Sign inSign in
ConceptAI & ML

Chain of thought

An emergent or learned search process where an LLM writes out intermediate reasoning steps in text before arriving at a final answer.
as Phillip Isola defines itMITThe wording closest to all 5 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

4

Each in their own terms, from the easiest level.

  • Andrej Karpathy

    Undergraduate

    Chains of thought in a model's head are an emergent property of optimization that represents the step-by-step reasoning process.
    • 24:45State of GPT: Pretraining, SFT, Reward Modeling & RLHF Pipeline
    • 2:32:05Deep Dive into Large Language Models: Pretraining to RLHF
  • Adam Brown

    Perimeter Institute · Undergraduate

    A prompting technique where a large language model is instructed to think step-by-step to arrive at an answer, significantly improving its reasoning performance.
    • 22:40Training Sand to Think: Artificial General Intelligence & Future of Physics
  • Sasha Rush

    Cornell University · Graduate

    A method where the model generates intermediate steps in the process of producing an answer.
    • 9:08Speculations on Test-Time Scaling for Large Language Models (o1)

Lectures that assume it

1

Connections

16

The lectures that define it or assume it, and the concepts next to it.

4 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.