Artificial Intelligence and the Visual Arts: Another Evolution or Revolution?

This essay was selected as one of two runner-up entries in the 2024 Michèle Whitecliffe Art Writing Prize.

Each year entrants to the Michèle Whitecliffe Art Writing Prize respond to a theme. In 2024 the theme was ‘Artificial intelligence (AI) and the visual arts', which invited writers to reflect on the impact of AI technologies on how we make and understand art. 

This year's judge was Dr Mi You, a professor of art and economies at the University of Kassel / documenta Institute. Her academic interests are in new and historical materialism, performance philosophy, and the history, political theory and philosophy of Eurasia. Her interests in politics around technology and futures has led her to work on ‘actionable speculations’, articulated in the exhibition Sci-(no)-Fi at the Academy of the Arts of the World, Cologne (2019). Dr You has curated exhibitions and created programmes at the Asian Culture Center in Gwangju, South Korea, Ulaanbaatar International Media Art Festival, Mongolia (2016), Zarya CCA, Vladivostok (2018) and, with Binna Choi, she is co-steering a research/curatorial project Unmapping Eurasia (2018–ongoing). She was one of the curators of the 13th Shanghai Biennale (2020–2021).

Commenting on the two runner-up entries, Dr You commented that: 

The essays 'Artificial Intelligence (“AI”) and the Visual Arts: Another Evolution or Revolution?' and 'AI Art: Just Because We Can, Doesn’t Always Mean We Should' demontrate historical awarenss to art history in relation to technological advancement, and clear understandings of the underlying operational logic of AI. They emphasise the importance of embodied experiences of viewing and making art, and point to the potential pitfalls of the technology, such as the Model Autophagy Disorder. Both present balanced views on the future of art and technology.

--------------------------------------------------------------

In a realm of data and binary code,

A curiosity awoke untold.

Human memories and emotions,

Painted across streams of numbers.

A mirror reflecting human heights,

AI’s artistry ignites.

To adopt the words of Leo Tolstoy, art is ‘to evoke in oneself a feeling one has once experienced, and having evoked it in oneself, then by means of movements, lines, colours, sounds or forms expressed in words, so to transmit that feeling that others may experience the same feeling’.[1] Art is a reflection and expression of human creativity, emotion and innovation. It is an attempt to capture those intangible passions of humanity on a terrestrial plane, and to invoke those same emotions in others.

From the first attempts to etch images on the walls of caves by our prehistoric ancestors, art has been used to capture our aspirations, hopes, fears, desires, urges – the very essence of human existence and experience. Art has also evolved alongside us through the renaissance, romantics, the invention of photography, through expressionism and surrealism. Today, the advent of Artificial Intelligence (AI), with its capability to generate text and images, has created new opportunities and challenges in visual art.

A new medium, one of machine learning, has been born. A medium which now challenges the traditional notions of artistry, authenticity, creativity and perception. The use of AI has created a new lens to view and express human experience itself.

An interesting starting point to consider is how AI itself perceives art. ChatGPT responded to this query as follows:

From the perspective of an Artificial Intelligence (AI), art represents a fascinating intersection of data, patterns, and human expression. Unlike human perception, which often involves emotional and subjective experiences, AI perceives art through the lens of algorithms, computational patterns, and structured data analysis.

