When we think of photography, most of us probably imagine a camera capturing images. And who could blame us for following that line of thought as it is pretty much what we’ve been doing since the advent of the art.
But what if you could capture sentiments and abstract feelings instead of actual images? Is that device still a camera, or is it something else?
The open-source Poetry Camera forces us to ask these questions. Powered by artificial intelligence and fueled by a passion for the project on the part of the developers Kelin Carolyn Zhang and Ryan Mather, the Poetry Camera aims to translate into words what the lens sees.
It’s a novel idea, to be sure, and one that is certainly made for the social media age.
PetaPixel reports that the device uses a Raspberry Pi single-board computer for image capture and, combined with OpenAI’s GPT-4 generative AI, produces poems based on the elements of the capture.
You can also choose the style of poem that you want to see, such as a haiku.
Speaking about the project, Ryan Mather told TechCrunch:
“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…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.”
Any thoughts that you might have on this brave new world of AI-assisted creation are welcome in the comments below.
We have some more headlines for you to read at this link right here.
