About two-and-a-half months ago, I started a project to identify my visual language and set some loose parameters to work within. After seven years of painting and a lot of experimentation, I felt like it was time to narrow things down a bit.
To do this, I created a bunch of documents. The main one contained photos of over 90 pieces of my work along with metadata about each, including what I liked and didn’t like about it. The others covered my creative history, why I make art, artists I like, art quotes that resonate with me, and photos I’ve taken of things I’m drawn to. Contextual stuff.
I uploaded all of this to Gemini Notebook.
Using a prompt that Google’s AI Mode constructed for me (invoking a “unified panel” of an archivist, an art historian, a cryptographer, and a Socratic mentor), I asked Notebook to analyse everything and “help me uncover patterns, repetitions, and the underlying DNA of my artistic voice”—without nudging me in any particular direction.
I was going to go into all of the details of the very long chat that followed, but I think that would’ve put too much pressure on the new work I make. It also wouldn’t have left any mystery. 😊
I will say the process was incredibly helpful, involved at least one profound realisation, and helped me land on the parameters I was looking for. AI is very good at pattern matching and being a mirror or sounding board. You just have to remember that that’s all it is.
Here are the parameters I landed on:
- Black surface
- Saturated colour (high or low contrast, with support from muted colours and neutrals)
- Felt/expressive representation
- Text
These won’t mean a lot to you, but they do to me. And hopefully it’ll become clear over time why.
I may not have anything to show for a little while, but I’m very excited to get on and make some new work. I hope you’ll stick around and see how it develops.
Image: Ranchslider sunrise, 2020. Acrylic on canvas, 8 x 8 inches.