Categories
AI AI: Large Language Models ChatGPT Prompt Engineering

Using ChatGPT to hold a debate…and learn

Robert Scoble tweeted yesterday about a series of ChatGPT prompts that he’s found very useful:

This is my favorite prompt. Do you have better for learning?

Multi step prompt.

1. Ask it to tell you all points of view on something or someone or anything. Photography, for instance.

2. Ask it to create a persona for each point.

3. Tell it to gather the persona’s all together into a group. Could be a debate club, a panel, a board of directors, or whatever you want.

4. Ask the group to debate the topic. Or anything but you will have a specific group around a committee.

A contextual committee. I am building many for different purposes.

A group focused around BBQ can answer food questions with that bias. … A committee for every context. Or problem. Or to teach you. Coach you. Assist you.

Contextual committees. Infinite fun.

I was intrigued – adding his suggestions for prompts to my growing collection of prompts. Here’s what I tried first:

Tell me all the points of view on the topic of beach reads.

The concept of “beach reads” refers to books that are typically read for pleasure during the summer or on vacation, often in a relaxing setting like the beach. There are various points of view on this topic, including:

  • Proponents of beach reads argue that they provide an enjoyable and lighthearted reading experience that is perfect for vacations or other leisure time. They believe that reading should be a pleasurable activity, and that beach reads offer a fun and engaging way to pass the time.
  • Critics of beach reads argue that they are often formulaic, poorly written, and lack substance. They believe that reading should be an intellectually stimulating activity, and that beach reads offer little in the way of challenging ideas or insights.
  • Some people believe that the concept of beach reads is outdated and that people should be free to read whatever they want, regardless of the season or location. They argue that the idea of categorizing books as “beach reads” is limiting and can prevent readers from exploring new genres or authors.
  • Others believe that the term “beach reads” is sexist and reinforces gender stereotypes, suggesting that women only read light and fluffy books while men prefer more serious and intellectual fare. They argue that this is a harmful and inaccurate portrayal of both genders and that readers should be encouraged to read whatever interests them, regardless of gender or perceived genre.
  • Finally, some people argue that the concept of beach reads is simply a marketing ploy, designed to sell more books during the summer months. They believe that the publishing industry has created the idea of beach reads to promote certain types of books and authors, rather than letting readers decide for themselves what they want to read.

Create a persona for each point of view.

Sure, here are five personas representing each of the five points of view on beach reads, debating the topic and coming to a joint recommendation:

  • Proponent of beach reads: Sarah is a young professional who loves to read for pleasure, especially when she goes on vacation. She believes that beach reads are a great way to relax and escape from the stress of everyday life. Sarah argues that reading should be a pleasurable activity, and that beach reads offer a fun and engaging way to pass the time.
  • Critic of beach reads: David is a literature professor who believes that reading should be an intellectually stimulating activity. He is skeptical of the concept of beach reads, arguing that they are often formulaic, poorly written, and lack substance. He believes that readers should be challenged by the books they read, rather than simply entertained.
  • Advocate of reading freedom: Maria is a librarian who believes that people should be free to read whatever they want, regardless of the season or location. She thinks that the idea of categorizing books as “beach reads” is limiting and can prevent readers from exploring new genres or authors. Maria believes that readers should be encouraged to read widely and follow their own interests.
  • Critic of gender stereotypes: Alex is a gender studies professor who believes that the term “beach reads” is sexist and reinforces harmful gender stereotypes. She argues that this idea suggests that women only read light and fluffy books while men prefer more serious and intellectual fare. Alex believes that readers should be encouraged to read whatever interests them, regardless of their gender or perceived genre.
  • Critic of marketing ploys: Chris is a publishing industry insider who believes that the concept of beach reads is simply a marketing ploy. He argues that the publishing industry has created the idea of beach reads to promote certain types of books and authors, rather than letting readers decide for themselves what they want to read.

Have them debate beach reads and come to a joint recommendation for readers

Sarah: I love beach reads! They’re a great way to relax and escape from the stress of everyday life.

David: I don’t agree. Beach reads are often poorly written and lack substance. Reading should be an intellectually stimulating activity.

Maria: I think people should be free to read whatever they want, regardless of the season or location. The idea of categorizing books as “beach reads” is limiting.

