Announcing our new Paper: The Prompt Report, with Co-authors from OpenAI & Microsoft!
Check it out →Welcome to the advanced section of the guide. Here, you will learn how to prompt LLMs (Large Language Models) programmatically and build components of GenAI agents.
Many of the methods covered in this section address the limitations of out-of-the-box LLMs such as their stagnant state of knowledge and lack of specialization. LLMs often come in a frozen state, unable to quickly update their training with recent data. For example, if you ask an out-of-the-box LLM the results of a recent sports game, it won't be able to provide the correct answer. To overcome this , we will explore prompting techniques that enhance the LLM's context, enabling it to deliver more accurate and up-to-date information.
This module will introduce you to complex prompting techniques, some of which have applications in state-of-the-art GenAI agents1. We will cover the process of building a chatbot like ChatGPT as well as incorporating external knowledge into your prompts. These prompt engineering techniques will elevate your prompting skills and allow you to start building GenAI agents.
By the end of this section, you will be able to utilize expert prompt engineering methods while learning more about LLMs.
Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., Dulepet, P. S., Vidyadhara, S., Ki, D., Agrawal, S., Pham, C., Kroiz, G., Li, F., Tao, H., Srivastava, A., … Resnik, P. (2024). The Prompt Report: A Systematic Survey of Prompting Techniques. https://arxiv.org/abs/2406.06608 ↩
Sign up and get the latest AI news, prompts, and tools.
Join 30,000+ readers from companies like OpenAI, Microsoft, Google, Meta and more!