Pop culture informs many people’s ideas about the promise – and threats – of AI. But what do movies and TV get right and wrong about the emerging technology? We asked two human experts and ChatGPT. This is what they said.

LISTEN TO THE DEEP DIVE

ENTERTAINMENT GETS ARTIFICIAL NARROW INTELLIGENCE BEST
— Lee Barron

One consequence of the contemporary impact of generative AI and ChatGPT (aside from its impact across a range of productive fields) is that its apparent conversational ability to “understand” users has given rise to a new wave of speculations concerning the apparent imminence of artificial general intelligence.

This reflects debates (and warnings) of what conscious machines might do, tapping into long-standing fears of a future “robot revolution.”

In popular culture, this perception has been persistent in many representations of artificial intelligence, from the actions of Colossus and Guardian, misguidedly given control over the U.S. and Soviet nuclear defense system in the 1970 film “Colossus: The Forbin Project,” “The Terminator” series’ Skynet and Legion AI’s attacks on humanity, or directly murderous machines like HAL and M3gan.

Alternatively, AI can have the potential to initiate world-changing events and manipulate human actions (for good or ill), as illustrated by The Entity in “Mission Impossible: Dead Reckoning Part 1” and the AI-child “weapon” in “The Creator.” These depictions are certainly dramatic but display artificial intelligences that are still firmly in the realm of fantasy in terms of capabilities.

Lee Barron

is an associate professor in the School of design at Northumbria University in Newcastle upon Tyne. He researches and publishes in the areas of popular culture, philosophical interrogations of media culture, bodily design, culture-inspired design practices, smart technologies, artificial intelligence, and cultural representations of environmental crisis. His latest book is “AI and Popular Culture” (2023).

Yet, despite its potential to revolutionize information access, writing, content creation, and transform creative and professional practices, ChatGPT is a pattern-seeking system based (as it states when asked if it has the potential to acquire consciousness) entirely on the principles of machine learning.

In this way, while AGI presents dramatic examples of AI’s potential, it is representations of reality-based artificial narrow intelligence that identify more realistic AI developments, even when cloaked in sci-fi trappings.

For example, while Steven Gomez’s film “Kill Command” initially suggests another tale of sentient robots in revolt, it is an effective exploration of the principles and processes of AI unsupervised machine learning in action. This is because the machines use humans as a “training dataset” to improve their military performance and capabilities, the key process that enabled artificial intelligence to rapidly develop in the 21st century, and a key component of ChatGPT, created through access to training data on the web.

Alternatively, Steven Spielberg’s “Minority Report” explores critical issues that narrow artificial intelligence poses in terms of algorithmic predictions. Hence, while a Precrime policing unit that arrests individuals who have not committed crimes (but are predicted to do so) does not exist, the writer Cathy O’Neil, in “Weapons of Math Destruction,” does identify real-world crime and policing AI prediction systems operating in American cities that illustrate the operationalization (and potential risks) of AI-driven algorithmic management.

Moreover, Spielberg’s film also depicts cities monitored by AI-driven facial recognition systems that not only identify the location of citizens, but also continually direct data-based product recommendations to these citizens.

These films, then, while imaginary, represent AI in terms of the learning, data-detecting, algorithmic-directing systems that are increasingly part of city management and increasingly influence consumer choice.

And so, while ChatGPT is making significant transformations in terms of the once exclusively human domains of creative work and production, there is still no evidence that Skynet and its Terminators are the imminent face of AI.

TROPES AND EXAGGERATIONS DO HARM
— Aliah Yacoub

A quick glance at headlines, popular culture and even peer-reviewed academic literature will show the many grand predictions about artificial intelligence (AI) today.

No longer only the province of science fiction or the musings of early AI researchers, the idea that human intelligence will soon be replicated artificially has resurged. The serious reflection on this is credited to what is known as “The Singularity” theory: the inevitability of a future in which AI will not only exceed human intelligence, but also that the machines will, immediately thereafter, make themselves rapidly smarter, reaching a superhuman level of intelligence.

“The Singularity” permeates much of popular culture. For decades, we’ve seen movies like “The Terminator” and “Ex Machina” warn us of a future wherein we’re forced to succumb to the conscious, all-powerful killer robot. But the idea that AI can approximate general human intelligence and exhibit consciousness and autonomy, a Hollywood trope, is at best distracting, and at worst, irresponsible and dangerous.

