In the ever-evolving world of artificial intelligence, one question lingers: Can human and AI creativity harmoniously coexist and complement each other to create a richer, more diverse landscape of innovation? Inspired by "Imagination Machine" by Martin Reeves & Jack Fuller, I embarked on a journey to discover the potential of combining human and AI imaginations. With the advanced AI chatbot GPT-4 as my guide, I explored the possibilities of this creative convergence. Contrary to the beliefs of some, AI systems like GPT-4 have already demonstrated an impressive ability to mimic human-like reasoning and imagination. For instance, GPT-4 was able to provide plausible explanations for why customers who liked Rambo also liked Fast & Furious, which challenged the "Imagination Machine" authors' assertion that AI could not understand such underlying dynamics.

AI image generators, which create fantastical sights at the intersection of dreams and reality, bubble up on every corner of the web. Their entertainment value is demonstrated by an ever-expanding treasure trove of whimsical and random images serving as indirect portals to the brains of human designers. A simple text prompt yields a nearly instantaneous image, satisfying our primitive brains, which are hardwired for instant gratification. Although seemingly nascent, the field of AI-generated art can be traced back as far as the 1960s with early attempts using symbolic rule-based approaches to make technical images. Yilun Du, a Ph.D. student in the Department of Electrical Engineering and Computer Science and affiliate of MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), recently developed a new method that makes models like DALL-E 2 more creative and have better scene understanding. Here, Du describes how these models work, whether this technical infrastructure can be applied to other domains, and how we draw the line between AI and human creativity.

AI image generators, which create fantastical sights at the intersection of dreams and reality, bubble up on every corner of the web. Their entertainment value is demonstrated by an ever-expanding treasure trove of whimsical and random images serving as indirect portals to the brains of human designers. A simple text prompt yields a nearly instantaneous image, satisfying our primitive brains, which are hardwired for instant gratification. Although seemingly nascent, the field of AI-generated art can be traced back as far as the 1960s with early attempts using symbolic rule-based approaches to make technical images. Yilun Du, a PhD student in the Department of Electrical Engineering and Computer Science and affiliate of MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL), recently developed a new method that makes models like DALL-E 2 more creative and have better scene understanding. Here, Du describes how these models work, whether this technical infrastructure can be applied to other domains, and how we draw the line between AI and human creativity.