Alex: I agree that the term “beach reads” is sexist and reinforces gender stereotypes. It suggests that women only read light and fluffy books while men prefer more serious and intellectual fare.

Chris: I think the concept of beach reads is simply a marketing ploy. The publishing industry has created the idea to promote certain types of books and authors.

Sarah: I understand that some beach reads may not be the most intellectually challenging, but they offer a fun and engaging way to pass the time. And as Maria said, people should be free to read whatever they want.

David: I agree that people should be free to read what they want, but I still believe that reading should be a challenging activity. However, there are some beach reads that can be intellectually stimulating.

Maria: Yes, readers should be encouraged to read widely and explore new genres and authors. But if someone wants to read a beach read, that’s fine too. Let’s recommend that readers choose books that they enjoy, whether they are beach reads or not.

Alex: I agree. Instead of limiting readers based on gender or perceived genre, let’s encourage them to read whatever interests them.

Chris: Sounds good to me. Let’s recommend that readers choose books based on their interests, rather than what’s marketed as a “beach read” or any other category. The most important thing is that people enjoy what they’re reading.

Sarah: Yes, it’s all about enjoying what you’re reading. For me, beach reads offer a chance to relax and escape into a fun story. And there are some beach reads that are well-written and have substance.

David: I agree that enjoyment is important, but I still think that readers should be challenged by what they’re reading. Perhaps we can recommend some beach reads that offer both entertainment and intellectual stimulation.

Maria: That’s a great idea, David. There are plenty of books that can be considered beach reads but still have substance. Maybe we could recommend some titles that fit that description?

Alex: I like that approach. Let’s make sure our recommendations are diverse and inclusive, so that readers of all genders and backgrounds can find something they enjoy.

Chris: Absolutely. And let’s be honest about the marketing behind the concept of beach reads. While it’s true that some books may be marketed as “beach reads,” that doesn’t mean they can’t be good books. Let’s focus on the quality of the writing and the story, rather than the marketing.

Sarah: I agree. Let’s recommend books that are enjoyable, diverse, and well-written, regardless of whether they are marketed as “beach reads” or not.

David: Agreed. And let’s also encourage readers to challenge themselves by trying new genres and authors, even if they don’t fit into the traditional “beach read” category.

Maria: Yes, and let’s not forget that reading is a personal activity. What one person considers a beach read may be different from someone else’s definition. It’s all about finding what you enjoy.

Alex: Absolutely. Let’s encourage readers to find books that resonate with them, regardless of any marketing labels. Reading is about personal enjoyment and growth, and that should always be our focus.

Chris: I couldn’t agree more. Let’s recommend books that offer both enjoyment and growth, and encourage readers to explore new genres and authors. With that approach, everyone can find their perfect beach read, no matter what that means to them.


Have each recommend their favorite beach read.

Sarah: My favorite beach read is “The Kiss Quotient” by Helen Hoang. It’s a romance novel with a unique premise and diverse characters that I found both entertaining and meaningful.

David: I recommend “The Martian” by Andy Weir. It’s a science fiction novel that’s both entertaining and intellectually stimulating. The main character’s struggle for survival on Mars is both thrilling and thought-provoking.

Maria: My favorite beach read is “The Joy Luck Club” by Amy Tan. It’s a literary novel that explores the relationships between mothers and daughters, and the challenges of immigrant families in America. It’s a beautifully written book that’s both engaging and thought-provoking.

Alex: I recommend “The Nightingale” by Kristin Hannah. It’s a historical fiction novel that explores the experiences of two sisters in France during World War II. The story is both heartbreaking and inspiring, and the characters are complex and relatable.

Chris: My favorite beach read is “Eleanor Oliphant is Completely Fine” by Gail Honeyman. It’s a contemporary fiction novel that follows the life of a socially awkward woman who learns to connect with others and find happiness. It’s both heartwarming and humorous, and the writing is top-notch.

Sarah: Another great beach read I recommend is “The Unhoneymooners” by Christina Lauren. It’s a romantic comedy that’s perfect for a beach day, with fun banter and an enemies-to-lovers plot that will keep you entertained.

