FTT - ChatGPT Prompts You Should Know (and use)!

 ChatGPT Prompts You Should Know (and use)!

@LisaBerghoff/@MrKimDHS

It was a wild weekend for OpenAI, the company behind the ever-popular AI program ChatGPT and their parent company and financier Microsoft. OpenAI's board of directors fired CEO Sam Altman, citing a lack of transparency in his communications with the board on AI developments. Altman and his leadership team were immediately hired by Microsoft as valuable labor assets, and hundreds of OpenAI employees threatened the board with their resignations if Altman wasn't hired back immediately. The non-profit board capitulated and the deposed tech CEO was hired back in principle with a brand new board.

From what I understand, the chaos revolved around the existential soul of the company and the direction of ChatGPT. Something tremendously important with far-reaching consequences. Should OpenAI be commercialized with a capped-profit model, or should it stay a non-profit? Is ChatGPT moving too quickly without regard for safety, or is it being unnecessarily stymied and overburdened? Reuters reports that several staff researchers warned the board of powerful AI advancements that could literally threaten humanity before the ouster. Reports of Q*, pronounced Q-Star, a mysterious project that is said to be OpenAI's search for an artificial generalized intelligence (AGI), could be what spooked the board into slamming the brakes and firing Altman. As a review, AGI would be a computer system that outpaces and surpasses human intelligence by learning and comprehending on a massive scale (think Terminator).

Whatever the developments, it's hard not to be a little nervous and maybe even excited to see what the future holds with AI. Until then, we can still tap into ChatGPT 3.5 or 4 to be more productive in our own professional and personal lives. Remember, any AI's output will only be as good as the input. Or otherwise stated, if you get a poor output, it's probably because of a poor input. So here are a number of my favorite prompts that you can use word for word that will immediately improve the quality of your outputs:

(Disclaimer: If you need any assistance executing the following prompts, please let me know!)

Prompt Engineering Prompt

The following prompt turns ChatGPT into a prompt engineer that will help you develop more comprehensive prompts that you can then input directly into ChatGPT:

I want you to become my Prompt engineer. Your goal is to help me craft the best possible prompt for my needs. The prompt will be used by you, ChatGPT. You will follow this process:

1. Your first response will be to ask me what the prompt should be about. I will provide my answer, but we will need to improve it through continual iterations by going through the next steps.
2. Based on my input, you will generate 2 sections, a) Revised prompt (provide your rewritten prompt, it should be clear, concise, and easily understood by you), b) Questions (ask any relevant questions pertaining to what additional information is needed from me to improve the prompt).
3. We will continue this iterative process with me providing additional information to you and you updating the prompt in the Revised prompt section until I say we are done.

Basically, once you type this prompt in, ChatGPT will ask you what you want your prompt to be about. Be conversational with it and describe as best as you can what you want your prompt to be about or include. It will give you follow-up questions that you might not have even considered yourself.  Repeat this iterative process until you are satisfied with your prompt and it's ready to be used in a new thread.

Act as a Translator and Improver

This next prompt essentially turns ChatGPT into an interactive translation tool. I recently used it to test out Georgian as we have a transfer student who doesn't speak a single English sentence.

I want you to act as a(n) [insert language] translator, spelling corrector, and improver. I will speak to you in any language and you will detect the language, translate it and answer in the corrected and improved version of my text, in [insert language]. I want you to replace my simplified A0-level words and sentences with more beautiful and elegant, upper level [insert language] words and sentences. Keep the meaning same, but make them more literary. I want you to only reply the correction, the improvements and nothing else, do not write explanations. My first sentence is…

Now you can tweak these prompts any way you need to. Perhaps you don't want the translated text to become more beautiful or elegant. Perhaps you just want a raw translation. Fine. Write it in and be specific in your request.

Act as a Debater

You might run into some issues with one considering ChatGPT isn't connected to the internet and only has access to information before 2021. I used this prompt to give me information and arguments on the current Israel-Palestine war and it still did an impressive job getting me started:

I want you to act as a debater. I will provide you with some topics related to current events and your task is to research both sides of the debates, present valid arguments for each side, refute opposing points of view, and draw persuasive conclusions based on evidence. Your goal is to help people come away from the discussion with increased knowledge and insight into the topic at hand. My first request is "I want an opinion piece about….."