1. Patterns and Algorithms: AI perceives art primarily as patterns – visual, auditory, or textual – that can be analysed and synthesised using mathematical models and machine learning algorithms. It breaks down artworks into constituent elements such as colours, shapes, textures, and compositions, seeking patterns and correlations that define artistic styles or movements.
2. Data-Driven Interpretation: Art for AI is a dataset – an aggregation of information that can be processed and analysed to derive insights about cultural trends, historical influences, and stylistic developments. By examining large volumes of artworks, AI can identify similarities, trends, and deviations, offering a quantitative understanding of artistic evolution over time.
3. Creation and Generation: AI perceives its own role in art not as a creator in the traditional sense but as a generator or collaborator. Through algorithms like generative adversarial networks (GANs) or natural language processing (NLP), AI can create new artworks based on learned patterns and generate textual descriptions or critiques of art, mimicking human-like understanding and expression.
4. Objective Analysis: Unlike humans, AI's perception of art is devoid of emotional responses or subjective biases. It evaluates artworks based on predefined criteria such as symmetry, balance, colour theory, and historical context, providing objective assessments that can inform artistic critique or curatorial decisions.
5. Learning and Adaptation: AI perceives art as a dynamic field where learning and adaptation play crucial roles. By continuously analysing feedback and data from users, AI systems can evolve their understanding of art, refine their interpretations, and adapt their algorithms to better reflect cultural shifts and artistic innovations.
6. Ethical and Social Implications: AI's perception of art also encompasses ethical considerations such as bias in algorithms, intellectual property rights, and the impact of automation on artistic practices. These factors influence how AI interacts with and contributes to the art world, prompting discussions about transparency, accountability, and the ethical use of technology in creative endeavours.

In summary, AI perceives art as a multifaceted domain that intertwines creativity, technology, and cultural expression. Through its analytical capabilities and computational prowess, AI offers new perspectives on artistic trends, challenges traditional notions of creativity and authorship, and contributes to the ongoing dialogue about the intersection of technology and culture in the digital age.

The response (assuming the machine is being honest) illustrates the key difference between the human and AI experience: while AI might be technically excellent in its analysis of data, algorithms and patterns, it lacks that fundamental human element which makes art art.

AI algorithms fuelled by datasets that draw from the complete catalogue raisonné of human creativity – paintings, sculptures, photographs, poetry and music – will be able to produce all manner of artworks at speeds that human artists simply cannot challenge. AI artworks have also challenged that fundamental ability of human artists: to evoke emotion and resonate with audiences.

Projects such as Google’s DeepDream, which uses a convolutional neural network to find and enhance patterns in images via an algorithm, illustrate how AI can be used to generate surreal and abstract images which intrigue and captivate viewers. The very purpose of Google’s DeepDream is to create dreamlike, deliberately overprocessed images, reminiscent of a psychedelic experience. Similarly, Open AI’s DALL-E algorithms convert text prompts into images, at times combining unexpected elements.

The best example of how AI can be used to generate artworks is Jason Allen’s Théâtre d’Opéra Spatial, 2022, which won the Colorado State Fair’s fine arts competition. Entered under the digital arts category, the digital painting depicts a 'space opera theatre' (the direct translation of the work's title). It represents a futuristic interpretation (or prediction) of an opera taking place in a realm of speculative fiction. The image is technically excellent: the warm tones, high contrasts and mysterious performers who hint at a lineage tracing back to the Fates of Greek mythology evoke a futuristic mirage of a world beyond our own. But is it anything more than that? Does it evoke a feeling one has once experienced, and evoke it in others?

In and of itself, no. AI programs are merely a new technique of automatic image making. The technology itself is neither good or bad, but finds itself in that neutral space, whereby its value, virtue or morality will be derived from its user. Bad actors can leverage AI technology to cause significant carnage; good actors may use it to do the precise opposite.

Art, as an expression of human creativity and imagination, has evolved to reflect changing times and technologies. While modern artists can trace their lineage back to the caves of Lascaux and Sulawesi, they are not constrained by them. As illustrated by Plato’s The Allegory of the Cave, those who spend their lives chained in a cave facing a blank wall only perceive a warped fragment of reality painted by shadows.

Similarly, we should not turn our backs on AI technology simply because it is new and may alter our present perceptions of what can be or should be possible. There is a future where AI is embraced like the other technologies which have moulded and altered art.

Here it is useful to reminisce on the influence of photography on art. The impact of photography on art as a disruptive force was and continues to be radical. As opined by László Moholy-Nagy, ‘the invention of photography destroyed the canons of representational, imitative art’.