David: For a more challenging beach read, I recommend “Sapiens: A Brief History of Humankind” by Yuval Noah Harari. It’s a nonfiction book that explores the history of human civilization and the future of our species. It’s thought-provoking and informative, but still accessible to general readers.

Maria: Another beach read I recommend is “Little Fires Everywhere” by Celeste Ng. It’s a literary novel that explores the complexities of family relationships and the impact of social status. The characters are well-developed and the writing is beautiful.

Alex: For a light but meaningful beach read, I recommend “The Alchemist” by Paulo Coelho. It’s a philosophical novel that follows a young shepherd boy on a journey to fulfill his dreams. The themes of self-discovery and personal growth make it a perfect beach read.

Chris: Another great beach read I recommend is “The Seven Husbands of Evelyn Hugo” by Taylor Jenkins Reid. It’s a historical fiction novel that explores the life of a Hollywood actress and the secrets she kept. The story is engaging and the characters are well-drawn, making it a perfect beach read for fans of character-driven fiction.

Good fun! – and a new way to explore a topic from multiple points of view using ChatGPT or Google Bard.

Categories
AI AI: Large Language Models ChatGPT Prompt Engineering

Ten Ways Anything Can Be Different in the Future

In the book Imaginable, author Jane McGonical had a description of how to pick an idea and explore it – by asking what’s true about it today, what might not be true about it in the future, and what are some clues or evidence of change that these ideas are plausible and realistic.

More specifically here’s what she wrote:

It’s called One Hundred Ways Anything Can Be Different in the Future. Here’s how it works: First, you pick a topic, like work, or food, or learning. Then you list one hundred things that are true about it today. The simpler or more obvious the fact, the better. Next, you rewrite each fact, one by one, so that ten years from now the opposite is true—no matter how ridiculous, at first, the new ideas sound. Finally, you look for clues, or evidence of change already happening today, that these ideas are plausible and realistic.

Imaginable by Jane McGonical

It dawned on me that this might be a fun example to explore in ChatGPT – and it was! My chat session follows below – it’s very exciting to use this tool for this kind of assistance in thinking!

Scott: This series of prompts is called 10 Ways Anything Can Be Different In the Future.

Great! I’m ready to help you explore different possibilities for the future. What topic would you like to explore?

Scott: Learning

Excellent choice! Let’s explore 10 ways learning could be different in the future:

  1. Personalized learning: In the future, personalized learning could become the norm. With advances in technology, AI could create personalized learning plans for each individual, taking into account their learning style, preferences, and strengths.
  2. Virtual and augmented reality: Virtual and augmented reality could revolutionize the way we learn by providing immersive experiences that allow learners to interact with information in a more engaging and interactive way.
  3. Gamification: Learning could become more game-like and interactive, with gamification elements incorporated into educational content to make it more engaging and enjoyable.
  4. Lifelong learning: In the future, learning could become a lifelong pursuit rather than something that only happens during the early years of life. Continuous education and upskilling could become the norm to keep up with the rapid pace of technological change.
  5. AI-powered tutoring: AI-powered tutoring could become more advanced, allowing for more personalized and effective teaching. Chatbots and virtual tutors could provide real-time feedback and support to learners.
  6. Collaborative learning: Collaborative learning could become more prevalent in the future, with learners working together on projects and assignments in virtual environments.
  7. Microlearning: Microlearning, or learning in small, bite-sized chunks, could become more common in the future. This could allow learners to fit learning into their busy lives more easily.
  8. Brain-computer interfaces: With the development of brain-computer interfaces, learning could become even more efficient and effective. Learners could directly interface with computers to learn new information or skills.
  9. Global learning: In the future, the world could become more interconnected, allowing for more opportunities for global learning. Learners could connect with others from different parts of the world to share knowledge and experiences.
  10. Biologically enhanced learning: With advances in biotechnology, it could be possible to enhance learning by manipulating brain chemistry or using gene editing to optimize cognitive functions.

These are just a few possibilities for how learning could be different in the future. The future of learning is exciting and full of potential!

Scott: For each of those 10 ways, now rewrite each making the opposite true.

