Skip to Main Content
Pollak Library

Artificial Intelligence (AI)

Creating Effective Prompts

image of a signing saying "Training"Remember, a prompt is the content you enter into a generative AI tool in order to receive your desired output. It may not immediately create the content you envisioned, and you may need to refine your prompt to generate an output that closer aligns to what you want. Generated output can change based on the quality of the prompt and implementing prompt engineering can refine your content to more efficiently use a language learning model. (From the University of Illinois Urbana-Champaign Library).

There are numerous prompt engineering models available. We have highlighted a few below and a quick web search will find many more.

PROMPT Design Framework by Sarah Hartman-Caverly, Librarian Penn State Berks

  • Persona - assign a role

  • Requirements - define parameters for output 

  • Organization - describe the structure of the output

  • Medium - describe the format of the output

  • Purpose - identify the rhetorical purpose and intended audience

  • Tone - specify the tone of output (ex: academic)

Example using this framework:

  • Original: Outline a paper about self-driving cars in cities with a lot of traffic

  • New: You are a college student majoring in transportation engineering. Produce a numbered, multi-level outline for a 7 page academic paper for a college-level transportation engineering class about the challenges and solutions for introducing self-driving cars into a high traffic city.

CLEAR Framework by Leo S. Lo, Dean of the College of University Libraries and Learning Sciences, University of New Mexico

  • Concise - Is there superfluous language?

  • Logical - Is the prompt structured logically like instructions should be?

  • Explicit - Is the prompt explicit enough about what to produce and in what format?

  • Adaptive - Do I need to adapt/change the prompt to get what I need?

  • Reflective - Is this what I needed? Is the information provided accurate and credible?

Example using this framework:

  • Original: Can you explain photosynthesis and lay it out in steps?

  • New: Provide a one page, step-by-step explanation of photosynthesis at the seventh grade level. 

  • Adaptive - revising the prompt if needed

  • Reflective - check factual information against credible sources

(From the University of Texas Libraries)

 

Art and AI

AI-generated images bring a whole new dimension to the fields of art, photography, advertising, design . . .

Questions arise about how to cite AI-generated images, and also about the ethical and even legal implications of AI accessing the work of visual artists online and using it, not necessarily with permission, as the basis for AI-generated art.

The controversy surrounding the training of AI art models centers on several key issues:

  • Copyright and intellectual property: Many AI models are trained on vast datasets of existing artwork without explicit permission from the original artists. This raises questions about whether using these images for training constitutes copyright infringement.
  • Lack of compensation: Artists whose work is used to train AI models generally don't receive compensation, even though their art contributes to the AI's capabilities.
  • Consent and control: Artists often have no say in whether their work is included in training datasets, and no way to opt out if they object.
  • Attribution and credit: When AI generates art inspired by or mimicking an artist's style, there's no clear mechanism for attributing or crediting the original artist's influence.
  • Data scraping ethics: Many training datasets are created by scraping images from the internet, which raises questions about privacy and the ethics of using publicly available data for commercial purposes.
  • Impact on the art market: There are concerns about how AI-generated art might affect the livelihoods of human artists and the overall art market.
  • Bias and representation: The datasets used for training can perpetuate or amplify existing biases in art representation, potentially marginalizing certain groups or styles.

(From Taft College Library)

A selection of AI image generators is available for experimentation. Note that the etiquette and ethical considerations surrounding the use of AI in creating art, music, and other content continue to evolve.

  • There's an AI for That: Find AI tools for everything
  • Adobe Firefly: Free through your UVU Adobe account. Adds watermark to images.
  • DALL·E 3: OpenAI's AI image creator. You must purchase credits to generate images.
  • Discord's Midjourney: Subscription-based with free trial. There is a learning curve to using the interface for the first time, we suggest doing a web search to learn how to use it.
  • Dream Studio: Login is required. You receive a limited number of free credits and then must pay.
  • Kapwing AI: Create videos, images, memes, and scripts.
  • Stable Diffusion: Free

Coding and AI

Using generative AI can be an effective way of generating computer code especially for people who are inexperienced in coding, such as researchers in fields other than computer science who need to create programs to analyze data. Any code generated by AI should be tested just as thoroughly as human generated cove to ensure there are no errors. (From Illinois Tech Glavin Library)