Prompt Engineering & AI Application deployment¶
This work is licensed under a Creative Commons Attribution 4.0 International License.
Welcome to our documentation on generative Artificial Intelligence (AI) prompt engineering and application integration in academic research and education. Generative AI is transforming the way we work, learn, and teach at the UArizona. To make the most of this revolutionary technology, you'll need to master the art of creating effective "prompts", the messages or requests that guide the ChatGPT's (or Bard's and Bing's) responses.
After the lesson, you should be able to:
* Explain why generative AI matters in education, research, and society
* Create effective prompts in ChatGPT, Bing, Bard, and other GPTs
* Understand how and when to use AI assistants in your daily work
Getting Started with ChatGPT
Getting Started with Bing Chat
ChatGPT is integrated into Microsoft's Edge Browser via Bing Chat.
Getting Started with Bard Chat
Go to our lesson on Daily Productivity with GPTs
Predictive text and auto completion are becoming more common in productivity software. Generative AI powered applications are making their way into everyday software like Word Processors, SMS text messaging, and spreadsheets. LLMs are also being released into productivity software like Microsoft Office 365 w/ CoPilot and Google's Docs and Sheets Workspace.
Go to our lesson on AI in the Classroom
Go to our lesson on Ethics
Research applications of generative AI and LLMs are broad. We obviously won't be able to teach all of them here, but hopefully this is an effective jumping off point:
Go to our lesson on GitHub CoPilot
Go to our lesson on the OpenAI API
Go to our lesson on OpenAI API Powered Extensions
Go to our lesson on HuggingFace Models
Go to our lesson on HuggingFace Datasets
Go to our lesson on Gradio UI
BARD - Google's general purpose LLM
Bi-directional Encoder Representations from Transformers (BERT) - is a family of masked-language models introduced in 2018 by researchers at Google , (Devlin et al. )
ChatGPT - OpenAI's general purpose LLM
CoPilot - GitHub (Microsoft/OpenAI) AI co-programmer, natively integrated as an extension in VS Code or GitHub CodeSpaces
Embeddings - process of transforming high-dimensional data, such as text or images, into low-dimensional vectors. Embeddings allow us to quantify the meaning and relationships of data.
Generative Pretrained Transformer (GPT) - are a family of large language models, which was introduced in 2018 by the American artificial intelligence organization OpenAI . (Radford et al. )
GitHub - the most widely used Version Control infrastructure, owned by Microsoft and natively integrated with OpenAI
DALL·E - OpenAI stable diffusion image generation model
HuggingFace - library for open source AI models and apps
Large Language Models (LLMs) - is a language model consisting of a neural network with many parameters (typically billions of weights or more), trained on large quantities of unlabelled text using self-supervised learning ()
Language Models for Dialog Applications (LaMDA) - Google's general purpose LLM
Latent Diffusion Model (LDM) () - machine learning models designed to learn the underlying structure of a dataset by mapping it to a lower-dimensional latent space.
Large Language Model Meta AI (LLAMA) - Meta's general purpose LLM
MidJourney - popular image generation platform (proprietary), which is accessed via Discord
Neural networks - () () - are similar to their biological counter parts, in the sense they have nodes which are interconnected. Rather than string-like neurons and synapses in biology, artificial networks are made of nodes connected by networks of 'weights' which can have positive or negative values.
OpenAI - private company responsible for the first LLMs and ChatGPT
Parameter - () is a value that the model can independently modify as it is trained. Parameters are derived from the training data upon which the model is trained. The number of parameters in the newest LLMs are typically counted in the billions to the trillions.
Segment-Anything (Meta) - is a recently released image and video segmentation technology that allows you to 'clip' a feature from an image with a single click.
Stable Diffusion - computer vision models for creating images from text
Token - a fundamental unit of text that GPT models use to process and generate language. A token can represent an individual character, a word, or a subword depending on the specific tokenization approach.
Tuning - the process of refining models to become more accurate
Weights - are the value by which a model multiplies another value. Weights are typically determined by the proportional value of the importance of the parameters. Weights signify the value of a specific set of parameters after self-training.
Zero-shot - learning where the AI observes samples from classes which were not observed during training, and needs to predict the class that they belong to.