Sure, here are 10 ways learning could be different in the opposite direction:

  1. Uniform learning: In the opposite future, there would be a standardized approach to learning for everyone, where every individual is taught the same curriculum regardless of their learning style, preferences, or strengths.
  2. Minimal use of technology: In this future, technology will play a minimal role in learning, and virtual and augmented reality will not be utilized for educational purposes.
  3. No gamification: The opposite future would not incorporate gamification elements into educational content. Learning would be a serious endeavor without any interactive or engaging elements.
  4. Limited learning opportunities: Learning would be limited to certain stages of life, and continuous education or upskilling would not be a priority. Individuals would be expected to learn everything they need to know during their school years.
  5. No AI-powered tutoring: The opposite future would not make use of AI-powered tutoring. Instead, learners would rely on traditional teaching methods with limited feedback and support.
  6. Individual learning: In this future, learners would not work together in virtual environments. Instead, individuals would learn independently, without any collaborative or interactive elements.
  7. No microlearning: Learning would not be delivered in bite-sized chunks in the opposite future. Instead, individuals would be expected to learn everything at once, without the option of fitting learning into their busy lives.
  8. No brain-computer interfaces: In the opposite future, there would be no brain-computer interfaces, and individuals would not be able to directly interface with computers to learn new information or skills.
  9. Limited global learning: In this future, there would be limited opportunities for global learning, and individuals would not be able to connect with others from different parts of the world to share knowledge and experiences.
  10. No biologically enhanced learning: In the opposite future, there would be no biotechnology advancements used to enhance learning. Individuals would have to rely on their natural cognitive abilities to learn.

Scott: Now let’s examine clues or evidence of change already happening today that these ideas are plausible and realistic.

Certainly! Here are some clues or evidence of change happening today that support the plausibility and realism of the ideas I presented earlier:

  1. Personalized learning: Personalized learning is already gaining traction in various fields such as medicine and marketing. Technology is now being developed to provide personalized learning plans to individuals, which can be adapted to their learning style, preferences, and strengths.
  2. Virtual and augmented reality: Virtual and augmented reality is already being used in various industries such as entertainment and gaming, and it is only a matter of time before it becomes more common in the educational industry.
  3. Gamification: Gamification has already been successfully incorporated into educational content to make it more engaging and enjoyable. Game-based learning is becoming more prevalent in schools and universities.
  4. Lifelong learning: Continuous education and upskilling are already becoming more important in today’s fast-paced and ever-changing world. Many companies and organizations are offering training and education programs for their employees to keep up with the latest trends and advancements.
  5. AI-powered tutoring: AI-powered tutoring is already being used in various educational contexts, such as language learning apps, where virtual tutors provide real-time feedback and support to learners.
  6. Collaborative learning: Collaborative learning is already being used in various educational settings, where learners work together on group projects and assignments.
  7. Microlearning: Microlearning is already being utilized in various industries, such as professional development and corporate training. Many companies offer microlearning modules to their employees to fit learning into their busy schedules.
  8. Brain-computer interfaces: Brain-computer interfaces are already being used in research, and they have shown promising results in enhancing cognitive functions such as memory and learning.
  9. Global learning: Global learning is already happening today, with online courses and virtual exchange programs connecting learners from different parts of the world.
  10. Biologically enhanced learning: Biotechnology advancements are already being used to treat various neurological and cognitive disorders, and it is only a matter of time before they are used to enhance learning as well.

These are just a few examples of the many clues and evidence of change already happening today that support the plausibility and realism of the ideas presented earlier. The future of learning is exciting and full of potential, and we are already seeing many of these changes happening today.

SJL+ChatGPT – May 4, 2023

After writing this post, I came across this article by Connie Chan at A16Z: Embracing the Future: How Chatbots Can Become Great Companions. In a way, that’s how I’ve been using both ChatGPT and Google Bard. Not as search engines to find other websites but, rather, as a thinking companion to explore ideas, learn more about historical topics, etc.

She writes:

Today’s AI chatbots are able to invoke emotions and provide companionship by asking us probing questions that go deeper into our psyche than chatbots of the past. (In fact, some are finding that these chatbots are better at providing companionship than providing facts.) By pulling information out of us, like therapists, and then having perfect recall of every detail we’ve ever told it, these companion chatbots can pattern match our behavior—and ultimately help us understand ourselves better.

