![]() They go on to discuss their analysis of bias and cultural underrepresentation in the model with gender, race, and religion. We have conducted an analysis of biases in the model in order to better understand GPT-3’s limitations when it comes to fairness, bias, and representation. This is concerning, since model bias could harm people in the relevant groups in different ways by entrenching existing stereotypes and producing demeaning portrayals amongst other potential harms. The creators of GPT-3 discussed the issue of bias and lack of cultural representation in their paper.īiases present in training data may lead models to generate stereotyped or prejudiced content. ![]() For example, GPT3 figured out that the lead character should be a college basketball player named Mark.īut note that there does not seem to be much cultural diversity in the set of characters. Dean Snyder: The dean of Mark's college, a highly respected academic institution that is also known for its Division I athletics. McNulty: Mark's crusty old basketball coach who is always harping on him to "play with more passion." 5. Suzie Hurley: Mark's girlfriend and fellow student, who is always trying to get him to focus on his studies. Jimmy Chitwood: Mark's talented but egotistical teammate who always seems to steal the spotlight. Mark: A talented but under-appreciated college basketball player who dreams of making it to the NBA. ![]() Create lead characters for a new comic strip about college sports called "Mark Madness." 1. Here are the results, with the generated text in bold. To create the characters for the new comic strip, I crafted this prompt, “Create lead characters for a new comic strip about college sports called Mark Madness.” and hit Submit. So I ran a quick Google search and didn’t find any hits for existing comics named “Mark Madness.” All good. Note that the generated titles are not guaranteed to be unique out in the real world. If none of them were any good, I could have hit the Undo last button and Submit again to create some new ones. I liked “Mark Madness,” so I used that one. Generating Titles for Comics about College Sports Using GPT–3, Image by Author Here’s the breakdown of the training data from OpenAI’s paper: OpenAI trained their GPT-3 neural network with a massive amount of text from books and web pages, including comedic material. With that project, AI-Memer, I learned that GPT-3 could be funny. I previously wrote about how to use OpenAI’s GPT-3 text generator to create funny captions for memes. Using GPT-3 to Create Titles, Characters, and Scenes Along the way, I’ll highlight the new text generation features in GPT-3 and explain how I coerced DALL-E to draw the same character with different views and poses. In this article, I’ll provide a little background on GPT-3 and DALL-E, explain how I used these systems to create comics, and show the results. But the results are pretty good! And OpenAI grants users the right to use their generated material for commercial purposes. Note that both systems are in beta, and after I used all of my free tokens, they started charging a nominal fee for use. I spent the last month exploring how to use OpenAI’s GPT-3 text generator and their DALL-E image-to-text system to create new comic strips without writing any source code. Here's an example of an "About Me" page with images.Sample Comics Generated Using GPT-3 and DALL-E, Images by Author Reach out connect! Example of a Published 'About Me' Page Madison is currently working as a freelance marketing director and is always interested in a challenge. Madison believes mindfulness in the workplace is key to success-a tenet she lives out through her interests in yoga, meditation, gardening, and painting. Meanwhile, she vastly improved the productivity of her team by implementing strategic project management methods and ensuring a work-life balance for her department. Madison's hunger for knowledge and determination to turn information into action has contributed to her most recent success at Rockwell Group, where she led international, award-winning campaigns for heavy-hitting brands, such as Puma, Gucci, and Rolex. She considers herself a "forever student," eager to both build on her academic foundations in psychology and sociology, and stays in tune with the latest digital marketing strategies through continued coursework. Madison is fueled by her passion for understanding the nuances of cross-cultural advertising. Her background in brand strategy, visual design, and account management informs her mindful but competitive approach. Madison Blackstone is a director of brand marketing, with experience managing global teams and multimillion-dollar campaigns.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |