An AI Article Not Really About AI
“You’re soaking in it.” That’s the sense THE innovation conversation of 2023 gives me about AI (aka generative computing, machine/deep learning, LLMs, et al). It’s everywhere. The topic of seemingly every current and upcoming tech conference panel? Yes. In daily headlines and non-stop LinkedIn comments? Sure. Core to every pitch deck presently? Of course. Heck, AI will probably be the rage at non-tech trade shows soon enough (Coat Hanger Innovation Summit ‘23 anyone?), and kindergarten kids will declare wanting to be prompt engineers when they grow up.
If you listen to the conversations, AI promises a new age that will disrupt our lives in ways we are only beginning to fathom, with impacts beyond the public’s initial forays into ChatGPT-powered term papers and other outputs from its rivals and relatives. Whether this new age is one of machine-driven empowerment and progress, one where dystopian fears are realized and truths are eroded, or some combination thereof is now speculated upon widely and loudly.
What’s struck me as much as the predictive scenarios and prospective use cases for AI is the pace at which it and its disruptive potential has entered the zeitgeist. It feels as if this has mainstreamed faster than any prior innovation, including the Internet. It’s one thing to observe folk in the tech world ret-con their creds (and keywords) to claim long-held expertise in and intent to incorporate AI into their platforms, but when late-night talk shows center bits around the technology, elderly, tech-averse relatives speak knowingly of the topic, students come home counseled about ChatGPT and academic integrity, and .ai domains proliferate, we’re seemingly up (or down) whatever curve consultants use to describe their innovation frameworks. Kudos to AI’s PR lobby.
We Believe
How is it that we have so quickly accepted an AI-infused future as a fait accompli? Recall that past disruptive technologies and services – such as the Web, mobile, e-commerce, and social media – certainly had their boosters and made news about their impact potential when they emerged, but the foreboding sense of how each would profoundly change our personal and professional lives simply wasn’t omnipresent. Instead, prior innovations needed to prove their transformative effects. This required some mix of accomplishments, including but not limited to HW/SW innovation and evolution, infrastructure deployment, acquisition of trust, and user scaling to achieve network effects.
As with many technologies that seem to suddenly break through in the public consciousness, foundational work on AI has been underway for decades. Still, AI in all its flavors is still quite early in its mass commercialization. In Internet-equivalent evolutionary time, we are perhaps at the stage when one would be using an NCSA Mosaic browser on a 9600 baud dial-up modem and wait hours to download a Quicktime movie trailer. Sure, it was very cool for its time, but not a capability set that was widely recognized for its game-changing potential. Yet AI is already heralded as the catalyst for a new age.
On the surface this is understandable. Today’s AI engines are accessible to the masses and produce highly demonstrable and, equally important, relatable deliverables. Via our phone or laptop, we can readily generate that term paper (though we shouldn’t), home repair instructions, or an article like this [ed. note: no Large Language Models were harmed in the making of this essay]. We can use a few words to prompt images like the ones in this article or generate almost-Hollywood-level VFX for our media creations. And we are entertained by “new” works emulating our favorite musicians, leaving labels and lawyers grappling with a new era of sampling and copyright challenges. For some, AI is already touching their lives directly in more profound ways, as AI models drawing upon massive data sets diagnose otherwise missed cancers and guide physicians’ treatment options toward improved efficacy and away from unnecessary therapies.
Further, these AI use cases are enabled by and benefit greatly from prior waves of disruption – such as the Web, mobile, and distributed compute and social communications infrastructures. These technologies enable the amplification of AI, fueling its mainstreaming by disseminating the news, hype, and speculation about our AI future instantly to all corners of the globe. In ways unmatched by the announcements of earlier developments, a crescendo of all things AI dominates our screens.
That may explain our mass awareness, but what’s to account for our forgone conclusion about AI’s coming transformative impact? Surely we must have a reason to believe it will be more than ChatGPT-powered scripts and faux-Oasis tracks. I believe we do, and it's simply this: we have normalized disruption. It starts with our technology experiences of the past few decades. After experiencing how the Web, mobile, et al have transformed so many aspects of our lives, they have seasoned us to expect disruption and step-level evolution. Whether we are old enough to remember payphones or have been born into the age of screens and instant everything, when it comes to technology, we have become conditioned to believe.
Life, Interrupted
Recent, non-technological disruptions have also contributed to our acclimation, demonstrating that change is not only possible, but it can be fast, massive, and tremendously impactful on our daily lives. Today’s politics of course, whatever your beliefs, have brought to the fore stresses and divisions at levels never before felt so strongly or amplified and perpetuated so greatly. While one can readily make the case that these realities have always been present in the fabric of America, it’s hard to deny that the disruption brought about by Trump’s election was stark and impactful and entirely unexpected as the outcome of a Presidential election. No longer.
Above all though is COVID. The pandemic was and remains the uber-disruptor on every level of society, a wave that crashed upon each of us directly, laying bare the precariousness of our norms. More than anything it shook our perception of society, safety, and our future in ways with which we are still grappling. In our (barely) post-pandemic state, we have come to understand and expect that disruption is to be expected and its impacts can be immense and potentially permanent, whether we’re speaking of the shift to remote work, an erosion of trust in assumed “solids” such as science and supply chains, or an overall instillment of fear in the new and unknown.
Accept The Unexpected
Today, whether we’ve seen a wave or three of disruption break upon our shores, or have only lived through the world-shaking events of recent years, I suggest that we have come to internalize an understanding that in our connected world, every successive disruption – technological, political, medical or otherwise – holds the potential to more greatly, strongly, and quickly flip our scripts and change our lives.
Through this lens, I can better understand why we are so bullish on AI and have essentially priced its proliferation into our societal P&L. It’s a broad set of disruptive technologies. They appear to work. We expect they will only get better as we have seen with other technologies. And we are now freshly conditioned to expect their disruption to be massive, if unpredictable.