Glossary · Term

backbone

← all terms

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

“… Add the scope caveats — main tables from single runs, and on a stronger backbone the edge thins to under two points on the easiest stream — and the defensible claim is narrower, …”
Episode 200 — The One Mechanism That Turns Twenty AI Clones Into an Actual Team

Mentioned in 29 episodes

  1. 200
    The One Mechanism That Turns Twenty AI Clones Into an Actual Team
  2. 182
    How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
  3. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
  4. 179
    How DeepSeek Made One User Faster Without Slowing Down the Crowd
  5. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
  6. 169
    Why Better Bug Reports Can Make AI Coding Agents Worse
  7. 166
    A Router That Beats the Frontier Models It Calls
  8. 155
    Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
  9. 145
    Building Forgetting Into a Language Model With One Extra Line of Code
  10. 144
    When an AI Agent Just Copies Its Tool — And Bigger Models Copy More
  11. 131
    Why Autonomous Research Agents Forget Their Own Lessons, and Arbor's Fix
  12. 130
    Why AI Agents Coordinate Better Through a Shared Board Than a Boss
  13. 129
    How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
  14. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
  15. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
  16. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
  17. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
  18. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model
  19. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
  20. 083
    Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves
  21. 064
    When Agent Memory Stops Being a Database and Starts Being a Skill
  22. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
  23. 051
    Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
  24. 048
    How a 30B Open Model Reached Olympiad Gold With the Right Recipe
  25. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
  26. 041
    When the Iteration Teaches the Model to Skip the Iteration
  27. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
  28. 031
    When Your AI Assistant Won't Let Go of Old Facts About You
  29. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger

Related terms

adapter agent attention head base model fine-tuning pretraining