Definition
Plain language
The main neural network that an AI system is built on top of.
As stated in the literature
The pretrained base model that an agentic or fine-tuned system is built on, often distinguished from auxiliary modules, adapters, or refinement heads.
Why it matters: Almost every modern AI system is layered on top of a pretrained backbone, and the choice of backbone usually dominates downstream behavior.
For example, a robotics policy might use Llama as its backbone and add a small vision adapter on top for image inputs.
Heard on the show
“But it does mean the "state-of-the-art" claim partially rests on backbone choice.”Episode 012 — Why AI Coding Agents Keep Trying to Debug Without a Debugger