This repository documents my progress on a prompt engineering course, focused on developing techniques and strategies for working with the latest generation of general-purpose Large Language Models (LLMs).

With the release of ChatGPT, LLMs have become increasingly mainstream, revolutionizing the way we interact with AI systems. Prior to ChatGPT, there were several notable advancements in NLP that have laid the foundation for this revolution, including the "Attention is All You Need" paper by Vaswani et. al., BERT, GPT-2, GPT-3, T5, RoBERTa, ELECTRA, and ALBERT. Although these advancements are highly important, they may not be widely known to the general public. The year 2023 marks a turning point in the mass adoption of these general-purpose models across various industries for generative tasks. As a Data Scientist, continuous learning is a key attribute, and staying on the cutting edge of LLM techniques is essential for providing optimally viable solutions in the era of AI-driven Natural Language Processing.

The primary goal of this course is to gain a deep understanding of prompt engineering techniques for effective interaction with LLMs. By mastering these strategies, I aim to improve my ability to develop innovative, effective, and efficient solutions using the power of natural language.

This repository is organized into the following chapters:

1. 😃 Basics: Introduction to prompt engineering and fundamental techniques
2. 💼 Basic Applications: Simple, practical applications of prompt engineering
3. 🧙‍♂️ Intermediate: Research-based PE techniques with moderate complexity
4. 🧪 Applied Prompting: Comprehensive PE process walkthroughs contributed by community members
5. 🚀 Advanced Applications: Powerful, and more complex applications of prompt engineering
6. ⚖️ Reliability: Enhancing the reliability of large language models (LLMs)
7. 🖼️ Image Prompting: Prompt engineering for text-to-image models, such as DALLE and Stable Diffusion
8. 🔓 Prompt Hacking: Offensive and defensive techniques for prompt hacking
9. 💪 Prompt Tuning: Refining prompts using gradient-based techniques
10. 🎲 Miscellaneous: A collection of additional topics and techniques related to prompt engineering