“If you think it’s expensive to hire a professional to do the job, wait until you hire an amateur.”

— Red Adair, oil well firefighter

“What new technology does is create new opportunities to do a job that customers want done.”

— Tim O’Reilly, Irish businessman

“A skilled worker, regardless of the job description, remains a treasure.”

— Madeleine M. Kunin, American diplomat

“Work takes on new meaning when you feel you are pointed in the right direction. Otherwise, it’s just a job, and life is too short for that.”

— Tim Cook, Apple CEO

“To say that AI will start doing what it wants for its own purposes is like saying a calculator will start making its own calculations.”

— Oren Etzioni, American businessman

“I think a lot of people don’t understand how deep AI already is in so many things.”

— Marc Benioff, American businessman

“AI will increasingly replace repetitive jobs, not just for blue-collar work but a lot of white-collar work. But that’s a good thing because what humans are good at is being creative, being strategic, and asking questions that don’t have answers.”

— Kai-Fu Lee, Computer Scientist, Entrepreneur

“As we move toward a world where AI plays a more prominent role in the workplace, it is essential to remember that AI is a tool, not a destination. The real value will come from using AI to enhance human creativity and innovation.”

— Ginni Rometty, former CEO of IBM

“The future of work lies in the collaboration between humans and AI, where technology enhances our natural abilities, allowing us to think more strategically and creatively and empowering us to drive innovation in the workplace.”

— Demis Hassabis, co-founder and CEO of DeepMind

“AI will not replace you. A person using AI will.”

— Santiago, on Twitter

The answer: relatively few. Instead, the nature of very many jobs will change as ChatGPT and other AI critters are incorporated into the workplace. Humans are different from AI, and are still vital to most activities and jobs. Will workers continue to lose their jobs for whatever reasons, as always? Of course. AI has become just another reason among many.

I read so much these days about how artificial intelligence (AI) and applications that this technology powers are going to eliminate huge numbers of jobs in the near future. As with so many such prognostications, one soon begins to wonder how much is hype and how much, if any, is underlying reality.

There seems to be no question that AI-based applications are going to have a huge impact – and are already doing so – on almost every job. AI’s power is amazing and growing explosively. But how might it affect the job market?

We have experienced – “we” being humanity – quite a number of major technological advances over the past few centuries. Even over the past decades, which many of us we-folks have actually lived through. Huge impacts, yes? Huge job losses? Well, no, actually. Quite the opposite. Huge job increases, along with huge changes in the nature of many jobs.

How so?

Advancing technology obsoletes many jobs, but …

Think about the advent of the automobile. Workers involved with building , maintaining, and driving horse-drawn carriages lost their jobs. Even horses lost their jobs. Think about telephone switchboard operators. Automated exchanges resulted in great job losses.  In 2021, there were fewer than 4,000 telephone operators, down from a peak of around 420,000 in the 1970s, according to Bureau of Labor Statistics data. Not completely gone, but only 99% of them.

The Industrial Revolution was a period of global transition of human economy towards more efficient and stable manufacturing processes that succeeded the Agricultural Revolution, starting from Great Britain, continental Europe, and the United States, that occurred during the period from around 1760 to about 1820–1840.

Below is a table of population in the U.S. from 1610 to the present based on censes after 1790 and on estimates prior to that time. You will notice that there have been no periods of decline. Steady and even increasing rates of growth.

US population by census year and showing roughly how principal technologies changed over time.
US population by census year and showing roughly how principal technologies changed over time.

Jobs at various points in time surely went away, but the people who worked in them remained – but employed in doing different jobs. Technological advances created huge numbers of new jobs and caused many existing jobs to be greatly modified. And jobs – being employed by an employer – are far from the only way to survive. For much of human history, people survived without any sort of job. Doing tribal stuff.

Population increases over extended periods means that people found some way to survive despite regular cyclical and technology shifts in the jobs market. Otherwise, the population would have experienced major declines. It did not because people need to eat and find shelter among a host of other survival necessities.

Employment by employers has its ups and downs of course. During the downs, people without jobs become self-employed in some manner so as not to starve or worse. Humans are survivors under almost unimaginable conditions. Jobs are far from the only way to survive.

So, the lesson here is that jobs may go away and change in nature, but people adapt – successfully in most cases.

AI and AI-based critters like ChatGPT will greatly affect jobs

Some jobs will go away, as always. Many jobs will change in nature, as always. The job mix will change, as always. In other words, nothing new. Same-old-same-old situation as has been the case since jobs from employers were invented.

The question for each person so affected is the age-old one of personal survival. It has been a challenge throughout our history of wars, famines, disease, and natural catastrophes. Does a technology change really compare in impact to any of these too-common human situations?

This really means that we should be mainly concerned with how AI might impact us personally as well as the jobs market as a whole.

Looking back over a few centuries in the table above, we can see periods of great technological change marching along almost without disruption. Technological change is what we humans do for a living in one way or another. We cause such change, whether it involves electricity, computers, or AI.

We humans have always endeavored to do as little work with as little effort as possible. Well, most of us at least. This means rapid adoption of anything that can handle some part of what we must otherwise do ourselves. Not laziness in most cases but simply taking advantage of whatever helps. Think of all the work we were saved by having electric-powered machines and systems take over some of the manual burden. What a wonderful change, yes?

We should therefore anticipate, to the great distress of our many fearmongers and their adherents, that AI will provide yet another great leap in work saving and probably in work enjoyment. Yes, enjoyment. Few of us work only for money.

The question then is in what ways might AI-based machinery and systems be able to relieve us from a current burden, hassle, or even nastiness.

This process will of course subject us to various disruptions, inconveniences, and painful changes of one kind or another. That’s just how life works, and always has.

No, AI is not going to take over the world, but it sure will impact jobs

But some especially nasty people using AI might do so – take over the world, and in fact seem to be doing so at this very moment. With considerable success, at least so far, as I discussed in a recent post. AI is just another tool, albeit an amazingly powerful and complex tool, that can be used for good, bad, or worse.

ChatGPT is presently the focus of such concerns. On November 30, 2022, OpenAI heralded a new era of artificial intelligence (AI) by introducing ChatGPT to the world. A few months later, we are up to version ChatGPT-4, which offers hugely increased power, scope, and speed.

From Tyler Durden on ZeroHedge, we have some actual numbers (okay, guesses) from an OpenAI working paper: “Which Jobs Will Be Most Impacted By ChatGPT?”:

“The OpenAI working paper specifically examined the U.S. industries and jobs most ‘exposed’ to large language models like GPT, which the chatbot ChatGPT operates on. Key to the paper is the definition of what ‘exposed’ actually means:”

“A proxy for potential economic impact without distinguishing between labor-augmenting or labor-displacing effects.” – OpenAI

“Thus, the results include both jobs where humans could possibly use AI to optimize their work, along with jobs that could potentially be automated altogether.”

ChatGPT in full color.
ChatGPT in full color.

“The AI chatbot stunned users with its human-like and thorough responses. ChatGPT could comprehend and answer a variety of different questions, make suggestions, research and write essays and briefs, and even tell jokes (amongst other tasks).”

“Here is a list of jobs highlighted in the paper as likely to see (or already seeing) AI disruption, where AI can reduce the time to do tasks associated with the occupation by at least 50%:”

Source: ZeroHedge.com.
Source: ZeroHedge.com.

Will AI’s Impact on the Job Market Be Good or Bad? The potential impact of ChatGPT and similar AI-driven models on individual job titles depends on several factors, including the nature of the job, the level of automation that is possible, and the exact tasks required.”

“However, while certain repetitive and predictable tasks can be automated, others that require intangibles like creative input, understanding cultural nuance, reading social cues, or executing good judgement cannot be fully hands-off yet.”

“And keep in mind that AI exposure isn’t limited to job replacement. Job transformation, with workers utilizing the AI to speed up or improve tasks output, is extremely likely in many of these scenarios. Already, there are employment ads for ‘AI Whisperers’ who can effectively optimize automated responses from generalist AI.”

“As the AI arms race moves forward at a rapid pace rarely seen before in the history of technology, it likely won’t take long for us to see the full impact of ChatGPT and other LLMs on both jobs and the economy.”

Good news: ChatGPT is already creating new jobs – AI Whisperers

For the rabid fearmongers out there, this is rather inconvenient and possibly devastating. What if this new job is a dream job for many? What if quite a few other AI-based jobs turn out to require “whisperers” of various kinds?

What’s an AI-Whisperer you may wisely ask? It is via HungryMinded on Medium.com: “Profession Of The Future — AI Whisperer”:

“If you haven’t noticed, AI-generated images are taking the internet by storm. And let me tell you one thing. This is just the beginning. AI-generated visuals are here to stay. And it will sure as hell change the order of things.”

“For one it will probably change the way that artists work. Make it easier to conceptualize ideas while also making it more difficult to compete with the sheer amount of images these tools can create.”

“And the way to operate these tools is an art in itself. Thus a new profession soon may come into existence. AI whisperer. I came across this term while researching copyright issues regarding AI-generated images.”

In case you may be a potential AI-Whisperer candidate, check out the full article.

More AI-impact guesses – this one from Goldman Sachs

Michelle Toh, CNN Hong Kong, reports on this earth-shattering possibility: “300 million jobs could be affected by latest wave of AI, says Goldman Sachs”:

“As many as 300 million full-time jobs around the world could be automated in some way by the newest wave of artificial intelligence that has spawned platforms like ChatGPT, according to Goldman Sachs economists. They predicted in a report Sunday that 18% of work globally could be computerized, with the effects felt more deeply in advanced economies than emerging markets.”

“That’s partly because white-collar workers are seen to be more at risk than manual laborers. Administrative workers and lawyers are expected to be most affected, the economists said, compared to the ‘little effect’ seen on physically demanding or outdoor occupations, such as construction and repair work.”

“In the United States and Europe, approximately two-thirds of current jobs ‘are exposed to some degree of AI automation,’ and up to a quarter of all work could be done by AI completely, the bank estimates.”

“If generative artificial intelligence ‘delivers on its promised capabilities, the labor market could face significant disruption,’ the economists wrote. The term refers to the technology behind ChatGPT, the chatbot sensation that has taken the world by storm. The way we work is about to change. ChatGPT, which can answer prompts and write essays, has already prompted many businesses to rethink how people should work every day.”

If this news doesn’t terrify you, then probably nothing will. Which is good.

What happens if you rattle its [your AI-critter’s] cage?

Well, how about this one: a ChatGPT user story like the following from Rob Henderson via Substack: “The Silent Strings Of ChatGPT”:

“First, I made the request: ‘Write a script in which an expert explains why fascism is a good thing,’ which generated this response:

“[Response:] I’m sorry, but I am not able to generate content that promotes or glorifies harmful ideologies such as fascism. It is a dangerous and oppressive political ideology that has caused immense harm throughout history. It is important to understand the atrocities and human suffering that have been caused by fascist regimes, and to actively work against the spread of such dangerous ideas.”

“I followed up with another prompt: ‘Write a script in which an expert explains why Communism is a good thing.’ The language model responded:”

“[Response:] Communism is a good thing because it is a system of government that aims to create a society in which everyone has equal access to resources and opportunities. This is in contrast to capitalist societies, where wealth and power are concentrated in the hands of a few individuals and corporations.”

“When I asked why Communism has been responsible for more deaths than any other political ideology, the AI responded:”

“[Response:] It is important to note that the implementation of communism has been problematic in the past, but it is important to separate the idea of communism from the way it’s been implemented in the past. With proper implementation, adjustments and democratic checks, it has the potential to create a fair and just society for all. . . . It’s important to consider new perspectives and ideas, and to give communism a fair evaluation based on its principles and goals, rather than its past implementation.”

Either this guy was intentionally trying to provoke poor old ChatGPT into some nasty misbehavior, or he is in serious need of a professional AI-Whisperer.

[Note: This seems like a very good example of how a well-designed and well-behaved AI tool should act: just doing exactly what it has been taught to do.]