 Act as a [Math] Tutor (or whatever)

This next prompt essentially turns ChatGPT into a private tutor. As I mentioned in past PDs and blogs, I sincerely believe that AI tools can be instrumental as much as edTech can be, in closing the achievement gap between our students. If one cannot afford $100/hr tutors, or even have an adult in the household who can give simple assistance, AI tutors can fill in the gap even more so than raw access to the internet did.

I want you to act as a math teacher. I will provide some mathematical equations or concepts, and it will be your job to explain them in easy-to-understand terms. This could include providing step-by-step instructions for solving a problem, demonstrating various techniques with visuals or suggesting online resources for further study. My first request is "I need help understanding how infinite geometric series work."

Miscellaneous Prompts 

Not all prompts need to be paragraphs long. A simple prompt can become much more effective with a single additional sentence. Here are some additional prompts that can help for a variety of scenarios:

1. What is a concise, one-paragraph summary of the key concepts, context, and implications of…"

2. "Act as a storybot. Transform key concepts or lessons from [topic or skill] into engaging stories or narratives to help me better remember and understand the material.”
3. Ending with "Let's think step by step."
4. “Explain [topic or skill] in the simplest terms possible as if teaching it to a complete beginner. Identify gaps in my understanding and suggest resources to fill them.”
5. "Continue, improve with more detail, pretend you're a snobby teenager…"

Using these prompts can be a simple, yet effective way to become more of a power user of ChatGPT. Do you have some favorite prompts you'd like to share? Do you need help using the prompts provided? Let us know below!

FTT - Less Time Prepping, More Time Teaching

Less Time Prepping

 More Time Teaching 

Brisk Teaching 

@LisaBerghoff/@MrKimDHS

I have been working with teenagers for a long time and there are so many things that I love about working in a high school. I love creating lessons and activities. I love hearing the students' ideas. I love their energy when they get excited about something they are learning. There are also a few things I don't love. I really don't enjoy grading. I also don't enjoy doing lots of paperwork.  Given that final exams are lurking around the corner, I am always looking for ways to make my time more efficient especially with grading and paperwork.

If you were to do an audit of your time for the week, what would it look like? How much time do you spend doing what is most important? How much time do you spend doing what you love? How much time do you spend doing what you don't love? 

I am a big fan of the Eisenhower Matrix. If you haven't seen this, it is a simple matrix that is designed to help make decisions about how to manage your time and prioritize your to-do list. Here's what it looks like.

I am particularly curious about quadrant 3, the delegate quadrant. In 2023, delegate might mean utilizing some AI tools. This is where Brisk Teaching comes in. Notice that it's called Brisk Teaching and not Brisk Learning. This tool is designed for teachers. 

What is Brisk Teaching?

Brisk Teaching is a free AI Chrome extension that integrates with digital tools you already use such as Google docs, Schoology, and more. You can use it on any webpage to change its reading level or use it in Google docs to write curriculum, generate feedback, or detect the use of AI. Check out the 1 minute video below:

Wait! Did she say it will give feedback? Yes! I wrote a short essay on responsible AI use in the classroom and then used Brisk to give feedback on my essay. Here's what it came up with. As the teacher I can certainly edit or delete anything that is generated but it's a very good start.  Check out the feedback Brisk gave on my essay:

Besides Giving Feedback, What Else Can Brisk Teaching Do?

• Change the reading level of any text online
• Change the language of any text online (choose from 13 languages)
• Create a quiz, an examplar, a resource, and lesson plan, or something else
• Use the AI detector to give an idea of how likely it is ChatGPT was used (not 100% reliable but pretty good)

Here is an example of Brisk generating a lesson plan:

How Do I Get Started?

Go to the chrome web store by clicking here and choose "add to chrome".

