> For the complete documentation index, see [llms.txt](https://primer.ought.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://primer.ought.org/readme.md).

# 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!

<figure><img src="/files/vXKQpTvTpArByGlgssdp" alt=""><figcaption><p>Example of a decomposition for <a href="/pages/UbJoCilnGLDiAXOVvq10">reasoning about papers</a>.</p></figcaption></figure>

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

<details>

<summary>How to cite this book</summary>

Please cite this book as:

{% code overflow="wrap" %}

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

{% endcode %}

BibTeX:

```latex
@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}
}
```

</details>