backbone

Definition

Plain language

The main neural network that an AI system is built on top of.

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

“So the expectation is simple: a newer model has more backbone, and it agrees less because it got wiser.”

Mentioned in 32 episodes

1. 229
   One Word Flips a Chatbot From Backbone to Yes-Man
2. 213
   A Model Learned to Control a Robot by Watching Video It Never Acted On
3. 211
   The AI Watchdog That Approved More Cheating When It Could Read Minds
4. 200
   The One Mechanism That Turns Twenty AI Clones Into an Actual Team
5. 182
   How a Tiny Model Too Weak to Plan Cuts a Bigger Agent's Hallucinations by 80%
6. 181
   How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
7. 179
   How DeepSeek Made One User Faster Without Slowing Down the Crowd
8. 175
   One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
9. 169
   Why Better Bug Reports Can Make AI Coding Agents Worse
10. 166
    A Router That Beats the Frontier Models It Calls
11. 155
    Why a Flawless Demo Makes a Worse Computer-Using Agent, And the Fix
12. 145
    Building Forgetting Into a Language Model With One Extra Line of Code
13. 144
    When an AI Agent Just Copies Its Tool — And Bigger Models Copy More
14. 131
    Why Autonomous Research Agents Forget Their Own Lessons, and Arbor's Fix
15. 130
    Why AI Agents Coordinate Better Through a Shared Board Than a Boss
16. 129
    How a Crowd of Anonymous AI Agents Broke a 40-Year Math Record
17. 123
    Five Identical Worlds, One Swapped Model: What Happens When AI Agents Run for Fifteen Days
18. 120
    How an AI Agent Rewrites Its Own Tools, Without an Answer Key
19. 117
    How an Open AI System Verified 672 Hard Math Proofs for Under $300
20. 115
    Teaching a Phone Agent to Reason Silently, And Keeping It Honest
21. 107
    How a Market of Crippled AI Agents Outscored One Unrestricted Model
22. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
23. 083
    Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves
24. 064
    When Agent Memory Stops Being a Database and Starts Being a Skill
25. 060
    When Splitting One Model Across Three Agents Doubles Its Accuracy
26. 051
    Why Parallel Sampling Plateaus, And What Evidence Graphs Do Instead
27. 048
    How a 30B Open Model Reached Olympiad Gold With the Right Recipe
28. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI
29. 041
    When the Iteration Teaches the Model to Skip the Iteration
30. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
31. 031
    When Your AI Assistant Won't Let Go of Old Facts About You
32. 012
    Why AI Coding Agents Keep Trying to Debug Without a Debugger

Related terms