Notes on a genre
-
You might have noticed that most presentations of art produced with the dazzling new image models include the text prompt. The pleasure, it seems, is not in the image; rather, it’s in the spectacle of the computer’s interpretation. I keep expecting this bond to loosen, and the images to find their footing as “mere” art, but the prompt sticks fast.
-
Nearly every artist is a genre artist. Form precedes content, even when the artist insists otherwise. There are exceptions, but they are rare, and the path is exceedingly dangerous: 10,000 illegible projects for every one with magnetism sufficient to re-align the world around its axes.
-
In that rare case, success simply founds a new genre.
-
AI artists are genre artists, too. Our genre is: “I see what you did there.”
-
This recalls the early days of synthesizers; what was Switched-On Bach if not “I see what you did there”? I hope that analogy is right, because the synth provides a healthy, sustainable template for these tools. Ubiquitous and unremarkable, controllable and hackable, with flavors ranging from fully corporate to gloriously DIY … I’m realizing, as I type this, that synthesizers might be one of the truly utopian technologies.
-
So it becomes a normative question: what choices, right now, could bend AI’s path towards the docility and diversity of the synth?
-
Many AI artists avidly metabolize each new technique or model as it appears, rushing headlong to plumb its new capabilities, last season’s cast aside. The objects of our fascination are often research papers and Colab notebooks, not “products”, but even so, this pattern fits (a bit too) comfortably into the tech economy of subscription everything, “accept upgrade”, a new phone every year.
-
“All fixed, fast-frozen relations, with their train of ancient and venerable prejudices and opinions, are swept away, all new-formed ones become antiquated before they can ossify.” Oy!
-
I hope to see more AI artists identify a technique or model they love and stick with it, even as the state of the art advances, leaving them behind. I don’t mean that in a crusty, regressive way; the vibe is not “640K ought to be enough for anybody.” I just want to suggest that it’s fun and satisying to form attachments to specific tools; to get good!
-
I’m proud of the fact that I’ve spent two solid years using OpenAI’s Jukebox, the same model, never amended or upgraded. I’ve embroidered the original code with my own customizations, and I feel like I still haven’t encountered a sliver of lurks inside its labyrinth. I hope they never make another one.
-
Jukebox has remained interesting and motivating to me in a way that none of the language or image models have, and I think that’s partially because it’s so difficult to use. Compared to “traditional” digital music production, nothing about Jukebox is faster; nothing is “better”. It’s just different, and, almost by chance, Jesse and I love that difference.
-
Using Jukebox feels like exploring the flooded ruins of a once-great city: exactly that slow, exactly that treacherous, exactly that enticing.