Categories
AI AI: Large Language Models ChatGPT Prompt Engineering

Prompt Engineering 101

With the evolution of these generative AI tools, there’s a new field of expertise that has emerged: prompt engineering. I thought it’d be useful for me to spend a bit of time diving into this field to see what I might learn. Where should I start? How about just asking ChatGPT for some help? – so that’s what I did:

I began by asking:

What’s the best strategy for developing skills in prompt engineering?

ChatGPT responded:

Prompt engineering is the process of creating effective prompts for AI language models to generate high-quality outputs. Here are some strategies you can use to develop your skills in prompt engineering:

  1. Practice: The best way to improve your prompt engineering skills is by practicing. Create prompts for different types of language models and see what kind of responses you get. Experiment with different wording, formatting, and other variables to see what works best.
  2. Study: Study the prompts used by other experts in the field. Analyze the structure and wording of their prompts, and try to understand why they are effective. This will help you to develop a better understanding of the nuances of prompt engineering.
  3. Learn about the model: Understanding the language model you are working with is crucial for prompt engineering. Learn about the architecture, the training data, and the limitations of the model. This will help you to create prompts that are better suited to the model’s capabilities.
  4. Focus on the task: When creating prompts, focus on the specific task you want the language model to perform. Be clear and concise about what you want the model to do, and structure your prompt accordingly.
  5. Test and iterate: Test your prompts with different language models, and see how they perform. Iterate on your prompts based on the results you get, and continue to refine your approach.

By practicing these strategies, you can improve your skills in prompt engineering and create more effective prompts for AI language models.

I continued:

Please provide a few examples of great prompts that we can study for learning.

ChatGPT:

Sure! Here are a few examples of great prompts that you can study for learning:

  1. GPT-3 for Creative Writing: “Write a short story about a woman who can talk to animals.” This prompt is specific, clear, and provides a clear direction for the AI language model to generate a creative story based on the given premise.
  2. T5 for Translation: “Translate the following sentence into Spanish: ‘I love to travel and try new foods.'” This prompt is clear and concise, specifying the task of translating a sentence from English to Spanish and providing the input text.
  3. GPT-2 for Chatbot: “You are a customer service representative for a bank. A customer calls to report a lost debit card. Write a response to the customer.” This prompt provides a clear context and task for the AI language model, allowing it to generate a realistic response as a customer service representative.
  4. GPT-3 for Question Answering: “What is the capital of Brazil?” This prompt is a simple and clear question, specifying the task of providing an answer to a specific question.

By studying these examples, you can learn how to create effective prompts for AI language models and improve your skills in prompt engineering.

I continued:

Provide five more examples.

ChatGPT:

Sure, here are five more examples of great prompts:

  1. GPT-3 for Content Creation: “Write an informative article about the benefits of meditation.” This prompt is specific and clear, providing a clear direction for the AI language model to generate a informative article on the given topic.
  2. T5 for Summarization: “Summarize the following article: ‘Study finds that drinking coffee reduces the risk of heart disease.'” This prompt is clear and concise, specifying the task of summarizing a given article and providing the input text.
  3. GPT-2 for Text Completion: “Complete the following sentence: ‘The best way to learn a new skill is…'”. This prompt is clear and concise, specifying the task of completing a sentence and providing the starting text.
  4. GPT-3 for Text Generation: “Write a poem about the beauty of nature.” This prompt is specific and clear, providing a clear direction for the AI language model to generate a poem based on the given theme.
  5. GPT-2 for Creative Writing: “Write a story about a detective who is trying to solve a murder case.” This prompt is specific and clear, providing a clear direction for the AI language model to generate a creative story based on the given premise.

By studying these examples, you can learn how to create effective prompts for a variety of tasks and improve your skills in prompt engineering.

I continued:

How about examples of longer more complex prompts?

