A Presentation for Central Florida TESOL

Welcome to your outsourced memory for today’s session. Not sure what outsourced memory is? No worries, you simply haven’t learned about outsourced memory and transactive thinking YET! But we will get to that shortly. Please feel free to follow along here as we go through today. This blog post contains everything I will be sharing with you today and more. Please feel free to share this resource with others, and if you have questions, or would like to share something with me, feel free to email me.

What about AI Detection? 

What are LLMs? Why Should I Care?

What do you mean by AI is language agnostic?

How Does All of This Affect My Classroom?

Let’s Chat

Some AI teaching Ideas

1. Using AI to Differentiated Learning
2. Using AI to develop scenario based learning
3. Using AI to develop “lesson specific” chatbots to get interactive feedback
4. Using AI to create annotation assignments for active reading.
5. Chapter summaries or “The Least You Should Know”
6. Using AI to develop pre-mails and outreach emails
7. Creating bottomless quiz and survey pools (Retrieval Practice/Enhanced Test Security)
8. Using AI to develop enhanced prompts & instructions (Retrieval Practice/Content building)
9. Using AI to develop enhanced discussion topics and threads (Course Analysis, review, re-design)
10. Using AI to develop/enhance rubrics in Canvas (student feedback)
11. Analyze quiz questions and develop explanations and follow up instruction responses (Enhanced Student Feedback)
12. Creating AI Chatbots or AI Prompts to help students analyze and get additional feedback from written assignments (Personalized Feedback)
13. Have AI design Text Expanded Feedback in Canvas (Practical Applications for Fast Feedback)

Picking a Team, Which AI Should I Learn?

ChatGPT: ChatGPT is an advanced language model by OpenAI, based on GPT-3.5. It excels in natural language understanding and generation. Trained on vast internet text data until September 2021, it’s proficient in answering questions, providing explanations, and assisting with diverse tasks. It’s a valuable tool for various applications, including virtual assistants and content generation.

Bard: Bard is a large language model developed by Google, also known as a conversational AI or chatbot trained to be informative and comprehensive. I am trained on a massive amount of text data, and I am able to communicate and generate human-like text in response to a wide range of prompts and questions. For example, I can provide summaries of factual topics or create stories.

Claude: Claude is an artificial intelligence created by Anthropic to be helpful, harmless, and honest. I’m designed to have natural conversations and provide useful information to users.

Prompting 101

1. Soft Prompting: Soft prompting involves giving AI a prompt that is open-ended and flexible, allowing room for creativity and varied responses. This method encourages AI to generate content that may not be bound by rigid constraints, enabling it to explore different ideas or perspectives within the given topic or theme.
2. Hard Prompting: Hard prompting entails providing AI with specific and tightly defined prompts that come with strict constraints and requirements. For instance, you could instruct AI to write a 10-line poem about a forest using vivid imagery and metaphors in the style of a particular poet. Hard prompts are ideal when you have a clear vision of the content you want AI to produce within specific parameters.
3. Chaining: Chaining involves the process of breaking down a complex request into a series of logical and sequential steps or instructions. This method is particularly useful when you want to guide AI through a multi-step task, ensuring that it follows a coherent chain of actions to achieve the desired outcome. For example, you might start by asking for examples of thesis statements, then proceed to inquire about supporting ideas, counterarguments, and so on, building a logical chain of inquiry.
4. Formatting: Formatting refers to the act of instructing AI to present information or responses in a specific structure or style that suits your needs. This method enables you to receive AI-generated content in a format that is easy to read, understand, and utilize. You can request formats such as bullet points, CSV files, or even styled text with HTML elements like bold and italics, depending on your requirements.
5. Framing: Framing involves setting the context and expectations for the kind of response you want from AI. It provides the AI with a framework within which it should generate its output. For instance, if you ask AI to “write a poem that conveys a sense of wonder about nature,” you are framing the request with the context of a poetic response centered around the theme of nature and wonder.
6. Priming: Priming is the act of providing relevant details, context, or background information to guide AI in generating a response. By priming AI with essential information, you help it produce more contextually accurate and relevant content. For example, you might specify that a poem should describe a forest and provide details about the trees, animals, and sensory experiences to create a vivid and immersive description.
7. Tuning: Tuning is the process of providing feedback to AI and iteratively refining its responses to meet your specific criteria or preferences. You can fine-tune AI-generated content by providing feedback on aspects like clarity, coherence, or style. This iterative feedback loop helps improve the quality of AI-generated responses over time.
8. Styling: Styling involves instructing AI to adopt a particular tone, writing style, or manner of expression in its responses. For example, you can request AI to respond in the philosophical style of a specific philosopher or in a tone that is optimistic and encouraging. Styling instructions influence the voice and character of AI-generated content.

AI Prompts for Teaching: A Spellbook

This guide demonstrates how carefully crafted prompts allow you to harness AI as a teaching and learning partner. You’ll find prompts to enhance course design, improve your own skills, provide student support, adapt content, and boost relevance and comprehension. With thoughtful prompt engineering, AI can save you time while also improving pedagogy and student outcomes.

Are there any other AI’s I should know about?

Firefly  Free Text to image AI

Glasp Youtube Summarizer  Pluggin that will connect Youtube to ChatGPT or Claude

D-ID Image to video AI

Descript Voice Cloning and Much More

Khanmigo Khan Academy’s AI Pilot

📋 Expand for Video Highlights:

• 00:00Links to an external site. AI can revolutionize education by providing every student with a personal tutor and every teacher with a teaching assistant.
• 01:59Links to an external site. Khan Academy’s AI tutor, Khanmigo, can detect and correct student mistakes, identify misconceptions, and prompt students to explain their reasoning.
• 03:19Links to an external site. Understanding context is crucial in computer programming exercises, even for non-computing backgrounds, and a platform can help with video comprehension, quizzes, and idea connections.
• 05:01Links to an external site. Khanmigo offers comprehensive coaching services for students, as shown by the launch of GPT-4 and the success of Khan World School.
• 07:10Links to an external site. Students can debate with AI on canceling student debt and use AI writing tools to collaborate on writing, while Khanmigo’s prototype uses generative AI to enhance reading comprehension.
• 09:30Links to an external site. AI technology and Khan Academy’s teacher mode help improve student writing skills and save time for teachers.
• 11:23Links to an external site. AI-powered education can be revolutionized with large language models like GPT-4, which can improve math and tutoring by allowing AI to think before speaking.
• 13:37Links to an external site. AI debate split between pessimistic and optimistic views, but active participation needed to ensure positive use cases and prevent dystopian future.

Copilot   Microsofts AI Tool – Not Yet Available to All, But It Is Coming!

Arthur C. Clarke

Clarke’s first law

When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong.

Clarke’s second law

The only way of discovering the limits of the possible is to venture a little way past them into the impossible.

Clarke’s third law

Any sufficiently advanced technology is indistinguishable from magic.