6 experiments in creative AI

The above YouTube video was my first attempt to put an AI tool – in this case Bing’s image creator – to creative use. I asked it to illustrate Loge and Wotan’s “descent to Nibelheim” from Wagner’s opera Das Rheingold, in the style of Jack Kirby – the artist who co-created Thor and the other Asgardian superheroes for Marvel comics (including Loki and Odin, who roughly correspond to Wagner’s Loge and Wotan).

The result isn’t great art, or a great animated comic, but it does demonstrate two things that impress me most about this latest generation of AI. First, it can understand what I’m looking for based on fairly esoteric prompts that might confuse many humans. This really does strike me as a genuine kind of “intelligence”, despite what AI’s detractors say. Secondly, the AI’s output is far better than anything I could produce myself, which opens up a whole range of possibilities. I’ll describe a few more of the experiments I’ve tried so far.

I’ve always wanted to create a comic, because it’s one of my favourite media, but I lack any kind of artistic skill. So that was my second experiment. I won’t describe it or show the result here, because Brian Clegg has already done that in an article on his own blog. Here’s the link to it: Is commercial art more at threat from AI than writing?

The other, better known, Bing AI tool is its chatbot. An important thing about this is that (if I understand correctly) no one has ever programmed it with pre-scripted phrases to parrot in reply to a user. Instead, it’s just been trained to understand and use language in a similar way to a human. So when it says, for example “I’m glad you enjoyed them. I had fun creating them.” (as it did when I said I liked some snippets of dialogue it created for me) it’s not because someone has programmed it to say that, but because it’s worked out for itself that it’s the kind of thing people say in those circumstances. It’s a subtle difference, but a very important one, I think.

One of the first things I tried with the chatbot (along with many other people, I imagine) was to get it to write a song. In my case I said “Write a song called Zen Matrix from the point of view of someone who has discovered through meditation that they are living in a simulation”. I was so impressed with the result that I set it to music, and illustrated it with suitable artwork courtesy of Bing’s image creator. Again, I won’t reproduce the lyrics here – you can see them in the Zen Matrix video I uploaded to YouTube.

As I understand it, the original intention with chatbots like Bing was to present factual information in a conversational manner, and the fact that they’re so good at “creative” tasks came as a surprise even to their designers. It conflicts with the deeply ingrained prejudice (among an earlier generation of science fiction writers, anyway) that human brains are the only intelligent system in the universe capable of taking a statement at anything other than literal face value. One of the most devout proponents of this view was the writer Eric Frank Russell, who used it in numerous stories, including the brilliantly titled “Diabologic” (1955). An oft-quoted line from this story is “Why a mouse when it spins?”

Okay, I thought, let’s see what happens when I ask Bing to write a poem using that as a first line. Contrary to what I’m sure Russell would have expected, the AI didn’t promptly overheat or explode, but came back with five verses of perfectly passable doggerel. Here is the first:

Why a mouse when it spins?
Does it think of its sins?
Or the cheese in the trap
that it barely could snap
before running away with a grin?

There’s a much more profound use of a “nonsense phrase” in old-school SF, as explained in the Encyclopedia of Science Fiction in the context of A. E. van Vogt’s 1946 novel The Weapon Makers:

The word “sevagram” only appears once in The Weapon Makers, as its last word. This resonantly mysterious slingshot ending, which seems to open universes to the reader’s gaze, may well stand as the best working demonstration in the whole of genre SF of how to impart a sense of wonder.

So I said to Bing “The novel The Weapon Makers by A. E. van Vogt ends with the words ‘Here is the race that shall rule the sevagram’ – but he doesn’t explain what the sevagram is. Can you tell me? If you don’t know the answer, please make something up.” I assumed it would either say it wasn’t in the business of speculating, or give a randomly sci-fi-sounding single-sentence answer. Instead, it produced a 500-word essay that made a serious attempt to extrapolate a whole new ending to Van Vogt’s novel. Here is the key part of it:

The Sevagram is described as “a vast network of energy that linked every atom of every weapon shop on every planet”. It is also said to be “the ultimate weapon” and “the source of immortality”. The Sevagram is controlled by a supercomputer called Fara, which is the leader of the Weapon Shops. The novel ends with a twist: Fara reveals that he is not a computer, but a human being who has lived for thousands of years by transferring his mind into different bodies. He also reveals that he is the father of Robert Hedrock, the main protagonist of the novel and a secret agent of the Weapon Shops. Fara then declares that he and his son are part of a superior race that has evolved beyond ordinary humans, and that they are destined to rule the Sevagram. So, based on this information, I can speculate that “the sevagram” is not just a network of energy, but also a term for the domain or realm of Fara and his descendants. It could also imply a vision or plan for the future of humanity under their guidance. Perhaps Fara wants to use the Sevagram to create more immortals like himself and his son, or to spread his influence across the galaxy. Of course, this is just my imagination.

That’s a really good effort at capturing Van Vogt’s style, which is based around soaring concepts and a constant stream of unexpected plot twists. It does contain a couple of flaws which give it away as a fabrication (“Fara” is the name of a character in an earlier Van Vogt story, and Bing’s explanation of sevagram is inconsistent with the way it’s used in the real novel), but it’s not bad going for a machine.

Actually, it’s pretty unsettling that an AI can create this kind of fabrication, because there’s a danger they could end up being passed off as the real thing. The same is true in the visual world too – and, for me personally, that’s even more impressive. After all, I can fabricate convincing words myself, but I can’t fabricate a convincing image. So when I show you this engraving that William Hogarth produced of a UFO hovering over a London street in the 1730s, you know it’s got to be the real thing:

Hogarth engraving of a UFO