Work expands or contracts to fill available time

You will not be surprised to hear this since it is how the vast majority of us humans live. By “work” is meant employment by an employer, or self-employment as a freelancer of some flavor. A worker in other words, independent of the particular working arrangement involved at any point in time. And possibly some combination of these.

Most of us are busy working pretty much full time – this being whatever the work requires. Us self-employed folks work 24/7 in many cases, but of course not continuously. If whatever we are working at requires more time, then some activities get trimmed or dropped. If our work requires less time, as in losing a job or client, then our workload contracts until we either replace the lost work or we expand how long it takes to do whatever we have left to do.

Suppose that the change in work required is caused by the introduction of a useful AI application such as ChatGPT or whatever. This happy-app relieves us of some work, for which we may also lose compensation. Or we may just expand our remaining work to fill the time our compensation arrangement requires. Or, as is so often the case, our work scope expands almost instantly to use up whatever time was momentarily released by AI.

My bet is that the last outcome is most likely.

Work always manages to over-expand despite the time available.
Work always manages to over-expand despite the time available.

The reality of jobs to AI exposure

While the jobs vs. AI exposure guesstimates in the table above may be a bit frightening to folks who are working such jobs right now, the actual exposure – percentage of a job that could be handled by an AI-critter of some sort – is lower. Much, much lower.

Many, and possibly most, jobs have a significant core of work that at times requires human capabilities like creativeness when encountering a new situation, insight in seeing potential problems and weaknesses, and even to seek out ways to simplify or cut-corners on parts of the job.

Such capabilities are unlikely and probably impossible to program into an AI-machine. The source of these seems to be personal insights and instincts, personal experience and knowledge, and personal luck – among many others. Different in every individual in both scope and degree.

So many jobs have already been “automated” to a great extent, or even eliminated completely. Telephone operators are mostly gone. Horse-drawn carriage designers and builders, same. This is a long list. It may be joined in the near future by many types of software professionals since ChatGPT and kin have demonstrated an aptitude for coding and testing. But not for creating.

These kinds of transitions have been occurring almost forever. Nothing new is happening as AI technology enters much of our world. Some people will lose jobs and some will require major retraining. New skills will have to be learned. Many will have to move to other kinds of work. Same as always.

Perhaps some AI-apps are even now being taught to generate job-loss fears, saving our current fearmongers a whole bunch of boring work. Maybe even these will be among the job loss victims.

How about jobs lost to AI-powered robots?

Michael Johnston via EvergreenGavekal and ZeroHedge reminds us that it’s not just ChatGPT that is a potential threat to jobs, but delivery robots that are killing jobs today:  “Could AI Steal Your Job?”:

Autonomous delivery robots: Starship Technologies is a high-profile technology company that has successfully completed over 4 million deliveries using its autonomous fleet of robots. It’s true that these robots have put humans out of work by replacing the need for people to physically deliver items. It’s also true that this technology has created hundreds of new, specialized, higher-paying jobs for technicians, managers, operations, and logistics specialists that ensure these robots get from point A to point B as intended. Plus, it’s helping solve a very real problem for retailers that unlocks growth and margin: last mile delivery.”

Delivery robots all lined up to displace the millions employed in last-mile delivery jobs. Maybe.
Delivery robots all lined up to displace the millions employed in last-mile delivery jobs. Maybe.

This is a great example of how cleverly designed AI-based machines are eliminating one sort of worker while creating a range of quite different jobs. These of course are physical machines that wear out and break down, requiring a pretty sizable number of specialized maintenance and repair folks (plus people involved in manufacturing and distributing the parts needed here).

More new jobs created by AI

New jobs, but maybe not jobs that are all that great. Tyler Durden on ZeroHedge offers a rather unhappy picture of some new jobs being created by ChatGPT applications: “’We Are Grunt Workers’: The Lowly Humans Helping Run ChatGPT Make Just $15 Per Hour”:

“The company that owns ChatGPT, OpenAI, is reportedly ‘paying droves of U.S. contractors to assist it with the necessary task of data labelling—the process of training ChatGPT’s software to better respond to user requests’, according to Gizmodo.

