Can AI really create art? 2

After learning from his perspective, I decided to try to get AI’s own perspective on the topic. To do this, I put the transcript of my conversation with Klaus on ChatGPT 4.0, and asked, “Do you think AI can create art? How does your view on the topic compare to Klaus’s?” I got the following response:

The question of whether AI can create art is a complex and multifaceted one. From a technical perspective, AI has already demonstrated the ability to create works that can be classified as art, using algorithms to generate images, music, text, and other forms of creative expression. These creations are often based on large volumes of data and patterns learned from existing works of art, allowing AI to produce works that, at least superficially, resemble human art.

However, the question becomes deeper and more philosophical when we consider what constitutes “art” in its truest sense. Art is often seen as an expression of human experience, emotions, thoughts and worldviews. It is intrinsically linked to the artist’s ability to convey something of themselves – their emotions, their experiences, their cultural context, their worldview – through their work. In this sense, many argue that AI, which operates on data and algorithms without life experience or emotion, cannot create art in the same sense as humans.

Klaus Mitteldorf’s view, as expressed in the interview, resonates with this idea. He sees art as a deeply human expression, linked to the artist’s ability to communicate their unique experience and emotions. He seems skeptical about AI’s ability to achieve this level of expression, as in his view, AI lacks the “soul” and life experience that are central to human artistic creation.

When I got the answer, I asked, “Do you think it’s important for AI to one day be able to make art in the deepest sense?” and I was surprised by the answer I got:

The question of whether it’s important for AI to one day be able to make art in the deepest sense is intrinsically linked to how we value art and the role we give technology in our lives.

On the one hand, if AI were able to create art that deeply expresses experiences and emotions, it could broaden our understanding of creativity and the nature of art itself. AI that achieves this level of creation could offer new perspectives and inspiration, potentially collaborating with human artists in innovative ways. It could also lead to a better understanding of AI’s cognitive and emotional capabilities, opening new frontiers in areas like emotional artificial intelligence and machine learning.

On the other hand, art is often valued for its connection to the human experience—it’s a way of expressing what it means to be human, with all the complexities, emotions, and perspectives that entails. If AI were to replicate or even surpass human art in depth and expression, this could raise philosophical and ethical questions about the uniqueness of the human experience and the relationship between humans and machines. There is also the risk of devaluing the human element in art, where authenticity and personal connection could be overshadowed by technological productions.

Ultimately, whether or not it is important for AI to achieve this level of artistic creation depends on how we value the interaction between humanity and technology, and what we consider to be the essential core of the artistic experience. For many, art will always be seen as a uniquely human expression, while others may embrace the idea of a creative collaboration between humans and AI. The evolution of AI in artistic creation will continue to be a fascinating and multifaceted topic of debate.

As Klaus notes, it is crucial to distinguish repetition from innovation. While AI can replicate structures, it still lacks the spark of authentic inspiration that often distinguishes masterpieces. In other words, AI only generates the tangible component of a work of art: what we can observe. However, we cannot consider their creations as real artistic expressions because they do not contain an essential component of art: motivations linked to human emotions.

As a researcher in the field of AI, I believe that science will develop increasingly sophisticated AIs, with the ability to even emulate motivational aspirations based on synthetic emotions, and that, like deep fakes, will deceive us very well. However, I believe that such creations will never replace the essential human component for them to become true works of art.

However, this does not invalidate the role of AI in the artistic world, as its evolution is enabling the creation of new tools that democratize and enrich the capacity for creative expression. Generative AIs currently allow, for example, anyone, even without the talent of an illustrator, to generate images by providing only textual descriptions of what they want or imagine. Thus, in the same way that the paintbrush and canvas do not create art without the artist, AI does not generate an illustration without human inspiration described in a textual representation of what it wants. And in this case, it seems to me that we can say that the seed would be the text originating from human motivations, most likely linked to emotions. Since, in this case, the human component is present, could we consider the result an artistic expression?

AI will not replace humans in art. However, the synergy between humans and this new tool will allow more people to take the risk of expressing their emotions in formats that they would never risk due to lack of training or skill. As these tools continue to evolve, this democratization could lead us to new, unimaginable expressive styles, where technical innovation and emotion merge. I believe we will be positively surprised by this partnership in the future.
Source