Ask whether large language models “think” and you’ll start a fight. A line of research borrowing from cognitive science — Global Workspace Theory — offers a more useful lens than the usual yes/no shouting match.
What Global Workspace Theory says
In neuroscience, the theory proposes that the brain has many specialized modules working in parallel, and consciousness is like a “stage” where one piece of information is broadcast to all of them at once. It’s a model of how scattered processing becomes unified, flexible behavior.
What researchers are finding in models
Some studies suggest large models develop internal structures that behave a little like this broadcast — certain representations that many parts of the network read from and write to, coordinating the rest. It’s a striking parallel, and a handle for probing how these systems organize information internally.
What it does — and doesn’t — mean
This is not evidence that models are conscious. It’s a hint that useful architectural ideas from brains may show up, in analog form, in trained networks. The value is practical: better mental models of what’s happening inside can lead to better interpretability, control, and safety.
The bigger question
“Do they think?” may be the wrong question. “What kind of information processing is this, and how do we understand and steer it?” is the one that actually moves the field forward.
Comments
Post a Comment