Have you ever stood in front of a redwood and wondered, “Wouldn’t it be great if this was poetry instead of a tree?” Neither did Joyce Kilmer. Kelin Carolyn Zhang and Ryan Mather, however, have set out to bridge the gap between AI tech and poetry with their captivating brainchild — the Poetry Camera. The open source device combines cutting-edge technology with artistic vision, resulting in a creation that pushes the boundaries of both fields.
At first glance, the Poetry Camera seems like another gadget in the ever-evolving landscape of digital devices. However, upon closer inspection, it becomes evident that this is no ordinary camera. Instead of merely capturing images, the Poetry Camera takes the concept of photography to new heights by generating thought-provoking poetry (or, well, as thought-provoking as AI poetry can get) based on the visuals it encounters.
Zhang and Mather, the masterminds behind this project, have seamlessly blended their expertise in technology and art to create a technically impressive and aesthetically captivating device.
The story of the Poetry Camera began as a personal passion project for Zhang and Mather, who found themselves captivated by the idea of merging their love for technology with their appreciation for the arts. In the early stages of development, they spent countless hours tinkering with various components and experimenting with different AI models to bring their vision to life.
“The project’s origin is when I got access to GPT-3. My first instinct was to play Dungeons & Dragons with it because I’m a nerd. I figured ‘if this thing could play Dungeons & Dragons, that would be impressive.’ And yeah, it did work for that. This was back when you had to do prompt engineering. So it took some elbow grease to get it to work. But I also had this idea of maybe making some camera as a project,” says Mather. “What if you took a camera, but it was a reaction to Instagram culture? What if text comes out instead of a photo? … Everyone prefers the book version over the movie, so it’s like that for capturing moments.”
As they refined their prototype, Zhang and Mather began to share their creation with friends and family at social gatherings. The reactions they received were nothing short of astonishing. People were fascinated by the concept of a camera that could generate poetry based on what it saw. The device quickly became the center of attention, sparking lively discussions and igniting the imagination of all who encountered it.
These initial reactions were a powerful motivator for Zhang and Mather to continue refining their invention. They realized that the Poetry Camera had the potential to bridge the gap between technology and art in a way that resonated with people. As word of the Poetry Camera spread, the duo were inundated with inquiries from curious individuals eager to experience the device for themselves. This interest led them to consider the possibility of transforming their project into a potential commercial product, making the magic of the Poetry Camera accessible to a broader audience.
The tech
At the heart of this innovative device lies a Raspberry Pi, a credit card-sized single-board computer that packs a powerful punch. This tiny yet mighty component serves as the brain of the Poetry Camera, enabling it to capture images and communicate with OpenAI’s GPT-4 to generate poetry.
A Raspberry Pi captures the image and then employs computer vision algorithms to analyze the visual data. The AI models then interpret the image, identifying key elements, colors, patterns and emotions within the frame. This information serves as the foundation for the poetry-generation process.
The intersection of art and technology
The Poetry Camera serves as a testament to the incredible potential at the intersection of art and technology. By harnessing the power of AI and machine learning, Zhang and Mather have created a device that not only captures the beauty of the world around us but also interprets it in a way that can be surprisingly touching. As technology, it’s simple, but I love how accessible Poetry Camera makes things. It becomes so easy to dare to dream and push the boundaries of what technology can achieve.
Screens dominate our daily lives; the Poetry Camera offers a refreshing departure from the norm. Rather than relying on a digital display to showcase its poetic outputs, the device employs a more tactile and immersive method of interaction. The generated poems are printed on paper, creating a physical embodiment of the artistic experience. The temporary nature of the art gets taken pretty far with Poetry Camera.
“We don’t save any of the images or the poems digitally. There are a few reasons for that: One, it’s easier. Two: privacy. Three, it adds extra meaning to the poems if they’re like these ephemeral sorts of artifacts. If you lose it, it’s gone,” Mather explains. “Everyone has a camera in their pocket through their cell phone now — we wanted to do something very different.”
The design philosophy extends beyond the device, influencing the entire user experience. Zhang and Mather have carefully crafted the Poetry Camera to foster a sense of wonder and discovery. Capturing an image, waiting for the AI to generate a poem and then receiving the printed output creates a sense of anticipation and surprise, enhancing the overall engagement with the device.
A reflection of the future of AI and personal computing
Zhang and Mather’s design philosophy for the Poetry Camera reflects their broader vision for the future of personal computing and AI. They believe technology should be seamlessly integrated into our daily lives, enhancing our experiences without overwhelming us with constant stimuli. By creating a device that prioritizes simplicity and artistic expression, they are challenging the status quo and paving the way for a new era of technology.
“I think poetry cameras are a microcosm of what will happen to many industries with AI. Poetry cameras are unlike a traditional discipline: You never met someone who says, ‘Oh, I’m a poetry photographer for corporate events,’ laughs Zhang. Poetry Cameras are in between this established field of photography and poetry. It is this new, weird thing. Most importantly, watching people interact with them is enjoyable: People find childlike joy in their playful persona.”