behavior — in words. The LLM produced the code. It wasn’t perfect, but it was real. I could read it, understand it, modify it. The barrier wasn’t gone, but it had moved. It was no longer between thought and code. It was between code and refinement — a much smaller gap.

This is what I mean when I say LLMs feel like Broca’s area for humanity. Broca’s area is the neural machinery that turns thought into speech — that bridges the gap between private meaning and public expression. LLMs do something analogous at the species level. They turn natural language — the language we think in — into the formal languages we’ve built our digital world on.

Not a replacement for thinking

I should be clear about what I’m not saying. I’m not saying LLMs replace thinking. Broca’s area doesn’t think for you — it doesn’t decide what to say, doesn’t weigh the ethics of saying it, doesn’t know whether the thought is true or kind or worth expressing. It just provides the language.

LLMs are the same. They don’t have the ideas. They don’t know what’s worth building or why. They can’t replace the clinical judgment that comes from years at the bedside, or the philosophical instinct that tells you which question is the right one to ask. What they can do is bridge the gap — turn the thought you already have into the form it needs to take.

That bridging function is not trivial. Language is not trivial. The difference between having an idea and being able to express it is the difference between having a map in your head and being able to give someone directions. One helps only you. The other changes what other people can reach.

Why this name matters

I named this site broca.id because the name carries both meanings I care about. It’s a medical reference — a nod to neuroanatomy, to the clinical training that shaped how I think. And it’s a metaphor for what makes this moment in technology different from the ones before it.

The printing press made ideas reproducible. The internet made them distributable. LLMs make them expressible — they lower the cost of turning a thought into something that exists outside your head.

That’s what this site is. Ideas, given language. A blog that exists because the gap between what I meant and what I could make finally closed.

If you’ve ever had an idea you couldn’t express — in code, in words, in any medium — you understand why this matters. Welcome.