The bots are coming, the bots are coming

The bots are coming, the bots are coming

Source: Image courtesy of Medjourney

Artificial intelligence and visual arts

Industrial intelligence (AI) will study itself in the field of healthcare, educationtransportation, trade, Policyand Finance, Security, and War (Ford, 2021) and replace many human jobs. Artificial intelligence is well suited to take on routine tasks, but will human creative endeavors be shunned? Exploring this question, I recently (Chatterjee, 2022) concluded that AI will profoundly influence how we think about art and what it might mean to be an artist.

Art, when it is most powerful, can evoke deep emotions and foster a new understanding of the world. The vast repository of images online on platforms such as Instagram, Facebook, and Flicker is categorized by people’s preferences. These rich stores of data, which are growing every day, mean that AI programs can be trained to spot patterns in images that people like. These patterns are summarized in their production.

AI need not be limited to producing ordinary images reduced to a low common denominator, such as liking. Historically, in experimental aesthetics, scientists asked participants if they liked a work of art, found it interesting, or considered it beautiful. Imagine a taxonomy of words describing art’s potential effects that includes general ratings like ‘like’ and ‘interest’ (Chatterjee & Cardillo, 2021) but also nuanced terms like “moving,” “challenging,” “uplifting,” or “nauseating” that capture the emotional range of artistic associations (Christensen et al., 2022).

A large database of artistic images categorized by such effects could serve as a training set for an AI that values ​​art. The objection that the AI ​​does not know what it is looking at or experiencing emotion is irrelevant. All it should be able to do is label a new photo with descriptions and effects—a more sophisticated version of labeling a photo as a black cat, even if you’ve never seen that cat.

Sequence transformation models, or transformers, are making great strides in natural language processing. Being able to use text to display images is an important step in producing artistic images. Dall-E 2, Imagen, and Midjourney are gaining popularity as art generators that produce images when prompts are fed (Kim, 2022). For example, I used Midjourney to produce this image below with the claim “Still Life with Fruit, Flowers, Vase, Dead Toy, Candle, and Skull in Renaissance Style.”

Image courtesy of Midjourney

Source: Image courtesy of Medjourney

Mystery often fuels the power of the artwork, forcing viewers to consider what it might mean. This fuzziness is a strength of the AI-generated art, which doesn’t have to worry about accuracy in the way that is necessary for an autonomous car to recognize children playing in the street. There is no correct answer in art.

Most theories creativity They include divergent and convergent thinking (Cortes et al., 2019). Divergent thinking involves coming up with many possibilities. When faced with a problem that needs a creative solution, generating many possibilities does not mean that they are the best or the best.

The evaluation phase then narrows the possibilities, and approaches a solution to identify a useful path forward. Artists are meant to go back and forth between disparate and convergent processes as they work towards their final product.

Artists can easily use AI as a tool (Kim, 2022)Where artists used the technology of their time (Hockney, 2001). They can write their intent for the image and then rate the created images. They may choose any of several images that are closest to their intent, expand their own perceptions, and select or modify them. The generative phase of creativity will be guided by artificial intelligence; The artist’s role is to select the input text and then evaluate the output of the final image.

chat

If AI-generated imagery can be used as a tool to stimulate creativity in visual artists, can thinkers and writers use AI to generate and consider new ideas expressed in language? ChatGPT suggests that using AI to generate ideas is possible. ChatGPT is an advanced AI language processing model that has just been released by OpenAI for public use. Generates humanoid text in response to queries. The model was trained using text databases of 570 GB of data obtained from books, web scripts, Wikipedia, articles and other texts written on the Internet.

For example when asking the following question:

In 500 words, speculate about the future role of artificial intelligence in art generation.

I received a response in less than a minute that was eerily similar to my last peer-reviewed paper (Chatterjee, 2022), which took over three months from application to acceptance. As you did, ChatGPT’s response also predicted a fully independent AI art maker. ChatGPT replied:

The future role of AI in generating art is a ripe topic for speculation. It is clear that artificial intelligence has the potential to revolutionize the way art is created and that it can open up new horizons for artistic expression.

One possible future scenario is that AI will become a tool that artists use to create new works of art. For example, an artist might use artificial intelligence software to create a rough draft of a painting, which they can then refine and perfect using their own skills and creativity. This may allow artists to experiment with new styles and techniques and create art that would be impossible for a human being to create alone.

Another possibility is that the AI ​​will become a fully independent art creator capable of creating original artwork without human intervention. This will require developing AI systems that have a deep understanding of the principles of art and can use this knowledge to create aesthetically pleasing works of art. These AI systems will potentially be able to generate a wide variety of art, from traditional paintings and sculptures to more experimental art forms, such as installations and digital art.

Either way, the integration of AI into the art world is likely to have a profound impact on how art is created and experienced. It could lead to the creation of new forms of art that blend the best of human creativity with the power of artificial intelligence and could change the way we think about what it means to be an artist. Ultimately, the future of AI in art is exciting and unpredictable, and it will be fascinating to see how it develops in the coming years.

conclusion

As AI continues to learn about itself in most parts of our lives, it will do so with art and perhaps literature. The art production tips and writing samples from the AI ​​may now be like the video game Pong that was popular when I was in high school. Pong is a far cry from the rich, immersive quality of games like Minecraft in the same way Dall-E and Midjourney’s visuals and ChatGPT’s verbiage may be a far cry from a future “educated” machine.

The idea that creative endeavors are a bulwark of humanity is untenable. For many people, AI will be a powerful tool and partner in creativity, especially when there is no “right” answer. Aesthetically sensitive machines will challenge our views of beauty, creativity, and perhaps our understanding of the nature of art.

#bots #coming #bots #coming

Leave a Comment

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