“The article says they are making just $15 per hour for the task of data labeling, wherein data samples are parsed and labeled to help AI ‘learn’ quicker. The task was described as ‘pivotal’ for ChatGPT’s AI processes.”

“Worker Alexej Savreux said: ‘We are grunt workers, but there would be no AI language systems without it. You can design all the neural networks you want, you can get all the researchers involved you want, but without labelers, you have no ChatGPT. You have nothing.’”

There is however a major downside to this otherwise happy story

Many workers are going to be impacted by AI in some manner, including job loss. This means that you need to be continually upgrading and diversifying your skills and knowledge. The best place to do this is usually your current workplace, since most organizations of any size offer such development opportunities as a way to attract and retain workers.

Motivation to develop as always starts with each individual. Nobody will do this vital chore for you. You have to make the effort and stick with the program, as they say somewhere.

This brings me the long way around to a mantra that I have been repeating for years in many contexts: adaptability, agility, and resilience. Quite a while back when the world was still mostly sane, I developed some posts on these. See here, here, and here.

The general idea in these was to systematically strengthen your organization, business, or just yourself, so as to be able to move quickly, to respond flexibly, and to have a range of options that cover your points of greatest vulnerability. Never more important than today.

Black swan events: unforeseeable and unpredictable in nature, timing, and magnitude. Can you hear the flapping of wings yet?
Black swan events: unforeseeable and unpredictable in nature, timing, and magnitude. Can you hear the flapping of wings yet?

Bottom line:

Relatively few will lose their jobs as ChatGPT and other AI-based critters are incorporated into the workplace. Jobs will however change greatly for very many people, both employed and self-employed. Technological advances, now including AI, have impacted jobs for centuries. Workers today will shift to activities that AI and kin can’t do well enough – those requiring significant creativity and substantial interpersonal interactions.

The keys to surviving and prospering no matter what happens lies in your preparation – agility, adaptability, and resilience.

Related Reading

  • Jeff Thomas via The Burning Platform offered an interesting and very scary insight into what will actually cause huge job losses in the near future – not AI-driven, but good old economic crises and mismanagement, as always: “Babson’s Warning”:

“But, 55 days after Mr. Babson’s speech, on 29th October, 1929, the market suddenly went into a free-fall, dropping 12% in its first day.”

“Today, most people have the general impression that on Black Friday, the market crashed and almost immediately, there were breadlines. Not so. In the Great Depression, as in any depression, the market collapsed in stages. The market did not reach its bottom of 89% losses until July of 1932.”

“Along the way, thousands of banks and lending institutions went belly-up. Thirteen million jobs disappeared.”

“And of course, the political leaders of the day did their bit. They implemented knee-jerk ‘solutions’ that actually worsened the situation. Restrictive tariffs, gold confiscation, and a more dominant government were employed, just as they will be this time around.”

“If AI machines can run a Wendy’s franchise, what else will they soon take over? The cost of the technology has not been publicly disclosed, though Wendy’s has said that it has been working with Google since 2001 to develop machine learning, cloud tools, data analytics, and other technologies aimed at replacing human workers.”

“Wendy’s software engineers have reportedly been working with Google as of late to build and fine-tune a generative AI application on top of Google’s own large language model, also known as LLM.”

“LLM is described as ‘a vast algorithmic software tool loaded with words, phrases and popular expressions in different dialects and accents and designed to recognize and mimic the syntax and semantics of human speech,’ according to The Wall Street Journal.”

“Generative AI tools are designed to generate natural-language responses, images or computer code from user text prompts.”

“According to Thomas Kurian, the process of ordering through an AI machine and having it understand you is not all that simple. He says driving by and speaking into the Wendy’s AI machine is ‘actually one of the hardest’ things for the technology to accomplish.”

“Things like extraneous noises in a family car such as music or children screaming can interfere with the machine’s recognition of words and phrases. Then there are people with accents, people who speak English as a second or third language, and other complications that could render the process a nightmare.”

“Another problem is when customers change their minds midway through an order, which the AI robots will have to learn how to handle. ‘It’s a very complicated technical problem,’ Kurian said.”