description: How to write compositional language model programs cover: https://oughtinc.github.io/static/images/primer-cover.jpeg coverY: 0

Factored Cognition Primer

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!

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

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

@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}
}