Artificial Creativity

artificial creativity in a cup overflowing with silicon impressionismOn the left I gave DeepAI a prompt of, “Artificial creativity in a cup overflowing with silicon.” in an impressionist style. It didn’t generate what I was thinking of, and it didn’t give me much.

I’d begun fiddling with ChatGPT, as I wrote about in, “A Chat With GPT on AI“. There, the answers were ambiguous – though necessarily so. In querying it on many things, though, I found the same style of answer more than once, and a certain fondness for words. This should be no surprise in present language models.

I’ve split myself in two world, since within me I have much overlap between technology and other interests and being creative. Previous experiments with doing it all on one site just seemed to confuse people. After all, they don’t expect someone to be both. In that regard, KnowProSE.com is more technical, while here on RealityFragments.com I do everything else.

Oddly, artificial intelligence is thought to challenge both the technical and creative and those with the overlap.

So I decided to ask ChatGPT to write something on creativity and see what it had to say. I was impressed with rationality yesterday. Today, let’s see what creativity I can get out of it.

ChatGPT Creative prompt
ChatGPT generated the following:

Artificial intelligence (AI) has made remarkable progress in recent years. From self-driving cars to natural language processing, AI is revolutionizing industries and transforming the way we live and work. But can AI be creative? The answer is a resounding yes.

AI algorithms can generate new and innovative ideas, produce original artwork, compose music, and even write novels. In this blog post, we’ll explore some examples of how creative an artificial intelligence can be.

  1. Art

AI algorithms can create unique and stunning pieces of artwork. These algorithms use machine learning techniques to analyze existing artwork, understand their composition and style, and then generate new pieces based on that information. One example of such AI-generated artwork is the “Portrait of Edmond de Belamy” by the Paris-based art collective Obvious. The portrait was sold for over $432,000 at Christie’s auction house in 2018.

  1. Music

AI algorithms can compose original music in various genres, including classical, jazz, and pop. These algorithms analyze existing music and use machine learning to identify patterns and structures. They can then use this information to create new pieces that are both unique and appealing to the human ear. One example of such an AI-generated piece of music is “Daddy’s Car,” which was composed by the Swedish AI startup Amper Music.

  1. Writing

AI algorithms can also write original works of fiction, poetry, and even news articles. These algorithms use natural language processing to understand the structure of language and then generate new pieces based on that understanding. One example of such an AI-generated work is “The Day a Computer Writes a Novel,” which was written by an AI program developed by a team at the Future University Hakodate in Japan.

  1. Inventing

AI algorithms can even invent new things. For example, a team of researchers at the University of Cambridge used an AI algorithm to design a new type of superconductor material. The algorithm analyzed data from thousands of existing superconductors and then used machine learning to identify new combinations of elements that could be used to create a more efficient material.

Conclusion

Artificial intelligence has come a long way in recent years, and its creative potential is becoming increasingly apparent. From generating new artwork and music to writing novels and inventing new materials, AI algorithms can produce original and innovative works that are both impressive and inspiring. As AI continues to advance, it’s exciting to think about what other creative feats it may achieve in the future.

Well, that is impressive. It’s a lot like someone showing a resume. But by itself, it doesn’t show much creativity, does it? It basically writes around some references. This is not to say that AI cannot be creative – the images I use these days are from DeepAI, as an example – but that creativity is limited to what the AI experiences through what it is trained on. It is limited by what it experiences, and what that limitation is… looks a lot like what we train it with.

Certainly, I think writing will be affected – and I have been mildly disillusioned about that. But I also believe that since an artificial intelligence only uses the information we share with it, it can’t truly be creative in a human sense because it lacks the human experience. It might throw words together or create images and music, but it can’t tell you how it feels the first time you eat ice cream or the way you feel when it falls.

It regurgitates in our language because it has no experience beyond what we feed it. It has no expectations, no way to love or hate other than the biases we feed them. When it comes to being human, it is not a competitor.

Unfortunately, though, it will be damned good at marketing.

One thought on “Artificial Creativity

Leave a Reply

Your email address will not be published. Required fields are marked *