ChatGPT:

Sure, here are some examples of longer, more complex prompts:

  1. GPT-3 for Language Modeling: “Given a list of ingredients, write a recipe for a vegan lasagna that serves six people. The recipe should be easy to follow and include instructions for preparing the ingredients, assembling the lasagna, and cooking it in the oven. Please also include suggestions for side dishes and serving ideas.”
  2. T5 for Question Answering: “Read the following passage about the history of the Industrial Revolution and answer the following questions in complete sentences. What were the main technological advancements of the Industrial Revolution? How did these advancements impact society at the time? What were some of the negative consequences of the Industrial Revolution?”
  3. GPT-2 for Creative Writing: “Write a short story about a time traveler who goes back in time to prevent a historical event from occurring. Describe the time traveler’s journey, the historical event, and the consequences of their actions.”
  4. GPT-3 for Text Generation: “Write a persuasive essay arguing that artificial intelligence will have a positive impact on society. The essay should include at least three reasons to support this argument, as well as counterarguments and rebuttals to potential criticisms of AI technology.”
  5. T5 for Text Classification: “Given a set of customer reviews for a restaurant, classify each review as positive, negative, or neutral. The reviews should be analyzed based on the tone, sentiment, and overall opinion expressed by the customer. Please provide a breakdown of the percentage of reviews in each category and identify any common themes or patterns that emerge.”

By studying these longer, more complex prompts, you can learn how to create prompts that are more detailed and nuanced, and better suited to complex tasks that require a higher level of language understanding.

I asked for some more examples…

ChatGPT:

Sure, here are some more examples of longer, complex prompts:

  1. GPT-3 for Language Modeling: “Write a short story about a group of astronauts who are stranded on a distant planet. The story should include descriptions of the planet’s landscape and environment, as well as the challenges that the astronauts face in their attempt to survive and find a way back to Earth.”
  2. T5 for Text Generation: “Write a research paper on the impact of social media on mental health. The paper should include a review of existing literature on the topic, as well as original research that examines the relationship between social media use and mental health outcomes. The paper should also discuss potential policy implications and recommendations for future research.”
  3. GPT-2 for Creative Writing: “Write a script for a short film about a young woman who is struggling to come to terms with her identity. The film should explore themes of identity, family, and self-discovery, and should feature a diverse cast of characters. The script should include dialogue, character descriptions, and stage directions.”
  4. T5 for Text Summarization: “Summarize a scientific article about the effects of climate change on ocean ecosystems. The summary should include key findings and conclusions from the article, as well as any recommendations for policy or further research.”
  5. GPT-3 for Text Classification: “Given a dataset of tweets about a controversial topic, classify each tweet as supportive, opposing, or neutral. The classification should take into account the tone and language used in each tweet, as well as any relevant hashtags or keywords. The results of the classification should be presented in a report that includes visualizations and insights about the distribution of tweets across categories.”

By studying these longer, more complex prompts, you can learn how to create prompts that are tailored to specific tasks and domains, and that require a higher degree of language comprehension and creativity.

Pretty cool – the teacher teaching me how to use the tool more effectively. Some of these prompts are quite interesting to explore. There are even more very interesting prompt examples in Impromptu, the new book by Reid Hoffman and GPT-4.


Update:

I asked ChatGPT to give me several examples of especially creative prompts I might try. Here’s what it offered:

Sure, here are some examples of especially creative prompts for ChatGPT:

  • “Tell me a story about a dragon who falls in love with a human”: This prompt could inspire ChatGPT to generate a creative and engaging story about a dragon who defies the odds and falls in love with a human.
  • “If you could travel anywhere in the universe, where would you go and why?”: This prompt could encourage ChatGPT to generate responses that explore the limits of imagination and creativity, taking the user on a journey through the universe.
  • “What would you say to a friend who is feeling down and needs some cheering up?”: This prompt could inspire ChatGPT to generate uplifting messages or advice that could help someone feeling sad or alone.
  • “What is the meaning of life, according to you?”: This prompt could encourage ChatGPT to generate responses that explore philosophical concepts and challenge users to think deeply about their values and beliefs.
  • “Can you teach me a new language or word?”: This prompt could inspire ChatGPT to generate responses that teach users new words or phrases in a different language, promoting cultural exchange and language learning.
  • “What is your favorite memory from your childhood?”: This prompt could encourage ChatGPT to generate responses that evoke feelings of nostalgia and warmth, inspiring users to reflect on their own childhood memories.
  • “If you could be any fictional character for a day, who would you be and why?”: This prompt could inspire ChatGPT to generate responses that explore the user’s imagination and allow them to escape into a world of fiction and fantasy.

Overall, creative prompts for ChatGPT can inspire it to generate responses that are not only accurate but also engaging and imaginative, taking users on an exciting journey through language and conversation.