A (world's first?) real time generative artificial intelligence artist.

Check out the dedicated website for all the details: https://www.tesseract.art/

Along with my co-collaborator Dr Richard Savery, Tesseract.art started from an idea during a discussion in early February 2022. We originally met in 2018 via Hanson Robotics, while collaborating on a project to teach the Sophia robot how to play piano and develop improvisational skills.

Our Tesseract Art system can be best described as a transfer function that takes multiple inputs, and generates multidimensional art as an output. The artwork can then be projected into a smaller number of dimensions, just like a human artist takes their experience of the world around them as input to their creative process in order to produce a painting or sculpture.

We have been working on this concept for a couple years, and we thought long and hard about what the inputs should be for Tessa, our Tesseract Artist. When we thought about what a human artist does for their inspiration - they use their understanding of the world through their collective experience, and also in many cases artists listen to music for inspiration while creating.

And so for our first implementation of Tessa, we chose to build a system that consumes music as an input into our neural network “mind.” We also chose to paint instead of sculpt for now, since the sculpting process is much longer and more difficult to physically manage.

We also wanted Tessa to be able to paint together in a live collaboration with musicians as a performance, so the artwork needs to be completed within a reasonable timeframe, the same amount of time that the musicians are performing.

And so we decided that Tessa in her first instance shall be a new generative artist, an artificially intelligent agent that listens to a live music performance and paints what it hears in real time, using a robot arm as an actuator.