Introduction to Generative Artificial Intelligence
https://bard.google.com/ or. https://chat.openai.com/
Generative AI is a type of artificial intelligence technology that can produce various types of content, including text, imagery, audio and synthetic data. The recent buzz around generative AI has been driven by the simplicity of new user interfaces for creating high-quality text, graphics and videos in a matter of seconds.
Two additional recent advances that will be discussed in more detail below have played a critical part in generative AI going mainstream: transformers and the breakthrough language models they enabled.
Transformers are a type of machine learning that made it possible for researchers to train ever-larger models without having to label all of the data in advance. New models could thus be trained on billions of pages of text, resulting in answers with more depth. In addition, transformers unlocked a new notion called attention that enabled models to track the connections between words across pages, chapters and books rather than just in individual sentences.
The rapid advances in so-called large language models (LLMs) -- i.e., models with billions or even trillions of parameters -- have opened a new era in which generative AI models can write engaging text, paint photorealistic images and even create somewhat entertaining sitcoms on the fly.
Typically, using generative AI starts with a simple text input, called a prompt, in which the user describes the output they want. Then, various algorithms generate new content according to what the prompt was asking for. For instance, if a user tells a text-to-image generator that they want a picture of ducks playing poker in the style of Vincent van Gogh, or a content generator that they want an essay about dark matter, the given system will oblige.
Beyond Prompt Engineering: Problem Formulation
So what human AI skill is going to withstand the test of time? What’s our enduring power tool in the AI age?
Problem formulation.
It’s all about how we humans identify, analyze, and define problems. When we can illustrate the problem, AI will provide the most efficient way to counter it.
AI cannot identify an unquantifiable problem that is not part of a current system, that’s the purview of humanity.
How is interacting with a chatbot such as Bard different from using a search engine?
Here’s what Bard said:
Bard is a conversational AI. This means that you can interact with Bard in a natural, conversational way. You can ask questions, make requests, and have a conversation with Bard. Search engines, on the other hand, are designed to return results based on keywords. You need to know what you're looking for in order to use a search engine effectively.
Bard can understand and respond to natural language. This means that you can ask Bard questions in a natural way, without having to use keywords or special syntax. For example, you could ask Bard "What is the capital of France?" or "What is the meaning of life?" Search engines, on the other hand, are not designed to understand natural language. You need to use keywords or special syntax in order to get the results you want.
Here are 5 ways for writing effective prompts for Bard:
Be specific. The more specific you are in your prompt, the better Bard will be able to understand what you want and generate a more accurate response. For example, instead of asking "Write me a poem," try something like "Write me a poem about a lost love."
Use keywords. When you're trying to get Bard to focus on a specific topic, use keywords in your prompt. For example, if you want Bard to write you a story about a dog, try using keywords like "dog," "pet," or "animal."
Provide examples. If you can, provide Bard with examples of the type of content you're looking for. For example, if you want Bard to write you a song, try providing a link to a song that you like.
Set a tone. If you want Bard to write you something that's funny, serious, or creative, let them know by setting a tone in your prompt. For example, you could start your prompt with something like "Write me a funny poem about a cat."
Be open to feedback. Once Bard has generated content, be sure to read it over and provide feedback. This will help Bard learn what you like and don't like, so that they can generate better content in the future.
Links:
Prompt Engineering https://www.promptingguide.ai/introduction/tips
How Might AI Change Assessment https://spencerauthor.com/ai-assessment/
Advanced ChatGPT Guide for Teachers https://youtu.be/WLozMORcdZ8