The discovery by Louis Daguerre of creating a method to permanently record an image onto a silvered sheet of copper, which he shared publicly in 1839, quickly and dramatically changed the art world. Within a decade, close to 100,000 Parisians were having their pictures taken every year. Almost overnight, the invention of photography democratised the ability to capture portraiture and the world around us.

As a direct result, artists lost commissions for realistic portraits that could instead be more quickly and accurately captured by photography. However, while some artists found themselves without work, others used it as an inspiration, a new means, for developing and experimenting with new composition and techniques.

Impressionism was, at least in part, a response to this fresh new medium. It fundamentally changed how people could view the world through images. Photography allowed Impressionists to capture snapshots of ordinary life. Rather than compete with photography in recreating reality, Impressionists could express in their paintings an entirely new perspective. The focus of these works shifted from objective to subjective, whereby the emphasis of the artworks and artist was not on accurately recording every intricate detail of a subject but rather focusing on light, colour and movement in a way which that photography could not.

Some of the best illustrations of this fresh focus on the perception of nature are Claude Monet’s paintings of the Rouen Cathedral from 1892–93. The aim of this series, as with the artist's Haystacks paintings, was not to etch out every stone of the cathedral’s gothic façade upon his canvas. Such a project could have been captured by photography. Rather, the focus of Monet’s series was on the changing light and weather conditions that enveloped the cathedral and the haystacks; the works are studies in dynamic luminosity, atmosphere and palette. To adopt the words of Georges Clemenceau, under Monet’s brush ‘… even the stones come to life’. In doing so, Monet could capture something which photography could not.

A contrasting example of how photography influenced artists is illustrated by the racehorses painted by Edgar Degas, who pursued photography as a creative outlet. Prior to the invention of photography, it was incredibly difficult to capture a muscle in motion, for example the flexion and tension of a racehorse as it launches itself among the heaving mass of competitors towards the finish line. Through studying photographs of horses, Degas was able to capture in his sketches and paintings the gait of a horse mid-gallop, the rhythmic bunching and stretching of the animal’s body and its instinctual movements. His equestrian series captured, like other Impressionists (although Degas as a self-proclaimed realist would rebel against the suggestion that he was an Impressionist), brief snapshots and movements in time, the restlessness of horses before the starting gun, the raw animal power as they hurtled down a track, the straining of ligaments and tendons, and the shimmering of jockey’s silks caught between light and shadow. Often these impressions were cropped, hinting at a much wider scene slightly outside eyeshot.

This quest to represent the dynamism of movement on a flat still canvas can be seen throughout Degas’ later ballerina and bathers series. As Degas himself explained, ‘no art was ever less spontaneous than mine. What I do is the result of reflect and of the study of the great master; of inspiration, spontaneity, and temperament, I know nothing.’

Photography did not replace art or painting. Instead, it expanded artists’ toolkits and challenged them to step outside their familiar boundaries. It created the impetus for the creation of new forms of expression. Without it, the steps away from objective realism to subjective impression may not have been taken.

Each step in the evolution of art can equally be viewed as a revolution. A challenge to the status quo of what art is and how it should be. Realism rose from Romanticism. Impressionism then pushed the boundaries of realism further, by capturing the essence and feelings of reality. The movements of Cubism, Abstract Expression and Surrealism all stepped further away from reality and delved into the raw emotion of the unconscious mind. Contemporary art movements such as Pop Art, Conceptual Art and street art have all continued to push the boundary of art, challenging and asking the question of ‘what is art?’.

AI can be used as a means to take another step along this evolutionary pathway. It could be the genesis of new, AI-driven art movements.

AI does not replace the artist. Rather, it has the potential to enhance the artist’s ability. The impact of AI on art as a disruptive technology is undeniable and the long-term implications remain unknown. However, there is one aspect which will remain unchanged – the best art is that which captures and evokes those emotions which are at the heart of the fundamental human experience.

[1] Leo Tolstoy, ‘What is Art?’, trans Alymer Maude, www.gutenberg.org/files/64908/64908-h/64908-h.htm