No, A.I. won’t be replacing your job any time soon

The power of ChatGPT (Microsoft) and Bard (Google) cannot be understated. They are immensely powerful tools that have literally changed the way we work and play. It’s difficult to imagine what things were like before.

But, if you believe everything you read in mainstream media, it won’t be long before people like us are out of a job. And while it’s unfortunately true that even at these early stages of A.I. advancement some jobs are already being replaced in specific industries (with mixed results), coders and other professions that require a high degree of creativity are far from being in danger of losing their jobs.

My rationale is simple: Even the most advanced A.I. systems, impressive as they may be, still lack the fundamental human qualities necessary for genuine creativity.

Emulating creativity presents an incredibly difficult challenge, given that it depends on a multitude of intricate factors such as experience, emotion, empathy, intuition, originality, imagination, cultural context, subjectivity, personal history, and countless others that escape me right now. Curious to know if ChatGPT was aware of its own limitations, I asked it and received this response:

Emotion and Empathy
Creativity often stems from a deep understanding of human emotions and experiences. Empathy, the ability to feel and relate to others' emotions, is crucial for creating emotionally resonant and empathetic content. AI lacks genuine emotional understanding and empathy.

Intuition
Creativity often involves relying on intuition and gut feelings to make decisions. AI operates based on data-driven algorithms and lacks the kind of intuitive decision-making that humans employ.

Imagination
Imagination is a fundamental aspect of creativity. It involves forming mental images of things that do not exist or have never been seen. AI generates responses based on patterns in existing data and doesn't possess the ability to imagine entirely novel concepts.

Originality
Creativity often revolves around generating novel and original ideas or solutions. AI can generate responses based on existing data, but it's not inherently capable of true originality.

Problem-Solving in Ambiguous Situations
Creativity often thrives in ambiguous or ill-defined problem situations. Humans excel at navigating ambiguity, making judgment calls, and thinking creatively to address complex, open-ended problems. AI struggles in such unstructured environments.

Cultural and Contextual Understanding
Creativity is deeply influenced by cultural, social, and historical context. Humans understand and draw upon these cultural nuances, whereas AI may lack the depth of understanding to create contextually relevant and culturally sensitive content.

Subjectivity
Creativity often involves subjective judgments, personal experiences, and individual perspectives. AI lacks the subjectivity that humans bring to creative endeavours.

Serendipity
Creative breakthroughs can often occur through chance discoveries or serendipitous moments. AI doesn't have the capacity for serendipity or accidental insights.

Narrative and Storytelling
Crafting compelling narratives and storytelling is a highly creative process. It requires an understanding of pacing, character development, and emotional resonance. AI can generate text but often lacks the depth and coherence required for rich storytelling.

Cross-Domain Thinking
Creative individuals often draw inspiration from diverse domains and disciplines. They connect seemingly unrelated ideas and concepts. AI operates within the constraints of its training data and may not naturally make these cross-domain connections.

Personal Motivation and Passion
Many creative endeavours are fuelled by personal motivation and passion. Humans are driven by their desires, interests, and a sense of purpose, which AI lacks.

In summary, AI tools lack the emotional depth, intuition, imagination, and the ability to navigate ambiguity and cultural context that are essential for genuine creativity. While AI can assist in creative tasks by providing suggestions and automating certain aspects, it still relies on the foundation of human creativity for its capabilities.

Bard gave a similar response, and ultimately we’re all in agreeance. Without these attributes the best A.I. can hope for is to emulate creativity, which I promise will be a far cry from the real thing.

Creativity In Action

I often cite what I believe to be the perfect encapsulation of this philosophy that anyone can understand. Let’s pretend you are David Fincher, director of The Social Network. You’ve finished the final edit of the movie and now turn your attention to making the trailer. It needs to be impactful and emotional.

In one scenario you turn to A.I. to suggest ideas, and it will return a few good ones that might work. Some might be very good.

In the other scenario, you put the task to creative humans and the result is this emotionally charged masterpiece:

What I aim to illustrate is the remarkable improbability, and perhaps even the impossibility, of any A.I. conceiving a concept as elegantly simple as this. The meticulous arrangement of social media screens interwoven with key moments in the movie, all set to the backdrop of a school choir performing Radiohead’s “Creep.”

Combining the profound emotional connection many people have with the particular song, its historical and cultural significance, its contrasting resonance with Mark Zuckerberg’s often-accused “creepiness,” and the sheer brilliance of the school choir’s performance. All of these elements are deeply rooted in human experiences and, in my view, place this concept far beyond the reach of any A.I.’s capacity, short of some magical fluke.

From a Programmers Perspective

For those who don’t spend their days coding, it’s easy to assume that programming is a purely mechanical task lacking any creativity. In reality this couldn’t be further from the truth. Just like any other discipline, there are times when the work may seem routine, but programming often demands imaginative thinking to tackle exceptionally complex problems. It’s these moments that keep me passionate about this field after more than 24 years.

A.I. tools have been invaluable in helping me resolve complex problems and solutions. However, they’ve also provided their fair share of comedic relief. Initially it was amusing to observe their responses to failure, with their apologies and attempts to rectify their mistakes, adopting a tone that almost attempts human behaviour.

Sometimes, especially with ChatGPT, I notice glaring flaws in the code they suggest. Rather than explicitly pointing out the issues, I might respond with a simple, “Are you sure about that?” The immediate response from the A.I. is an apology, followed by a correct (most of the time) response. It’s a bit of a mystery why they don’t get it right the first time, but this tendency to occasionally get it wrong the first time like we humans often do makes me wonder if it’s a learned behaviour.

All this underscores the role of A.I. to assist in accomplishing tasks, rather than doing all the work for you. Your expertise and experience remains paramount.

Novice or non-programmers aiming to leverage A.I. to bring their grand application ideas to reality will have an extremely difficult time.

However, if you’re an experienced programmer, you can instantly discern when the code it generates is suboptimal, unsuitable, erroneous, or completely nonsensical (I find it particularly amusing when it offers up some sort of hybrid JavaScript and PHP combination that it has ‘invented’). Your own knowledge and experience are ultimately what will lead you to completing your goal.

A (Human) Summary

In the grand scheme of things, A.I. is a permanent fixture in our future, and its capabilities will undoubtedly continue to improve over time. However, the absence of specific human attributes will impede its ability to attain genuine creativity, which is why those in creative professions will never need to worry about becoming redundant.

The true challenge lies in the hands of the engineers responsible for bringing A.I. to the mainstream public, who will be tasked with finding creative solutions to compensate for the obvious human deficiencies.

This is undoubtedly an even greater challenge than maintaining an L.L.M. or Generative A.I. But that’s a topic for another day.

More Articles