Factored Cognition Primer

How to write compositional language model programs

You’ll learn how to:

• Amplify language models like GPT-3 through recursive question-answering and debate

• Reason about long texts by combining search and generation

• Run decompositions quickly by parallelizing language model calls

• Build human-in-the-loop agents

• Use verification of answers and reasoning steps to improve responses

• And more!

Example of a decomposition for reasoning about papers.

The book focuses on techniques that are likely to remain relevant for better language models.

How to cite this book

Please cite this book as:

A. Stuhlmüller and J. Reppert and L. Stebbing (2022). Factored Cognition Primer. Retrieved December 6, 2022 from https://primer.ought.org.

BibTeX:

@misc{primer2022,
  author = {Stuhlmüller, Andreas and Reppert, Justin and Stebbing, Luke},
  title = {Factored Cognition Primer},
  year = {2022},
  howpublished = {\url{https://primer.ought.org}},
  urldate = {2022-12-06}
}