> For the complete documentation index, see [llms.txt](https://university.obvious.in/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://university.obvious.in/working-with-features/building-with-ai/understand-the-tech.md).

# Understand the tech

{% hint style="info" %}
**Assumed audience:** You’re a product manager working on an LLM powered feature. You’re familiar with how LLMs work. Use this as a starting point to think about the problems that LLMs are best suited to solve, and to start experimenting with these solutions.
{% endhint %}

## 👋 Introduction

Large Language Models provide a way for computers to understand natural human language and respond meaningfully. This was not possible prior to 2022.

***

## 1️⃣ Understand the tech

> Think of LLMs as small reasoning engines rather than as a magical black box to throw stuff into. The small reasoning engine approach makes it reliable, reduce hallucinations and reduce cost of operation as well.

{% embed url="<https://youtu.be/VXkDaDDJjoA?T=2941>" %}

> Try not to misuse the LLM - like don’t answer someone’s birthday using an LLM just because you can. Using an LLM for it is less reliable and more expensive than querying a database.

{% embed url="<https://www.youtube.com/watch?v=WqYBx2gB6vA>" %}

***

## 2️⃣ Further reading

{% embed url="<https://www.promptingguide.ai/>" fullWidth="false" %}

{% embed url="<https://platform.openai.com/docs/guides/fine-tuning>" %}

{% embed url="<https://maggieappleton.com/squish-structure>" %}

{% embed url="<https://research.ibm.com/blog/retrieval-augmented-generation-RAG>" %}

***