loss

Definition

A number that measures how wrong a model's outputs are, which training tries to make smaller.

A scalar objective function quantifying the discrepancy between model predictions and targets; gradients of the loss drive parameter updates.

Mentioned in 14 episodes

1. 077
   Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
2. 074
   How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
3. 070
   When Models Know the Answer But Say the Wrong Thing Anyway
4. 060
   When Splitting One Model Across Three Agents Doubles Its Accuracy
5. 053
   An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
6. 043
   When 'This Is False' Doesn't Stick: Why Models Learn the Lie Anyway
7. 041
   When the Iteration Teaches the Model to Skip the Iteration
8. 040
   Two Frozen Models Learn to Whisper: Coupling Through Hidden States
9. 038
   How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
10. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
11. 026
    What RL Actually Does to Language Models, at the Token Level
12. 025
    The Missing Gradient Term That Predicts Sycophancy in RLHF
13. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
14. 001
    When AI Models Quietly Protect Each Other From Shutdown

Related concepts