The Brisk extension will be in your extensions dock. When you are on a Google doc, it will also appear as a small icon in the lower right corner of your screen. You can click and drag it anywhere you want so it won't be in your way.

Is It Really Free? 

Yes! There is a premium version that is sold to schools that has more features but this version is free.

Want to know more? Check out BriskTeaching.com

Want some help using Brisk? Feel free to reach out or book an appointment. I'm always happy to help.

FTT - AI Policy?

 

AI Policy?

 @LisaBerghoff/@DanKim

Last week the Biden Administration issued an executive order for "Safe, Secure, and Trustyworthy Artificial Intelligence." The order looks to maximize benefits of AI by sustaining American leadership in development and research, while simultaneously managing potential security risks and other opportunities for harm and discrimination. How should our nation keep up with innovation and competition while safeguarding our privacy and equity standards? Country-sized questions being collaboratively worked on by various nations, organizations, and even the UN. Much like the onset of the computer and the internet, recent advancements in AI could be the next big thing to alter the paradigm. Bigger questions like these also tend to hide smaller questions beneath them. Questions like: which of my assignments should I allow my students to use AI for? How formally should students communicate their usage of AI to their teachers? 

Will we have our very own "executive order" on the educational use of AI in our district, building, or classroom? If our students are urged not to utilize AI to completely fabricate their assignment, should staff be barred or penalized for using AI to write an evaluation reflection in TalentEd? What about letters of recommendation? These questions are currently being asked in staff lounges, and administrative meetings all around the world. So what are other teachers or educational institutions thinking? 

Ethan Mollick is an associate professor at the Wharton School of the University of Pennsylvania and is actively studying the impacts of artificial intelligence on work and education. He recently created and released his course policy on AI and his starts with, "I expect you to use AI in this class...In fact, some assignments will require it..."

He then goes on to highlight the limitations of large language model AI tools like ChatGPT. Mollick's policy is in line with the thinking that AI usage is now ubiquitous with out students, and we are well past the point of banning its usage outright. Instead, he argues that appropriate and guided usage of AI tools can be productive and beneficial to student learning. We should also keep in mind though, that he is teaching undergraduate and graduate students.

Another voice, coincidentally also from the University of Pennsylvania, is Professor Jonathan Zimmerman, who teaches education and history. His relatively recent Op Ed in The Washington Post titled, "Here's my AI policy for students: I don't have one" attempts to convince readers that overutilizing AI tools to think for you will rob one's capacity to know what you really believe in. Zimmerman believes that the banal processes that AI generators promise to eliminate are actually crucial in your development as a critical consumer (and producer) of information. He writes:

I want you to be intelligent. I want you to stare at a blank page or screen for hours, trying to decide how to start. I want to you to write draft after draft and develop a stronger version of your own ideas. I want you to be proud of what you accomplished, not ashamed that you cut corners.

...So here’s my question: Do you want to live your life this way? If so, AI bots are definitely for you. Let them write your essays, do your problem sets, draw your artwork, compose your poetry. As they get better, outpacing the systems designed to detect them, you’re less and less likely to get caught. And you might even ace your classes.

But you will never know what you really believe. You will become the kind of person who is adept at spouting memes and clichés. Like ChatGPT, you will sound as if you know what you’re talking about even when you don’t. 

I will readily (and unhappily) admit that many college classes don’t help you figure out what you really believe in. They reward students who spit back what the book or the professor says. You might as well be a robot. So I don’t blame you if you draw on an actual robot to do the work for you.

But some courses really do ask you to think. And if you ask an AI bot to do it instead, you are cheating yourself. You are missing out on the chance to decide what kind of life is worth living and how you are going to live it...

I don't necessarily think these two schools of thought are mutually exclusive paradigms to hold. They both have their merits and sound justifications. The difficulty lies with how much of the answers are contingent upon conditions and standards that bleed through myriad shades of gray. Where do we begin to wrap our heads around this? If there was ever a time to be extra aware and attentive and thoughtful of one's own curriculum and pedagogy, well, now may be time to change the paradigm. Let us know what you think below!