Generative AI - a student's guide: Start here

Machine learning is a subfield of artificial intelligence that gives computers the ability to learn without explicitly being programmed. Machine learning is behind chatbots and predictive text, language translation apps, the media your streaming services suggest to you, and how your social media feeds are presented. 

Source

Generative AI is a subset of artificial intelligence that predicts the sequence of words, images, or sounds to generate coherent and contextually relevant content based on its training data and user prompts.

ChatGPT is just one example of generative AI, and is one of four broad-category types of AI known as "limited memory" AI. Limited memory AI is distinct from "reactive" AI, which is unable to build memory or store information for future, it can only respond to the current input.

Sources

Large language models (LLMs) are a type of generative AI. They use deep learning algorithms to process large amounts of text. They are designed to understand the structure of natural language and to pick out meanings and relationships between words. These models are capable of processing context, identifying and extracting information from text, and making predictions about a text’s content. They are trained on extremely large datasets. Chatbots, like ChatGPT, version GPT-3.5, was trained on a 45 terabyte dataset which is equivalent to over 292 million pages of documents, or 499 billion words.

Sources

A chatbot is a computer program designed to simulate conversation with human users, often through text-based interfaces like messaging apps, websites, or voice assistants. Chatbots are typically powered by artificial intelligence (AI) and natural language processing (NLP) technologies, allowing them to process and respond to user prompts in a human-like way.* ChatGPT is an example of a chatbot.

Source

"Prompts" are the user inputs into a chatbot AI, such as ChatGPT. Prompts are used to guide the chatbot to generate a response or perform a task for us (output). Prompt engineering is the process of planning and refining our prompts so that chatbot outputs meet our needs. At a basic user level, this includes critical evaluation of the quality of the outputs we receive, relative to the quality of our prompts and our needs. This process includes meta-cognitive analysis of our own thinking and reasoning. The process of prompt engineering has powerful meta-cognitive and critical thinking potential in teaching and learning.

"Prompt Engineer" is a job in itself and also a desirable skill within other careers. Demand for prompt engineering skills is going to grow as generative AI continues to advance.

A prompt engineer* has this advice for chatbot end-users in developing their prompts for relevant and useful outputs:

• be as specific and clear as you can
• do not assume the AI knows anything, because it doesn’t
• the AI doesn’t think, it reacts
• do not depend on keywords because the AI evaluates based upon context (meaning, ideas), not keywords
• if you don’t get an answer the first time around, try re-phrasing, re-wording or even re-thinking your question

Sources

GPT are the abbreviated initials for "generative pre-trained transformer"

ChatGPT user prompt:: please explain generative pretrained transformer to someone who is not an AI expert

ChatGPT output:

"A Generative Pretrained Transformer (GPT) is a type of artificial intelligence that has been trained to generate text that looks like it was written by a human. The 'pretrained' part means that it has already learned a lot about how language works, so it can understand things like grammar and sentence structure.

The 'transformer' part refers to the way it processes language. It breaks down text into smaller parts, called "tokens," and then looks at how those tokens are related to each other to understand the meaning of the text.

The 'generative' part means that it can use that understanding to create new text on its own. So if you give it a prompt like 'write a story about a magical castle,' it can come up with a whole story all by itself, using the knowledge it has learned about language.

It's like having a really advanced robot assistant that can help you write things, but instead of just following your commands, it can actually come up with its own ideas and write them down for you."

------------------

One of the reasons that I chose to let ChatGPT describe GPT is that I can control the level of complexity through the criteria of my prompt. On many sites that include information about what GPT is and a bit about how it works ("a bit" because for ChatGPT this is proprietary information in the details), the level of complexity is too steep for many people, like me, who do not already have a background in in AI. I could also ask the chatbot to describe it to a 12 year old or a 5 year old, or more nuanced, such as "for a college freshman just starting their AI degree"!

The other reason is to demonstrate the value of AI as a study aid. This can empower students to generate information about a complex concept on their own terms, as a way to scaffold their own learning and understanding. (Note, sometimes outputs are factually wrong, but for well-established concepts, such as GPT, outputs are more likely to be consistently factually reliable as long as the user knows enough about the concept to compose a valid prompt.)