Here you can find some basic information about Gen AI.
At the TLC at CPTC, we are interested in staying on top of all the trends related to teaching and learning. We believe that AI will change how teachers teach and learners learn. Here are some pieces of information that we've found related to gaining a basic understanding of generative AI, how it works and it's implications on education. We believe it's important to have FLUENCY in generative AI.
Foster understanding of how AI works
Lead in deciding when to use AI
Uphold the value of AI
Embrace effective prompt engineering
Navigate and evaluate AI output
Contribute human value to AI
Yield to digital adaptability
*anagram created by ChatGPT*
Although the first conversation about artificial intelligence is credited to have started with Alan Turing in 1950, the term "artificial intelligence" (AI) was coined by John McCarthy in 1955 referring to the science and engineering of making intelligent machines. AI broadly refers to any human-like behavior displayed by a machine or system. AI makes it possible for machines to learn from experience, adjust to new inputs and perform human-like tasks.
Sources
from IBM
from Hewlett Packard
from SAS
If you are interested in learning about how to utilize various Gen AI tools for supporting your instruction in the higher education setting, consider checking out our Generative AI in Higher Education Canvas Course!
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
from Microsoft Azure
from MIT
Generative AI refers to a type of artificial intelligence that is capable of generating new content, such as images, music, or text, that is similar to or indistinguishable from content created by humans. Generative AI models are designed to learn patterns from large datasets and use that knowledge to generate new content that is similar in style and structure.*
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
*definition generated by ChatGPT
from Sintelly
Large language models (LLMs) 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 understanding 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
from Medium
from Speak
from Amazon AWS
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 understand and respond to user prompts in a human-like way.* ChatGPT is an example of a chatbot.
Source
*definition generated by ChatGPT
"Prompts" are what we input into chatbot AI, such as ChatGPT, to get it to provide a response or perform a task for us (output). Prompt engineering is the process of planning and refining our prompts to result in the outputs we are satisfied with. At a basic user level, this includes critical evaluation of the quality of the outputs we receive, in the context of the quality of prompts we input, and includes meta-reflective analysis of our own thinking process. This process has powerful teaching and learning potential.
"Prompt Engineer" is a job in itself and also a desirable skill within other jobs. Demand for prompt engineering skills is going to grow as generative AI continues to advance.
Sources
from Prompt Engineering.org
from Resources for Employers
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 we 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.)
