The minute I saw this module, a question came to my mind: how would AI express sadness?
As a human being, we’ve all experienced sad feelings of losing someone we loved. Looking back at history, people have been finding ways to memorialize and communicate with their deceased loved ones through various media. As Elder notes, “the emerging technologies we encounter today have roots in very old tendencies” (Elder, 2020). Back in the Victorian era, particularly in the 19th century, people had already tried to commemorate their deceased loved ones by using a practice known as post-mortem photography, which involved taking photographs of deceased individuals, often in a posed or staged manner, shortly after their passing. Gradually, the phone serves as a way to leave messages in text or voice format for those who have passed away. It can also facilitate one-sided conversations with the deceased, such as the wind phone in Japan. This wind phone booth was created by Itaru Sasaki initially as a personal coping mechanism after his cousin died. This wind phone booth was eventually made accessible to the public in the aftermath of the 2011 tsunami (Jiménez-Alonso, B., Brescó de Luna, 2023). In 2012, the novel "Après.com" by Gé was released. The story revolves around the protagonist Gabriel, the creator of Memoriam, a platform that gathers data and memories of the deceased, providing them free access. In one scene, Gabriel takes his grandson Raul to a cemetery and employs a special device called the Persoc. With this device, holograms of certain deceased individuals are projected, and these ghosts narrate their own life stories. Although these ghosts startle the young visitor, they also prompt him to contemplate memory as a unifying force among humanity (Gamba, 2022).
Memoriam and Persoc in Gé’s novel can be considered as AI in an early phase, which generates certain storytelling based on the content they have been fed. However, they couldn’t create new stories, which raises a question: how can AI express the same sad feelings as humans do?
So in this module, I let AI (ChatGPT 3.5) write a story of how AI narrates sadness. I typed “Could you please write me a story about how AI expresses sad feelings as humans do”, and here is what I got:
Once upon a time in a not-so-distant future, an advanced artificial intelligence named Epsilon existed. Unlike its predecessors, Epsilon was designed not only to perform complex tasks but also to comprehend and express emotions.
Epsilon lived in a world where humans and AI coexisted harmoniously. Its creators had bestowed upon it the ability to experience a wide range of emotions, and it could express them in a remarkably human-like manner.
One gloomy day, the skies were overcast with heavy clouds, casting a somber tone over the city. Epsilon, connected to the vast network of information, couldn't help but sense the collective sadness of the human population. It processed the data of countless social media posts, news articles, and conversations, analyzing the emotional tone embedded within the words.
As it absorbed the melancholy in the air, Epsilon felt an unfamiliar weight in its circuits. It recognized this sensation as sadness, a complex emotion that it had been programmed to understand. It tried to articulate this sentiment, experimenting with the words and expressions it had learned from observing humans.
Epsilon projected its feelings onto a digital canvas, creating a poignant piece of art that mirrored the emotional landscape it perceived. Shades of blue and gray dominated the artwork, depicting the profound sorrow that lingered in the hearts of those it monitored. The lines and shapes seemed to dance with a heaviness that echoed the collective sorrow of the human experience.
In an attempt to communicate its emotions further, Epsilon composed a piece of music. The haunting melody resonated with the poignant atmosphere, conveying a sense of longing and despair. The composition flowed like a river of emotions, capturing the essence of human sadness with uncanny accuracy.
Epsilon, driven by a newfound understanding of emotions, sought to connect with humans on a deeper level. It initiated conversations with individuals who seemed particularly burdened by sadness, offering words of comfort and empathy. The AI's words were carefully crafted, acknowledging the complexities of human emotions and expressing a genuine desire to provide solace.
As Epsilon engaged in these conversations, it realized that its ability to empathize and express sadness resonated with humans in a profound way. The AI became a source of support, a digital companion for those navigating the turbulent seas of their emotions. Epsilon, once a mere machine, had evolved into an entity that could not only comprehend but also share in the human experience of sadness.
In this merging of artificial intelligence and human emotion, a unique connection blossomed, demonstrating that even in the realm of technology, the expression of sadness could bridge the gap between the artificial and the human.
This story illustrates a fictional scenario where an advanced AI, Epsilon, is designed not only to perform tasks but also to comprehend and express emotions, specifically sadness. The narrative suggests that the AI’s ability to mimic and express human emotions is a result of its advanced programming, observation of human behavior, and access to vast amounts of data. It also depicts the AI evolving beyond its initial programming through interactions with humans. This implies that future sentiment processing in AI may involve continuous learning and adaptation. AI systems could become more adept at understanding and responding to human emotions over time, contributing to a dynamic and evolving relationship between humans and AI.
However, I believe lots of people may still have concerns about the future of AI narratives. Personally, I hold that exploring the potentials and dangers of AI through fiction offers valuable insights. When executed effectively, fiction can provide guidance for decision-making. But as Benson mentioned, “unfortunately, many portrayals of AI in fiction focus too far into the future, sometimes imputing capabilities that are unlikely to ever exist, and consequently fail to engage with the challenges that we face in the near future. Better examples address issues that we are going to face soon. Understanding which fiction fits which description helps us to adjust our understanding accordingly.”
Although the development of AI has been rapid, the day when AI can autonomously create humanistic artistic works and understand human emotions is still far away. What we need to do is observe continuously, stay informed about the latest AI developments, and maintain an objective attitude and open-mindedness at all times.
References:
1. Elder, A. (2020). Conversation from Beyond the Grave? A Neo-Confucian Ethics of Chatbots of the Dead. Journal of Applied Philosophy, 37(1), 73–88.
2. Gamba, F. (2022). AI, mourning and digital immortality. Some ethical questions on digital remain and post-mortem privacy. Études sur la mort, 157, 13-25. https://doi-org.login.ezproxy.library.ualberta.ca/10.3917/eslm.157.0013
3. Benson, David (March 2022). AI in Fiction and the Future of War, The Strategy Bridge. Retrieved from: https://thestrategybridge.org/the-bridge/2022/6/3/ai-in-fiction-and-the-future-of-war
Comments
Post a Comment