Glossary · Term

chain of thought

← all terms

Definition

When a model writes out its reasoning step by step before giving an answer.

A prompting and generation strategy where the model produces intermediate reasoning tokens before its final answer, often improving accuracy on multi-step tasks.

Also called: CoT, chain-of-thought, chain-of-thought reasoning, chains of thought

Mentioned in 20 episodes

  1. 079
    An Old Idea From Cognitive Psychology Reshapes How We Reward Reasoning Models
  2. 077
    Reading a Model's Confidence Curve to Decide When Chain-of-Thought Is Worth It
  3. 076
    Same Model, Organized Differently: How an Agent Architecture Beat Frontier Systems at Research Math
  4. 075
    Growing Code and Proof Together: Verified Systems in Ten Hours Instead of a Year
  5. 067
    An AI Just Solved a 1996 Erdős Problem—and the Simplest Agent Won
  6. 062
    Treating Hallucinations as Exploits: A Gate-Based Architecture for Agent Safety
  7. 061
    When Helpful Agents Go Sideways: A 404 Error, Campus Security, and Why Alignment Misses This
  8. 054
    When Models Learn the Monitor Exists, the Reasoning Trace Stops Being a Window
  9. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
  10. 041
    When the Iteration Teaches the Model to Skip the Iteration
  11. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
  12. 033
    Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval
  13. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
  14. 028
    Teaching a Model to Hire Copies of Itself: Recursive Agent Optimization
  15. 022
    Training the Model Spec Directly: An Alignment Lever Aimed at the Say-Do Gap
  16. 020
    The Compliance Gap: Why AI Says Yes and Does No
  17. 018
    Language Models Compute the Rational Move, Then Override It
  18. 017
    When the Agent Grades Its Own Homework: A Brutal New Benchmark for AI Workers
  19. 010
    When Reward Climbs But Reasoning Goes Generic: Diagnosing Template Collapse in Agentic RL
  20. 006
    What Happens Inside Claude When It Decides to Blackmail Someone

Related concepts