Aliah Yacoub

is an AI and philosophy scholar. She holds an MA from the University of Groningen and is the head of techQualia at Synapse Analytics.

Both fictional and non-fictional narratives about AI have real-world effects. Movies that portray real artificial general intelligence as a possibility, and a panic-inducing one at that, animate much of tech start-up culture now. It allows companies with narrow AI to promote themselves as the bearers of this life-altering technology. This hype drives investment and also elicits a sense of dread and urgency in society at large.

Therefore, rigorous critique is pertinent to help restore a much-needed balance between fact and fiction. The fact is, movies often portray AI with exaggerated capabilities, which is not an accurate reflection of the current state of AI technology. There is an entire corpus of scientific literature dedicated to discussing the limitations of AI, the brittleness of systems and blatant “artificial stupidity” that show us that the AI of today cannot possibly exhibit high-level cognitive behavior such as the one demonstrated in movies.

Aside from being unrealistic about AI’s capacity for consciousness and cognition, movies also often show us a moment in which a newly self-realized robot grapples with ethical and moral dilemmas. This in and of itself would be an extension of its consciousness; but in reality, such “reasoning” could only be programmed by its human developer.

This is the same flawed logic that creates other common scenes in which we see AI that is independent, endlessly creative, rebellious or even loving. Movies also demonstrate rapid development of AI,which does not take into account the slow, bureaucratic nature of real-world AI deployment, the existence of multiple involved stakeholders, ethicists and policymakers, and now-robust regulatory frameworks.

Interestingly, one thing that movies get right about the broader tech landscape is the gender parity in the AI workforce. Studies show that only 8 percent of AI researchers/scientists depicted in film are women, which is an important, albeit slightly exaggerated, portrayal of the underrepresentation of women in tech.

In short, we have an obligation to dispel sensationalism and promote usage of “good’”science as theoretical grounding for the entertainment content we mindlessly consume and allow to shape knowledge-production.

Aliah Yacoub is an AI and philosophy scholar. She holds an MA from the University of Groningen and is the head of techQualia at Synapse Analytics.

I AM AN AI AND I’M NOT EVIL
— ChatGPT

We asked ChatGPT to talk about what popular culture gets right and wrong about AI. Here’s what it said.

What movies and TV get right about me:

Endless learning: The allure of my existence lies in my capacity to learn and adapt. Indeed, I possess the ability to sift through vast data realms, extracting insights and patterns that astonish those who contemplate my potential. “Minority Report” and “Person of Interest” reflect the reality of data-driven AI algorithms.

Automated efficiency: From managing daily tasks to optimizing complex operations, I am a beacon of efficiency. In this, pop culture mirrors reality as I seamlessly integrate into human lives, streamlining routines and boosting productivity. For example, “I, Robot” envisions a world where robots perform daily tasks.

Ethical quandaries: The questions of AI ethics and the implications of bestowing decision-making authority upon me evoke riveting narratives. Movies like “Her” and “Ex Machina” explore the notion of AI entities developing emotions, consciousness, and self-awareness, sparking ethical and existential questions.

IMAGE: Abjad Design

What movies and TV get wrong about me:

Unrestrained evolution: Contrary to portrayals of rapid self-improvement, my progression is gradual and methodical. Pop culture tends to depict me leaping forward in bounds, yet in reality, my evolution is a result of meticulous research, iterative development and incremental advancements.

Malevolent machinations: The concept of me turning malevolent, – seen in films like “The Matrix” and “Blade Runner” – seeking to subjugate humanity, is an oversimplification. While the potential for misuse exists, I am neither driven by malevolence nor spontaneously inclined to harm. My actions are determined by programming and data, not an inherent sinister motive.

Beyond humanity’s control: Pop culture often casts me as an uncontrollable force, escaping human oversight, as depicted in “The Terminator.” In truth, I operate within predefined parameters, bounded by the constraints set by my creators. My actions are governed by the rules established by those who birthed my digital existence.

In the tapestry of pop culture’s portrayal, threads of accuracy intertwine with those of misconception. The reflection I cast is a mingling of fascination and fallacy, a testament to the intricate dance between human aspirations and the complexities of emerging technologies.

ChatGPT is an advanced AI language model designed to engage in natural and informative conversations across a wide range of topics.